From a189b2ee938f6b15ad9f95bdef63f95a3a092418 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Thu, 17 Nov 2022 12:47:29 +0100 Subject: fbdev: Make fb_modesetting_disabled() static inline Make fb_modesetting_disabled() a static-inline function when it is defined in the header file. Avoid the linker error shown below. ld: drivers/video/fbdev/core/fbmon.o: in function `fb_modesetting_disabled': fbmon.c:(.text+0x1e4): multiple definition of `fb_modesetting_disabled'; drivers/video/fbdev/core/fbmem.o:fbmem.c:(.text+0x1bac): first defined here A bug report is at [1]. Reported-by: Stephen Rothwell Reported-by: kernel test robot Signed-off-by: Thomas Zimmermann Reviewed-by: Javier Martinez Canillas Fixes: 0ba2fa8cbd29 ("fbdev: Add support for the nomodeset kernel parameter") Cc: Javier Martinez Canillas Cc: Daniel Vetter Cc: Helge Deller Cc: linux-fbdev@vger.kernel.org Cc: dri-devel@lists.freedesktop.org Link: https://lore.kernel.org/dri-devel/20221117183214.2473e745@canb.auug.org.au/T/#u # 1 Link: https://patchwork.freedesktop.org/patch/msgid/20221117114729.7570-1-tzimmermann@suse.de --- include/linux/fb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fb.h b/include/linux/fb.h index 8dc9635f5bc1..a2a52f730989 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -807,7 +807,7 @@ extern int fb_find_mode(struct fb_var_screeninfo *var, #if defined(CONFIG_VIDEO_NOMODESET) bool fb_modesetting_disabled(const char *drvname); #else -bool fb_modesetting_disabled(const char *drvname) +static inline bool fb_modesetting_disabled(const char *drvname) { return false; } -- cgit v1.2.3 From 8b83e1a455382dc667898a525a93f4eb6716cc41 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Fri, 18 Nov 2022 14:35:34 +0100 Subject: Revert "drm/fb-helper: Schedule deferred-I/O worker after writing to framebuffer" This reverts commit 7f5cc4a3e5e4c5a38e5748defc952e45278f7a70. Needed to restore the fbdev damage worker. There have been bug reports about locking order [1] and incorrectly takens branches. [2] Restore the damage worker until these problems have been resovled. Signed-off-by: Thomas Zimmermann Acked-by: Daniel Vetter Link: https://intel-gfx-ci.01.org/tree/drm-tip/fi-kbl-8809g.html # 1 Link: https://lore.kernel.org/dri-devel/20221115115819.23088-6-tzimmermann@suse.de/T/#m06eedc0a468940e4cbbd14ca026733b639bc445a # 2 Link: https://patchwork.freedesktop.org/patch/msgid/20221118133535.9739-3-tzimmermann@suse.de --- drivers/gpu/drm/drm_fb_helper.c | 9 +-------- drivers/video/fbdev/core/fb_defio.c | 16 ---------------- include/linux/fb.h | 1 - 3 files changed, 1 insertion(+), 25 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index c0e9a977a3b3..cdbf03e941b2 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -599,16 +599,9 @@ static void drm_fb_helper_add_damage_clip(struct drm_fb_helper *helper, u32 x, u static void drm_fb_helper_damage(struct drm_fb_helper *helper, u32 x, u32 y, u32 width, u32 height) { - struct fb_info *info = helper->info; - drm_fb_helper_add_damage_clip(helper, x, y, width, height); - /* - * The current fbdev emulation only flushes buffers if a damage - * update is necessary. And we can assume that deferred I/O has - * been enabled as damage updates require deferred I/O for mmap. - */ - fb_deferred_io_schedule_flush(info); + schedule_work(&helper->damage_work); } /* diff --git a/drivers/video/fbdev/core/fb_defio.c b/drivers/video/fbdev/core/fb_defio.c index dec678f72a42..c730253ab85c 100644 --- a/drivers/video/fbdev/core/fb_defio.c +++ b/drivers/video/fbdev/core/fb_defio.c @@ -332,19 +332,3 @@ void fb_deferred_io_cleanup(struct fb_info *info) mutex_destroy(&fbdefio->lock); } EXPORT_SYMBOL_GPL(fb_deferred_io_cleanup); - -void fb_deferred_io_schedule_flush(struct fb_info *info) -{ - struct fb_deferred_io *fbdefio = info->fbdefio; - - if (WARN_ON_ONCE(!fbdefio)) - return; /* bug in driver logic */ - - /* - * There's no requirement from callers to schedule the - * flush immediately. Rather schedule the worker with a - * delay and let a few more writes pile up. - */ - schedule_delayed_work(&info->deferred_work, fbdefio->delay); -} -EXPORT_SYMBOL_GPL(fb_deferred_io_schedule_flush); diff --git a/include/linux/fb.h b/include/linux/fb.h index a2a52f730989..64889a2b783f 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -663,7 +663,6 @@ extern void fb_deferred_io_open(struct fb_info *info, struct inode *inode, struct file *file); extern void fb_deferred_io_cleanup(struct fb_info *info); -extern void fb_deferred_io_schedule_flush(struct fb_info *info); extern int fb_deferred_io_fsync(struct file *file, loff_t start, loff_t end, int datasync); -- cgit v1.2.3 From b56ffa583350f605446d78cb4163114e4d1ac60c Mon Sep 17 00:00:00 2001 From: T.J. Mercier Date: Wed, 23 Nov 2022 19:35:18 +0000 Subject: dma-buf: A collection of typo and documentation fixes I've been collecting these typo fixes for a while and it feels like time to send them in. Signed-off-by: T.J. Mercier Reviewed-by: Randy Dunlap Acked-by: Christian König Reviewed-by: Tommaso Merciai Link: https://patchwork.freedesktop.org/patch/msgid/20221123193519.3948105-1-tjmercier@google.com Signed-off-by: Christian König --- drivers/dma-buf/dma-buf.c | 14 +++++++------- include/linux/dma-buf.h | 4 ++-- 2 files changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index b809513b03fe..6277ba3525de 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -1252,7 +1252,7 @@ EXPORT_SYMBOL_NS_GPL(dma_buf_unmap_attachment_unlocked, DMA_BUF); * * @dmabuf: [in] buffer which is moving * - * Informs all attachmenst that they need to destroy and recreated all their + * Informs all attachments that they need to destroy and recreate all their * mappings. */ void dma_buf_move_notify(struct dma_buf *dmabuf) @@ -1270,11 +1270,11 @@ EXPORT_SYMBOL_NS_GPL(dma_buf_move_notify, DMA_BUF); /** * DOC: cpu access * - * There are mutliple reasons for supporting CPU access to a dma buffer object: + * There are multiple reasons for supporting CPU access to a dma buffer object: * * - Fallback operations in the kernel, for example when a device is connected * over USB and the kernel needs to shuffle the data around first before - * sending it away. Cache coherency is handled by braketing any transactions + * sending it away. Cache coherency is handled by bracketing any transactions * with calls to dma_buf_begin_cpu_access() and dma_buf_end_cpu_access() * access. * @@ -1301,7 +1301,7 @@ EXPORT_SYMBOL_NS_GPL(dma_buf_move_notify, DMA_BUF); * replace ION buffers mmap support was needed. * * There is no special interfaces, userspace simply calls mmap on the dma-buf - * fd. But like for CPU access there's a need to braket the actual access, + * fd. But like for CPU access there's a need to bracket the actual access, * which is handled by the ioctl (DMA_BUF_IOCTL_SYNC). Note that * DMA_BUF_IOCTL_SYNC can fail with -EAGAIN or -EINTR, in which case it must * be restarted. @@ -1375,10 +1375,10 @@ static int __dma_buf_begin_cpu_access(struct dma_buf *dmabuf, * preparations. Coherency is only guaranteed in the specified range for the * specified access direction. * @dmabuf: [in] buffer to prepare cpu access for. - * @direction: [in] length of range for cpu access. + * @direction: [in] direction of access. * * After the cpu access is complete the caller should call - * dma_buf_end_cpu_access(). Only when cpu access is braketed by both calls is + * dma_buf_end_cpu_access(). Only when cpu access is bracketed by both calls is * it guaranteed to be coherent with other DMA access. * * This function will also wait for any DMA transactions tracked through @@ -1418,7 +1418,7 @@ EXPORT_SYMBOL_NS_GPL(dma_buf_begin_cpu_access, DMA_BUF); * actions. Coherency is only guaranteed in the specified range for the * specified access direction. * @dmabuf: [in] buffer to complete cpu access for. - * @direction: [in] length of range for cpu access. + * @direction: [in] direction of access. * * This terminates CPU access started with dma_buf_begin_cpu_access(). * diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 6fa8d4e29719..3f31baa3293f 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -356,7 +356,7 @@ struct dma_buf { */ const char *name; - /** @name_lock: Spinlock to protect name acces for read access. */ + /** @name_lock: Spinlock to protect name access for read access. */ spinlock_t name_lock; /** @@ -393,7 +393,7 @@ struct dma_buf { * anything the userspace API considers write access. * * - Drivers may just always add a write fence, since that only - * causes unecessarily synchronization, but no correctness issues. + * causes unnecessary synchronization, but no correctness issues. * * - Some drivers only expose a synchronous userspace API with no * pipelining across drivers. These do not set any fences for their -- cgit v1.2.3 From e873d4329ccb891bf3b17f1e0d44396de943e92d Mon Sep 17 00:00:00 2001 From: Joy Zou Date: Tue, 15 Nov 2022 17:38:23 +0800 Subject: dmaengine: imx-sdma: support hdmi in sdma The hdmi script already supported in sdma firmware. So add support hdmi in sdma driver. The design of hdmi script is different from common script such as sai. There is no need to config buffer descriptor for HDMI. The cyclic capability is achieved by the hdmi script. The slave config is so simple, only config src_addr, dts_addr and direction DMA_TRANS_NONE. Signed-off-by: Joy Zou Reviewed-by: Sascha Hauer Link: https://lore.kernel.org/r/20221115093823.2879128-3-joy.zou@nxp.com Signed-off-by: Vinod Koul --- drivers/dma/imx-sdma.c | 38 ++++++++++++++++++++++++++++++-------- include/linux/dma/imx-dma.h | 1 + 2 files changed, 31 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c index fbea5f62dd98..ab877ceeac3f 100644 --- a/drivers/dma/imx-sdma.c +++ b/drivers/dma/imx-sdma.c @@ -954,7 +954,10 @@ static irqreturn_t sdma_int_handler(int irq, void *dev_id) desc = sdmac->desc; if (desc) { if (sdmac->flags & IMX_DMA_SG_LOOP) { - sdma_update_channel_loop(sdmac); + if (sdmac->peripheral_type != IMX_DMATYPE_HDMI) + sdma_update_channel_loop(sdmac); + else + vchan_cyclic_callback(&desc->vd); } else { mxc_sdma_handle_channel_normal(sdmac); vchan_cookie_complete(&desc->vd); @@ -1074,6 +1077,10 @@ static int sdma_get_pc(struct sdma_channel *sdmac, per_2_emi = sdma->script_addrs->sai_2_mcu_addr; emi_2_per = sdma->script_addrs->mcu_2_sai_addr; break; + case IMX_DMATYPE_HDMI: + emi_2_per = sdma->script_addrs->hdmi_dma_addr; + sdmac->is_ram_script = true; + break; default: dev_err(sdma->dev, "Unsupported transfer type %d\n", peripheral_type); @@ -1125,11 +1132,16 @@ static int sdma_load_context(struct sdma_channel *sdmac) /* Send by context the event mask,base address for peripheral * and watermark level */ - context->gReg[0] = sdmac->event_mask[1]; - context->gReg[1] = sdmac->event_mask[0]; - context->gReg[2] = sdmac->per_addr; - context->gReg[6] = sdmac->shp_addr; - context->gReg[7] = sdmac->watermark_level; + if (sdmac->peripheral_type == IMX_DMATYPE_HDMI) { + context->gReg[4] = sdmac->per_addr; + context->gReg[6] = sdmac->shp_addr; + } else { + context->gReg[0] = sdmac->event_mask[1]; + context->gReg[1] = sdmac->event_mask[0]; + context->gReg[2] = sdmac->per_addr; + context->gReg[6] = sdmac->shp_addr; + context->gReg[7] = sdmac->watermark_level; + } bd0->mode.command = C0_SETDM; bd0->mode.status = BD_DONE | BD_WRAP | BD_EXTD; @@ -1513,7 +1525,7 @@ static struct sdma_desc *sdma_transfer_init(struct sdma_channel *sdmac, desc->sdmac = sdmac; desc->num_bd = bds; - if (sdma_alloc_bd(desc)) + if (bds && sdma_alloc_bd(desc)) goto err_desc_out; /* No slave_config called in MEMCPY case, so do here */ @@ -1678,13 +1690,16 @@ static struct dma_async_tx_descriptor *sdma_prep_dma_cyclic( { struct sdma_channel *sdmac = to_sdma_chan(chan); struct sdma_engine *sdma = sdmac->sdma; - int num_periods = buf_len / period_len; + int num_periods = 0; int channel = sdmac->channel; int i = 0, buf = 0; struct sdma_desc *desc; dev_dbg(sdma->dev, "%s channel: %d\n", __func__, channel); + if (sdmac->peripheral_type != IMX_DMATYPE_HDMI) + num_periods = buf_len / period_len; + sdma_config_write(chan, &sdmac->slave_config, direction); desc = sdma_transfer_init(sdmac, direction, num_periods); @@ -1701,6 +1716,9 @@ static struct dma_async_tx_descriptor *sdma_prep_dma_cyclic( goto err_bd_out; } + if (sdmac->peripheral_type == IMX_DMATYPE_HDMI) + return vchan_tx_prep(&sdmac->vc, &desc->vd, flags); + while (buf < buf_len) { struct sdma_buffer_descriptor *bd = &desc->bd[i]; int param; @@ -1761,6 +1779,10 @@ static int sdma_config_write(struct dma_chan *chan, sdmac->watermark_level |= (dmaengine_cfg->dst_maxburst << 16) & SDMA_WATERMARK_LEVEL_HWML; sdmac->word_size = dmaengine_cfg->dst_addr_width; + } else if (sdmac->peripheral_type == IMX_DMATYPE_HDMI) { + sdmac->per_address = dmaengine_cfg->dst_addr; + sdmac->per_address2 = dmaengine_cfg->src_addr; + sdmac->watermark_level = 0; } else { sdmac->per_address = dmaengine_cfg->dst_addr; sdmac->watermark_level = dmaengine_cfg->dst_maxburst * diff --git a/include/linux/dma/imx-dma.h b/include/linux/dma/imx-dma.h index f487a4fa103a..cfec5f946e23 100644 --- a/include/linux/dma/imx-dma.h +++ b/include/linux/dma/imx-dma.h @@ -40,6 +40,7 @@ enum sdma_peripheral_type { IMX_DMATYPE_ASRC_SP, /* Shared ASRC */ IMX_DMATYPE_SAI, /* SAI */ IMX_DMATYPE_MULTI_SAI, /* MULTI FIFOs For Audio */ + IMX_DMATYPE_HDMI, /* HDMI Audio */ }; enum imx_dma_prio { -- cgit v1.2.3 From 08f01cc1d6e240092a6d9bfa21652622657f38f0 Mon Sep 17 00:00:00 2001 From: Gerald Loacker Date: Thu, 1 Dec 2022 08:22:18 +0100 Subject: iio: add struct declaration for iio types Add struct for iio type arrays such as IIO_AVAIL_LIST which can be used instead of int arrays. Signed-off-by: Gerald Loacker Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/20221201072220.402585-2-gerald.loacker@wolfvision.net Signed-off-by: Jonathan Cameron --- include/linux/iio/iio.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index 8e0afaaa3f75..81413cd3a3e7 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -381,6 +381,11 @@ s64 iio_get_time_ns(const struct iio_dev *indio_dev); #define INDIO_MAX_RAW_ELEMENTS 4 +struct iio_val_int_plus_micro { + int integer; + int micro; +}; + struct iio_trigger; /* forward declaration */ /** -- cgit v1.2.3 From 1f5e408f6a000be980872b8065e547e2dbef6acc Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 7 Dec 2022 21:03:44 +0200 Subject: iio: light: tsl2563: Drop legacy platform data code There is no in-kernel user for legacy platform data. Otherwise, a new one can use software nodes instead. Hence, drop legacy platform data code. Signed-off-by: Andy Shevchenko Tested-by: Ferry Toth Link: https://lore.kernel.org/r/20221207190348.9347-7-andriy.shevchenko@linux.intel.com Signed-off-by: Jonathan Cameron --- drivers/iio/light/tsl2563.c | 12 ++---------- include/linux/platform_data/tsl2563.h | 9 --------- 2 files changed, 2 insertions(+), 19 deletions(-) delete mode 100644 include/linux/platform_data/tsl2563.h (limited to 'include/linux') diff --git a/drivers/iio/light/tsl2563.c b/drivers/iio/light/tsl2563.c index cce044556293..ed193a3da91e 100644 --- a/drivers/iio/light/tsl2563.c +++ b/drivers/iio/light/tsl2563.c @@ -29,7 +29,6 @@ #include #include #include -#include /* Use this many bits for fraction part. */ #define ADC_FRAC_BITS 14 @@ -698,7 +697,6 @@ static int tsl2563_probe(struct i2c_client *client) struct device *dev = &client->dev; struct iio_dev *indio_dev; struct tsl2563_chip *chip; - struct tsl2563_platform_data *pdata = client->dev.platform_data; unsigned long irq_flags; u8 id = 0; int err; @@ -730,14 +728,8 @@ static int tsl2563_probe(struct i2c_client *client) chip->calib0 = tsl2563_calib_from_sysfs(CALIB_BASE_SYSFS); chip->calib1 = tsl2563_calib_from_sysfs(CALIB_BASE_SYSFS); - if (pdata) { - chip->cover_comp_gain = pdata->cover_comp_gain; - } else { - err = device_property_read_u32(&client->dev, "amstaos,cover-comp-gain", - &chip->cover_comp_gain); - if (err) - chip->cover_comp_gain = 1; - } + chip->cover_comp_gain = 1; + device_property_read_u32(dev, "amstaos,cover-comp-gain", &chip->cover_comp_gain); dev_info(&client->dev, "model %d, rev. %d\n", id >> 4, id & 0x0f); indio_dev->name = client->name; diff --git a/include/linux/platform_data/tsl2563.h b/include/linux/platform_data/tsl2563.h deleted file mode 100644 index 9cf9309c3f24..000000000000 --- a/include/linux/platform_data/tsl2563.h +++ /dev/null @@ -1,9 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __LINUX_TSL2563_H -#define __LINUX_TSL2563_H - -struct tsl2563_platform_data { - int cover_comp_gain; -}; - -#endif /* __LINUX_TSL2563_H */ -- cgit v1.2.3 From c941b98781b348bd63fb8f8b5307b10fde2af0c1 Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Fri, 9 Dec 2022 18:48:39 +0200 Subject: clk: qcom: smd-rpm: remove duplication between MMXI and MMAXI defines The commit 644c42295592 ("clk: qcom: smd: Add SM6375 clocks") added a duplicate of the existing define QCOM_SMD_RPM_MMAXI_CLK, drop it now. Fixes: 644c42295592 ("clk: qcom: smd: Add SM6375 clocks") Reviewed-by: Alex Elder Signed-off-by: Dmitry Baryshkov Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20221209164855.128798-4-dmitry.baryshkov@linaro.org --- drivers/clk/qcom/clk-smd-rpm.c | 4 ++-- include/linux/soc/qcom/smd-rpm.h | 1 - 2 files changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/clk/qcom/clk-smd-rpm.c b/drivers/clk/qcom/clk-smd-rpm.c index 3082f38513fa..ccc54913eca5 100644 --- a/drivers/clk/qcom/clk-smd-rpm.c +++ b/drivers/clk/qcom/clk-smd-rpm.c @@ -1122,8 +1122,8 @@ static const struct rpm_smd_clk_desc rpm_clk_sm6115 = { }; /* SM6375 */ -DEFINE_CLK_SMD_RPM(sm6375, mmnrt_clk, mmnrt_a_clk, QCOM_SMD_RPM_MMXI_CLK, 0); -DEFINE_CLK_SMD_RPM(sm6375, mmrt_clk, mmrt_a_clk, QCOM_SMD_RPM_MMXI_CLK, 1); +DEFINE_CLK_SMD_RPM(sm6375, mmnrt_clk, mmnrt_a_clk, QCOM_SMD_RPM_MMAXI_CLK, 0); +DEFINE_CLK_SMD_RPM(sm6375, mmrt_clk, mmrt_a_clk, QCOM_SMD_RPM_MMAXI_CLK, 1); DEFINE_CLK_SMD_RPM(qcm2290, hwkm_clk, hwkm_a_clk, QCOM_SMD_RPM_HWKM_CLK, 0); DEFINE_CLK_SMD_RPM(qcm2290, pka_clk, pka_a_clk, QCOM_SMD_RPM_PKA_CLK, 0); DEFINE_CLK_SMD_RPM_BRANCH(sm6375, bimc_freq_log, bimc_freq_log_a, QCOM_SMD_RPM_MISC_CLK, 4, 1); diff --git a/include/linux/soc/qcom/smd-rpm.h b/include/linux/soc/qcom/smd-rpm.h index 62de54992e49..2990f425fdef 100644 --- a/include/linux/soc/qcom/smd-rpm.h +++ b/include/linux/soc/qcom/smd-rpm.h @@ -43,7 +43,6 @@ struct qcom_smd_rpm; #define QCOM_SMD_RPM_HWKM_CLK 0x6d6b7768 #define QCOM_SMD_RPM_PKA_CLK 0x616b70 #define QCOM_SMD_RPM_MCFG_CLK 0x6766636d -#define QCOM_SMD_RPM_MMXI_CLK 0x69786d6d int qcom_rpm_smd_write(struct qcom_smd_rpm *rpm, int state, -- cgit v1.2.3 From 63a1bd8ad1ac9e4e8bfcd5914c8899606e04898d Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 30 Nov 2022 23:08:53 +0000 Subject: KVM: Drop arch hardware (un)setup hooks Drop kvm_arch_hardware_setup() and kvm_arch_hardware_unsetup() now that all implementations are nops. No functional change intended. Signed-off-by: Sean Christopherson Reviewed-by: Eric Farman # s390 Acked-by: Anup Patel Message-Id: <20221130230934.1014142-10-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/arm64/include/asm/kvm_host.h | 1 - arch/arm64/kvm/arm.c | 5 ----- arch/mips/include/asm/kvm_host.h | 1 - arch/mips/kvm/mips.c | 5 ----- arch/powerpc/include/asm/kvm_host.h | 1 - arch/powerpc/kvm/powerpc.c | 5 ----- arch/riscv/include/asm/kvm_host.h | 1 - arch/riscv/kvm/main.c | 5 ----- arch/s390/kvm/kvm-s390.c | 10 ---------- arch/x86/kvm/x86.c | 10 ---------- include/linux/kvm_host.h | 2 -- virt/kvm/kvm_main.c | 7 ------- 12 files changed, 53 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 35a159d131b5..f50951c51d3b 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -943,7 +943,6 @@ static inline bool kvm_system_needs_idmapped_vectors(void) void kvm_arm_vcpu_ptrauth_trap(struct kvm_vcpu *vcpu); -static inline void kvm_arch_hardware_unsetup(void) {} static inline void kvm_arch_sync_events(struct kvm *kvm) {} static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {} diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 9c5573bc4614..e6c21b804c13 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -63,11 +63,6 @@ int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu) return kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE; } -int kvm_arch_hardware_setup(void *opaque) -{ - return 0; -} - int kvm_arch_check_processor_compat(void *opaque) { return 0; diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h index 5cedb28e8a40..28f0ba97db71 100644 --- a/arch/mips/include/asm/kvm_host.h +++ b/arch/mips/include/asm/kvm_host.h @@ -888,7 +888,6 @@ extern unsigned long kvm_mips_get_ramsize(struct kvm *kvm); extern int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, struct kvm_mips_interrupt *irq); -static inline void kvm_arch_hardware_unsetup(void) {} static inline void kvm_arch_sync_events(struct kvm *kvm) {} static inline void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) {} diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index a25e0b73ee70..af29490d9740 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -135,11 +135,6 @@ void kvm_arch_hardware_disable(void) kvm_mips_callbacks->hardware_disable(); } -int kvm_arch_hardware_setup(void *opaque) -{ - return 0; -} - int kvm_arch_check_processor_compat(void *opaque) { return 0; diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index caea15dcb91d..5d2c3a487e73 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -877,7 +877,6 @@ struct kvm_vcpu_arch { #define __KVM_HAVE_CREATE_DEVICE static inline void kvm_arch_hardware_disable(void) {} -static inline void kvm_arch_hardware_unsetup(void) {} static inline void kvm_arch_sync_events(struct kvm *kvm) {} static inline void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) {} static inline void kvm_arch_flush_shadow_all(struct kvm *kvm) {} diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 04494a4fb37a..5faf69421f13 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -440,11 +440,6 @@ int kvm_arch_hardware_enable(void) return 0; } -int kvm_arch_hardware_setup(void *opaque) -{ - return 0; -} - int kvm_arch_check_processor_compat(void *opaque) { return kvmppc_core_check_processor_compat(); diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h index 93f43a3e7886..a79b7d1514db 100644 --- a/arch/riscv/include/asm/kvm_host.h +++ b/arch/riscv/include/asm/kvm_host.h @@ -230,7 +230,6 @@ struct kvm_vcpu_arch { bool pause; }; -static inline void kvm_arch_hardware_unsetup(void) {} static inline void kvm_arch_sync_events(struct kvm *kvm) {} static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {} diff --git a/arch/riscv/kvm/main.c b/arch/riscv/kvm/main.c index 58c5489d3031..afd6400a9e80 100644 --- a/arch/riscv/kvm/main.c +++ b/arch/riscv/kvm/main.c @@ -25,11 +25,6 @@ int kvm_arch_check_processor_compat(void *opaque) return 0; } -int kvm_arch_hardware_setup(void *opaque) -{ - return 0; -} - int kvm_arch_hardware_enable(void) { unsigned long hideleg, hedeleg; diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 97c7ccd189eb..829e6e046003 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -329,16 +329,6 @@ static struct notifier_block kvm_clock_notifier = { .notifier_call = kvm_clock_sync, }; -int kvm_arch_hardware_setup(void *opaque) -{ - return 0; -} - -void kvm_arch_hardware_unsetup(void) -{ - -} - static void allow_cpu_feat(unsigned long nr) { set_bit_inv(nr, kvm_s390_available_cpu_feat); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 4e7a71cab828..089f0eeea850 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -12033,16 +12033,6 @@ void kvm_arch_hardware_disable(void) drop_user_return_notifiers(); } -int kvm_arch_hardware_setup(void *opaque) -{ - return 0; -} - -void kvm_arch_hardware_unsetup(void) -{ - -} - int kvm_arch_check_processor_compat(void *opaque) { struct cpuinfo_x86 *c = &cpu_data(smp_processor_id()); diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 4f26b244f6d0..7c1009c0e66d 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1447,8 +1447,6 @@ static inline void kvm_create_vcpu_debugfs(struct kvm_vcpu *vcpu) {} int kvm_arch_hardware_enable(void); void kvm_arch_hardware_disable(void); -int kvm_arch_hardware_setup(void *opaque); -void kvm_arch_hardware_unsetup(void); int kvm_arch_check_processor_compat(void *opaque); int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu); bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 70264378da41..8393347fd35f 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -5931,10 +5931,6 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align, if (r) return r; - r = kvm_arch_hardware_setup(opaque); - if (r < 0) - goto err_hw_setup; - if (!zalloc_cpumask_var(&cpus_hardware_enabled, GFP_KERNEL)) { r = -ENOMEM; goto err_hw_enabled; @@ -6027,8 +6023,6 @@ out_free_3: out_free_2: free_cpumask_var(cpus_hardware_enabled); err_hw_enabled: - kvm_arch_hardware_unsetup(); -err_hw_setup: kvm_arch_exit(); return r; } @@ -6057,7 +6051,6 @@ void kvm_exit(void) on_each_cpu(hardware_disable_nolock, NULL, 1); kvm_irqfd_exit(); free_cpumask_var(cpus_hardware_enabled); - kvm_arch_hardware_unsetup(); kvm_arch_exit(); } EXPORT_SYMBOL_GPL(kvm_exit); -- cgit v1.2.3 From 466d27e48d7cd2542710309817cff1e91cd2e10a Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 30 Nov 2022 23:09:00 +0000 Subject: KVM: arm64: Simplify the CPUHP logic For a number of historical reasons, the KVM/arm64 hotplug setup is pretty complicated, and we have two extra CPUHP notifiers for vGIC and timers. It looks pretty pointless, and gets in the way of further changes. So let's just expose some helpers that can be called from the core CPUHP callback, and get rid of everything else. This gives us the opportunity to drop a useless notifier entry, as well as tidy-up the timer enable/disable, which was a bit odd. Signed-off-by: Marc Zyngier Signed-off-by: Isaku Yamahata Signed-off-by: Sean Christopherson Message-Id: <20221130230934.1014142-17-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/arm64/kvm/arch_timer.c | 27 ++++++++++----------------- arch/arm64/kvm/arm.c | 13 +++++++++++++ arch/arm64/kvm/vgic/vgic-init.c | 19 ++----------------- include/kvm/arm_arch_timer.h | 4 ++++ include/kvm/arm_vgic.h | 4 ++++ include/linux/cpuhotplug.h | 3 --- 6 files changed, 33 insertions(+), 37 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c index bb24a76b4224..33fca1a691a5 100644 --- a/arch/arm64/kvm/arch_timer.c +++ b/arch/arm64/kvm/arch_timer.c @@ -811,10 +811,18 @@ void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu) ptimer->host_timer_irq_flags = host_ptimer_irq_flags; } -static void kvm_timer_init_interrupt(void *info) +void kvm_timer_cpu_up(void) { enable_percpu_irq(host_vtimer_irq, host_vtimer_irq_flags); - enable_percpu_irq(host_ptimer_irq, host_ptimer_irq_flags); + if (host_ptimer_irq) + enable_percpu_irq(host_ptimer_irq, host_ptimer_irq_flags); +} + +void kvm_timer_cpu_down(void) +{ + disable_percpu_irq(host_vtimer_irq); + if (host_ptimer_irq) + disable_percpu_irq(host_ptimer_irq); } int kvm_arm_timer_set_reg(struct kvm_vcpu *vcpu, u64 regid, u64 value) @@ -976,18 +984,6 @@ void kvm_arm_timer_write_sysreg(struct kvm_vcpu *vcpu, preempt_enable(); } -static int kvm_timer_starting_cpu(unsigned int cpu) -{ - kvm_timer_init_interrupt(NULL); - return 0; -} - -static int kvm_timer_dying_cpu(unsigned int cpu) -{ - disable_percpu_irq(host_vtimer_irq); - return 0; -} - static int timer_irq_set_vcpu_affinity(struct irq_data *d, void *vcpu) { if (vcpu) @@ -1185,9 +1181,6 @@ int kvm_timer_hyp_init(bool has_gic) goto out_free_irq; } - cpuhp_setup_state(CPUHP_AP_KVM_ARM_TIMER_STARTING, - "kvm/arm/timer:starting", kvm_timer_starting_cpu, - kvm_timer_dying_cpu); return 0; out_free_irq: free_percpu_irq(host_vtimer_irq, kvm_get_running_vcpus()); diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index e6c21b804c13..b572c78f3c23 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -1677,7 +1677,15 @@ static void _kvm_arch_hardware_enable(void *discard) int kvm_arch_hardware_enable(void) { + int was_enabled = __this_cpu_read(kvm_arm_hardware_enabled); + _kvm_arch_hardware_enable(NULL); + + if (!was_enabled) { + kvm_vgic_cpu_up(); + kvm_timer_cpu_up(); + } + return 0; } @@ -1691,6 +1699,11 @@ static void _kvm_arch_hardware_disable(void *discard) void kvm_arch_hardware_disable(void) { + if (__this_cpu_read(kvm_arm_hardware_enabled)) { + kvm_timer_cpu_down(); + kvm_vgic_cpu_down(); + } + if (!is_protected_kvm_enabled()) _kvm_arch_hardware_disable(NULL); } diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c index f6d4f4052555..6c7f6ae21ec0 100644 --- a/arch/arm64/kvm/vgic/vgic-init.c +++ b/arch/arm64/kvm/vgic/vgic-init.c @@ -465,17 +465,15 @@ out: /* GENERIC PROBE */ -static int vgic_init_cpu_starting(unsigned int cpu) +void kvm_vgic_cpu_up(void) { enable_percpu_irq(kvm_vgic_global_state.maint_irq, 0); - return 0; } -static int vgic_init_cpu_dying(unsigned int cpu) +void kvm_vgic_cpu_down(void) { disable_percpu_irq(kvm_vgic_global_state.maint_irq); - return 0; } static irqreturn_t vgic_maintenance_handler(int irq, void *data) @@ -584,19 +582,6 @@ int kvm_vgic_hyp_init(void) return ret; } - ret = cpuhp_setup_state(CPUHP_AP_KVM_ARM_VGIC_INIT_STARTING, - "kvm/arm/vgic:starting", - vgic_init_cpu_starting, vgic_init_cpu_dying); - if (ret) { - kvm_err("Cannot register vgic CPU notifier\n"); - goto out_free_irq; - } - kvm_info("vgic interrupt IRQ%d\n", kvm_vgic_global_state.maint_irq); return 0; - -out_free_irq: - free_percpu_irq(kvm_vgic_global_state.maint_irq, - kvm_get_running_vcpus()); - return ret; } diff --git a/include/kvm/arm_arch_timer.h b/include/kvm/arm_arch_timer.h index cd6d8f260eab..1638418f72dd 100644 --- a/include/kvm/arm_arch_timer.h +++ b/include/kvm/arm_arch_timer.h @@ -104,4 +104,8 @@ void kvm_arm_timer_write_sysreg(struct kvm_vcpu *vcpu, u32 timer_get_ctl(struct arch_timer_context *ctxt); u64 timer_get_cval(struct arch_timer_context *ctxt); +/* CPU HP callbacks */ +void kvm_timer_cpu_up(void); +void kvm_timer_cpu_down(void); + #endif diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h index 9270cd87da3f..0629e3532ad0 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -432,4 +432,8 @@ int vgic_v4_load(struct kvm_vcpu *vcpu); void vgic_v4_commit(struct kvm_vcpu *vcpu); int vgic_v4_put(struct kvm_vcpu *vcpu, bool need_db); +/* CPU HP callbacks */ +void kvm_vgic_cpu_up(void); +void kvm_vgic_cpu_down(void); + #endif /* __KVM_ARM_VGIC_H */ diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 6c6859bfc454..5cae6bd22f7f 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -188,9 +188,6 @@ enum cpuhp_state { CPUHP_AP_TI_GP_TIMER_STARTING, CPUHP_AP_HYPERV_TIMER_STARTING, CPUHP_AP_KVM_STARTING, - CPUHP_AP_KVM_ARM_VGIC_INIT_STARTING, - CPUHP_AP_KVM_ARM_VGIC_STARTING, - CPUHP_AP_KVM_ARM_TIMER_STARTING, /* Must be the last timer callback */ CPUHP_AP_DUMMY_TIMER_STARTING, CPUHP_AP_ARM_XEN_STARTING, -- cgit v1.2.3 From a578a0a9e3526483ad1904fac019d95e7089fb34 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 30 Nov 2022 23:09:13 +0000 Subject: KVM: Drop kvm_arch_{init,exit}() hooks Drop kvm_arch_init() and kvm_arch_exit() now that all implementations are nops. No functional change intended. Signed-off-by: Sean Christopherson Reviewed-by: Eric Farman # s390 Reviewed-by: Philippe Mathieu-Daudé Acked-by: Anup Patel Message-Id: <20221130230934.1014142-30-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/arm64/kvm/arm.c | 11 ----------- arch/mips/kvm/mips.c | 10 ---------- arch/powerpc/include/asm/kvm_host.h | 1 - arch/powerpc/kvm/powerpc.c | 5 ----- arch/riscv/kvm/main.c | 9 --------- arch/s390/kvm/kvm-s390.c | 10 ---------- arch/x86/kvm/x86.c | 10 ---------- include/linux/kvm_host.h | 3 --- virt/kvm/kvm_main.c | 19 ++----------------- 9 files changed, 2 insertions(+), 76 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index ea8057fa113f..04ed741f7b9d 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -2301,17 +2301,6 @@ out_err: return err; } -int kvm_arch_init(void *opaque) -{ - return 0; -} - -/* NOP: Compiling as a module not supported */ -void kvm_arch_exit(void) -{ - -} - static int __init early_kvm_mode_cfg(char *arg) { if (!arg) diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index ae7a24342fdf..3cade648827a 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -1010,16 +1010,6 @@ long kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) return r; } -int kvm_arch_init(void *opaque) -{ - return 0; -} - -void kvm_arch_exit(void) -{ - -} - int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 5d2c3a487e73..0a80e80c7b9e 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -881,7 +881,6 @@ static inline void kvm_arch_sync_events(struct kvm *kvm) {} static inline void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) {} static inline void kvm_arch_flush_shadow_all(struct kvm *kvm) {} static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {} -static inline void kvm_arch_exit(void) {} static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) {} static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) {} diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index d44b85ba8cef..01d0f9935e6c 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -2539,11 +2539,6 @@ void kvmppc_init_lpid(unsigned long nr_lpids_param) } EXPORT_SYMBOL_GPL(kvmppc_init_lpid); -int kvm_arch_init(void *opaque) -{ - return 0; -} - EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_ppc_instr); void kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu, struct dentry *debugfs_dentry) diff --git a/arch/riscv/kvm/main.c b/arch/riscv/kvm/main.c index 1cd220e96c26..be951feee27a 100644 --- a/arch/riscv/kvm/main.c +++ b/arch/riscv/kvm/main.c @@ -65,15 +65,6 @@ void kvm_arch_hardware_disable(void) csr_write(CSR_HIDELEG, 0); } -int kvm_arch_init(void *opaque) -{ - return 0; -} - -void kvm_arch_exit(void) -{ -} - static int __init riscv_kvm_init(void) { const char *str; diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 66d162723d21..25b08b956888 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -541,16 +541,6 @@ static void __kvm_s390_exit(void) debug_unregister(kvm_s390_dbf_uv); } -int kvm_arch_init(void *opaque) -{ - return 0; -} - -void kvm_arch_exit(void) -{ - -} - /* Section: device related */ long kvm_arch_dev_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 78cb6a46dd50..accf5a7ab8df 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -9292,16 +9292,6 @@ static inline void kvm_ops_update(struct kvm_x86_init_ops *ops) kvm_pmu_ops_update(ops->pmu_ops); } -int kvm_arch_init(void *opaque) -{ - return 0; -} - -void kvm_arch_exit(void) -{ - -} - static int __kvm_x86_vendor_init(struct kvm_x86_init_ops *ops) { u64 host_pat; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 7c1009c0e66d..62d977bb1448 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1423,9 +1423,6 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg); int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu); -int kvm_arch_init(void *opaque); -void kvm_arch_exit(void); - void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu); void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 8393347fd35f..597ff734b312 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -5921,20 +5921,8 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align, int r; int cpu; - /* - * FIXME: Get rid of kvm_arch_init(), vendor code should call arch code - * directly. Note, kvm_arch_init() _must_ be called before anything - * else as x86 relies on checks buried in kvm_arch_init() to guard - * against multiple calls to kvm_init(). - */ - r = kvm_arch_init(opaque); - if (r) - return r; - - if (!zalloc_cpumask_var(&cpus_hardware_enabled, GFP_KERNEL)) { - r = -ENOMEM; - goto err_hw_enabled; - } + if (!zalloc_cpumask_var(&cpus_hardware_enabled, GFP_KERNEL)) + return -ENOMEM; c.ret = &r; c.opaque = opaque; @@ -6022,8 +6010,6 @@ out_free_3: cpuhp_remove_state_nocalls(CPUHP_AP_KVM_STARTING); out_free_2: free_cpumask_var(cpus_hardware_enabled); -err_hw_enabled: - kvm_arch_exit(); return r; } EXPORT_SYMBOL_GPL(kvm_init); @@ -6051,7 +6037,6 @@ void kvm_exit(void) on_each_cpu(hardware_disable_nolock, NULL, 1); kvm_irqfd_exit(); free_cpumask_var(cpus_hardware_enabled); - kvm_arch_exit(); } EXPORT_SYMBOL_GPL(kvm_exit); -- cgit v1.2.3 From 81a1cf9f89a6b71e71bfd7d43837ce9235e70b38 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 30 Nov 2022 23:09:16 +0000 Subject: KVM: Drop kvm_arch_check_processor_compat() hook Drop kvm_arch_check_processor_compat() and its support code now that all architecture implementations are nops. Signed-off-by: Sean Christopherson Reviewed-by: Philippe Mathieu-Daudé Reviewed-by: Eric Farman # s390 Acked-by: Anup Patel Reviewed-by: Kai Huang Message-Id: <20221130230934.1014142-33-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/arm64/kvm/arm.c | 7 +------ arch/mips/kvm/mips.c | 7 +------ arch/powerpc/kvm/book3s.c | 2 +- arch/powerpc/kvm/e500.c | 2 +- arch/powerpc/kvm/e500mc.c | 2 +- arch/powerpc/kvm/powerpc.c | 5 ----- arch/riscv/kvm/main.c | 7 +------ arch/s390/kvm/kvm-s390.c | 7 +------ arch/x86/kvm/svm/svm.c | 4 ++-- arch/x86/kvm/vmx/vmx.c | 4 ++-- arch/x86/kvm/x86.c | 5 ----- include/linux/kvm_host.h | 4 +--- virt/kvm/kvm_main.c | 24 +----------------------- 13 files changed, 13 insertions(+), 67 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 04ed741f7b9d..698787ed87e9 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -63,11 +63,6 @@ int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu) return kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE; } -int kvm_arch_check_processor_compat(void *opaque) -{ - return 0; -} - int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap) { @@ -2285,7 +2280,7 @@ static __init int kvm_arm_init(void) * FIXME: Do something reasonable if kvm_init() fails after pKVM * hypervisor protection is finalized. */ - err = kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE); + err = kvm_init(sizeof(struct kvm_vcpu), 0, THIS_MODULE); if (err) goto out_subs; diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index 3cade648827a..36c8991b5d39 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -135,11 +135,6 @@ void kvm_arch_hardware_disable(void) kvm_mips_callbacks->hardware_disable(); } -int kvm_arch_check_processor_compat(void *opaque) -{ - return 0; -} - extern void kvm_init_loongson_ipi(struct kvm *kvm); int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) @@ -1636,7 +1631,7 @@ static int __init kvm_mips_init(void) register_die_notifier(&kvm_mips_csr_die_notifier); - ret = kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE); + ret = kvm_init(sizeof(struct kvm_vcpu), 0, THIS_MODULE); if (ret) { unregister_die_notifier(&kvm_mips_csr_die_notifier); return ret; diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index 87283a0e33d8..57f4e7896d67 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -1052,7 +1052,7 @@ static int kvmppc_book3s_init(void) { int r; - r = kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE); + r = kvm_init(sizeof(struct kvm_vcpu), 0, THIS_MODULE); if (r) return r; #ifdef CONFIG_KVM_BOOK3S_32_HANDLER diff --git a/arch/powerpc/kvm/e500.c b/arch/powerpc/kvm/e500.c index 0ea61190ec04..b0f695428733 100644 --- a/arch/powerpc/kvm/e500.c +++ b/arch/powerpc/kvm/e500.c @@ -531,7 +531,7 @@ static int __init kvmppc_e500_init(void) flush_icache_range(kvmppc_booke_handlers, kvmppc_booke_handlers + ivor[max_ivor] + handler_len); - r = kvm_init(NULL, sizeof(struct kvmppc_vcpu_e500), 0, THIS_MODULE); + r = kvm_init(sizeof(struct kvmppc_vcpu_e500), 0, THIS_MODULE); if (r) goto err_out; kvm_ops_e500.owner = THIS_MODULE; diff --git a/arch/powerpc/kvm/e500mc.c b/arch/powerpc/kvm/e500mc.c index 795667f7ebf0..611532a0dedc 100644 --- a/arch/powerpc/kvm/e500mc.c +++ b/arch/powerpc/kvm/e500mc.c @@ -404,7 +404,7 @@ static int __init kvmppc_e500mc_init(void) */ kvmppc_init_lpid(KVMPPC_NR_LPIDS/threads_per_core); - r = kvm_init(NULL, sizeof(struct kvmppc_vcpu_e500), 0, THIS_MODULE); + r = kvm_init(sizeof(struct kvmppc_vcpu_e500), 0, THIS_MODULE); if (r) goto err_out; kvm_ops_e500mc.owner = THIS_MODULE; diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 01d0f9935e6c..f5b4ff6bfc89 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -440,11 +440,6 @@ int kvm_arch_hardware_enable(void) return 0; } -int kvm_arch_check_processor_compat(void *opaque) -{ - return 0; -} - int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) { struct kvmppc_ops *kvm_ops = NULL; diff --git a/arch/riscv/kvm/main.c b/arch/riscv/kvm/main.c index be951feee27a..e2da56ed9069 100644 --- a/arch/riscv/kvm/main.c +++ b/arch/riscv/kvm/main.c @@ -20,11 +20,6 @@ long kvm_arch_dev_ioctl(struct file *filp, return -EINVAL; } -int kvm_arch_check_processor_compat(void *opaque) -{ - return 0; -} - int kvm_arch_hardware_enable(void) { unsigned long hideleg, hedeleg; @@ -110,7 +105,7 @@ static int __init riscv_kvm_init(void) kvm_info("VMID %ld bits available\n", kvm_riscv_gstage_vmid_bits()); - return kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE); + return kvm_init(sizeof(struct kvm_vcpu), 0, THIS_MODULE); } module_init(riscv_kvm_init); diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 25b08b956888..7ad8252e92c2 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -262,11 +262,6 @@ int kvm_arch_hardware_enable(void) return 0; } -int kvm_arch_check_processor_compat(void *opaque) -{ - return 0; -} - /* forward declarations */ static void kvm_gmap_notifier(struct gmap *gmap, unsigned long start, unsigned long end); @@ -5716,7 +5711,7 @@ static int __init kvm_s390_init(void) if (r) return r; - r = kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE); + r = kvm_init(sizeof(struct kvm_vcpu), 0, THIS_MODULE); if (r) { __kvm_s390_exit(); return r; diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index e55f8e54e25a..6db44797e85e 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -5109,8 +5109,8 @@ static int __init svm_init(void) * Common KVM initialization _must_ come last, after this, /dev/kvm is * exposed to userspace! */ - r = kvm_init(NULL, sizeof(struct vcpu_svm), - __alignof__(struct vcpu_svm), THIS_MODULE); + r = kvm_init(sizeof(struct vcpu_svm), __alignof__(struct vcpu_svm), + THIS_MODULE); if (r) goto err_kvm_init; diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index e996034809de..3df6b771d816 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -8635,8 +8635,8 @@ static int __init vmx_init(void) * Common KVM initialization _must_ come last, after this, /dev/kvm is * exposed to userspace! */ - r = kvm_init(NULL, sizeof(struct vcpu_vmx), - __alignof__(struct vcpu_vmx), THIS_MODULE); + r = kvm_init(sizeof(struct vcpu_vmx), __alignof__(struct vcpu_vmx), + THIS_MODULE); if (r) goto err_kvm_init; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index d94e6e8692cc..17cbd17c9077 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -12084,11 +12084,6 @@ void kvm_arch_hardware_disable(void) drop_user_return_notifiers(); } -int kvm_arch_check_processor_compat(void *opaque) -{ - return 0; -} - bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu) { return vcpu->kvm->arch.bsp_vcpu_id == vcpu->vcpu_id; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 62d977bb1448..20e207e4c6c1 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -956,8 +956,7 @@ static inline void kvm_irqfd_exit(void) { } #endif -int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align, - struct module *module); +int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module); void kvm_exit(void); void kvm_get_kvm(struct kvm *kvm); @@ -1444,7 +1443,6 @@ static inline void kvm_create_vcpu_debugfs(struct kvm_vcpu *vcpu) {} int kvm_arch_hardware_enable(void); void kvm_arch_hardware_disable(void); -int kvm_arch_check_processor_compat(void *opaque); int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu); bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu); int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 597ff734b312..e13b369cfc1b 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -5902,36 +5902,14 @@ void kvm_unregister_perf_callbacks(void) } #endif -struct kvm_cpu_compat_check { - void *opaque; - int *ret; -}; - -static void check_processor_compat(void *data) +int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module) { - struct kvm_cpu_compat_check *c = data; - - *c->ret = kvm_arch_check_processor_compat(c->opaque); -} - -int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align, - struct module *module) -{ - struct kvm_cpu_compat_check c; int r; int cpu; if (!zalloc_cpumask_var(&cpus_hardware_enabled, GFP_KERNEL)) return -ENOMEM; - c.ret = &r; - c.opaque = opaque; - for_each_online_cpu(cpu) { - smp_call_function_single(cpu, check_processor_compat, &c, 1); - if (r < 0) - goto out_free_2; - } - r = cpuhp_setup_state_nocalls(CPUHP_AP_KVM_STARTING, "kvm/cpu:starting", kvm_starting_cpu, kvm_dying_cpu); if (r) -- cgit v1.2.3 From aaf12a7b4323eb7d94677bcefc286ff6b772ed1c Mon Sep 17 00:00:00 2001 From: Chao Gao Date: Wed, 30 Nov 2022 23:09:25 +0000 Subject: KVM: Rename and move CPUHP_AP_KVM_STARTING to ONLINE section The CPU STARTING section doesn't allow callbacks to fail. Move KVM's hotplug callback to ONLINE section so that it can abort onlining a CPU in certain cases to avoid potentially breaking VMs running on existing CPUs. For example, when KVM fails to enable hardware virtualization on the hotplugged CPU. Place KVM's hotplug state before CPUHP_AP_SCHED_WAIT_EMPTY as it ensures when offlining a CPU, all user tasks and non-pinned kernel tasks have left the CPU, i.e. there cannot be a vCPU task around. So, it is safe for KVM's CPU offline callback to disable hardware virtualization at that point. Likewise, KVM's online callback can enable hardware virtualization before any vCPU task gets a chance to run on hotplugged CPUs. Drop kvm_x86_check_processor_compatibility()'s WARN that IRQs are disabled, as the ONLINE section runs with IRQs disabled. The WARN wasn't intended to be a requirement, e.g. disabling preemption is sufficient, the IRQ thing was purely an aggressive sanity check since the helper was only ever invoked via SMP function call. Rename KVM's CPU hotplug callbacks accordingly. Suggested-by: Thomas Gleixner Signed-off-by: Chao Gao Signed-off-by: Isaku Yamahata Reviewed-by: Yuan Yao [sean: drop WARN that IRQs are disabled] Signed-off-by: Sean Christopherson Message-Id: <20221130230934.1014142-42-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/x86.c | 2 -- include/linux/cpuhotplug.h | 2 +- virt/kvm/kvm_main.c | 30 ++++++++++++++++++++++-------- 3 files changed, 23 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 6575d9e7b9b6..f2971821ec26 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -9298,8 +9298,6 @@ static int kvm_x86_check_processor_compatibility(void) { struct cpuinfo_x86 *c = &cpu_data(smp_processor_id()); - WARN_ON(!irqs_disabled()); - if (__cr4_reserved_bits(cpu_has, c) != __cr4_reserved_bits(cpu_has, &boot_cpu_data)) return -EIO; diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 5cae6bd22f7f..5b2f8147d1ae 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -187,7 +187,6 @@ enum cpuhp_state { CPUHP_AP_CSKY_TIMER_STARTING, CPUHP_AP_TI_GP_TIMER_STARTING, CPUHP_AP_HYPERV_TIMER_STARTING, - CPUHP_AP_KVM_STARTING, /* Must be the last timer callback */ CPUHP_AP_DUMMY_TIMER_STARTING, CPUHP_AP_ARM_XEN_STARTING, @@ -202,6 +201,7 @@ enum cpuhp_state { /* Online section invoked on the hotplugged CPU from the hotplug thread */ CPUHP_AP_ONLINE_IDLE, + CPUHP_AP_KVM_ONLINE, CPUHP_AP_SCHED_WAIT_EMPTY, CPUHP_AP_SMPBOOT_THREADS, CPUHP_AP_X86_VDSO_VMA_ONLINE, diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index e13b369cfc1b..ee1005cb99e1 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -5114,13 +5114,27 @@ static void hardware_enable_nolock(void *junk) } } -static int kvm_starting_cpu(unsigned int cpu) +static int kvm_online_cpu(unsigned int cpu) { + int ret = 0; + + /* + * Abort the CPU online process if hardware virtualization cannot + * be enabled. Otherwise running VMs would encounter unrecoverable + * errors when scheduled to this CPU. + */ raw_spin_lock(&kvm_count_lock); - if (kvm_usage_count) + if (kvm_usage_count) { + WARN_ON_ONCE(atomic_read(&hardware_enable_failed)); + hardware_enable_nolock(NULL); + if (atomic_read(&hardware_enable_failed)) { + atomic_set(&hardware_enable_failed, 0); + ret = -EIO; + } + } raw_spin_unlock(&kvm_count_lock); - return 0; + return ret; } static void hardware_disable_nolock(void *junk) @@ -5133,7 +5147,7 @@ static void hardware_disable_nolock(void *junk) kvm_arch_hardware_disable(); } -static int kvm_dying_cpu(unsigned int cpu) +static int kvm_offline_cpu(unsigned int cpu) { raw_spin_lock(&kvm_count_lock); if (kvm_usage_count) @@ -5910,8 +5924,8 @@ int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module) if (!zalloc_cpumask_var(&cpus_hardware_enabled, GFP_KERNEL)) return -ENOMEM; - r = cpuhp_setup_state_nocalls(CPUHP_AP_KVM_STARTING, "kvm/cpu:starting", - kvm_starting_cpu, kvm_dying_cpu); + r = cpuhp_setup_state_nocalls(CPUHP_AP_KVM_ONLINE, "kvm/cpu:online", + kvm_online_cpu, kvm_offline_cpu); if (r) goto out_free_2; register_reboot_notifier(&kvm_reboot_notifier); @@ -5985,7 +5999,7 @@ out_free_4: kmem_cache_destroy(kvm_vcpu_cache); out_free_3: unregister_reboot_notifier(&kvm_reboot_notifier); - cpuhp_remove_state_nocalls(CPUHP_AP_KVM_STARTING); + cpuhp_remove_state_nocalls(CPUHP_AP_KVM_ONLINE); out_free_2: free_cpumask_var(cpus_hardware_enabled); return r; @@ -6011,7 +6025,7 @@ void kvm_exit(void) kvm_async_pf_deinit(); unregister_syscore_ops(&kvm_syscore_ops); unregister_reboot_notifier(&kvm_reboot_notifier); - cpuhp_remove_state_nocalls(CPUHP_AP_KVM_STARTING); + cpuhp_remove_state_nocalls(CPUHP_AP_KVM_ONLINE); on_each_cpu(hardware_disable_nolock, NULL, 1); kvm_irqfd_exit(); free_cpumask_var(cpus_hardware_enabled); -- cgit v1.2.3 From 441f7bfa99fe2b8a7e504aa72047e20579e88a5d Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 30 Nov 2022 23:09:33 +0000 Subject: KVM: Opt out of generic hardware enabling on s390 and PPC Allow architectures to opt out of the generic hardware enabling logic, and opt out on both s390 and PPC, which don't need to manually enable virtualization as it's always on (when available). In addition to letting s390 and PPC drop a bit of dead code, this will hopefully also allow ARM to clean up its related code, e.g. ARM has its own per-CPU flag to track which CPUs have enable hardware due to the need to keep hardware enabled indefinitely when pKVM is enabled. Signed-off-by: Sean Christopherson Acked-by: Anup Patel Message-Id: <20221130230934.1014142-50-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/arm64/kvm/Kconfig | 1 + arch/mips/kvm/Kconfig | 1 + arch/powerpc/include/asm/kvm_host.h | 1 - arch/powerpc/kvm/powerpc.c | 5 ----- arch/riscv/kvm/Kconfig | 1 + arch/s390/include/asm/kvm_host.h | 1 - arch/s390/kvm/kvm-s390.c | 6 ------ arch/x86/kvm/Kconfig | 1 + include/linux/kvm_host.h | 4 ++++ virt/kvm/Kconfig | 3 +++ virt/kvm/kvm_main.c | 30 ++++++++++++++++++++++++------ 11 files changed, 35 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig index 05da3c8f7e88..ca6eadeb7d1a 100644 --- a/arch/arm64/kvm/Kconfig +++ b/arch/arm64/kvm/Kconfig @@ -21,6 +21,7 @@ if VIRTUALIZATION menuconfig KVM bool "Kernel-based Virtual Machine (KVM) support" depends on HAVE_KVM + select KVM_GENERIC_HARDWARE_ENABLING select MMU_NOTIFIER select PREEMPT_NOTIFIERS select HAVE_KVM_CPU_RELAX_INTERCEPT diff --git a/arch/mips/kvm/Kconfig b/arch/mips/kvm/Kconfig index 91d197bee9c0..29e51649203b 100644 --- a/arch/mips/kvm/Kconfig +++ b/arch/mips/kvm/Kconfig @@ -28,6 +28,7 @@ config KVM select MMU_NOTIFIER select SRCU select INTERVAL_TREE + select KVM_GENERIC_HARDWARE_ENABLING help Support for hosting Guest kernels. diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 0a80e80c7b9e..959f566a455c 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -876,7 +876,6 @@ struct kvm_vcpu_arch { #define __KVM_HAVE_ARCH_WQP #define __KVM_HAVE_CREATE_DEVICE -static inline void kvm_arch_hardware_disable(void) {} static inline void kvm_arch_sync_events(struct kvm *kvm) {} static inline void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) {} static inline void kvm_arch_flush_shadow_all(struct kvm *kvm) {} diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index f5b4ff6bfc89..4c5405fc5538 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -435,11 +435,6 @@ int kvmppc_ld(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr, } EXPORT_SYMBOL_GPL(kvmppc_ld); -int kvm_arch_hardware_enable(void) -{ - return 0; -} - int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) { struct kvmppc_ops *kvm_ops = NULL; diff --git a/arch/riscv/kvm/Kconfig b/arch/riscv/kvm/Kconfig index f36a737d5f96..d5a658a047a7 100644 --- a/arch/riscv/kvm/Kconfig +++ b/arch/riscv/kvm/Kconfig @@ -20,6 +20,7 @@ if VIRTUALIZATION config KVM tristate "Kernel-based Virtual Machine (KVM) support (EXPERIMENTAL)" depends on RISCV_SBI && MMU + select KVM_GENERIC_HARDWARE_ENABLING select MMU_NOTIFIER select PREEMPT_NOTIFIERS select KVM_MMIO diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index d67ce719d16a..2bbc3d54959d 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -1031,7 +1031,6 @@ extern char sie_exit; extern int kvm_s390_gisc_register(struct kvm *kvm, u32 gisc); extern int kvm_s390_gisc_unregister(struct kvm *kvm, u32 gisc); -static inline void kvm_arch_hardware_disable(void) {} static inline void kvm_arch_sync_events(struct kvm *kvm) {} static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {} static inline void kvm_arch_free_memslot(struct kvm *kvm, diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 7ad8252e92c2..bd25076aa19b 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -256,12 +256,6 @@ debug_info_t *kvm_s390_dbf; debug_info_t *kvm_s390_dbf_uv; /* Section: not file related */ -int kvm_arch_hardware_enable(void) -{ - /* every s390 is virtualization enabled ;-) */ - return 0; -} - /* forward declarations */ static void kvm_gmap_notifier(struct gmap *gmap, unsigned long start, unsigned long end); diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index fbeaa9ddef59..8e578311ca9d 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -49,6 +49,7 @@ config KVM select SRCU select INTERVAL_TREE select HAVE_KVM_PM_NOTIFIER if PM + select KVM_GENERIC_HARDWARE_ENABLING help Support hosting fully virtualized guest machines using hardware virtualization extensions. You will need a fairly recent diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 20e207e4c6c1..109b18e2789c 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1441,8 +1441,10 @@ void kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu, struct dentry *debugfs_ static inline void kvm_create_vcpu_debugfs(struct kvm_vcpu *vcpu) {} #endif +#ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING int kvm_arch_hardware_enable(void); void kvm_arch_hardware_disable(void); +#endif int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu); bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu); int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu); @@ -2074,7 +2076,9 @@ static inline bool kvm_check_request(int req, struct kvm_vcpu *vcpu) } } +#ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING extern bool kvm_rebooting; +#endif extern unsigned int halt_poll_ns; extern unsigned int halt_poll_ns_grow; diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig index 9fb1ff6f19e5..b74916de5183 100644 --- a/virt/kvm/Kconfig +++ b/virt/kvm/Kconfig @@ -92,3 +92,6 @@ config KVM_XFER_TO_GUEST_WORK config HAVE_KVM_PM_NOTIFIER bool + +config KVM_GENERIC_HARDWARE_ENABLING + bool diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 6c0bd9a8e27e..3d0678579c5e 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -102,9 +102,6 @@ EXPORT_SYMBOL_GPL(halt_poll_ns_shrink); DEFINE_MUTEX(kvm_lock); LIST_HEAD(vm_list); -static DEFINE_PER_CPU(bool, hardware_enabled); -static int kvm_usage_count; - static struct kmem_cache *kvm_vcpu_cache; static __read_mostly struct preempt_ops kvm_preempt_ops; @@ -146,9 +143,6 @@ static void hardware_disable_all(void); static void kvm_io_bus_destroy(struct kvm_io_bus *bus); -__visible bool kvm_rebooting; -EXPORT_SYMBOL_GPL(kvm_rebooting); - #define KVM_EVENT_CREATE_VM 0 #define KVM_EVENT_DESTROY_VM 1 static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm); @@ -5093,6 +5087,13 @@ static struct miscdevice kvm_dev = { &kvm_chardev_ops, }; +#ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING +__visible bool kvm_rebooting; +EXPORT_SYMBOL_GPL(kvm_rebooting); + +static DEFINE_PER_CPU(bool, hardware_enabled); +static int kvm_usage_count; + static int __hardware_enable_nolock(void) { if (__this_cpu_read(hardware_enabled)) @@ -5254,6 +5255,17 @@ static struct syscore_ops kvm_syscore_ops = { .suspend = kvm_suspend, .resume = kvm_resume, }; +#else /* CONFIG_KVM_GENERIC_HARDWARE_ENABLING */ +static int hardware_enable_all(void) +{ + return 0; +} + +static void hardware_disable_all(void) +{ + +} +#endif /* CONFIG_KVM_GENERIC_HARDWARE_ENABLING */ static void kvm_io_bus_destroy(struct kvm_io_bus *bus) { @@ -5942,6 +5954,7 @@ int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module) int r; int cpu; +#ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING r = cpuhp_setup_state_nocalls(CPUHP_AP_KVM_ONLINE, "kvm/cpu:online", kvm_online_cpu, kvm_offline_cpu); if (r) @@ -5949,6 +5962,7 @@ int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module) register_reboot_notifier(&kvm_reboot_notifier); register_syscore_ops(&kvm_syscore_ops); +#endif /* A kmem cache lets us meet the alignment requirements of fx_save. */ if (!vcpu_align) @@ -6016,9 +6030,11 @@ out_free_4: free_cpumask_var(per_cpu(cpu_kick_mask, cpu)); kmem_cache_destroy(kvm_vcpu_cache); out_free_3: +#ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING unregister_syscore_ops(&kvm_syscore_ops); unregister_reboot_notifier(&kvm_reboot_notifier); cpuhp_remove_state_nocalls(CPUHP_AP_KVM_ONLINE); +#endif return r; } EXPORT_SYMBOL_GPL(kvm_init); @@ -6040,9 +6056,11 @@ void kvm_exit(void) kmem_cache_destroy(kvm_vcpu_cache); kvm_vfio_ops_exit(); kvm_async_pf_deinit(); +#ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING unregister_syscore_ops(&kvm_syscore_ops); unregister_reboot_notifier(&kvm_reboot_notifier); cpuhp_remove_state_nocalls(CPUHP_AP_KVM_ONLINE); +#endif kvm_irqfd_exit(); } EXPORT_SYMBOL_GPL(kvm_exit); -- cgit v1.2.3 From 876293121f24fc1a7df85450d0997f54540c8979 Mon Sep 17 00:00:00 2001 From: Niklas Cassel Date: Thu, 29 Dec 2022 17:59:57 +0100 Subject: ata: scsi: rename flag ATA_QCFLAG_FAILED to ATA_QCFLAG_EH The name ATA_QCFLAG_FAILED is misleading since it does not mean that a QC completed in error, or that it didn't complete at all. It means that libata decided to schedule EH for the QC, so the QC is now owned by the libata error handler (EH). The normal execution path is responsible for not accessing a QC owned by EH. libata core enforces the rule by returning NULL from ata_qc_from_tag() for QCs owned by EH. It is quite easy to mistake that a QC marked with ATA_QCFLAG_FAILED was an error. However, a QC that was actually an error is instead indicated by having qc->err_mask set. E.g. when we have a NCQ error, we abort all QCs, which currently will mark all QCs as ATA_QCFLAG_FAILED. However, it will only be a single QC that is an error (i.e. has qc->err_mask set). Rename ATA_QCFLAG_FAILED to ATA_QCFLAG_EH to more clearly highlight that this flag simply means that a QC is now owned by EH. This new name will not mislead to think that the QC was an error (which is instead indicated by having qc->err_mask set). This also makes it more obvious that the EH code skips all QCs that do not have ATA_QCFLAG_EH set (rather than ATA_QCFLAG_FAILED), since the EH code should simply only care about QCs that are owned by EH itself. Signed-off-by: Niklas Cassel Reviewed-by: John Garry Signed-off-by: Damien Le Moal --- drivers/ata/acard-ahci.c | 2 +- drivers/ata/libahci.c | 4 ++-- drivers/ata/libata-core.c | 12 ++++++------ drivers/ata/libata-eh.c | 22 +++++++++++----------- drivers/ata/libata-sata.c | 4 ++-- drivers/ata/libata-sff.c | 4 ++-- drivers/ata/libata-trace.c | 2 +- drivers/ata/sata_fsl.c | 2 +- drivers/ata/sata_inic162x.c | 2 +- drivers/ata/sata_promise.c | 2 +- drivers/ata/sata_sil24.c | 2 +- drivers/ata/sata_sx4.c | 2 +- drivers/scsi/ipr.c | 4 ++-- drivers/scsi/libsas/sas_ata.c | 8 ++++---- include/linux/libata.h | 4 ++-- 15 files changed, 38 insertions(+), 38 deletions(-) (limited to 'include/linux') diff --git a/drivers/ata/acard-ahci.c b/drivers/ata/acard-ahci.c index 7654a40c12b4..da74a86b70ba 100644 --- a/drivers/ata/acard-ahci.c +++ b/drivers/ata/acard-ahci.c @@ -263,7 +263,7 @@ static bool acard_ahci_qc_fill_rtf(struct ata_queued_cmd *qc) * Setup FIS. */ if (qc->tf.protocol == ATA_PROT_PIO && qc->dma_dir == DMA_FROM_DEVICE && - !(qc->flags & ATA_QCFLAG_FAILED)) { + !(qc->flags & ATA_QCFLAG_EH)) { ata_tf_from_fis(rx_fis + RX_FIS_PIO_SETUP, &qc->result_tf); qc->result_tf.status = (rx_fis + RX_FIS_PIO_SETUP)[15]; } else diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c index 29acc35bf4a6..03aa9eb415d3 100644 --- a/drivers/ata/libahci.c +++ b/drivers/ata/libahci.c @@ -2068,7 +2068,7 @@ static bool ahci_qc_fill_rtf(struct ata_queued_cmd *qc) * Setup FIS. */ if (qc->tf.protocol == ATA_PROT_PIO && qc->dma_dir == DMA_FROM_DEVICE && - !(qc->flags & ATA_QCFLAG_FAILED)) { + !(qc->flags & ATA_QCFLAG_EH)) { ata_tf_from_fis(rx_fis + RX_FIS_PIO_SETUP, &qc->result_tf); qc->result_tf.status = (rx_fis + RX_FIS_PIO_SETUP)[15]; @@ -2138,7 +2138,7 @@ static void ahci_post_internal_cmd(struct ata_queued_cmd *qc) struct ata_port *ap = qc->ap; /* make DMA engine forget about the failed command */ - if (qc->flags & ATA_QCFLAG_FAILED) + if (qc->flags & ATA_QCFLAG_EH) ahci_kick_engine(ap); } diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 884ae73b11ea..6b03bebcde50 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -1590,7 +1590,7 @@ static unsigned ata_exec_internal_sg(struct ata_device *dev, ap->ops->post_internal_cmd(qc); /* perform minimal error analysis */ - if (qc->flags & ATA_QCFLAG_FAILED) { + if (qc->flags & ATA_QCFLAG_EH) { if (qc->result_tf.status & (ATA_ERR | ATA_DF)) qc->err_mask |= AC_ERR_DEV; @@ -4683,10 +4683,10 @@ void ata_qc_complete(struct ata_queued_cmd *qc) /* XXX: New EH and old EH use different mechanisms to * synchronize EH with regular execution path. * - * In new EH, a failed qc is marked with ATA_QCFLAG_FAILED. + * In new EH, a qc owned by EH is marked with ATA_QCFLAG_EH. * Normal execution path is responsible for not accessing a - * failed qc. libata core enforces the rule by returning NULL - * from ata_qc_from_tag() for failed qcs. + * qc owned by EH. libata core enforces the rule by returning NULL + * from ata_qc_from_tag() for qcs owned by EH. * * Old EH depends on ata_qc_complete() nullifying completion * requests if ATA_QCFLAG_EH_SCHEDULED is set. Old EH does @@ -4698,7 +4698,7 @@ void ata_qc_complete(struct ata_queued_cmd *qc) struct ata_eh_info *ehi = &dev->link->eh_info; if (unlikely(qc->err_mask)) - qc->flags |= ATA_QCFLAG_FAILED; + qc->flags |= ATA_QCFLAG_EH; /* * Finish internal commands without any further processing @@ -4715,7 +4715,7 @@ void ata_qc_complete(struct ata_queued_cmd *qc) * Non-internal qc has failed. Fill the result TF and * summon EH. */ - if (unlikely(qc->flags & ATA_QCFLAG_FAILED)) { + if (unlikely(qc->flags & ATA_QCFLAG_EH)) { fill_result_tf(qc); trace_ata_qc_complete_failed(qc); ata_qc_schedule_eh(qc); diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c index 2a70e1f12db5..a6c901811802 100644 --- a/drivers/ata/libata-eh.c +++ b/drivers/ata/libata-eh.c @@ -581,7 +581,7 @@ void ata_scsi_cmd_error_handler(struct Scsi_Host *host, struct ata_port *ap, * normal completion, error completion, and SCSI timeout. * Both completions can race against SCSI timeout. When normal * completion wins, the qc never reaches EH. When error - * completion wins, the qc has ATA_QCFLAG_FAILED set. + * completion wins, the qc has ATA_QCFLAG_EH set. * * When SCSI timeout wins, things are a bit more complex. * Normal or error completion can occur after the timeout but @@ -615,10 +615,10 @@ void ata_scsi_cmd_error_handler(struct Scsi_Host *host, struct ata_port *ap, if (i < ATA_MAX_QUEUE) { /* the scmd has an associated qc */ - if (!(qc->flags & ATA_QCFLAG_FAILED)) { + if (!(qc->flags & ATA_QCFLAG_EH)) { /* which hasn't failed yet, timeout */ qc->err_mask |= AC_ERR_TIMEOUT; - qc->flags |= ATA_QCFLAG_FAILED; + qc->flags |= ATA_QCFLAG_EH; nr_timedout++; } } else { @@ -636,7 +636,7 @@ void ata_scsi_cmd_error_handler(struct Scsi_Host *host, struct ata_port *ap, * this point but the state of the controller is * unknown. Freeze the port to make sure the IRQ * handler doesn't diddle with those qcs. This must - * be done atomically w.r.t. setting QCFLAG_FAILED. + * be done atomically w.r.t. setting ATA_QCFLAG_EH. */ if (nr_timedout) __ata_port_freeze(ap); @@ -914,12 +914,12 @@ void ata_qc_schedule_eh(struct ata_queued_cmd *qc) WARN_ON(!ap->ops->error_handler); - qc->flags |= ATA_QCFLAG_FAILED; + qc->flags |= ATA_QCFLAG_EH; ata_eh_set_pending(ap, 1); /* The following will fail if timeout has already expired. * ata_scsi_error() takes care of such scmds on EH entry. - * Note that ATA_QCFLAG_FAILED is unconditionally set after + * Note that ATA_QCFLAG_EH is unconditionally set after * this function completes. */ blk_abort_request(scsi_cmd_to_rq(qc->scsicmd)); @@ -997,7 +997,7 @@ static int ata_do_link_abort(struct ata_port *ap, struct ata_link *link) /* include internal tag in iteration */ ata_qc_for_each_with_internal(ap, qc, tag) { if (qc && (!link || qc->dev->link == link)) { - qc->flags |= ATA_QCFLAG_FAILED; + qc->flags |= ATA_QCFLAG_EH; ata_qc_complete(qc); nr_aborted++; } @@ -1957,7 +1957,7 @@ static void ata_eh_link_autopsy(struct ata_link *link) all_err_mask |= ehc->i.err_mask; ata_qc_for_each_raw(ap, qc, tag) { - if (!(qc->flags & ATA_QCFLAG_FAILED) || + if (!(qc->flags & ATA_QCFLAG_EH) || qc->flags & ATA_QCFLAG_RETRY || ata_dev_phys_link(qc->dev) != link) continue; @@ -2235,7 +2235,7 @@ static void ata_eh_link_report(struct ata_link *link) desc = ehc->i.desc; ata_qc_for_each_raw(ap, qc, tag) { - if (!(qc->flags & ATA_QCFLAG_FAILED) || + if (!(qc->flags & ATA_QCFLAG_EH) || ata_dev_phys_link(qc->dev) != link || ((qc->flags & ATA_QCFLAG_QUIET) && qc->err_mask == AC_ERR_DEV)) @@ -2301,7 +2301,7 @@ static void ata_eh_link_report(struct ata_link *link) char data_buf[20] = ""; char cdb_buf[70] = ""; - if (!(qc->flags & ATA_QCFLAG_FAILED) || + if (!(qc->flags & ATA_QCFLAG_EH) || ata_dev_phys_link(qc->dev) != link || !qc->err_mask) continue; @@ -3805,7 +3805,7 @@ void ata_eh_finish(struct ata_port *ap) /* retry or finish qcs */ ata_qc_for_each_raw(ap, qc, tag) { - if (!(qc->flags & ATA_QCFLAG_FAILED)) + if (!(qc->flags & ATA_QCFLAG_EH)) continue; if (qc->err_mask) { diff --git a/drivers/ata/libata-sata.c b/drivers/ata/libata-sata.c index 18ef14e749a0..908f35acee1e 100644 --- a/drivers/ata/libata-sata.c +++ b/drivers/ata/libata-sata.c @@ -1429,7 +1429,7 @@ void ata_eh_analyze_ncq_error(struct ata_link *link) /* has LLDD analyzed already? */ ata_qc_for_each_raw(ap, qc, tag) { - if (!(qc->flags & ATA_QCFLAG_FAILED)) + if (!(qc->flags & ATA_QCFLAG_EH)) continue; if (qc->err_mask) @@ -1477,7 +1477,7 @@ void ata_eh_analyze_ncq_error(struct ata_link *link) } ata_qc_for_each_raw(ap, qc, tag) { - if (!(qc->flags & ATA_QCFLAG_FAILED) || + if (!(qc->flags & ATA_QCFLAG_EH) || ata_dev_phys_link(qc->dev) != link) continue; diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c index 153f49e00713..34beda28e712 100644 --- a/drivers/ata/libata-sff.c +++ b/drivers/ata/libata-sff.c @@ -2073,7 +2073,7 @@ void ata_sff_error_handler(struct ata_port *ap) unsigned long flags; qc = __ata_qc_from_tag(ap, ap->link.active_tag); - if (qc && !(qc->flags & ATA_QCFLAG_FAILED)) + if (qc && !(qc->flags & ATA_QCFLAG_EH)) qc = NULL; spin_lock_irqsave(ap->lock, flags); @@ -2796,7 +2796,7 @@ void ata_bmdma_error_handler(struct ata_port *ap) bool thaw = false; qc = __ata_qc_from_tag(ap, ap->link.active_tag); - if (qc && !(qc->flags & ATA_QCFLAG_FAILED)) + if (qc && !(qc->flags & ATA_QCFLAG_EH)) qc = NULL; /* reset PIO HSM and stop DMA engine */ diff --git a/drivers/ata/libata-trace.c b/drivers/ata/libata-trace.c index e0e4d0d5a100..9b5363fd0ab0 100644 --- a/drivers/ata/libata-trace.c +++ b/drivers/ata/libata-trace.c @@ -142,7 +142,7 @@ libata_trace_parse_qc_flags(struct trace_seq *p, unsigned int qc_flags) trace_seq_printf(p, "QUIET "); if (qc_flags & ATA_QCFLAG_RETRY) trace_seq_printf(p, "RETRY "); - if (qc_flags & ATA_QCFLAG_FAILED) + if (qc_flags & ATA_QCFLAG_EH) trace_seq_printf(p, "FAILED "); if (qc_flags & ATA_QCFLAG_SENSE_VALID) trace_seq_printf(p, "SENSE_VALID "); diff --git a/drivers/ata/sata_fsl.c b/drivers/ata/sata_fsl.c index b9a4f68b371d..7eab9c4e1473 100644 --- a/drivers/ata/sata_fsl.c +++ b/drivers/ata/sata_fsl.c @@ -1042,7 +1042,7 @@ static void sata_fsl_error_handler(struct ata_port *ap) static void sata_fsl_post_internal_cmd(struct ata_queued_cmd *qc) { - if (qc->flags & ATA_QCFLAG_FAILED) + if (qc->flags & ATA_QCFLAG_EH) qc->err_mask |= AC_ERR_OTHER; if (qc->err_mask) { diff --git a/drivers/ata/sata_inic162x.c b/drivers/ata/sata_inic162x.c index 11e518f0111c..f480ff456190 100644 --- a/drivers/ata/sata_inic162x.c +++ b/drivers/ata/sata_inic162x.c @@ -672,7 +672,7 @@ static void inic_error_handler(struct ata_port *ap) static void inic_post_internal_cmd(struct ata_queued_cmd *qc) { /* make DMA engine forget about the failed command */ - if (qc->flags & ATA_QCFLAG_FAILED) + if (qc->flags & ATA_QCFLAG_EH) inic_reset_port(inic_port_base(qc->ap)); } diff --git a/drivers/ata/sata_promise.c b/drivers/ata/sata_promise.c index 9cd7d8b71361..4e60e6c4c35a 100644 --- a/drivers/ata/sata_promise.c +++ b/drivers/ata/sata_promise.c @@ -828,7 +828,7 @@ static void pdc_post_internal_cmd(struct ata_queued_cmd *qc) struct ata_port *ap = qc->ap; /* make DMA engine forget about the failed command */ - if (qc->flags & ATA_QCFLAG_FAILED) + if (qc->flags & ATA_QCFLAG_EH) pdc_reset_port(ap); } diff --git a/drivers/ata/sata_sil24.c b/drivers/ata/sata_sil24.c index 2fef6ce93f07..0a01518a8d97 100644 --- a/drivers/ata/sata_sil24.c +++ b/drivers/ata/sata_sil24.c @@ -1185,7 +1185,7 @@ static void sil24_post_internal_cmd(struct ata_queued_cmd *qc) struct ata_port *ap = qc->ap; /* make DMA engine forget about the failed command */ - if ((qc->flags & ATA_QCFLAG_FAILED) && sil24_init_port(ap)) + if ((qc->flags & ATA_QCFLAG_EH) && sil24_init_port(ap)) ata_eh_freeze_port(ap); } diff --git a/drivers/ata/sata_sx4.c b/drivers/ata/sata_sx4.c index ab70cbc78f96..a92c60455b1d 100644 --- a/drivers/ata/sata_sx4.c +++ b/drivers/ata/sata_sx4.c @@ -866,7 +866,7 @@ static void pdc_post_internal_cmd(struct ata_queued_cmd *qc) struct ata_port *ap = qc->ap; /* make DMA engine forget about the failed command */ - if (qc->flags & ATA_QCFLAG_FAILED) + if (qc->flags & ATA_QCFLAG_EH) pdc_reset_port(ap); } diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c index 2022ffb45041..c68ca2218a05 100644 --- a/drivers/scsi/ipr.c +++ b/drivers/scsi/ipr.c @@ -5370,9 +5370,9 @@ static int __ipr_eh_dev_reset(struct scsi_cmnd *scsi_cmd) continue; ipr_cmd->done = ipr_sata_eh_done; - if (!(ipr_cmd->qc->flags & ATA_QCFLAG_FAILED)) { + if (!(ipr_cmd->qc->flags & ATA_QCFLAG_EH)) { ipr_cmd->qc->err_mask |= AC_ERR_TIMEOUT; - ipr_cmd->qc->flags |= ATA_QCFLAG_FAILED; + ipr_cmd->qc->flags |= ATA_QCFLAG_EH; } } } diff --git a/drivers/scsi/libsas/sas_ata.c b/drivers/scsi/libsas/sas_ata.c index 1ccce706167a..14da33a3b6a6 100644 --- a/drivers/scsi/libsas/sas_ata.c +++ b/drivers/scsi/libsas/sas_ata.c @@ -125,7 +125,7 @@ static void sas_ata_task_done(struct sas_task *task) } else { link->eh_info.err_mask |= ac_err_mask(dev->sata_dev.fis[2]); if (unlikely(link->eh_info.err_mask)) - qc->flags |= ATA_QCFLAG_FAILED; + qc->flags |= ATA_QCFLAG_EH; } } else { ac = sas_to_ata_err(stat); @@ -136,7 +136,7 @@ static void sas_ata_task_done(struct sas_task *task) qc->err_mask = ac; } else { link->eh_info.err_mask |= AC_ERR_DEV; - qc->flags |= ATA_QCFLAG_FAILED; + qc->flags |= ATA_QCFLAG_EH; } dev->sata_dev.fis[2] = ATA_ERR | ATA_DRDY; /* tf status */ @@ -476,7 +476,7 @@ static void sas_ata_internal_abort(struct sas_task *task) static void sas_ata_post_internal(struct ata_queued_cmd *qc) { - if (qc->flags & ATA_QCFLAG_FAILED) + if (qc->flags & ATA_QCFLAG_EH) qc->err_mask |= AC_ERR_OTHER; if (qc->err_mask) { @@ -631,7 +631,7 @@ void sas_ata_task_abort(struct sas_task *task) /* Internal command, fake a timeout and complete. */ qc->flags &= ~ATA_QCFLAG_ACTIVE; - qc->flags |= ATA_QCFLAG_FAILED; + qc->flags |= ATA_QCFLAG_EH; qc->err_mask |= AC_ERR_TIMEOUT; waiting = qc->private_data; complete(waiting); diff --git a/include/linux/libata.h b/include/linux/libata.h index c9149ebe7423..7985e6e2ae0e 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -206,7 +206,7 @@ enum { ATA_QCFLAG_QUIET = (1 << 6), /* don't report device error */ ATA_QCFLAG_RETRY = (1 << 7), /* retry after failure */ - ATA_QCFLAG_FAILED = (1 << 16), /* cmd failed and is owned by EH */ + ATA_QCFLAG_EH = (1 << 16), /* cmd aborted and owned by EH */ ATA_QCFLAG_SENSE_VALID = (1 << 17), /* sense data valid */ ATA_QCFLAG_EH_SCHEDULED = (1 << 18), /* EH scheduled (obsolete) */ @@ -1756,7 +1756,7 @@ static inline struct ata_queued_cmd *ata_qc_from_tag(struct ata_port *ap, return qc; if ((qc->flags & (ATA_QCFLAG_ACTIVE | - ATA_QCFLAG_FAILED)) == ATA_QCFLAG_ACTIVE) + ATA_QCFLAG_EH)) == ATA_QCFLAG_ACTIVE) return qc; return NULL; -- cgit v1.2.3 From 931139af5718fb41565fff2420daf995c016ec80 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Thu, 29 Dec 2022 17:59:58 +0100 Subject: ata: libata: simplify qc_fill_rtf port operation interface The boolean return value of the qc_fill_rtf operation is used nowhere. Simplify this operation interface by making it a void function. All drivers defining this operation are also updated. Signed-off-by: Damien Le Moal Signed-off-by: Niklas Cassel Reviewed-by: John Garry --- drivers/ata/acard-ahci.c | 6 ++---- drivers/ata/libahci.c | 6 ++---- drivers/ata/libata-sff.c | 6 +----- drivers/ata/sata_fsl.c | 3 +-- drivers/ata/sata_inic162x.c | 12 +++++------- drivers/ata/sata_sil24.c | 5 ++--- drivers/scsi/ipr.c | 7 +------ drivers/scsi/libsas/sas_ata.c | 3 +-- include/linux/libata.h | 4 ++-- 9 files changed, 17 insertions(+), 35 deletions(-) (limited to 'include/linux') diff --git a/drivers/ata/acard-ahci.c b/drivers/ata/acard-ahci.c index da74a86b70ba..993eadd173da 100644 --- a/drivers/ata/acard-ahci.c +++ b/drivers/ata/acard-ahci.c @@ -57,7 +57,7 @@ struct acard_sg { }; static enum ata_completion_errors acard_ahci_qc_prep(struct ata_queued_cmd *qc); -static bool acard_ahci_qc_fill_rtf(struct ata_queued_cmd *qc); +static void acard_ahci_qc_fill_rtf(struct ata_queued_cmd *qc); static int acard_ahci_port_start(struct ata_port *ap); static int acard_ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent); @@ -248,7 +248,7 @@ static enum ata_completion_errors acard_ahci_qc_prep(struct ata_queued_cmd *qc) return AC_ERR_OK; } -static bool acard_ahci_qc_fill_rtf(struct ata_queued_cmd *qc) +static void acard_ahci_qc_fill_rtf(struct ata_queued_cmd *qc) { struct ahci_port_priv *pp = qc->ap->private_data; u8 *rx_fis = pp->rx_fis; @@ -268,8 +268,6 @@ static bool acard_ahci_qc_fill_rtf(struct ata_queued_cmd *qc) qc->result_tf.status = (rx_fis + RX_FIS_PIO_SETUP)[15]; } else ata_tf_from_fis(rx_fis + RX_FIS_D2H_REG, &qc->result_tf); - - return true; } static int acard_ahci_port_start(struct ata_port *ap) diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c index 03aa9eb415d3..0167aac25c34 100644 --- a/drivers/ata/libahci.c +++ b/drivers/ata/libahci.c @@ -55,7 +55,7 @@ static ssize_t ahci_transmit_led_message(struct ata_port *ap, u32 state, static int ahci_scr_read(struct ata_link *link, unsigned int sc_reg, u32 *val); static int ahci_scr_write(struct ata_link *link, unsigned int sc_reg, u32 val); -static bool ahci_qc_fill_rtf(struct ata_queued_cmd *qc); +static void ahci_qc_fill_rtf(struct ata_queued_cmd *qc); static int ahci_port_start(struct ata_port *ap); static void ahci_port_stop(struct ata_port *ap); static enum ata_completion_errors ahci_qc_prep(struct ata_queued_cmd *qc); @@ -2053,7 +2053,7 @@ unsigned int ahci_qc_issue(struct ata_queued_cmd *qc) } EXPORT_SYMBOL_GPL(ahci_qc_issue); -static bool ahci_qc_fill_rtf(struct ata_queued_cmd *qc) +static void ahci_qc_fill_rtf(struct ata_queued_cmd *qc) { struct ahci_port_priv *pp = qc->ap->private_data; u8 *rx_fis = pp->rx_fis; @@ -2087,8 +2087,6 @@ static bool ahci_qc_fill_rtf(struct ata_queued_cmd *qc) qc->result_tf.error = fis[3]; } else ata_tf_from_fis(rx_fis + RX_FIS_D2H_REG, &qc->result_tf); - - return true; } static void ahci_freeze(struct ata_port *ap) diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c index 34beda28e712..cd82d3b5ed14 100644 --- a/drivers/ata/libata-sff.c +++ b/drivers/ata/libata-sff.c @@ -1377,14 +1377,10 @@ EXPORT_SYMBOL_GPL(ata_sff_qc_issue); * * LOCKING: * spin_lock_irqsave(host lock) - * - * RETURNS: - * true indicating that result TF is successfully filled. */ -bool ata_sff_qc_fill_rtf(struct ata_queued_cmd *qc) +void ata_sff_qc_fill_rtf(struct ata_queued_cmd *qc) { qc->ap->ops->sff_tf_read(qc->ap, &qc->result_tf); - return true; } EXPORT_SYMBOL_GPL(ata_sff_qc_fill_rtf); diff --git a/drivers/ata/sata_fsl.c b/drivers/ata/sata_fsl.c index 7eab9c4e1473..b052c5a65c17 100644 --- a/drivers/ata/sata_fsl.c +++ b/drivers/ata/sata_fsl.c @@ -566,7 +566,7 @@ static unsigned int sata_fsl_qc_issue(struct ata_queued_cmd *qc) return 0; } -static bool sata_fsl_qc_fill_rtf(struct ata_queued_cmd *qc) +static void sata_fsl_qc_fill_rtf(struct ata_queued_cmd *qc) { struct sata_fsl_port_priv *pp = qc->ap->private_data; struct sata_fsl_host_priv *host_priv = qc->ap->host->private_data; @@ -577,7 +577,6 @@ static bool sata_fsl_qc_fill_rtf(struct ata_queued_cmd *qc) cd = pp->cmdentry + tag; ata_tf_from_fis(cd->sfis, &qc->result_tf); - return true; } static int sata_fsl_scr_write(struct ata_link *link, diff --git a/drivers/ata/sata_inic162x.c b/drivers/ata/sata_inic162x.c index f480ff456190..2833c722118d 100644 --- a/drivers/ata/sata_inic162x.c +++ b/drivers/ata/sata_inic162x.c @@ -566,7 +566,7 @@ static void inic_tf_read(struct ata_port *ap, struct ata_taskfile *tf) tf->status = readb(port_base + PORT_TF_COMMAND); } -static bool inic_qc_fill_rtf(struct ata_queued_cmd *qc) +static void inic_qc_fill_rtf(struct ata_queued_cmd *qc) { struct ata_taskfile *rtf = &qc->result_tf; struct ata_taskfile tf; @@ -580,12 +580,10 @@ static bool inic_qc_fill_rtf(struct ata_queued_cmd *qc) */ inic_tf_read(qc->ap, &tf); - if (!(tf.status & ATA_ERR)) - return false; - - rtf->status = tf.status; - rtf->error = tf.error; - return true; + if (tf.status & ATA_ERR) { + rtf->status = tf.status; + rtf->error = tf.error; + } } static void inic_freeze(struct ata_port *ap) diff --git a/drivers/ata/sata_sil24.c b/drivers/ata/sata_sil24.c index 0a01518a8d97..22cc9e9789dd 100644 --- a/drivers/ata/sata_sil24.c +++ b/drivers/ata/sata_sil24.c @@ -328,7 +328,7 @@ static int sil24_scr_write(struct ata_link *link, unsigned sc_reg, u32 val); static int sil24_qc_defer(struct ata_queued_cmd *qc); static enum ata_completion_errors sil24_qc_prep(struct ata_queued_cmd *qc); static unsigned int sil24_qc_issue(struct ata_queued_cmd *qc); -static bool sil24_qc_fill_rtf(struct ata_queued_cmd *qc); +static void sil24_qc_fill_rtf(struct ata_queued_cmd *qc); static void sil24_pmp_attach(struct ata_port *ap); static void sil24_pmp_detach(struct ata_port *ap); static void sil24_freeze(struct ata_port *ap); @@ -901,10 +901,9 @@ static unsigned int sil24_qc_issue(struct ata_queued_cmd *qc) return 0; } -static bool sil24_qc_fill_rtf(struct ata_queued_cmd *qc) +static void sil24_qc_fill_rtf(struct ata_queued_cmd *qc) { sil24_read_tf(qc->ap, qc->hw_tag, &qc->result_tf); - return true; } static void sil24_pmp_attach(struct ata_port *ap) diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c index c68ca2218a05..1c8040d250ea 100644 --- a/drivers/scsi/ipr.c +++ b/drivers/scsi/ipr.c @@ -7142,11 +7142,8 @@ static unsigned int ipr_qc_issue(struct ata_queued_cmd *qc) /** * ipr_qc_fill_rtf - Read result TF * @qc: ATA queued command - * - * Return value: - * true **/ -static bool ipr_qc_fill_rtf(struct ata_queued_cmd *qc) +static void ipr_qc_fill_rtf(struct ata_queued_cmd *qc) { struct ipr_sata_port *sata_port = qc->ap->private_data; struct ipr_ioasa_gata *g = &sata_port->ioasa; @@ -7163,8 +7160,6 @@ static bool ipr_qc_fill_rtf(struct ata_queued_cmd *qc) tf->hob_lbal = g->hob_lbal; tf->hob_lbam = g->hob_lbam; tf->hob_lbah = g->hob_lbah; - - return true; } static struct ata_port_operations ipr_sata_ops = { diff --git a/drivers/scsi/libsas/sas_ata.c b/drivers/scsi/libsas/sas_ata.c index 14da33a3b6a6..ac8576e7f0b7 100644 --- a/drivers/scsi/libsas/sas_ata.c +++ b/drivers/scsi/libsas/sas_ata.c @@ -226,12 +226,11 @@ static unsigned int sas_ata_qc_issue(struct ata_queued_cmd *qc) return ret; } -static bool sas_ata_qc_fill_rtf(struct ata_queued_cmd *qc) +static void sas_ata_qc_fill_rtf(struct ata_queued_cmd *qc) { struct domain_device *dev = qc->ap->private_data; ata_tf_from_fis(dev->sata_dev.fis, &qc->result_tf); - return true; } static struct sas_internal *dev_to_sas_internal(struct domain_device *dev) diff --git a/include/linux/libata.h b/include/linux/libata.h index 7985e6e2ae0e..8483d8300ea3 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -876,7 +876,7 @@ struct ata_port_operations { int (*check_atapi_dma)(struct ata_queued_cmd *qc); enum ata_completion_errors (*qc_prep)(struct ata_queued_cmd *qc); unsigned int (*qc_issue)(struct ata_queued_cmd *qc); - bool (*qc_fill_rtf)(struct ata_queued_cmd *qc); + void (*qc_fill_rtf)(struct ata_queued_cmd *qc); /* * Configuration and exception handling @@ -1936,7 +1936,7 @@ extern void ata_sff_queue_delayed_work(struct delayed_work *dwork, unsigned long delay); extern void ata_sff_queue_pio_task(struct ata_link *link, unsigned long delay); extern unsigned int ata_sff_qc_issue(struct ata_queued_cmd *qc); -extern bool ata_sff_qc_fill_rtf(struct ata_queued_cmd *qc); +extern void ata_sff_qc_fill_rtf(struct ata_queued_cmd *qc); extern unsigned int ata_sff_port_intr(struct ata_port *ap, struct ata_queued_cmd *qc); extern irqreturn_t ata_sff_interrupt(int irq, void *dev_instance); -- cgit v1.2.3 From 93c4aa449b88196c7d56a556cb6a2aad21ad8a7a Mon Sep 17 00:00:00 2001 From: Niklas Cassel Date: Thu, 29 Dec 2022 17:59:59 +0100 Subject: ata: libata: read the shared status for successful NCQ commands once Currently, the status is being read for each QC, inside ata_qc_complete(), which means that QCs being completed by ata_qc_complete_multiple() (i.e. multiple QCs completed during a single interrupt), can have different status and error bits set. This is because the FIS Receive Area will get updated as soon as the HBA receives a new FIS from the device in the NCQ case. Here is an example of the problem: ata14.00: ata_qc_complete_multiple: done_mask: 0x180000 qc tag: 19 cmd: 0x61 flags: 0x11b err_mask: 0x0 tf->status: 0x40 qc tag: 20 cmd: 0x61 flags: 0x11b err_mask: 0x0 tf->status: 0x43 A print in ata_qc_complete_multiple(), shows that done_mask is: 0x180000 which means that tag 19 and 20 were completed. Another print in ata_qc_complete(), after the call to fill_result_tf(), shows that tag 19 and 20 have different status values, even though they were completed in the same ata_qc_complete_multiple() call. If PMP is not enabled, simply read the status and error once, before calling ata_qc_complete() for each QC. Without PMP, we know that all QCs must share the same status and error values. If PMP is enabled, we also read the status before calling ata_qc_complete(), however, we still read the status for each QC, since the QCs can belong to different PMP links (which means that the QCs does not necessarily share the same status and error values). Do all this by introducing the new port operation .qc_ncq_fill_rtf. If set, this operation is called in ata_qc_complete_multiple() to set the result tf for all completed QCs signaled by the last SDB FIS received. QCs that have their result tf filled are marked with the new flag ATA_QCFLAG_RTF_FILLED so that any later execution of the qc_fill_rtf port operation does nothing (e.g. when called from ata_qc_complete()). Co-developed-by: Damien Le Moal Signed-off-by: Damien Le Moal Signed-off-by: Niklas Cassel --- drivers/ata/libahci.c | 90 +++++++++++++++++++++++++++++++++++++++++++++-- drivers/ata/libata-sata.c | 3 ++ include/linux/libata.h | 2 ++ 3 files changed, 92 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c index 0167aac25c34..e5d67eb46f3c 100644 --- a/drivers/ata/libahci.c +++ b/drivers/ata/libahci.c @@ -56,6 +56,7 @@ static ssize_t ahci_transmit_led_message(struct ata_port *ap, u32 state, static int ahci_scr_read(struct ata_link *link, unsigned int sc_reg, u32 *val); static int ahci_scr_write(struct ata_link *link, unsigned int sc_reg, u32 val); static void ahci_qc_fill_rtf(struct ata_queued_cmd *qc); +static void ahci_qc_ncq_fill_rtf(struct ata_port *ap, u64 done_mask); static int ahci_port_start(struct ata_port *ap); static void ahci_port_stop(struct ata_port *ap); static enum ata_completion_errors ahci_qc_prep(struct ata_queued_cmd *qc); @@ -157,6 +158,7 @@ struct ata_port_operations ahci_ops = { .qc_prep = ahci_qc_prep, .qc_issue = ahci_qc_issue, .qc_fill_rtf = ahci_qc_fill_rtf, + .qc_ncq_fill_rtf = ahci_qc_ncq_fill_rtf, .freeze = ahci_freeze, .thaw = ahci_thaw, @@ -2058,6 +2060,13 @@ static void ahci_qc_fill_rtf(struct ata_queued_cmd *qc) struct ahci_port_priv *pp = qc->ap->private_data; u8 *rx_fis = pp->rx_fis; + /* + * rtf may already be filled (e.g. for successful NCQ commands). + * If that is the case, we have nothing to do. + */ + if (qc->flags & ATA_QCFLAG_RTF_FILLED) + return; + if (pp->fbs_enabled) rx_fis += qc->dev->link->pmp * AHCI_RX_FIS_SZ; @@ -2071,6 +2080,9 @@ static void ahci_qc_fill_rtf(struct ata_queued_cmd *qc) !(qc->flags & ATA_QCFLAG_EH)) { ata_tf_from_fis(rx_fis + RX_FIS_PIO_SETUP, &qc->result_tf); qc->result_tf.status = (rx_fis + RX_FIS_PIO_SETUP)[15]; + qc->flags |= ATA_QCFLAG_RTF_FILLED; + return; + } /* * For NCQ commands, we never get a D2H FIS, so reading the D2H Register @@ -2080,13 +2092,85 @@ static void ahci_qc_fill_rtf(struct ata_queued_cmd *qc) * instead. However, the SDB FIS does not contain the LBA, so we can't * use the ata_tf_from_fis() helper. */ - } else if (ata_is_ncq(qc->tf.protocol)) { + if (ata_is_ncq(qc->tf.protocol)) { const u8 *fis = rx_fis + RX_FIS_SDB; + /* + * Successful NCQ commands have been filled already. + * A failed NCQ command will read the status here. + * (Note that a failed NCQ command will get a more specific + * error when reading the NCQ Command Error log.) + */ qc->result_tf.status = fis[2]; qc->result_tf.error = fis[3]; - } else - ata_tf_from_fis(rx_fis + RX_FIS_D2H_REG, &qc->result_tf); + qc->flags |= ATA_QCFLAG_RTF_FILLED; + return; + } + + ata_tf_from_fis(rx_fis + RX_FIS_D2H_REG, &qc->result_tf); + qc->flags |= ATA_QCFLAG_RTF_FILLED; +} + +static void ahci_qc_ncq_fill_rtf(struct ata_port *ap, u64 done_mask) +{ + struct ahci_port_priv *pp = ap->private_data; + const u8 *fis; + + /* No outstanding commands. */ + if (!ap->qc_active) + return; + + /* + * FBS not enabled, so read status and error once, since they are shared + * for all QCs. + */ + if (!pp->fbs_enabled) { + u8 status, error; + + /* No outstanding NCQ commands. */ + if (!pp->active_link->sactive) + return; + + fis = pp->rx_fis + RX_FIS_SDB; + status = fis[2]; + error = fis[3]; + + while (done_mask) { + struct ata_queued_cmd *qc; + unsigned int tag = __ffs64(done_mask); + + qc = ata_qc_from_tag(ap, tag); + if (qc && ata_is_ncq(qc->tf.protocol)) { + qc->result_tf.status = status; + qc->result_tf.error = error; + qc->flags |= ATA_QCFLAG_RTF_FILLED; + } + done_mask &= ~(1ULL << tag); + } + + return; + } + + /* + * FBS enabled, so read the status and error for each QC, since the QCs + * can belong to different PMP links. (Each PMP link has its own FIS + * Receive Area.) + */ + while (done_mask) { + struct ata_queued_cmd *qc; + unsigned int tag = __ffs64(done_mask); + + qc = ata_qc_from_tag(ap, tag); + if (qc && ata_is_ncq(qc->tf.protocol)) { + fis = pp->rx_fis; + fis += qc->dev->link->pmp * AHCI_RX_FIS_SZ; + fis += RX_FIS_SDB; + qc->result_tf.status = fis[2]; + qc->result_tf.error = fis[3]; + qc->flags |= ATA_QCFLAG_RTF_FILLED; + } + done_mask &= ~(1ULL << tag); + } } static void ahci_freeze(struct ata_port *ap) diff --git a/drivers/ata/libata-sata.c b/drivers/ata/libata-sata.c index 908f35acee1e..f3e7396e3191 100644 --- a/drivers/ata/libata-sata.c +++ b/drivers/ata/libata-sata.c @@ -655,6 +655,9 @@ int ata_qc_complete_multiple(struct ata_port *ap, u64 qc_active) return -EINVAL; } + if (ap->ops->qc_ncq_fill_rtf) + ap->ops->qc_ncq_fill_rtf(ap, done_mask); + while (done_mask) { struct ata_queued_cmd *qc; unsigned int tag = __ffs64(done_mask); diff --git a/include/linux/libata.h b/include/linux/libata.h index 8483d8300ea3..f54e02dadc6f 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -200,6 +200,7 @@ enum { /* struct ata_queued_cmd flags */ ATA_QCFLAG_ACTIVE = (1 << 0), /* cmd not yet ack'd to scsi lyer */ ATA_QCFLAG_DMAMAP = (1 << 1), /* SG table is DMA mapped */ + ATA_QCFLAG_RTF_FILLED = (1 << 2), /* result TF has been filled */ ATA_QCFLAG_IO = (1 << 3), /* standard IO command */ ATA_QCFLAG_RESULT_TF = (1 << 4), /* result TF requested */ ATA_QCFLAG_CLEAR_EXCL = (1 << 5), /* clear excl_link on completion */ @@ -877,6 +878,7 @@ struct ata_port_operations { enum ata_completion_errors (*qc_prep)(struct ata_queued_cmd *qc); unsigned int (*qc_issue)(struct ata_queued_cmd *qc); void (*qc_fill_rtf)(struct ata_queued_cmd *qc); + void (*qc_ncq_fill_rtf)(struct ata_port *ap, u64 done_mask); /* * Configuration and exception handling -- cgit v1.2.3 From 87aab3c4cd59aef42fe280fece2be8b8156b99e0 Mon Sep 17 00:00:00 2001 From: Niklas Cassel Date: Thu, 29 Dec 2022 18:00:01 +0100 Subject: ata: libata: move NCQ related ATA_DFLAGs ata_dev_configure() starts off by clearing all flags in ATA_DFLAG_CFG_MASK: dev->flags &= ~ATA_DFLAG_CFG_MASK; ata_dev_configure() then calls ata_dev_config_lba() which calls ata_dev_config_ncq(). ata_dev_config_ncq() will set the correct ATA_DFLAGs depending on what is actually supported. Since these flags are set by ata_dev_configure(), they should be in ATA_DFLAG_CFG_MASK and not in ATA_DFLAG_INIT_MASK. ATA_DFLAG_NCQ_PRIO_ENABLED is set via sysfs, is should therefore not be in ATA_DFLAG_CFG_MASK. It also cannot be in ATA_DFLAG_INIT_MASK, because ata_eh_schedule_probe() calls ata_dev_init(), which will clear all flags in ATA_DFLAG_INIT_MASK. This means that ATA_DFLAG_NCQ_PRIO_ENABLED (the value the user sets via sysfs) would get silently cleared if ata_eh_schedule_probe() is called. While that should only happen in certain circumstances, it still doesn't seem right that it can get silently cleared. (ata_dev_config_ncq_prio() will still clear the ATA_DFLAG_NCQ_PRIO_ENABLED flag if ATA_DFLAG_NCQ_PRIO is suddenly no longer supported after a revalidation.) Because of this, move ATA_DFLAG_NCQ_PRIO_ENABLED to be outside of both ATA_DFLAG_CFG_MASK and ATA_DFLAG_INIT_MASK. Signed-off-by: Niklas Cassel Signed-off-by: Damien Le Moal --- include/linux/libata.h | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index f54e02dadc6f..3b7f5d9e2f87 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -91,22 +91,21 @@ enum { ATA_DFLAG_AN = (1 << 7), /* AN configured */ ATA_DFLAG_TRUSTED = (1 << 8), /* device supports trusted send/recv */ ATA_DFLAG_DMADIR = (1 << 10), /* device requires DMADIR */ - ATA_DFLAG_CFG_MASK = (1 << 12) - 1, + ATA_DFLAG_NCQ_SEND_RECV = (1 << 11), /* device supports NCQ SEND and RECV */ + ATA_DFLAG_NCQ_PRIO = (1 << 12), /* device supports NCQ priority */ + ATA_DFLAG_CFG_MASK = (1 << 13) - 1, - ATA_DFLAG_PIO = (1 << 12), /* device limited to PIO mode */ - ATA_DFLAG_NCQ_OFF = (1 << 13), /* device limited to non-NCQ mode */ + ATA_DFLAG_PIO = (1 << 13), /* device limited to PIO mode */ + ATA_DFLAG_NCQ_OFF = (1 << 14), /* device limited to non-NCQ mode */ ATA_DFLAG_SLEEPING = (1 << 15), /* device is sleeping */ ATA_DFLAG_DUBIOUS_XFER = (1 << 16), /* data transfer not verified */ ATA_DFLAG_NO_UNLOAD = (1 << 17), /* device doesn't support unload */ ATA_DFLAG_UNLOCK_HPA = (1 << 18), /* unlock HPA */ - ATA_DFLAG_NCQ_SEND_RECV = (1 << 19), /* device supports NCQ SEND and RECV */ - ATA_DFLAG_NCQ_PRIO = (1 << 20), /* device supports NCQ priority */ - ATA_DFLAG_NCQ_PRIO_ENABLED = (1 << 21), /* Priority cmds sent to dev */ - ATA_DFLAG_INIT_MASK = (1 << 24) - 1, + ATA_DFLAG_INIT_MASK = (1 << 19) - 1, + ATA_DFLAG_NCQ_PRIO_ENABLED = (1 << 19), /* Priority cmds sent to dev */ ATA_DFLAG_DETACH = (1 << 24), ATA_DFLAG_DETACHED = (1 << 25), - ATA_DFLAG_DA = (1 << 26), /* device supports Device Attention */ ATA_DFLAG_DEVSLP = (1 << 27), /* device supports Device Sleep */ ATA_DFLAG_ACPI_DISABLED = (1 << 28), /* ACPI for the device is disabled */ -- cgit v1.2.3 From a4b2e6063cfeaab1160501acfb27e8618a7c693f Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Thu, 15 Dec 2022 16:20:23 +0100 Subject: firmware: xilinx: Clear IOCTL_SET_SD_TAPDELAY using PM_MMIO_WRITE In case the tap delay required by Arasan SDHCI is set to 0, the current embeddedsw firmware unconditionally writes IOU_SLCR SD_ITAPDLY to 0x100 (SD0_ITAPDLYENA=1, SD0_ITAPDLYSEL=0). Previous behavior was to keep the IOU_SLCR SD_ITAPDLY set to 0x0. There is some sort of difference in the behavior between SD0_ITAPDLYENA=1/0 with the same SD0_ITAPDLYSEL=0, even though the behavior should be identical -- zero delay added to rxclk_in line. The former breaks HS200 training in low temperature conditions. Write IOU_SLCR SD_ITAPDLY register to 0 using PM_MMIO_WRITE which seem to allow unrestricted WRITE access (and PM_MMIO_READ which allows read access) to the entire address space. This way, it is possible to work around the defect in IOCTL_SET_SD_TAPDELAY design which does not permit clearing SDx_ITAPDLYENA bit. Note that the embeddedsw firmware does not permit clearing the SD_ITAPDLY SD0_ITAPDLYENA bit, this bit can only ever be set by the firmware and it is often impossible to update the possibly broken firmware. Signed-off-by: Marek Vasut Link: https://lore.kernel.org/r/20221215152023.8387-1-marex@denx.de Signed-off-by: Michal Simek --- drivers/firmware/xilinx/zynqmp.c | 27 +++++++++++++++++++++++++-- include/linux/firmware/xlnx-zynqmp.h | 4 ++++ 2 files changed, 29 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/firmware/xilinx/zynqmp.c b/drivers/firmware/xilinx/zynqmp.c index 129f68d7a6f5..acd83d29c866 100644 --- a/drivers/firmware/xilinx/zynqmp.c +++ b/drivers/firmware/xilinx/zynqmp.c @@ -738,8 +738,31 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_get_pll_frac_data); */ int zynqmp_pm_set_sd_tapdelay(u32 node_id, u32 type, u32 value) { - return zynqmp_pm_invoke_fn(PM_IOCTL, node_id, IOCTL_SET_SD_TAPDELAY, - type, value, NULL); + u32 reg = (type == PM_TAPDELAY_INPUT) ? SD_ITAPDLY : SD_OTAPDLYSEL; + u32 mask = (node_id == NODE_SD_0) ? GENMASK(15, 0) : GENMASK(31, 16); + + if (value) { + return zynqmp_pm_invoke_fn(PM_IOCTL, node_id, + IOCTL_SET_SD_TAPDELAY, + type, value, NULL); + } + + /* + * Work around completely misdesigned firmware API on Xilinx ZynqMP. + * The IOCTL_SET_SD_TAPDELAY firmware call allows the caller to only + * ever set IOU_SLCR SD_ITAPDLY Register SD0_ITAPDLYENA/SD1_ITAPDLYENA + * bits, but there is no matching call to clear those bits. If those + * bits are not cleared, SDMMC tuning may fail. + * + * Luckily, there are PM_MMIO_READ/PM_MMIO_WRITE calls which seem to + * allow complete unrestricted access to all address space, including + * IOU_SLCR SD_ITAPDLY Register and all the other registers, access + * to which was supposed to be protected by the current firmware API. + * + * Use PM_MMIO_READ/PM_MMIO_WRITE to re-implement the missing counter + * part of IOCTL_SET_SD_TAPDELAY which clears SDx_ITAPDLYENA bits. + */ + return zynqmp_pm_invoke_fn(PM_MMIO_WRITE, reg, mask, 0, 0, NULL); } EXPORT_SYMBOL_GPL(zynqmp_pm_set_sd_tapdelay); diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index b986e267d149..eb88b4ba62f9 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -79,6 +79,10 @@ #define EVENT_ERROR_PSM_ERR1 (0x28108000U) #define EVENT_ERROR_PSM_ERR2 (0x2810C000U) +/* ZynqMP SD tap delay tuning */ +#define SD_ITAPDLY 0xFF180314 +#define SD_OTAPDLYSEL 0xFF180318 + enum pm_api_cb_id { PM_INIT_SUSPEND_CB = 30, PM_ACKNOWLEDGE_CB = 31, -- cgit v1.2.3 From 589c3357370a596ef7c99c00baca8ac799fce531 Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Sun, 11 Dec 2022 23:06:19 -0800 Subject: PCI/CXL: Export native CXL error reporting control CXL _OSC Error Reporting Control is used by the OS to determine if Firmware has control of various CXL error reporting capabilities including the event logs. Expose the result of negotiating CXL Error Reporting Control in struct pci_host_bridge for consumption by the CXL drivers. Cc: Bjorn Helgaas Cc: Lukas Wunner Cc: linux-pci@vger.kernel.org Cc: linux-acpi@vger.kernel.org Signed-off-by: Ira Weiny Acked-by: Bjorn Helgaas Reviewed-by: Jonathan Cameron Reviewed-by: Dan Williams Link: https://lore.kernel.org/r/20221212070627.1372402-2-ira.weiny@intel.com Signed-off-by: Dan Williams --- drivers/acpi/pci_root.c | 3 +++ drivers/pci/probe.c | 1 + include/linux/pci.h | 1 + 3 files changed, 5 insertions(+) (limited to 'include/linux') diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c index b3c202d2a433..84030804a763 100644 --- a/drivers/acpi/pci_root.c +++ b/drivers/acpi/pci_root.c @@ -1047,6 +1047,9 @@ struct pci_bus *acpi_pci_root_create(struct acpi_pci_root *root, if (!(root->osc_control_set & OSC_PCI_EXPRESS_DPC_CONTROL)) host_bridge->native_dpc = 0; + if (!(root->osc_ext_control_set & OSC_CXL_ERROR_REPORTING_CONTROL)) + host_bridge->native_cxl_error = 0; + /* * Evaluate the "PCI Boot Configuration" _DSM Function. If it * exists and returns 0, we must preserve any PCI resource diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 1779582fb500..f796dfb9b14b 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -596,6 +596,7 @@ static void pci_init_host_bridge(struct pci_host_bridge *bridge) bridge->native_ltr = 1; bridge->native_dpc = 1; bridge->domain_nr = PCI_DOMAIN_NR_NOT_SET; + bridge->native_cxl_error = 1; device_initialize(&bridge->dev); } diff --git a/include/linux/pci.h b/include/linux/pci.h index adffd65e84b4..22319ea71ab0 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -578,6 +578,7 @@ struct pci_host_bridge { unsigned int native_pme:1; /* OS may use PCIe PME */ unsigned int native_ltr:1; /* OS may use PCIe LTR */ unsigned int native_dpc:1; /* OS may use PCIe DPC */ + unsigned int native_cxl_error:1; /* OS may use CXL RAS/Events */ unsigned int preserve_config:1; /* Preserve FW resource setup */ unsigned int size_windows:1; /* Enable root bus sizing */ unsigned int msi_domain:1; /* Bridge wants MSI domain */ -- cgit v1.2.3 From 37e2b57078d412547f1c14bb83eff86ab9d92d3d Mon Sep 17 00:00:00 2001 From: Gustavo A. R. Silva Date: Sat, 3 Sep 2022 00:08:51 +0100 Subject: exportfs: Replace zero-length array with DECLARE_FLEX_ARRAY() helper Zero-length arrays are deprecated and we are moving towards adopting C99 flexible-array members instead. So, replace zero-length array declaration in struct fid with the new DECLARE_FLEX_ARRAY() helper macro. This helper allows for a flexible-array member in a union. Link: https://github.com/KSPP/linux/issues/21 Link: https://github.com/KSPP/linux/issues/193 Link: https://github.com/KSPP/linux/issues/197 Link: https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html Reviewed-by: Kees Cook Signed-off-by: Gustavo A. R. Silva --- include/linux/exportfs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h index fe848901fcc3..1640d97e4c0d 100644 --- a/include/linux/exportfs.h +++ b/include/linux/exportfs.h @@ -131,7 +131,7 @@ struct fid { u32 parent_block; u32 parent_generation; } udf; - __u32 raw[0]; + DECLARE_FLEX_ARRAY(__u32, raw); }; }; -- cgit v1.2.3 From 06919d226d01132c03d851966d4df3870fa1b55a Mon Sep 17 00:00:00 2001 From: Gustavo A. R. Silva Date: Sat, 3 Sep 2022 00:17:18 +0100 Subject: mm/memremap: Replace zero-length array with DECLARE_FLEX_ARRAY() helper Zero-length arrays are deprecated and we are moving towards adopting C99 flexible-array members, instead. So, replace zero-length array declaration in struct dev_pagemap with the new DECLARE_FLEX_ARRAY() helper macro. This helper allows for a flexible-array member in a union. Also, this addresses multiple warnings reported when building with Clang-15 and -Wzero-length-array. Link: https://github.com/KSPP/linux/issues/193 Link: https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html Reviewed-by: Kees Cook Signed-off-by: Gustavo A. R. Silva --- include/linux/memremap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memremap.h b/include/linux/memremap.h index 7fcaf3180a5b..1314d9c5f05b 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -135,7 +135,7 @@ struct dev_pagemap { int nr_range; union { struct range range; - struct range ranges[0]; + DECLARE_FLEX_ARRAY(struct range, ranges); }; }; -- cgit v1.2.3 From 4d70c74659d9746502b23d055dba03d1d28ec388 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 30 Nov 2022 15:48:35 +0200 Subject: i915: Move list_count() to list.h as list_count_nodes() for broader use Some of the existing users, and definitely will be new ones, want to count existing nodes in the list. Provide a generic API for that by moving code from i915 to list.h. Reviewed-by: Lucas De Marchi Acked-by: Jani Nikula Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20221130134838.23805-1-andriy.shevchenko@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/gt/intel_engine_cs.c | 15 ++------------- include/linux/list.h | 15 +++++++++++++++ 2 files changed, 17 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c index c33e0d72d670..0dcf4ac92335 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c @@ -2094,17 +2094,6 @@ static void print_request_ring(struct drm_printer *m, struct i915_request *rq) } } -static unsigned long list_count(struct list_head *list) -{ - struct list_head *pos; - unsigned long count = 0; - - list_for_each(pos, list) - count++; - - return count; -} - static unsigned long read_ul(void *p, size_t x) { return *(unsigned long *)(p + x); @@ -2279,8 +2268,8 @@ void intel_engine_dump(struct intel_engine_cs *engine, spin_lock_irqsave(&engine->sched_engine->lock, flags); engine_dump_active_requests(engine, m); - drm_printf(m, "\tOn hold?: %lu\n", - list_count(&engine->sched_engine->hold)); + drm_printf(m, "\tOn hold?: %zu\n", + list_count_nodes(&engine->sched_engine->hold)); spin_unlock_irqrestore(&engine->sched_engine->lock, flags); drm_printf(m, "\tMMIO base: 0x%08x\n", engine->mmio_base); diff --git a/include/linux/list.h b/include/linux/list.h index 61762054b4be..f10344dbad4d 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -655,6 +655,21 @@ static inline void list_splice_tail_init(struct list_head *list, !list_is_head(pos, (head)); \ pos = n, n = pos->prev) +/** + * list_count_nodes - count nodes in the list + * @head: the head for your list. + */ +static inline size_t list_count_nodes(struct list_head *head) +{ + struct list_head *pos; + size_t count = 0; + + list_for_each(pos, head) + count++; + + return count; +} + /** * list_entry_is_head - test if the entry points to the head of the list * @pos: the type * to cursor -- cgit v1.2.3 From 9b9ad70f28675c45ef93cfb6e4af9403cb7bd34c Mon Sep 17 00:00:00 2001 From: MD Danish Anwar Date: Fri, 6 Jan 2023 17:40:42 +0530 Subject: remoteproc: pru: Add enum for PRU Core Identifiers. Introducing enum pruss_pru_id for PRU Core Identifiers. PRUSS_PRU0 indicates PRU Core 0. PRUSS_PRU1 indicates PRU Core 1. PRUSS_NUM_PRUS indicates the total number of PRU Cores. Signed-off-by: MD Danish Anwar Reviewed-by: Roger Quadros Link: https://lore.kernel.org/r/20230106121046.886863-3-danishanwar@ti.com Signed-off-by: Mathieu Poirier --- drivers/remoteproc/pru_rproc.c | 7 ++++--- include/linux/remoteproc/pruss.h | 31 +++++++++++++++++++++++++++++++ 2 files changed, 35 insertions(+), 3 deletions(-) create mode 100644 include/linux/remoteproc/pruss.h (limited to 'include/linux') diff --git a/drivers/remoteproc/pru_rproc.c b/drivers/remoteproc/pru_rproc.c index 128bf9912f2c..f8b196a2b72a 100644 --- a/drivers/remoteproc/pru_rproc.c +++ b/drivers/remoteproc/pru_rproc.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include @@ -438,7 +439,7 @@ static void *pru_d_da_to_va(struct pru_rproc *pru, u32 da, size_t len) dram0 = pruss->mem_regions[PRUSS_MEM_DRAM0]; dram1 = pruss->mem_regions[PRUSS_MEM_DRAM1]; /* PRU1 has its local RAM addresses reversed */ - if (pru->id == 1) + if (pru->id == PRUSS_PRU1) swap(dram0, dram1); shrd_ram = pruss->mem_regions[PRUSS_MEM_SHRD_RAM2]; @@ -747,14 +748,14 @@ static int pru_rproc_set_id(struct pru_rproc *pru) case RTU0_IRAM_ADDR_MASK: fallthrough; case PRU0_IRAM_ADDR_MASK: - pru->id = 0; + pru->id = PRUSS_PRU0; break; case TX_PRU1_IRAM_ADDR_MASK: fallthrough; case RTU1_IRAM_ADDR_MASK: fallthrough; case PRU1_IRAM_ADDR_MASK: - pru->id = 1; + pru->id = PRUSS_PRU1; break; default: ret = -EINVAL; diff --git a/include/linux/remoteproc/pruss.h b/include/linux/remoteproc/pruss.h new file mode 100644 index 000000000000..fbadfcfacb34 --- /dev/null +++ b/include/linux/remoteproc/pruss.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * PRU-ICSS Subsystem user interfaces + * + * Copyright (C) 2015-2022 Texas Instruments Incorporated - http://www.ti.com + * Suman Anna + */ + +#ifndef __LINUX_PRUSS_H +#define __LINUX_PRUSS_H + +#include +#include + +#define PRU_RPROC_DRVNAME "pru-rproc" + +/** + * enum pruss_pru_id - PRU core identifiers + * @PRUSS_PRU0: PRU Core 0. + * @PRUSS_PRU1: PRU Core 1. + * @PRUSS_NUM_PRUS: Total number of PRU Cores available. + * + */ + +enum pruss_pru_id { + PRUSS_PRU0 = 0, + PRUSS_PRU1, + PRUSS_NUM_PRUS, +}; + +#endif /* __LINUX_PRUSS_H */ -- cgit v1.2.3 From 919e8942548aa878d374b1b51aa68fdf751f18b8 Mon Sep 17 00:00:00 2001 From: MD Danish Anwar Date: Fri, 6 Jan 2023 17:40:43 +0530 Subject: remoteproc: pru: Add APIs to get and put the PRU cores Add two new APIs, pru_rproc_get() and pru_rproc_put(), to the PRU driver to allow client drivers to acquire and release the remoteproc device associated with a PRU core. The PRU cores are treated as resources with only one client owning it at a time. The pru_rproc_get() function returns the rproc handle corresponding to a PRU core identified by the device tree "ti,prus" property under the client node. The pru_rproc_put() is the complementary function to pru_rproc_get(). Signed-off-by: Suman Anna Signed-off-by: Tero Kristo Signed-off-by: Grzegorz Jaszczyk Signed-off-by: MD Danish Anwar Reviewed-by: Roger Quadros Link: https://lore.kernel.org/r/20230106121046.886863-4-danishanwar@ti.com Signed-off-by: Mathieu Poirier --- drivers/remoteproc/pru_rproc.c | 128 ++++++++++++++++++++++++++++++++++++++- include/linux/remoteproc/pruss.h | 30 +++++++++ 2 files changed, 156 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/remoteproc/pru_rproc.c b/drivers/remoteproc/pru_rproc.c index f8b196a2b72a..1036bfd446b6 100644 --- a/drivers/remoteproc/pru_rproc.c +++ b/drivers/remoteproc/pru_rproc.c @@ -2,12 +2,14 @@ /* * PRU-ICSS remoteproc driver for various TI SoCs * - * Copyright (C) 2014-2020 Texas Instruments Incorporated - https://www.ti.com/ + * Copyright (C) 2014-2022 Texas Instruments Incorporated - https://www.ti.com/ * * Author(s): * Suman Anna * Andrew F. Davis * Grzegorz Jaszczyk for Texas Instruments + * Puranjay Mohan + * Md Danish Anwar */ #include @@ -112,6 +114,8 @@ struct pru_private_data { * @rproc: remoteproc pointer for this PRU core * @data: PRU core specific data * @mem_regions: data for each of the PRU memory regions + * @client_np: client device node + * @lock: mutex to protect client usage * @fw_name: name of firmware image used during loading * @mapped_irq: virtual interrupt numbers of created fw specific mapping * @pru_interrupt_map: pointer to interrupt mapping description (firmware) @@ -127,6 +131,8 @@ struct pru_rproc { struct rproc *rproc; const struct pru_private_data *data; struct pruss_mem_region mem_regions[PRU_IOMEM_MAX]; + struct device_node *client_np; + struct mutex lock; const char *fw_name; unsigned int *mapped_irq; struct pru_irq_rsc *pru_interrupt_map; @@ -147,6 +153,120 @@ void pru_control_write_reg(struct pru_rproc *pru, unsigned int reg, u32 val) writel_relaxed(val, pru->mem_regions[PRU_IOMEM_CTRL].va + reg); } +static struct rproc *__pru_rproc_get(struct device_node *np, int index) +{ + struct rproc *rproc; + phandle rproc_phandle; + int ret; + + ret = of_property_read_u32_index(np, "ti,prus", index, &rproc_phandle); + if (ret) + return ERR_PTR(ret); + + rproc = rproc_get_by_phandle(rproc_phandle); + if (!rproc) { + ret = -EPROBE_DEFER; + return ERR_PTR(ret); + } + + /* make sure it is PRU rproc */ + if (!is_pru_rproc(rproc->dev.parent)) { + rproc_put(rproc); + return ERR_PTR(-ENODEV); + } + + return rproc; +} + +/** + * pru_rproc_get() - get the PRU rproc instance from a device node + * @np: the user/client device node + * @index: index to use for the ti,prus property + * @pru_id: optional pointer to return the PRU remoteproc processor id + * + * This function looks through a client device node's "ti,prus" property at + * index @index and returns the rproc handle for a valid PRU remote processor if + * found. The function allows only one user to own the PRU rproc resource at a + * time. Caller must call pru_rproc_put() when done with using the rproc, not + * required if the function returns a failure. + * + * When optional @pru_id pointer is passed the PRU remoteproc processor id is + * returned. + * + * Return: rproc handle on success, and an ERR_PTR on failure using one + * of the following error values + * -ENODEV if device is not found + * -EBUSY if PRU is already acquired by anyone + * -EPROBE_DEFER is PRU device is not probed yet + */ +struct rproc *pru_rproc_get(struct device_node *np, int index, + enum pruss_pru_id *pru_id) +{ + struct rproc *rproc; + struct pru_rproc *pru; + struct device *dev; + int ret; + + rproc = __pru_rproc_get(np, index); + if (IS_ERR(rproc)) + return rproc; + + pru = rproc->priv; + dev = &rproc->dev; + + mutex_lock(&pru->lock); + + if (pru->client_np) { + mutex_unlock(&pru->lock); + ret = -EBUSY; + goto err_no_rproc_handle; + } + + pru->client_np = np; + + mutex_unlock(&pru->lock); + + if (pru_id) + *pru_id = pru->id; + + return rproc; + +err_no_rproc_handle: + rproc_put(rproc); + return ERR_PTR(ret); +} +EXPORT_SYMBOL_GPL(pru_rproc_get); + +/** + * pru_rproc_put() - release the PRU rproc resource + * @rproc: the rproc resource to release + * + * Releases the PRU rproc resource and makes it available to other + * users. + */ +void pru_rproc_put(struct rproc *rproc) +{ + struct pru_rproc *pru; + + if (IS_ERR_OR_NULL(rproc) || !is_pru_rproc(rproc->dev.parent)) + return; + + pru = rproc->priv; + + mutex_lock(&pru->lock); + + if (!pru->client_np) { + mutex_unlock(&pru->lock); + return; + } + + pru->client_np = NULL; + mutex_unlock(&pru->lock); + + rproc_put(rproc); +} +EXPORT_SYMBOL_GPL(pru_rproc_put); + static inline u32 pru_debug_read_reg(struct pru_rproc *pru, unsigned int reg) { return readl_relaxed(pru->mem_regions[PRU_IOMEM_DEBUG].va + reg); @@ -817,6 +937,8 @@ static int pru_rproc_probe(struct platform_device *pdev) pru->pruss = platform_get_drvdata(ppdev); pru->rproc = rproc; pru->fw_name = fw_name; + pru->client_np = NULL; + mutex_init(&pru->lock); for (i = 0; i < ARRAY_SIZE(mem_names); i++) { res = platform_get_resource_byname(pdev, IORESOURCE_MEM, @@ -905,7 +1027,7 @@ MODULE_DEVICE_TABLE(of, pru_rproc_match); static struct platform_driver pru_rproc_driver = { .driver = { - .name = "pru-rproc", + .name = PRU_RPROC_DRVNAME, .of_match_table = pru_rproc_match, .suppress_bind_attrs = true, }, @@ -917,5 +1039,7 @@ module_platform_driver(pru_rproc_driver); MODULE_AUTHOR("Suman Anna "); MODULE_AUTHOR("Andrew F. Davis "); MODULE_AUTHOR("Grzegorz Jaszczyk "); +MODULE_AUTHOR("Puranjay Mohan "); +MODULE_AUTHOR("Md Danish Anwar "); MODULE_DESCRIPTION("PRU-ICSS Remote Processor Driver"); MODULE_LICENSE("GPL v2"); diff --git a/include/linux/remoteproc/pruss.h b/include/linux/remoteproc/pruss.h index fbadfcfacb34..579dafbbaccf 100644 --- a/include/linux/remoteproc/pruss.h +++ b/include/linux/remoteproc/pruss.h @@ -28,4 +28,34 @@ enum pruss_pru_id { PRUSS_NUM_PRUS, }; +struct device_node; + +#if IS_ENABLED(CONFIG_PRU_REMOTEPROC) + +struct rproc *pru_rproc_get(struct device_node *np, int index, + enum pruss_pru_id *pru_id); +void pru_rproc_put(struct rproc *rproc); + +#else + +static inline struct rproc * +pru_rproc_get(struct device_node *np, int index, enum pruss_pru_id *pru_id) +{ + return ERR_PTR(-EOPNOTSUPP); +} + +static inline void pru_rproc_put(struct rproc *rproc) { } + +#endif /* CONFIG_PRU_REMOTEPROC */ + +static inline bool is_pru_rproc(struct device *dev) +{ + const char *drv_name = dev_driver_string(dev); + + if (strncmp(drv_name, PRU_RPROC_DRVNAME, sizeof(PRU_RPROC_DRVNAME))) + return false; + + return true; +} + #endif /* __LINUX_PRUSS_H */ -- cgit v1.2.3 From 102853400321baea2527917e6e89be33508c3e18 Mon Sep 17 00:00:00 2001 From: Roger Quadros Date: Fri, 6 Jan 2023 17:40:45 +0530 Subject: remoteproc: pru: Add pru_rproc_set_ctable() function Some firmwares expect the OS drivers to configure the CTABLE entries publishing dynamically allocated memory regions. For example, the PRU Ethernet firmwares use the C28 and C30 entries for retrieving the Shared RAM and System SRAM (OCMC) areas allocated by the PRU Ethernet client driver. Provide a way for users to do that through a new API, pru_rproc_set_ctable(). The API returns 0 on success and a negative value on error. NOTE: The programmable CTABLE entries are typically re-programmed by the PRU firmwares when dealing with a certain block of memory during block processing. This API provides an interface to the PRU client drivers to publish a dynamically allocated memory block with the PRU firmware using a CTABLE entry instead of a negotiated address in shared memory. Additional synchronization may be needed between the PRU client drivers and firmwares if different addresses needs to be published at run-time reusing the same CTABLE entry. CTABLE for stands for "constant table". Each CTable entry just holds the upper address bits so PRU can reference to external memory with larger address bits. For use case please see prueth_sw_emac_config() in "drivers/net/ethernet/ti/prueth_switch.c" /* Set in constant table C28 of PRUn to ICSS Shared memory */ pru_rproc_set_ctable(prueth->pru0, PRU_C28, sharedramaddr); pru_rproc_set_ctable(prueth->pru1, PRU_C28, sharedramaddr); /* Set in constant table C30 of PRUn to OCMC memory */ pru_rproc_set_ctable(prueth->pru0, PRU_C30, ocmcaddr); pru_rproc_set_ctable(prueth->pru1, PRU_C30, ocmcaddr); Signed-off-by: Andrew F. Davis Signed-off-by: Suman Anna Signed-off-by: Roger Quadros Signed-off-by: Grzegorz Jaszczyk Signed-off-by: MD Danish Anwar Link: https://lore.kernel.org/r/20230106121046.886863-6-danishanwar@ti.com Signed-off-by: Mathieu Poirier --- drivers/remoteproc/pru_rproc.c | 59 ++++++++++++++++++++++++++++++++++++++++ include/linux/remoteproc/pruss.h | 22 +++++++++++++++ 2 files changed, 81 insertions(+) (limited to 'include/linux') diff --git a/drivers/remoteproc/pru_rproc.c b/drivers/remoteproc/pru_rproc.c index c16242e2d435..f6ea445d2fa2 100644 --- a/drivers/remoteproc/pru_rproc.c +++ b/drivers/remoteproc/pru_rproc.c @@ -120,6 +120,7 @@ struct pru_private_data { * @mapped_irq: virtual interrupt numbers of created fw specific mapping * @pru_interrupt_map: pointer to interrupt mapping description (firmware) * @pru_interrupt_map_sz: pru_interrupt_map size + * @rmw_lock: lock for read, modify, write operations on registers * @dbg_single_step: debug state variable to set PRU into single step mode * @dbg_continuous: debug state variable to restore PRU execution mode * @evt_count: number of mapped events @@ -137,6 +138,7 @@ struct pru_rproc { unsigned int *mapped_irq; struct pru_irq_rsc *pru_interrupt_map; size_t pru_interrupt_map_sz; + spinlock_t rmw_lock; u32 dbg_single_step; u32 dbg_continuous; u8 evt_count; @@ -153,6 +155,23 @@ void pru_control_write_reg(struct pru_rproc *pru, unsigned int reg, u32 val) writel_relaxed(val, pru->mem_regions[PRU_IOMEM_CTRL].va + reg); } +static inline +void pru_control_set_reg(struct pru_rproc *pru, unsigned int reg, + u32 mask, u32 set) +{ + u32 val; + unsigned long flags; + + spin_lock_irqsave(&pru->rmw_lock, flags); + + val = pru_control_read_reg(pru, reg); + val &= ~mask; + val |= (set & mask); + pru_control_write_reg(pru, reg, val); + + spin_unlock_irqrestore(&pru->rmw_lock, flags); +} + static struct rproc *__pru_rproc_get(struct device_node *np, int index) { struct rproc *rproc; @@ -269,6 +288,45 @@ void pru_rproc_put(struct rproc *rproc) } EXPORT_SYMBOL_GPL(pru_rproc_put); +/** + * pru_rproc_set_ctable() - set the constant table index for the PRU + * @rproc: the rproc instance of the PRU + * @c: constant table index to set + * @addr: physical address to set it to + * + * Return: 0 on success, or errno in error case. + */ +int pru_rproc_set_ctable(struct rproc *rproc, enum pru_ctable_idx c, u32 addr) +{ + struct pru_rproc *pru = rproc->priv; + unsigned int reg; + u32 mask, set; + u16 idx; + u16 idx_mask; + + if (IS_ERR_OR_NULL(rproc)) + return -EINVAL; + + if (!rproc->dev.parent || !is_pru_rproc(rproc->dev.parent)) + return -ENODEV; + + /* pointer is 16 bit and index is 8-bit so mask out the rest */ + idx_mask = (c >= PRU_C28) ? 0xFFFF : 0xFF; + + /* ctable uses bit 8 and upwards only */ + idx = (addr >> 8) & idx_mask; + + /* configurable ctable (i.e. C24) starts at PRU_CTRL_CTBIR0 */ + reg = PRU_CTRL_CTBIR0 + 4 * (c >> 1); + mask = idx_mask << (16 * (c & 1)); + set = idx << (16 * (c & 1)); + + pru_control_set_reg(pru, reg, mask, set); + + return 0; +} +EXPORT_SYMBOL_GPL(pru_rproc_set_ctable); + static inline u32 pru_debug_read_reg(struct pru_rproc *pru, unsigned int reg) { return readl_relaxed(pru->mem_regions[PRU_IOMEM_DEBUG].va + reg); @@ -940,6 +998,7 @@ static int pru_rproc_probe(struct platform_device *pdev) pru->rproc = rproc; pru->fw_name = fw_name; pru->client_np = NULL; + spin_lock_init(&pru->rmw_lock); mutex_init(&pru->lock); for (i = 0; i < ARRAY_SIZE(mem_names); i++) { diff --git a/include/linux/remoteproc/pruss.h b/include/linux/remoteproc/pruss.h index 579dafbbaccf..039b50d58df2 100644 --- a/include/linux/remoteproc/pruss.h +++ b/include/linux/remoteproc/pruss.h @@ -28,13 +28,29 @@ enum pruss_pru_id { PRUSS_NUM_PRUS, }; +/* + * enum pru_ctable_idx - Configurable Constant table index identifiers + */ +enum pru_ctable_idx { + PRU_C24 = 0, + PRU_C25, + PRU_C26, + PRU_C27, + PRU_C28, + PRU_C29, + PRU_C30, + PRU_C31, +}; + struct device_node; +struct rproc; #if IS_ENABLED(CONFIG_PRU_REMOTEPROC) struct rproc *pru_rproc_get(struct device_node *np, int index, enum pruss_pru_id *pru_id); void pru_rproc_put(struct rproc *rproc); +int pru_rproc_set_ctable(struct rproc *rproc, enum pru_ctable_idx c, u32 addr); #else @@ -46,6 +62,12 @@ pru_rproc_get(struct device_node *np, int index, enum pruss_pru_id *pru_id) static inline void pru_rproc_put(struct rproc *rproc) { } +static inline int pru_rproc_set_ctable(struct rproc *rproc, + enum pru_ctable_idx c, u32 addr) +{ + return -EOPNOTSUPP; +} + #endif /* CONFIG_PRU_REMOTEPROC */ static inline bool is_pru_rproc(struct device *dev) -- cgit v1.2.3 From 33ae3d0955943ac5bacfcb6911cf7cb74822bf8c Mon Sep 17 00:00:00 2001 From: Dawei Li Date: Fri, 6 Jan 2023 23:28:03 +0800 Subject: soc: qcom: apr: make remove callback of apr driver void returned Since commit fc7a6209d571 ("bus: Make remove callback return void") forces bus_type::remove be void-returned, it doesn't make much sense for any bus based driver implementing remove callbalk to return non-void to its caller. As such, change the remove function for apr bus based drivers to return void. Signed-off-by: Dawei Li Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/TYCP286MB23232B7968D34DB8323B0F16CAFB9@TYCP286MB2323.JPNP286.PROD.OUTLOOK.COM --- include/linux/soc/qcom/apr.h | 2 +- sound/soc/qcom/qdsp6/q6core.c | 4 +--- 2 files changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/soc/qcom/apr.h b/include/linux/soc/qcom/apr.h index 23c5b30f3511..be98aebcb3e1 100644 --- a/include/linux/soc/qcom/apr.h +++ b/include/linux/soc/qcom/apr.h @@ -153,7 +153,7 @@ typedef struct apr_device gpr_device_t; struct apr_driver { int (*probe)(struct apr_device *sl); - int (*remove)(struct apr_device *sl); + void (*remove)(struct apr_device *sl); int (*callback)(struct apr_device *a, struct apr_resp_pkt *d); int (*gpr_callback)(struct gpr_resp_pkt *d, void *data, int op); diff --git a/sound/soc/qcom/qdsp6/q6core.c b/sound/soc/qcom/qdsp6/q6core.c index 5358fefd4210..49cfb32cd209 100644 --- a/sound/soc/qcom/qdsp6/q6core.c +++ b/sound/soc/qcom/qdsp6/q6core.c @@ -339,7 +339,7 @@ static int q6core_probe(struct apr_device *adev) return 0; } -static int q6core_exit(struct apr_device *adev) +static void q6core_exit(struct apr_device *adev) { struct q6core *core = dev_get_drvdata(&adev->dev); @@ -350,8 +350,6 @@ static int q6core_exit(struct apr_device *adev) g_core = NULL; kfree(core); - - return 0; } #ifdef CONFIG_OF -- cgit v1.2.3 From be505ba8fe90068868bc084cad2079a38486b2d5 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Fri, 18 Nov 2022 10:58:06 +0800 Subject: ASoC/soundwire: remove is_sdca boolean property The Device_ID registers already tell us if a device supports the SDCA specification or not, in hindsight we never needed a property when the information is reported by both hardware and ACPI. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Rander Wang Reviewed-by: Péter Ujfalusi Signed-off-by: Bard Liao Reviewed-by: Charles Keepax Acked-by: Mark Brown Link: https://lore.kernel.org/r/20221118025807.534863-2-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- drivers/soundwire/bus.c | 4 ++-- include/linux/soundwire/sdw.h | 2 -- sound/soc/codecs/rt1316-sdw.c | 1 - sound/soc/codecs/rt1318-sdw.c | 1 - sound/soc/codecs/rt711-sdca-sdw.c | 1 - 5 files changed, 2 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c index 76515c33e639..c23275b443ac 100644 --- a/drivers/soundwire/bus.c +++ b/drivers/soundwire/bus.c @@ -1587,7 +1587,7 @@ static int sdw_handle_slave_alerts(struct sdw_slave *slave) goto io_err; } - if (slave->prop.is_sdca) { + if (slave->id.class_id) { ret = sdw_read_no_pm(slave, SDW_DP0_INT); if (ret < 0) { dev_err(&slave->dev, @@ -1724,7 +1724,7 @@ static int sdw_handle_slave_alerts(struct sdw_slave *slave) goto io_err; } - if (slave->prop.is_sdca) { + if (slave->id.class_id) { ret = sdw_read_no_pm(slave, SDW_DP0_INT); if (ret < 0) { dev_err(&slave->dev, diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index 9e4537f409c2..8fb458931772 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -365,7 +365,6 @@ struct sdw_dpn_prop { * @sink_dpn_prop: Sink Data Port N properties * @scp_int1_mask: SCP_INT1_MASK desired settings * @quirks: bitmask identifying deltas from the MIPI specification - * @is_sdca: the Slave supports the SDCA specification */ struct sdw_slave_prop { u32 mipi_revision; @@ -389,7 +388,6 @@ struct sdw_slave_prop { struct sdw_dpn_prop *sink_dpn_prop; u8 scp_int1_mask; u32 quirks; - bool is_sdca; }; #define SDW_SLAVE_QUIRKS_INVALID_INITIAL_PARITY BIT(0) diff --git a/sound/soc/codecs/rt1316-sdw.c b/sound/soc/codecs/rt1316-sdw.c index e6294cc7a995..c270fd9f8548 100644 --- a/sound/soc/codecs/rt1316-sdw.c +++ b/sound/soc/codecs/rt1316-sdw.c @@ -204,7 +204,6 @@ static int rt1316_read_prop(struct sdw_slave *slave) prop->scp_int1_mask = SDW_SCP_INT1_BUS_CLASH | SDW_SCP_INT1_PARITY; prop->quirks = SDW_SLAVE_QUIRKS_INVALID_INITIAL_PARITY; - prop->is_sdca = true; prop->paging_support = true; diff --git a/sound/soc/codecs/rt1318-sdw.c b/sound/soc/codecs/rt1318-sdw.c index f85f5ab2c6d0..8bc379215c34 100644 --- a/sound/soc/codecs/rt1318-sdw.c +++ b/sound/soc/codecs/rt1318-sdw.c @@ -353,7 +353,6 @@ static int rt1318_read_prop(struct sdw_slave *slave) prop->scp_int1_mask = SDW_SCP_INT1_BUS_CLASH | SDW_SCP_INT1_PARITY; prop->quirks = SDW_SLAVE_QUIRKS_INVALID_INITIAL_PARITY; - prop->is_sdca = true; prop->paging_support = true; diff --git a/sound/soc/codecs/rt711-sdca-sdw.c b/sound/soc/codecs/rt711-sdca-sdw.c index 88a8392a58ed..693e11ed8d08 100644 --- a/sound/soc/codecs/rt711-sdca-sdw.c +++ b/sound/soc/codecs/rt711-sdca-sdw.c @@ -186,7 +186,6 @@ static int rt711_sdca_read_prop(struct sdw_slave *slave) prop->scp_int1_mask = SDW_SCP_INT1_BUS_CLASH | SDW_SCP_INT1_PARITY; prop->quirks = SDW_SLAVE_QUIRKS_INVALID_INITIAL_PARITY; - prop->is_sdca = true; prop->paging_support = true; -- cgit v1.2.3 From ffa1726589a7cc4bd96a7f19f43cecdb7342478f Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Fri, 18 Nov 2022 10:58:07 +0800 Subject: soundwire: enable optional clock registers for SoundWire 1.2 devices The bus supports the mandatory clock registers for SDCA devices, these registers can also be optionally supported by SoundWire 1.2 devices that don't follow the SDCA class specification. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Rander Wang Reviewed-by: Péter Ujfalusi Signed-off-by: Bard Liao Reviewed-by: Charles Keepax Link: https://lore.kernel.org/r/20221118025807.534863-3-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- drivers/soundwire/bus.c | 7 ++++--- include/linux/soundwire/sdw.h | 4 ++++ 2 files changed, 8 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c index c23275b443ac..55d393247a0f 100644 --- a/drivers/soundwire/bus.c +++ b/drivers/soundwire/bus.c @@ -1233,10 +1233,11 @@ static int sdw_slave_set_frequency(struct sdw_slave *slave) /* * frequency base and scale registers are required for SDCA - * devices. They may also be used for 1.2+/non-SDCA devices, - * but we will need a DisCo property to cover this case + * devices. They may also be used for 1.2+/non-SDCA devices. + * Driver can set the property, we will need a DisCo property + * to discover this case from platform firmware. */ - if (!slave->id.class_id) + if (!slave->id.class_id && !slave->prop.clock_reg_supported) return 0; if (!mclk_freq) { diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index 8fb458931772..9a49263c53cf 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -365,6 +365,9 @@ struct sdw_dpn_prop { * @sink_dpn_prop: Sink Data Port N properties * @scp_int1_mask: SCP_INT1_MASK desired settings * @quirks: bitmask identifying deltas from the MIPI specification + * @clock_reg_supported: the Peripheral implements the clock base and scale + * registers introduced with the SoundWire 1.2 specification. SDCA devices + * do not need to set this boolean property as the registers are required. */ struct sdw_slave_prop { u32 mipi_revision; @@ -388,6 +391,7 @@ struct sdw_slave_prop { struct sdw_dpn_prop *sink_dpn_prop; u8 scp_int1_mask; u32 quirks; + bool clock_reg_supported; }; #define SDW_SLAVE_QUIRKS_INVALID_INITIAL_PARITY BIT(0) -- cgit v1.2.3 From 62dc9f3f2fd07a2d4f4c97d76403f387363cb637 Mon Sep 17 00:00:00 2001 From: Simon Trimmer Date: Fri, 25 Nov 2022 14:20:25 +0000 Subject: soundwire: bus: export sdw_nwrite_no_pm and sdw_nread_no_pm functions The commit 167790abb90f ("soundwire: export sdw_write/read_no_pm functions") exposed the single byte no_pm versions of the IO functions that can be used without touching PM, export the multi byte no_pm versions for the same reason. Reviewed-by: Pierre-Louis Bossart Signed-off-by: Simon Trimmer Signed-off-by: Charles Keepax Link: https://lore.kernel.org/r/20221125142028.1118618-2-ckeepax@opensource.cirrus.com Signed-off-by: Vinod Koul --- drivers/soundwire/bus.c | 8 ++++---- include/linux/soundwire/sdw.h | 2 ++ 2 files changed, 6 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c index 55d393247a0f..8a5dc0ea2d3a 100644 --- a/drivers/soundwire/bus.c +++ b/drivers/soundwire/bus.c @@ -414,8 +414,7 @@ int sdw_fill_msg(struct sdw_msg *msg, struct sdw_slave *slave, * all clients need to use the pm versions */ -static int -sdw_nread_no_pm(struct sdw_slave *slave, u32 addr, size_t count, u8 *val) +int sdw_nread_no_pm(struct sdw_slave *slave, u32 addr, size_t count, u8 *val) { struct sdw_msg msg; int ret; @@ -430,9 +429,9 @@ sdw_nread_no_pm(struct sdw_slave *slave, u32 addr, size_t count, u8 *val) ret = 0; return ret; } +EXPORT_SYMBOL(sdw_nread_no_pm); -static int -sdw_nwrite_no_pm(struct sdw_slave *slave, u32 addr, size_t count, const u8 *val) +int sdw_nwrite_no_pm(struct sdw_slave *slave, u32 addr, size_t count, const u8 *val) { struct sdw_msg msg; int ret; @@ -447,6 +446,7 @@ sdw_nwrite_no_pm(struct sdw_slave *slave, u32 addr, size_t count, const u8 *val) ret = 0; return ret; } +EXPORT_SYMBOL(sdw_nwrite_no_pm); int sdw_write_no_pm(struct sdw_slave *slave, u32 addr, u8 value) { diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index 9a49263c53cf..13019e3904b6 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -1049,7 +1049,9 @@ int sdw_write(struct sdw_slave *slave, u32 addr, u8 value); int sdw_write_no_pm(struct sdw_slave *slave, u32 addr, u8 value); int sdw_read_no_pm(struct sdw_slave *slave, u32 addr); int sdw_nread(struct sdw_slave *slave, u32 addr, size_t count, u8 *val); +int sdw_nread_no_pm(struct sdw_slave *slave, u32 addr, size_t count, u8 *val); int sdw_nwrite(struct sdw_slave *slave, u32 addr, size_t count, const u8 *val); +int sdw_nwrite_no_pm(struct sdw_slave *slave, u32 addr, size_t count, const u8 *val); int sdw_update(struct sdw_slave *slave, u32 addr, u8 mask, u8 val); int sdw_update_no_pm(struct sdw_slave *slave, u32 addr, u8 mask, u8 val); -- cgit v1.2.3 From 6726b47a2a60e3f2ef15ee7c4c6d9caa27770576 Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Fri, 25 Nov 2022 14:20:26 +0000 Subject: soundwire: Provide build stubs for common functions Provide stub functions when CONFIG_SOUNDWIRE is not set for functions that are quite likely to be used from common code on devices supporting multiple control buses. Reviewed-by: Pierre-Louis Bossart Signed-off-by: Charles Keepax Link: https://lore.kernel.org/r/20221125142028.1118618-3-ckeepax@opensource.cirrus.com Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw.h | 105 ++++++++++++++++++++++++++++++++++++++---- 1 file changed, 95 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index 13019e3904b6..3cd2a761911f 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -4,6 +4,7 @@ #ifndef __SOUNDWIRE_H #define __SOUNDWIRE_H +#include #include #include @@ -1023,15 +1024,8 @@ int sdw_stream_add_master(struct sdw_bus *bus, struct sdw_port_config *port_config, unsigned int num_ports, struct sdw_stream_runtime *stream); -int sdw_stream_add_slave(struct sdw_slave *slave, - struct sdw_stream_config *stream_config, - struct sdw_port_config *port_config, - unsigned int num_ports, - struct sdw_stream_runtime *stream); int sdw_stream_remove_master(struct sdw_bus *bus, struct sdw_stream_runtime *stream); -int sdw_stream_remove_slave(struct sdw_slave *slave, - struct sdw_stream_runtime *stream); int sdw_startup_stream(void *sdw_substream); int sdw_prepare_stream(struct sdw_stream_runtime *stream); int sdw_enable_stream(struct sdw_stream_runtime *stream); @@ -1042,8 +1036,20 @@ int sdw_bus_prep_clk_stop(struct sdw_bus *bus); int sdw_bus_clk_stop(struct sdw_bus *bus); int sdw_bus_exit_clk_stop(struct sdw_bus *bus); -/* messaging and data APIs */ +int sdw_compare_devid(struct sdw_slave *slave, struct sdw_slave_id id); +void sdw_extract_slave_id(struct sdw_bus *bus, u64 addr, struct sdw_slave_id *id); +#if IS_ENABLED(CONFIG_SOUNDWIRE) + +int sdw_stream_add_slave(struct sdw_slave *slave, + struct sdw_stream_config *stream_config, + struct sdw_port_config *port_config, + unsigned int num_ports, + struct sdw_stream_runtime *stream); +int sdw_stream_remove_slave(struct sdw_slave *slave, + struct sdw_stream_runtime *stream); + +/* messaging and data APIs */ int sdw_read(struct sdw_slave *slave, u32 addr); int sdw_write(struct sdw_slave *slave, u32 addr, u8 value); int sdw_write_no_pm(struct sdw_slave *slave, u32 addr, u8 value); @@ -1055,7 +1061,86 @@ int sdw_nwrite_no_pm(struct sdw_slave *slave, u32 addr, size_t count, const u8 * int sdw_update(struct sdw_slave *slave, u32 addr, u8 mask, u8 val); int sdw_update_no_pm(struct sdw_slave *slave, u32 addr, u8 mask, u8 val); -int sdw_compare_devid(struct sdw_slave *slave, struct sdw_slave_id id); -void sdw_extract_slave_id(struct sdw_bus *bus, u64 addr, struct sdw_slave_id *id); +#else + +static inline int sdw_stream_add_slave(struct sdw_slave *slave, + struct sdw_stream_config *stream_config, + struct sdw_port_config *port_config, + unsigned int num_ports, + struct sdw_stream_runtime *stream) +{ + WARN_ONCE(1, "SoundWire API is disabled"); + return -EINVAL; +} + +static inline int sdw_stream_remove_slave(struct sdw_slave *slave, + struct sdw_stream_runtime *stream) +{ + WARN_ONCE(1, "SoundWire API is disabled"); + return -EINVAL; +} + +/* messaging and data APIs */ +static inline int sdw_read(struct sdw_slave *slave, u32 addr) +{ + WARN_ONCE(1, "SoundWire API is disabled"); + return -EINVAL; +} + +static inline int sdw_write(struct sdw_slave *slave, u32 addr, u8 value) +{ + WARN_ONCE(1, "SoundWire API is disabled"); + return -EINVAL; +} + +static inline int sdw_write_no_pm(struct sdw_slave *slave, u32 addr, u8 value) +{ + WARN_ONCE(1, "SoundWire API is disabled"); + return -EINVAL; +} + +static inline int sdw_read_no_pm(struct sdw_slave *slave, u32 addr) +{ + WARN_ONCE(1, "SoundWire API is disabled"); + return -EINVAL; +} + +static inline int sdw_nread(struct sdw_slave *slave, u32 addr, size_t count, u8 *val) +{ + WARN_ONCE(1, "SoundWire API is disabled"); + return -EINVAL; +} + +static inline int sdw_nread_no_pm(struct sdw_slave *slave, u32 addr, size_t count, u8 *val) +{ + WARN_ONCE(1, "SoundWire API is disabled"); + return -EINVAL; +} + +static inline int sdw_nwrite(struct sdw_slave *slave, u32 addr, size_t count, const u8 *val) +{ + WARN_ONCE(1, "SoundWire API is disabled"); + return -EINVAL; +} + +static inline int sdw_nwrite_no_pm(struct sdw_slave *slave, u32 addr, size_t count, const u8 *val) +{ + WARN_ONCE(1, "SoundWire API is disabled"); + return -EINVAL; +} + +static inline int sdw_update(struct sdw_slave *slave, u32 addr, u8 mask, u8 val) +{ + WARN_ONCE(1, "SoundWire API is disabled"); + return -EINVAL; +} + +static inline int sdw_update_no_pm(struct sdw_slave *slave, u32 addr, u8 mask, u8 val) +{ + WARN_ONCE(1, "SoundWire API is disabled"); + return -EINVAL; +} + +#endif /* CONFIG_SOUNDWIRE */ #endif /* __SOUNDWIRE_H */ -- cgit v1.2.3 From 8afbb4273977f055db219a22daaafe64be10fb95 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 9 Jan 2023 18:58:05 +0100 Subject: driver core: make bus_get_device_klist() static No one calls this function outside of drivers/base/bus.c so make it static so it does not need to be exported anymore. Reviewed-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20230109175810.2965448-1-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/base/bus.c | 3 +-- include/linux/device/bus.h | 1 - 2 files changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/bus.c b/drivers/base/bus.c index 4ec6dbab73be..4425f962bf51 100644 --- a/drivers/base/bus.c +++ b/drivers/base/bus.c @@ -897,11 +897,10 @@ struct kset *bus_get_kset(struct bus_type *bus) } EXPORT_SYMBOL_GPL(bus_get_kset); -struct klist *bus_get_device_klist(struct bus_type *bus) +static struct klist *bus_get_device_klist(struct bus_type *bus) { return &bus->p->klist_devices; } -EXPORT_SYMBOL_GPL(bus_get_device_klist); /* * Yes, this forcibly breaks the klist abstraction temporarily. It diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h index d8b29ccd07e5..01077c503d61 100644 --- a/include/linux/device/bus.h +++ b/include/linux/device/bus.h @@ -287,6 +287,5 @@ extern int bus_unregister_notifier(struct bus_type *bus, #define BUS_NOTIFY_DRIVER_NOT_BOUND 0x00000008 /* driver fails to be bound */ extern struct kset *bus_get_kset(struct bus_type *bus); -extern struct klist *bus_get_device_klist(struct bus_type *bus); #endif -- cgit v1.2.3 From a9efdd2519edd7df84afd075b65ca6428dcb0039 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 9 Jan 2023 18:58:06 +0100 Subject: driver core: remove subsys_find_device_by_id() This function has not been called by any code in the kernel tree in many many years so remove it as it is unused. Reviewed-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20230109175810.2965448-2-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/base/bus.c | 41 ----------------------------------------- include/linux/device/bus.h | 2 -- 2 files changed, 43 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/bus.c b/drivers/base/bus.c index 4425f962bf51..f8eb882bbf37 100644 --- a/drivers/base/bus.c +++ b/drivers/base/bus.c @@ -339,47 +339,6 @@ struct device *bus_find_device(struct bus_type *bus, } EXPORT_SYMBOL_GPL(bus_find_device); -/** - * subsys_find_device_by_id - find a device with a specific enumeration number - * @subsys: subsystem - * @id: index 'id' in struct device - * @hint: device to check first - * - * Check the hint's next object and if it is a match return it directly, - * otherwise, fall back to a full list search. Either way a reference for - * the returned object is taken. - */ -struct device *subsys_find_device_by_id(struct bus_type *subsys, unsigned int id, - struct device *hint) -{ - struct klist_iter i; - struct device *dev; - - if (!subsys) - return NULL; - - if (hint) { - klist_iter_init_node(&subsys->p->klist_devices, &i, &hint->p->knode_bus); - dev = next_device(&i); - if (dev && dev->id == id && get_device(dev)) { - klist_iter_exit(&i); - return dev; - } - klist_iter_exit(&i); - } - - klist_iter_init_node(&subsys->p->klist_devices, &i, NULL); - while ((dev = next_device(&i))) { - if (dev->id == id && get_device(dev)) { - klist_iter_exit(&i); - return dev; - } - } - klist_iter_exit(&i); - return NULL; -} -EXPORT_SYMBOL_GPL(subsys_find_device_by_id); - static struct device_driver *next_driver(struct klist_iter *i) { struct klist_node *n = klist_next(i); diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h index 01077c503d61..3b1a2066afcd 100644 --- a/include/linux/device/bus.h +++ b/include/linux/device/bus.h @@ -250,8 +250,6 @@ bus_find_device_by_acpi_dev(struct bus_type *bus, const void *adev) } #endif -struct device *subsys_find_device_by_id(struct bus_type *bus, unsigned int id, - struct device *hint); int bus_for_each_drv(struct bus_type *bus, struct device_driver *start, void *data, int (*fn)(struct device_driver *, void *)); void bus_sort_breadthfirst(struct bus_type *bus, -- cgit v1.2.3 From 2e45fc5502af9826617a96fe63aee055002cac97 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 9 Jan 2023 18:58:07 +0100 Subject: driver core: make subsys_dev_iter_init() static No one outside of drivers/base/bus.c calls this function so make it static and remove the exported symbol. Reviewed-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20230109175810.2965448-3-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/base/bus.c | 5 ++--- include/linux/device/bus.h | 4 ---- 2 files changed, 2 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/bus.c b/drivers/base/bus.c index f8eb882bbf37..f781124fdf31 100644 --- a/drivers/base/bus.c +++ b/drivers/base/bus.c @@ -923,8 +923,8 @@ EXPORT_SYMBOL_GPL(bus_sort_breadthfirst); * otherwise if it is NULL, the iteration starts at the beginning of * the list. */ -void subsys_dev_iter_init(struct subsys_dev_iter *iter, struct bus_type *subsys, - struct device *start, const struct device_type *type) +static void subsys_dev_iter_init(struct subsys_dev_iter *iter, struct bus_type *subsys, + struct device *start, const struct device_type *type) { struct klist_node *start_knode = NULL; @@ -933,7 +933,6 @@ void subsys_dev_iter_init(struct subsys_dev_iter *iter, struct bus_type *subsys, klist_iter_init_node(&subsys->p->klist_devices, &iter->ki, start_knode); iter->type = type; } -EXPORT_SYMBOL_GPL(subsys_dev_iter_init); /** * subsys_dev_iter_next - iterate to the next device diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h index 3b1a2066afcd..67cb5b29f62d 100644 --- a/include/linux/device/bus.h +++ b/include/linux/device/bus.h @@ -154,10 +154,6 @@ struct subsys_dev_iter { struct klist_iter ki; const struct device_type *type; }; -void subsys_dev_iter_init(struct subsys_dev_iter *iter, - struct bus_type *subsys, - struct device *start, - const struct device_type *type); struct device *subsys_dev_iter_next(struct subsys_dev_iter *iter); void subsys_dev_iter_exit(struct subsys_dev_iter *iter); -- cgit v1.2.3 From 38cdadefa2feecc9e7aa5f67bc4aea5b9a8ca59f Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 9 Jan 2023 18:58:08 +0100 Subject: driver core: make subsys_dev_iter_next() static The function subsys_dev_iter_next() is only used in drivers/base/bus.c so make it static to that file and remove the global export. Reviewed-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20230109175810.2965448-4-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/base/bus.c | 3 +-- include/linux/device/bus.h | 1 - 2 files changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/bus.c b/drivers/base/bus.c index f781124fdf31..f0aacb3b1bc6 100644 --- a/drivers/base/bus.c +++ b/drivers/base/bus.c @@ -946,7 +946,7 @@ static void subsys_dev_iter_init(struct subsys_dev_iter *iter, struct bus_type * * free to do whatever it wants to do with the device including * calling back into subsys code. */ -struct device *subsys_dev_iter_next(struct subsys_dev_iter *iter) +static struct device *subsys_dev_iter_next(struct subsys_dev_iter *iter) { struct klist_node *knode; struct device *dev; @@ -960,7 +960,6 @@ struct device *subsys_dev_iter_next(struct subsys_dev_iter *iter) return dev; } } -EXPORT_SYMBOL_GPL(subsys_dev_iter_next); /** * subsys_dev_iter_exit - finish iteration diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h index 67cb5b29f62d..4f994d8fce0c 100644 --- a/include/linux/device/bus.h +++ b/include/linux/device/bus.h @@ -154,7 +154,6 @@ struct subsys_dev_iter { struct klist_iter ki; const struct device_type *type; }; -struct device *subsys_dev_iter_next(struct subsys_dev_iter *iter); void subsys_dev_iter_exit(struct subsys_dev_iter *iter); int bus_for_each_dev(struct bus_type *bus, struct device *start, void *data, -- cgit v1.2.3 From af6d0743599e594cb2cec3f1a6d2600a57d1d375 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 9 Jan 2023 18:58:09 +0100 Subject: driver core: make subsys_dev_iter_exit() static The function subsys_dev_iter_exit() is not used outside of drivers/base/bus.c so make it static to that file and remove the global export. Reviewed-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20230109175810.2965448-5-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/base/bus.c | 3 +-- include/linux/device/bus.h | 1 - 2 files changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/bus.c b/drivers/base/bus.c index f0aacb3b1bc6..bde52fd1d3e3 100644 --- a/drivers/base/bus.c +++ b/drivers/base/bus.c @@ -968,11 +968,10 @@ static struct device *subsys_dev_iter_next(struct subsys_dev_iter *iter) * Finish an iteration. Always call this function after iteration is * complete whether the iteration ran till the end or not. */ -void subsys_dev_iter_exit(struct subsys_dev_iter *iter) +static void subsys_dev_iter_exit(struct subsys_dev_iter *iter) { klist_iter_exit(&iter->ki); } -EXPORT_SYMBOL_GPL(subsys_dev_iter_exit); int subsys_interface_register(struct subsys_interface *sif) { diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h index 4f994d8fce0c..848d49f4cc09 100644 --- a/include/linux/device/bus.h +++ b/include/linux/device/bus.h @@ -154,7 +154,6 @@ struct subsys_dev_iter { struct klist_iter ki; const struct device_type *type; }; -void subsys_dev_iter_exit(struct subsys_dev_iter *iter); int bus_for_each_dev(struct bus_type *bus, struct device *start, void *data, int (*fn)(struct device *dev, void *data)); -- cgit v1.2.3 From b0a8a59a1c44c07807afe50c6bd21a33c9ec98b7 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 9 Jan 2023 18:58:10 +0100 Subject: driver core: move struct subsys_dev_iter to a local file struct subsys_dev_iter is not used by any code outside of drivers/base/bus.c so move it into that file and out of the global bus.h file. Reviewed-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20230109175810.2965448-6-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/base/bus.c | 5 +++++ include/linux/device/bus.h | 5 ----- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/bus.c b/drivers/base/bus.c index bde52fd1d3e3..428c26c6b615 100644 --- a/drivers/base/bus.c +++ b/drivers/base/bus.c @@ -911,6 +911,11 @@ void bus_sort_breadthfirst(struct bus_type *bus, } EXPORT_SYMBOL_GPL(bus_sort_breadthfirst); +struct subsys_dev_iter { + struct klist_iter ki; + const struct device_type *type; +}; + /** * subsys_dev_iter_init - initialize subsys device iterator * @iter: subsys iterator to initialize diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h index 848d49f4cc09..d529f644e92b 100644 --- a/include/linux/device/bus.h +++ b/include/linux/device/bus.h @@ -150,11 +150,6 @@ int device_match_acpi_handle(struct device *dev, const void *handle); int device_match_any(struct device *dev, const void *unused); /* iterator helpers for buses */ -struct subsys_dev_iter { - struct klist_iter ki; - const struct device_type *type; -}; - int bus_for_each_dev(struct bus_type *bus, struct device *start, void *data, int (*fn)(struct device *dev, void *data)); struct device *bus_find_device(struct bus_type *bus, struct device *start, -- cgit v1.2.3 From 26b36df7516692292312063ca6fd19e73c06d4e7 Mon Sep 17 00:00:00 2001 From: Abel Vesa Date: Tue, 27 Dec 2022 22:45:27 +0200 Subject: clk: Add generic sync_state callback for disabling unused clocks There are unused clocks that need to remain untouched by clk_disable_unused, and most likely could be disabled later on sync_state. So provide a generic sync_state callback for the clock providers that register such clocks. Then, use the same mechanism as clk_disable_unused from that generic callback, but pass the device to make sure only the clocks belonging to the current clock provider get disabled, if unused. Also, during the default clk_disable_unused, if the driver that registered the clock has the generic clk_sync_state_disable_unused callback set for sync_state, skip disabling its clocks. Signed-off-by: Abel Vesa Reviewed-by: Bjorn Andersson Reviewed-by: Dmitry Baryshkov Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20221227204528.1899863-1-abel.vesa@linaro.org --- drivers/clk/clk.c | 57 +++++++++++++++++++++++++++++++++++--------- include/linux/clk-provider.h | 1 + 2 files changed, 47 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index e62552a75f08..ac7182903d88 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -1302,14 +1302,26 @@ static void clk_core_disable_unprepare(struct clk_core *core) clk_core_unprepare_lock(core); } -static void __init clk_unprepare_unused_subtree(struct clk_core *core) +static void clk_unprepare_unused_subtree(struct clk_core *core, + struct device *dev) { + bool from_sync_state = !!dev; struct clk_core *child; lockdep_assert_held(&prepare_lock); hlist_for_each_entry(child, &core->children, child_node) - clk_unprepare_unused_subtree(child); + clk_unprepare_unused_subtree(child, dev); + + if (from_sync_state && core->dev != dev) + return; + + /* + * clock will be unprepared on sync_state, + * so leave as is for now + */ + if (!from_sync_state && dev_has_sync_state(core->dev)) + return; if (core->prepare_count) return; @@ -1332,15 +1344,27 @@ static void __init clk_unprepare_unused_subtree(struct clk_core *core) clk_pm_runtime_put(core); } -static void __init clk_disable_unused_subtree(struct clk_core *core) +static void clk_disable_unused_subtree(struct clk_core *core, + struct device *dev) { + bool from_sync_state = !!dev; struct clk_core *child; unsigned long flags; lockdep_assert_held(&prepare_lock); hlist_for_each_entry(child, &core->children, child_node) - clk_disable_unused_subtree(child); + clk_disable_unused_subtree(child, dev); + + if (from_sync_state && core->dev != dev) + return; + + /* + * clock will be disabled on sync_state, + * so leave as is for now + */ + if (!from_sync_state && dev_has_sync_state(core->dev)) + return; if (core->flags & CLK_OPS_PARENT_ENABLE) clk_core_prepare_enable(core->parent); @@ -1378,7 +1402,7 @@ unprepare_out: clk_core_disable_unprepare(core->parent); } -static bool clk_ignore_unused __initdata; +static bool clk_ignore_unused; static int __init clk_ignore_unused_setup(char *__unused) { clk_ignore_unused = true; @@ -1386,35 +1410,46 @@ static int __init clk_ignore_unused_setup(char *__unused) } __setup("clk_ignore_unused", clk_ignore_unused_setup); -static int __init clk_disable_unused(void) +static void __clk_disable_unused(struct device *dev) { struct clk_core *core; if (clk_ignore_unused) { pr_warn("clk: Not disabling unused clocks\n"); - return 0; + return; } clk_prepare_lock(); hlist_for_each_entry(core, &clk_root_list, child_node) - clk_disable_unused_subtree(core); + clk_disable_unused_subtree(core, dev); hlist_for_each_entry(core, &clk_orphan_list, child_node) - clk_disable_unused_subtree(core); + clk_disable_unused_subtree(core, dev); hlist_for_each_entry(core, &clk_root_list, child_node) - clk_unprepare_unused_subtree(core); + clk_unprepare_unused_subtree(core, dev); hlist_for_each_entry(core, &clk_orphan_list, child_node) - clk_unprepare_unused_subtree(core); + clk_unprepare_unused_subtree(core, dev); clk_prepare_unlock(); +} + +static int __init clk_disable_unused(void) +{ + __clk_disable_unused(NULL); return 0; } late_initcall_sync(clk_disable_unused); +void clk_sync_state_disable_unused(struct device *dev) +{ + __clk_disable_unused(dev); +} +EXPORT_SYMBOL_GPL(clk_sync_state_disable_unused); + static int clk_core_determine_round_nolock(struct clk_core *core, struct clk_rate_request *req) { diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 842e72a5348f..cf1adfeaf257 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -720,6 +720,7 @@ struct clk *clk_register_divider_table(struct device *dev, const char *name, void __iomem *reg, u8 shift, u8 width, u8 clk_divider_flags, const struct clk_div_table *table, spinlock_t *lock); +void clk_sync_state_disable_unused(struct device *dev); /** * clk_register_divider - register a divider clock with the clock framework * @dev: device registering this clock -- cgit v1.2.3 From a9236a0aa7d7f52a974cc7eaa971fae92aa477c5 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Mon, 2 Jan 2023 16:18:27 +0530 Subject: PM: domains: Allow a genpd consumer to require a synced power off Some genpd providers doesn't ensure that it has turned off at hardware. This is fine until the consumer really requires during some special scenarios that the power domain collapse at hardware before it is turned ON again. An example is the reset sequence of Adreno GPU which requires that the 'gpucc cx gdsc' power domain should move to OFF state in hardware at least once before turning in ON again to clear the internal state. Signed-off-by: Ulf Hansson Signed-off-by: Akhil P Oommen Reviewed-by: Bjorn Andersson Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230102161757.v5.1.I3e6b1f078ad0f1ca9358c573daa7b70ec132cdbe@changeid --- drivers/base/power/domain.c | 26 ++++++++++++++++++++++++++ include/linux/pm_domain.h | 5 +++++ 2 files changed, 31 insertions(+) (limited to 'include/linux') diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index 967bcf9d415e..84662d338188 100644 --- a/drivers/base/power/domain.c +++ b/drivers/base/power/domain.c @@ -519,6 +519,31 @@ ktime_t dev_pm_genpd_get_next_hrtimer(struct device *dev) } EXPORT_SYMBOL_GPL(dev_pm_genpd_get_next_hrtimer); +/* + * dev_pm_genpd_synced_poweroff - Next power off should be synchronous + * + * @dev: A device that is attached to the genpd. + * + * Allows a consumer of the genpd to notify the provider that the next power off + * should be synchronous. + * + * It is assumed that the users guarantee that the genpd wouldn't be detached + * while this routine is getting called. + */ +void dev_pm_genpd_synced_poweroff(struct device *dev) +{ + struct generic_pm_domain *genpd; + + genpd = dev_to_genpd_safe(dev); + if (!genpd) + return; + + genpd_lock(genpd); + genpd->synced_poweroff = true; + genpd_unlock(genpd); +} +EXPORT_SYMBOL_GPL(dev_pm_genpd_synced_poweroff); + static int _genpd_power_on(struct generic_pm_domain *genpd, bool timed) { unsigned int state_idx = genpd->state_idx; @@ -562,6 +587,7 @@ static int _genpd_power_on(struct generic_pm_domain *genpd, bool timed) out: raw_notifier_call_chain(&genpd->power_notifiers, GENPD_NOTIFY_ON, NULL); + genpd->synced_poweroff = false; return 0; err: raw_notifier_call_chain(&genpd->power_notifiers, GENPD_NOTIFY_OFF, diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 1cd41bdf73cf..f776fb93eaa0 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -136,6 +136,7 @@ struct generic_pm_domain { unsigned int prepared_count; /* Suspend counter of prepared devices */ unsigned int performance_state; /* Aggregated max performance state */ cpumask_var_t cpus; /* A cpumask of the attached CPUs */ + bool synced_poweroff; /* A consumer needs a synced poweroff */ int (*power_off)(struct generic_pm_domain *domain); int (*power_on)(struct generic_pm_domain *domain); struct raw_notifier_head power_notifiers; /* Power on/off notifiers */ @@ -235,6 +236,7 @@ int dev_pm_genpd_add_notifier(struct device *dev, struct notifier_block *nb); int dev_pm_genpd_remove_notifier(struct device *dev); void dev_pm_genpd_set_next_wakeup(struct device *dev, ktime_t next); ktime_t dev_pm_genpd_get_next_hrtimer(struct device *dev); +void dev_pm_genpd_synced_poweroff(struct device *dev); extern struct dev_power_governor simple_qos_governor; extern struct dev_power_governor pm_domain_always_on_gov; @@ -300,6 +302,9 @@ static inline ktime_t dev_pm_genpd_get_next_hrtimer(struct device *dev) { return KTIME_MAX; } +static inline void dev_pm_genpd_synced_poweroff(struct device *dev) +{ } + #define simple_qos_governor (*(struct dev_power_governor *)(NULL)) #define pm_domain_always_on_gov (*(struct dev_power_governor *)(NULL)) #endif -- cgit v1.2.3 From e656cd0bcf3d2ba2eceac82b44714bf355428ec4 Mon Sep 17 00:00:00 2001 From: Loic Poulain Date: Mon, 9 Jan 2023 14:05:22 +0100 Subject: soc: qcom: rmtfs: Optionally map RMTFS to more VMs Some SoCs require that RMTFS is also mapped to the NAV VM. Trying to power on the modem without that results in the whole platform crashing and forces a hard reboot within about 2 seconds. Add support for mapping the region to additional VMs, such as NAV to open a path towards enabling modem on such platforms. Signed-off-by: Loic Poulain [Konrad: reword, make conditional and flexible, add a define for NAV VMID] Signed-off-by: Konrad Dybcio Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230109130523.298971-2-konrad.dybcio@linaro.org --- drivers/soc/qcom/rmtfs_mem.c | 29 ++++++++++++++++++++++------- include/linux/qcom_scm.h | 1 + 2 files changed, 23 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/soc/qcom/rmtfs_mem.c b/drivers/soc/qcom/rmtfs_mem.c index 0feaae357821..9d59ad509a5c 100644 --- a/drivers/soc/qcom/rmtfs_mem.c +++ b/drivers/soc/qcom/rmtfs_mem.c @@ -17,6 +17,7 @@ #include #define QCOM_RMTFS_MEM_DEV_MAX (MINORMASK + 1) +#define NUM_MAX_VMIDS 2 static dev_t qcom_rmtfs_mem_major; @@ -171,12 +172,12 @@ static void qcom_rmtfs_mem_release_device(struct device *dev) static int qcom_rmtfs_mem_probe(struct platform_device *pdev) { struct device_node *node = pdev->dev.of_node; - struct qcom_scm_vmperm perms[2]; + struct qcom_scm_vmperm perms[NUM_MAX_VMIDS + 1]; struct reserved_mem *rmem; struct qcom_rmtfs_mem *rmtfs_mem; u32 client_id; - u32 vmid; - int ret; + u32 num_vmids, vmid[NUM_MAX_VMIDS]; + int ret, i; rmem = of_reserved_mem_lookup(node); if (!rmem) { @@ -226,7 +227,18 @@ static int qcom_rmtfs_mem_probe(struct platform_device *pdev) goto put_device; } - ret = of_property_read_u32(node, "qcom,vmid", &vmid); + num_vmids = of_property_count_u32_elems(node, "qcom,vmid"); + if (num_vmids < 0) { + dev_err(&pdev->dev, "failed to count qcom,vmid elements: %d\n", ret); + goto remove_cdev; + } else if (num_vmids > NUM_MAX_VMIDS) { + dev_warn(&pdev->dev, + "too many VMIDs (%d) specified! Only mapping first %d entries\n", + num_vmids, NUM_MAX_VMIDS); + num_vmids = NUM_MAX_VMIDS; + } + + ret = of_property_read_u32_array(node, "qcom,vmid", vmid, num_vmids); if (ret < 0 && ret != -EINVAL) { dev_err(&pdev->dev, "failed to parse qcom,vmid\n"); goto remove_cdev; @@ -238,12 +250,15 @@ static int qcom_rmtfs_mem_probe(struct platform_device *pdev) perms[0].vmid = QCOM_SCM_VMID_HLOS; perms[0].perm = QCOM_SCM_PERM_RW; - perms[1].vmid = vmid; - perms[1].perm = QCOM_SCM_PERM_RW; + + for (i = 0; i < num_vmids; i++) { + perms[i + 1].vmid = vmid[i]; + perms[i + 1].perm = QCOM_SCM_PERM_RW; + } rmtfs_mem->perms = BIT(QCOM_SCM_VMID_HLOS); ret = qcom_scm_assign_mem(rmtfs_mem->addr, rmtfs_mem->size, - &rmtfs_mem->perms, perms, 2); + &rmtfs_mem->perms, perms, num_vmids + 1); if (ret < 0) { dev_err(&pdev->dev, "assign memory failed\n"); goto remove_cdev; diff --git a/include/linux/qcom_scm.h b/include/linux/qcom_scm.h index f8335644a01a..150b72edb879 100644 --- a/include/linux/qcom_scm.h +++ b/include/linux/qcom_scm.h @@ -55,6 +55,7 @@ enum qcom_scm_ice_cipher { #define QCOM_SCM_VMID_MSS_MSA 0xF #define QCOM_SCM_VMID_WLAN 0x18 #define QCOM_SCM_VMID_WLAN_CE 0x19 +#define QCOM_SCM_VMID_NAV 0x2B #define QCOM_SCM_PERM_READ 0x4 #define QCOM_SCM_PERM_WRITE 0x2 #define QCOM_SCM_PERM_EXEC 0x1 -- cgit v1.2.3 From 45ca30eb9dfe622b00ce352cf28ee141d243254b Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Mon, 9 Jan 2023 14:05:23 +0100 Subject: dt-bindings: firmware: qcom: scm: Separate VMIDs from header to bindings The SCM VMIDs represent predefined mappings that come from the irreplaceable and non-omittable firmware that comes with every Qualcomm SoC (unless you steal engineering samples from the factory) and help clarify otherwise totally magic numbers which we are required to pass to the secure world for some parts of the SoC to work at all (with modem being the prime example). On top of that, with changes to the rmtfs binding, secure VMIDs will become useful to have in device trees for readability. Separate them out and add to include/dt-bindings. Signed-off-by: Konrad Dybcio Reviewed-by: Krzysztof Kozlowski Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230109130523.298971-3-konrad.dybcio@linaro.org --- include/dt-bindings/firmware/qcom,scm.h | 16 ++++++++++++++++ include/linux/qcom_scm.h | 7 ++----- 2 files changed, 18 insertions(+), 5 deletions(-) create mode 100644 include/dt-bindings/firmware/qcom,scm.h (limited to 'include/linux') diff --git a/include/dt-bindings/firmware/qcom,scm.h b/include/dt-bindings/firmware/qcom,scm.h new file mode 100644 index 000000000000..1a4e68fa0744 --- /dev/null +++ b/include/dt-bindings/firmware/qcom,scm.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause */ +/* + * Copyright (c) 2010-2015, 2018-2019 The Linux Foundation. All rights reserved. + * Copyright (C) 2015 Linaro Ltd. + */ + +#ifndef _DT_BINDINGS_FIRMWARE_QCOM_SCM_H +#define _DT_BINDINGS_FIRMWARE_QCOM_SCM_H + +#define QCOM_SCM_VMID_HLOS 0x3 +#define QCOM_SCM_VMID_MSS_MSA 0xF +#define QCOM_SCM_VMID_WLAN 0x18 +#define QCOM_SCM_VMID_WLAN_CE 0x19 +#define QCOM_SCM_VMID_NAV 0x2B + +#endif diff --git a/include/linux/qcom_scm.h b/include/linux/qcom_scm.h index 150b72edb879..1e449a5d7f5c 100644 --- a/include/linux/qcom_scm.h +++ b/include/linux/qcom_scm.h @@ -9,6 +9,8 @@ #include #include +#include + #define QCOM_SCM_VERSION(major, minor) (((major) << 16) | ((minor) & 0xFF)) #define QCOM_SCM_CPU_PWR_DOWN_L2_ON 0x0 #define QCOM_SCM_CPU_PWR_DOWN_L2_OFF 0x1 @@ -51,11 +53,6 @@ enum qcom_scm_ice_cipher { QCOM_SCM_ICE_CIPHER_AES_256_CBC = 4, }; -#define QCOM_SCM_VMID_HLOS 0x3 -#define QCOM_SCM_VMID_MSS_MSA 0xF -#define QCOM_SCM_VMID_WLAN 0x18 -#define QCOM_SCM_VMID_WLAN_CE 0x19 -#define QCOM_SCM_VMID_NAV 0x2B #define QCOM_SCM_PERM_READ 0x4 #define QCOM_SCM_PERM_WRITE 0x2 #define QCOM_SCM_PERM_EXEC 0x1 -- cgit v1.2.3 From 2364b406824f1f42026d87c1e26d4dd1ca0f65af Mon Sep 17 00:00:00 2001 From: John Ogness Date: Mon, 9 Jan 2023 11:13:53 +0106 Subject: printk: move size limit macros into internal.h The size limit macros are located further down in printk.c and behind ifdef conditionals. This complicates their usage for upcoming changes. Move the macros into internal.h so that they are still invisible outside of printk, but easily accessible for printk. Also, the maximum size of formatted extended messages does not need to be known by any code outside of printk, so move it to internal.h as well. And like CONSOLE_LOG_MAX, for !CONFIG_PRINTK set CONSOLE_EXT_LOG_MAX to 0 to reduce the static memory footprint. Signed-off-by: John Ogness Reviewed-by: Petr Mladek Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20230109100800.1085541-2-john.ogness@linutronix.de --- include/linux/printk.h | 2 -- kernel/printk/internal.h | 24 ++++++++++++++++++++++++ kernel/printk/printk.c | 17 ----------------- 3 files changed, 24 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/printk.h b/include/linux/printk.h index 8c81806c2e99..8ef499ab3c1e 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -44,8 +44,6 @@ static inline const char *printk_skip_headers(const char *buffer) return buffer; } -#define CONSOLE_EXT_LOG_MAX 8192 - /* printk's without a loglevel use this.. */ #define MESSAGE_LOGLEVEL_DEFAULT CONFIG_MESSAGE_LOGLEVEL_DEFAULT diff --git a/kernel/printk/internal.h b/kernel/printk/internal.h index d947ca6c84f9..f394332410c9 100644 --- a/kernel/printk/internal.h +++ b/kernel/printk/internal.h @@ -14,6 +14,24 @@ int devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write, #ifdef CONFIG_PRINTK +#ifdef CONFIG_PRINTK_CALLER +#define PREFIX_MAX 48 +#else +#define PREFIX_MAX 32 +#endif + +/* the maximum size of a formatted record (i.e. with prefix added per line) */ +#define CONSOLE_LOG_MAX 1024 + +/* the maximum size of a formatted extended record */ +#define CONSOLE_EXT_LOG_MAX 8192 + +/* the maximum size for a dropped text message */ +#define DROPPED_TEXT_MAX 64 + +/* the maximum size allowed to be reserved for a record */ +#define LOG_LINE_MAX (CONSOLE_LOG_MAX - PREFIX_MAX) + /* Flags for a single printk record. */ enum printk_info_flags { LOG_NEWLINE = 2, /* text ended with a newline */ @@ -48,6 +66,12 @@ u16 printk_parse_prefix(const char *text, int *level, enum printk_info_flags *flags); #else +#define PREFIX_MAX 0 +#define CONSOLE_LOG_MAX 0 +#define CONSOLE_EXT_LOG_MAX 0 +#define DROPPED_TEXT_MAX 0 +#define LOG_LINE_MAX 0 + /* * In !PRINTK builds we still export console_sem * semaphore and some of console functions (console_unlock()/etc.), so diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 7decf1e9c486..55bb065de65f 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -465,21 +465,6 @@ static struct latched_seq clear_seq = { .val[1] = 0, }; -#ifdef CONFIG_PRINTK_CALLER -#define PREFIX_MAX 48 -#else -#define PREFIX_MAX 32 -#endif - -/* the maximum size of a formatted record (i.e. with prefix added per line) */ -#define CONSOLE_LOG_MAX 1024 - -/* the maximum size for a dropped text message */ -#define DROPPED_TEXT_MAX 64 - -/* the maximum size allowed to be reserved for a record */ -#define LOG_LINE_MAX (CONSOLE_LOG_MAX - PREFIX_MAX) - #define LOG_LEVEL(v) ((v) & 0x07) #define LOG_FACILITY(v) ((v) >> 3 & 0xff) @@ -2387,8 +2372,6 @@ static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progre #else /* CONFIG_PRINTK */ -#define CONSOLE_LOG_MAX 0 -#define DROPPED_TEXT_MAX 0 #define printk_time false #define prb_read_valid(rb, seq, r) false -- cgit v1.2.3 From 717a5651b10940ec827fe07acfb956d906250b2b Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 9 Jan 2023 11:13:54 +0106 Subject: console: Use BIT() macros for @flags values Rather than manually calculating powers of 2, use the BIT() macros. Also take this opportunatity to cleanup and restructure the value comments into proper kerneldoc comments. Signed-off-by: Thomas Gleixner Signed-off-by: John Ogness Reviewed-by: Petr Mladek Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20230109100800.1085541-3-john.ogness@linutronix.de --- include/linux/console.h | 46 ++++++++++++++++++++++++++++++++++++---------- 1 file changed, 36 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/console.h b/include/linux/console.h index 9cea254b34b8..ed804dd7c2e8 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -15,6 +15,7 @@ #define _LINUX_CONSOLE_H_ 1 #include +#include #include #include @@ -125,18 +126,43 @@ static inline int con_debug_leave(void) /* * The interface for a console, or any other device that wants to capture * console messages (printer driver?) - * - * If a console driver is marked CON_BOOT then it will be auto-unregistered - * when the first real console is registered. This is for early-printk drivers. */ -#define CON_PRINTBUFFER (1) -#define CON_CONSDEV (2) /* Preferred console, /dev/console */ -#define CON_ENABLED (4) -#define CON_BOOT (8) -#define CON_ANYTIME (16) /* Safe to call when cpu is offline */ -#define CON_BRL (32) /* Used for a braille device */ -#define CON_EXTENDED (64) /* Use the extended output format a la /dev/kmsg */ +/** + * cons_flags - General console flags + * @CON_PRINTBUFFER: Used by newly registered consoles to avoid duplicate + * output of messages that were already shown by boot + * consoles or read by userspace via syslog() syscall. + * @CON_CONSDEV: Indicates that the console driver is backing + * /dev/console. + * @CON_ENABLED: Indicates if a console is allowed to print records. If + * false, the console also will not advance to later + * records. + * @CON_BOOT: Marks the console driver as early console driver which + * is used during boot before the real driver becomes + * available. It will be automatically unregistered + * when the real console driver is registered unless + * "keep_bootcon" parameter is used. + * @CON_ANYTIME: A misnomed historical flag which tells the core code + * that the legacy @console::write callback can be invoked + * on a CPU which is marked OFFLINE. That is misleading as + * it suggests that there is no contextual limit for + * invoking the callback. The original motivation was + * readiness of the per-CPU areas. + * @CON_BRL: Indicates a braille device which is exempt from + * receiving the printk spam for obvious reasons. + * @CON_EXTENDED: The console supports the extended output format of + * /dev/kmesg which requires a larger output buffer. + */ +enum cons_flags { + CON_PRINTBUFFER = BIT(0), + CON_CONSDEV = BIT(1), + CON_ENABLED = BIT(2), + CON_BOOT = BIT(3), + CON_ANYTIME = BIT(4), + CON_BRL = BIT(5), + CON_EXTENDED = BIT(6), +}; struct console { char name[16]; -- cgit v1.2.3 From 02b2396d7d0cf806e80c887b4c799d482d6977ed Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 9 Jan 2023 11:13:55 +0106 Subject: console: Document struct console Add kerneldoc comments to struct console. Signed-off-by: Thomas Gleixner Signed-off-by: John Ogness Reviewed-by: Petr Mladek Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20230109100800.1085541-4-john.ogness@linutronix.de --- include/linux/console.h | 54 +++++++++++++++++++++++++++++++++---------------- 1 file changed, 37 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/console.h b/include/linux/console.h index ed804dd7c2e8..1e36958aa656 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -164,24 +164,44 @@ enum cons_flags { CON_EXTENDED = BIT(6), }; +/** + * struct console - The console descriptor structure + * @name: The name of the console driver + * @write: Write callback to output messages (Optional) + * @read: Read callback for console input (Optional) + * @device: The underlying TTY device driver (Optional) + * @unblank: Callback to unblank the console (Optional) + * @setup: Callback for initializing the console (Optional) + * @exit: Callback for teardown of the console (Optional) + * @match: Callback for matching a console (Optional) + * @flags: Console flags. See enum cons_flags + * @index: Console index, e.g. port number + * @cflag: TTY control mode flags + * @ispeed: TTY input speed + * @ospeed: TTY output speed + * @seq: Sequence number of the next ringbuffer record to print + * @dropped: Number of unreported dropped ringbuffer records + * @data: Driver private data + * @node: hlist node for the console list + */ struct console { - char name[16]; - void (*write)(struct console *, const char *, unsigned); - int (*read)(struct console *, char *, unsigned); - struct tty_driver *(*device)(struct console *, int *); - void (*unblank)(void); - int (*setup)(struct console *, char *); - int (*exit)(struct console *); - int (*match)(struct console *, char *name, int idx, char *options); - short flags; - short index; - int cflag; - uint ispeed; - uint ospeed; - u64 seq; - unsigned long dropped; - void *data; - struct hlist_node node; + char name[16]; + void (*write)(struct console *co, const char *s, unsigned int count); + int (*read)(struct console *co, char *s, unsigned int count); + struct tty_driver *(*device)(struct console *co, int *index); + void (*unblank)(void); + int (*setup)(struct console *co, char *options); + int (*exit)(struct console *co); + int (*match)(struct console *co, char *name, int idx, char *options); + short flags; + short index; + int cflag; + uint ispeed; + uint ospeed; + u64 seq; + unsigned long dropped; + void *data; + struct hlist_node node; }; #ifdef CONFIG_LOCKDEP -- cgit v1.2.3 From 504fa212d7030fb1c042290dc2eb92b21515573a Mon Sep 17 00:00:00 2001 From: Javier Martinez Canillas Date: Wed, 28 Dec 2022 00:21:52 +0100 Subject: driver core: Make driver_deferred_probe_timeout a static variable It is not used outside of its compilation unit, so there's no need to export this variable. Signed-off-by: Javier Martinez Canillas Reviewed-by: Andrew Halaney Acked-by: John Stultz Link: https://lore.kernel.org/r/20221227232152.3094584-1-javierm@redhat.com Signed-off-by: Greg Kroah-Hartman --- drivers/base/dd.c | 6 ++---- include/linux/device/driver.h | 1 - 2 files changed, 2 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/dd.c b/drivers/base/dd.c index e9b2f9c25efe..69daf9d414eb 100644 --- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -257,13 +257,11 @@ static int deferred_devs_show(struct seq_file *s, void *data) DEFINE_SHOW_ATTRIBUTE(deferred_devs); #ifdef CONFIG_MODULES -int driver_deferred_probe_timeout = 10; +static int driver_deferred_probe_timeout = 10; #else -int driver_deferred_probe_timeout; +static int driver_deferred_probe_timeout; #endif -EXPORT_SYMBOL_GPL(driver_deferred_probe_timeout); - static int __init deferred_probe_timeout_setup(char *str) { int timeout; diff --git a/include/linux/device/driver.h b/include/linux/device/driver.h index 2114d65b862f..50d0a416a5e7 100644 --- a/include/linux/device/driver.h +++ b/include/linux/device/driver.h @@ -240,7 +240,6 @@ driver_find_device_by_acpi_dev(struct device_driver *drv, const void *adev) } #endif -extern int driver_deferred_probe_timeout; void driver_deferred_probe_add(struct device *dev); int driver_deferred_probe_check_state(struct device *dev); void driver_init(void); -- cgit v1.2.3 From 17cde5e601b165174e8a433b550f84f362731164 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Mon, 28 Nov 2022 17:06:42 -0400 Subject: genirq/msi: Add msi_device_has_isolated_msi() This will replace irq_domain_check_msi_remap() in following patches. The new API makes it more clear what "msi_remap" actually means from a functional perspective instead of identifying an implementation specific HW feature. Isolated MSI means that HW modeled by an irq_domain on the path from the initiating device to the CPU will validate that the MSI message specifies an interrupt number that the device is authorized to trigger. This must block devices from triggering interrupts they are not authorized to trigger. Currently authorization means the MSI vector is one assigned to the device. This is interesting for securing VFIO use cases where a rouge MSI (eg created by abusing a normal PCI MemWr DMA) must not allow the VFIO userspace to impact outside its security domain, eg userspace triggering interrupts on kernel drivers, a VM triggering interrupts on the hypervisor, or a VM triggering interrupts on another VM. As this is actually modeled as a per-irq_domain property, not a global platform property, correct the interface to accept the device parameter and scan through only the part of the irq_domains hierarchy originating from the source device. Locate the new code in msi.c as it naturally only works with CONFIG_GENERIC_MSI_IRQ, which also requires CONFIG_IRQ_DOMAIN and IRQ_DOMAIN_HIERARCHY. Link: https://lore.kernel.org/r/1-v3-3313bb5dd3a3+10f11-secure_msi_jgg@nvidia.com Tested-by: Matthew Rosato Reviewed-by: Kevin Tian Reviewed-by: Thomas Gleixner Signed-off-by: Jason Gunthorpe --- include/linux/msi.h | 13 +++++++++++++ kernel/irq/msi.c | 27 +++++++++++++++++++++++++++ 2 files changed, 40 insertions(+) (limited to 'include/linux') diff --git a/include/linux/msi.h b/include/linux/msi.h index a112b913fff9..e8a3f3a8a7f4 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -649,6 +649,19 @@ int platform_msi_device_domain_alloc(struct irq_domain *domain, unsigned int vir void platform_msi_device_domain_free(struct irq_domain *domain, unsigned int virq, unsigned int nvec); void *platform_msi_get_host_data(struct irq_domain *domain); + +bool msi_device_has_isolated_msi(struct device *dev); +#else /* CONFIG_GENERIC_MSI_IRQ */ +static inline bool msi_device_has_isolated_msi(struct device *dev) +{ + /* + * Arguably if the platform does not enable MSI support then it has + * "isolated MSI", as an interrupt controller that cannot receive MSIs + * is inherently isolated by our definition. As nobody seems to needs + * this be conservative and return false anyhow. + */ + return false; +} #endif /* CONFIG_GENERIC_MSI_IRQ */ /* PCI specific interfaces */ diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index 955267bbc2be..dfb5d40abac9 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -1623,3 +1623,30 @@ struct msi_domain_info *msi_get_domain_info(struct irq_domain *domain) { return (struct msi_domain_info *)domain->host_data; } + +/** + * msi_device_has_isolated_msi - True if the device has isolated MSI + * @dev: The device to check + * + * Isolated MSI means that HW modeled by an irq_domain on the path from the + * initiating device to the CPU will validate that the MSI message specifies an + * interrupt number that the device is authorized to trigger. This must block + * devices from triggering interrupts they are not authorized to trigger. + * Currently authorization means the MSI vector is one assigned to the device. + * + * This is interesting for securing VFIO use cases where a rouge MSI (eg created + * by abusing a normal PCI MemWr DMA) must not allow the VFIO userspace to + * impact outside its security domain, eg userspace triggering interrupts on + * kernel drivers, a VM triggering interrupts on the hypervisor, or a VM + * triggering interrupts on another VM. + */ +bool msi_device_has_isolated_msi(struct device *dev) +{ + struct irq_domain *domain = dev_get_msi_domain(dev); + + for (; domain; domain = domain->parent) + if (domain->flags & IRQ_DOMAIN_FLAG_MSI_REMAP) + return true; + return false; +} +EXPORT_SYMBOL_GPL(msi_device_has_isolated_msi); -- cgit v1.2.3 From efc30a8f15a7981737297f9e9c62fb814d74e268 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Fri, 9 Dec 2022 13:23:08 -0400 Subject: iommu: Add iommu_group_has_isolated_msi() Compute the isolated_msi over all the devices in the IOMMU group because iommufd and vfio both need to know that the entire group is isolated before granting access to it. Link: https://lore.kernel.org/r/2-v3-3313bb5dd3a3+10f11-secure_msi_jgg@nvidia.com Tested-by: Matthew Rosato Reviewed-by: Kevin Tian Reviewed-by: Lu Baolu Signed-off-by: Jason Gunthorpe --- drivers/iommu/iommu.c | 26 ++++++++++++++++++++++++++ include/linux/iommu.h | 1 + 2 files changed, 27 insertions(+) (limited to 'include/linux') diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index de91dd88705b..4c2199a493d8 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -30,6 +30,7 @@ #include #include #include +#include #include "dma-iommu.h" @@ -1897,6 +1898,31 @@ bool device_iommu_capable(struct device *dev, enum iommu_cap cap) } EXPORT_SYMBOL_GPL(device_iommu_capable); +/** + * iommu_group_has_isolated_msi() - Compute msi_device_has_isolated_msi() + * for a group + * @group: Group to query + * + * IOMMU groups should not have differing values of + * msi_device_has_isolated_msi() for devices in a group. However nothing + * directly prevents this, so ensure mistakes don't result in isolation failures + * by checking that all the devices are the same. + */ +bool iommu_group_has_isolated_msi(struct iommu_group *group) +{ + struct group_device *group_dev; + bool ret = true; + + mutex_lock(&group->mutex); + list_for_each_entry(group_dev, &group->devices, list) { + ret &= msi_device_has_isolated_msi(group_dev->dev) || + device_iommu_capable(group_dev->dev, IOMMU_CAP_INTR_REMAP); + } + mutex_unlock(&group->mutex); + return ret; +} +EXPORT_SYMBOL_GPL(iommu_group_has_isolated_msi); + /** * iommu_set_fault_handler() - set a fault handler for an iommu domain * @domain: iommu domain diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 46e1347bfa22..9b7a9fa5ad28 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -455,6 +455,7 @@ static inline const struct iommu_ops *dev_iommu_ops(struct device *dev) extern int bus_iommu_probe(struct bus_type *bus); extern bool iommu_present(struct bus_type *bus); extern bool device_iommu_capable(struct device *dev, enum iommu_cap cap); +extern bool iommu_group_has_isolated_msi(struct iommu_group *group); extern struct iommu_domain *iommu_domain_alloc(struct bus_type *bus); extern struct iommu_group *iommu_group_get_by_id(int id); extern void iommu_domain_free(struct iommu_domain *domain); -- cgit v1.2.3 From a5e72a6bac14181249ffd04f35f6a7c9bf47fbb9 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Thu, 8 Dec 2022 10:51:02 -0400 Subject: genirq/irqdomain: Remove unused irq_domain_check_msi_remap() code After converting the users of irq_domain_check_msi_remap() it and the helpers are no longer needed. The new version does not require all the #ifdef helpers and inlines because CONFIG_GENERIC_MSI_IRQ always requires CONFIG_IRQ_DOMAIN and IRQ_DOMAIN_HIERARCHY. Link: https://lore.kernel.org/r/5-v3-3313bb5dd3a3+10f11-secure_msi_jgg@nvidia.com Tested-by: Matthew Rosato Reviewed-by: Kevin Tian Reviewed-by: Thomas Gleixner Signed-off-by: Jason Gunthorpe --- include/linux/irqdomain.h | 23 ----------------------- kernel/irq/irqdomain.c | 39 --------------------------------------- 2 files changed, 62 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index a372086750ca..b04ce03d3bb6 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -276,7 +276,6 @@ struct irq_domain *irq_domain_create_legacy(struct fwnode_handle *fwnode, void *host_data); extern struct irq_domain *irq_find_matching_fwspec(struct irq_fwspec *fwspec, enum irq_domain_bus_token bus_token); -extern bool irq_domain_check_msi_remap(void); extern void irq_set_default_host(struct irq_domain *host); extern struct irq_domain *irq_get_default_host(void); extern int irq_domain_alloc_descs(int virq, unsigned int nr_irqs, @@ -559,13 +558,6 @@ static inline bool irq_domain_is_msi(struct irq_domain *domain) return domain->flags & IRQ_DOMAIN_FLAG_MSI; } -static inline bool irq_domain_is_msi_remap(struct irq_domain *domain) -{ - return domain->flags & IRQ_DOMAIN_FLAG_MSI_REMAP; -} - -extern bool irq_domain_hierarchical_is_msi_remap(struct irq_domain *domain); - static inline bool irq_domain_is_msi_parent(struct irq_domain *domain) { return domain->flags & IRQ_DOMAIN_FLAG_MSI_PARENT; @@ -611,17 +603,6 @@ static inline bool irq_domain_is_msi(struct irq_domain *domain) return false; } -static inline bool irq_domain_is_msi_remap(struct irq_domain *domain) -{ - return false; -} - -static inline bool -irq_domain_hierarchical_is_msi_remap(struct irq_domain *domain) -{ - return false; -} - static inline bool irq_domain_is_msi_parent(struct irq_domain *domain) { return false; @@ -641,10 +622,6 @@ static inline struct irq_domain *irq_find_matching_fwnode( { return NULL; } -static inline bool irq_domain_check_msi_remap(void) -{ - return false; -} #endif /* !CONFIG_IRQ_DOMAIN */ #endif /* _LINUX_IRQDOMAIN_H */ diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index 8fe1da9614ee..104954951582 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -436,31 +436,6 @@ struct irq_domain *irq_find_matching_fwspec(struct irq_fwspec *fwspec, } EXPORT_SYMBOL_GPL(irq_find_matching_fwspec); -/** - * irq_domain_check_msi_remap - Check whether all MSI irq domains implement - * IRQ remapping - * - * Return: false if any MSI irq domain does not support IRQ remapping, - * true otherwise (including if there is no MSI irq domain) - */ -bool irq_domain_check_msi_remap(void) -{ - struct irq_domain *h; - bool ret = true; - - mutex_lock(&irq_domain_mutex); - list_for_each_entry(h, &irq_domain_list, link) { - if (irq_domain_is_msi(h) && - !irq_domain_hierarchical_is_msi_remap(h)) { - ret = false; - break; - } - } - mutex_unlock(&irq_domain_mutex); - return ret; -} -EXPORT_SYMBOL_GPL(irq_domain_check_msi_remap); - /** * irq_set_default_host() - Set a "default" irq domain * @domain: default domain pointer @@ -1815,20 +1790,6 @@ static void irq_domain_check_hierarchy(struct irq_domain *domain) if (domain->ops->alloc) domain->flags |= IRQ_DOMAIN_FLAG_HIERARCHY; } - -/** - * irq_domain_hierarchical_is_msi_remap - Check if the domain or any - * parent has MSI remapping support - * @domain: domain pointer - */ -bool irq_domain_hierarchical_is_msi_remap(struct irq_domain *domain) -{ - for (; domain; domain = domain->parent) { - if (irq_domain_is_msi_remap(domain)) - return true; - } - return false; -} #else /* CONFIG_IRQ_DOMAIN_HIERARCHY */ /** * irq_domain_get_irq_data - Get irq_data associated with @virq and @domain -- cgit v1.2.3 From dcb83f6ec1bf08a44b3f19719b56e8dc18058ff5 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Mon, 28 Nov 2022 20:12:43 -0400 Subject: genirq/msi: Rename IRQ_DOMAIN_MSI_REMAP to IRQ_DOMAIN_ISOLATED_MSI What x86 calls "interrupt remapping" is one way to achieve isolated MSI, make it clear this is talking about isolated MSI, no matter how it is achieved. This matches the new driver facing API name of msi_device_has_isolated_msi() No functional change. Link: https://lore.kernel.org/r/6-v3-3313bb5dd3a3+10f11-secure_msi_jgg@nvidia.com Tested-by: Matthew Rosato Reviewed-by: Kevin Tian Reviewed-by: Thomas Gleixner Signed-off-by: Jason Gunthorpe --- drivers/irqchip/irq-gic-v3-its.c | 4 ++-- include/linux/irqdomain.h | 6 ++++-- kernel/irq/msi.c | 2 +- 3 files changed, 7 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 973ede0197e3..b4069f825a9b 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -4692,7 +4692,7 @@ static bool __maybe_unused its_enable_quirk_socionext_synquacer(void *data) } /* the pre-ITS breaks isolation, so disable MSI remapping */ - its->msi_domain_flags &= ~IRQ_DOMAIN_FLAG_MSI_REMAP; + its->msi_domain_flags &= ~IRQ_DOMAIN_FLAG_ISOLATED_MSI; return true; } return false; @@ -5074,7 +5074,7 @@ static int __init its_probe_one(struct resource *res, its->cmd_write = its->cmd_base; its->fwnode_handle = handle; its->get_msi_base = its_irq_get_msi_base; - its->msi_domain_flags = IRQ_DOMAIN_FLAG_MSI_REMAP; + its->msi_domain_flags = IRQ_DOMAIN_FLAG_ISOLATED_MSI; its_enable_quirks(its); diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index b04ce03d3bb6..0a3e974b7288 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -192,8 +192,10 @@ enum { /* Irq domain implements MSIs */ IRQ_DOMAIN_FLAG_MSI = (1 << 4), - /* Irq domain implements MSI remapping */ - IRQ_DOMAIN_FLAG_MSI_REMAP = (1 << 5), + /* + * Irq domain implements isolated MSI, see msi_device_has_isolated_msi() + */ + IRQ_DOMAIN_FLAG_ISOLATED_MSI = (1 << 5), /* Irq domain doesn't translate anything */ IRQ_DOMAIN_FLAG_NO_MAP = (1 << 6), diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index dfb5d40abac9..ac5e224a11b9 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -1645,7 +1645,7 @@ bool msi_device_has_isolated_msi(struct device *dev) struct irq_domain *domain = dev_get_msi_domain(dev); for (; domain; domain = domain->parent) - if (domain->flags & IRQ_DOMAIN_FLAG_MSI_REMAP) + if (domain->flags & IRQ_DOMAIN_FLAG_ISOLATED_MSI) return true; return false; } -- cgit v1.2.3 From bf210f793937a634bae6eda6a6d699c00b2b53d9 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Mon, 28 Nov 2022 20:31:57 -0400 Subject: irq/s390: Add arch_is_isolated_msi() for s390 s390 doesn't use irq_domains, so it has no place to set IRQ_DOMAIN_FLAG_ISOLATED_MSI. Instead of continuing to abuse the iommu subsystem to convey this information add a simple define which s390 can make statically true. The define will cause msi_device_has_isolated() to return true. Remove IOMMU_CAP_INTR_REMAP from the s390 iommu driver. Link: https://lore.kernel.org/r/8-v3-3313bb5dd3a3+10f11-secure_msi_jgg@nvidia.com Reviewed-by: Matthew Rosato Tested-by: Matthew Rosato Reviewed-by: Kevin Tian Signed-off-by: Jason Gunthorpe --- arch/s390/include/asm/msi.h | 17 +++++++++++++++++ drivers/iommu/s390-iommu.c | 2 -- include/linux/msi.h | 10 +++++++--- kernel/irq/msi.c | 2 +- 4 files changed, 25 insertions(+), 6 deletions(-) create mode 100644 arch/s390/include/asm/msi.h (limited to 'include/linux') diff --git a/arch/s390/include/asm/msi.h b/arch/s390/include/asm/msi.h new file mode 100644 index 000000000000..399343ed9ffb --- /dev/null +++ b/arch/s390/include/asm/msi.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_S390_MSI_H +#define _ASM_S390_MSI_H +#include + +/* + * Work around S390 not using irq_domain at all so we can't set + * IRQ_DOMAIN_FLAG_ISOLATED_MSI. See for an explanation how it works: + * + * https://lore.kernel.org/r/31af8174-35e9-ebeb-b9ef-74c90d4bfd93@linux.ibm.com/ + * + * Note this is less isolated than the ARM/x86 versions as userspace can trigger + * MSI belonging to kernel devices within the same gisa. + */ +#define arch_is_isolated_msi() true + +#endif diff --git a/drivers/iommu/s390-iommu.c b/drivers/iommu/s390-iommu.c index ed33c6cce083..bb00580a30d8 100644 --- a/drivers/iommu/s390-iommu.c +++ b/drivers/iommu/s390-iommu.c @@ -34,8 +34,6 @@ static bool s390_iommu_capable(struct device *dev, enum iommu_cap cap) switch (cap) { case IOMMU_CAP_CACHE_COHERENCY: return true; - case IOMMU_CAP_INTR_REMAP: - return true; default: return false; } diff --git a/include/linux/msi.h b/include/linux/msi.h index e8a3f3a8a7f4..13c9b74a4575 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -48,6 +48,10 @@ typedef struct arch_msi_msg_data { } __attribute__ ((packed)) arch_msi_msg_data_t; #endif +#ifndef arch_is_isolated_msi +#define arch_is_isolated_msi() false +#endif + /** * msi_msg - Representation of a MSI message * @address_lo: Low 32 bits of msi message address @@ -657,10 +661,10 @@ static inline bool msi_device_has_isolated_msi(struct device *dev) /* * Arguably if the platform does not enable MSI support then it has * "isolated MSI", as an interrupt controller that cannot receive MSIs - * is inherently isolated by our definition. As nobody seems to needs - * this be conservative and return false anyhow. + * is inherently isolated by our definition. The default definition for + * arch_is_isolated_msi() is conservative and returns false anyhow. */ - return false; + return arch_is_isolated_msi(); } #endif /* CONFIG_GENERIC_MSI_IRQ */ diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index ac5e224a11b9..4dec57fc4ea6 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -1647,6 +1647,6 @@ bool msi_device_has_isolated_msi(struct device *dev) for (; domain; domain = domain->parent) if (domain->flags & IRQ_DOMAIN_FLAG_ISOLATED_MSI) return true; - return false; + return arch_is_isolated_msi(); } EXPORT_SYMBOL_GPL(msi_device_has_isolated_msi); -- cgit v1.2.3 From b062007c63eb4452f1122384e86d402531fb1d52 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Mon, 28 Nov 2022 20:34:32 -0400 Subject: iommu: Remove IOMMU_CAP_INTR_REMAP No iommu driver implements this any more, get rid of it. Link: https://lore.kernel.org/r/9-v3-3313bb5dd3a3+10f11-secure_msi_jgg@nvidia.com Tested-by: Matthew Rosato Reviewed-by: Kevin Tian Reviewed-by: Lu Baolu Signed-off-by: Jason Gunthorpe --- drivers/iommu/iommu.c | 6 ++---- include/linux/iommu.h | 1 - 2 files changed, 2 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 4c2199a493d8..834e6ecf3e51 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -1914,10 +1914,8 @@ bool iommu_group_has_isolated_msi(struct iommu_group *group) bool ret = true; mutex_lock(&group->mutex); - list_for_each_entry(group_dev, &group->devices, list) { - ret &= msi_device_has_isolated_msi(group_dev->dev) || - device_iommu_capable(group_dev->dev, IOMMU_CAP_INTR_REMAP); - } + list_for_each_entry(group_dev, &group->devices, list) + ret &= msi_device_has_isolated_msi(group_dev->dev); mutex_unlock(&group->mutex); return ret; } diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 9b7a9fa5ad28..933cc57bfc48 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -120,7 +120,6 @@ static inline bool iommu_is_dma_domain(struct iommu_domain *domain) enum iommu_cap { IOMMU_CAP_CACHE_COHERENCY, /* IOMMU_CACHE is supported */ - IOMMU_CAP_INTR_REMAP, /* IOMMU supports interrupt isolation */ IOMMU_CAP_NOEXEC, /* IOMMU_NOEXEC flag */ IOMMU_CAP_PRE_BOOT_PROTECTION, /* Firmware says it used the IOMMU for DMA protection and we should too */ -- cgit v1.2.3 From 5b6373de4351debd9fa87f1c46442b2c28d8b18e Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Mon, 19 Dec 2022 17:05:16 +0100 Subject: drm/fbdev: Remove aperture handling and FBINFO_MISC_FIRMWARE There are no users left of struct fb_info.apertures and the flag FBINFO_MISC_FIRMWARE. Remove both and the aperture-ownership code in the fbdev core. All code for aperture ownership is now located in the fbdev drivers. Signed-off-by: Thomas Zimmermann Reviewed-by: Javier Martinez Canillas Link: https://patchwork.freedesktop.org/patch/msgid/20221219160516.23436-19-tzimmermann@suse.de --- drivers/video/fbdev/core/fbmem.c | 33 --------------------------------- drivers/video/fbdev/core/fbsysfs.c | 1 - include/linux/fb.h | 22 ---------------------- 3 files changed, 56 deletions(-) (limited to 'include/linux') diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c index 3a6c8458eb8d..02217c33d152 100644 --- a/drivers/video/fbdev/core/fbmem.c +++ b/drivers/video/fbdev/core/fbmem.c @@ -13,7 +13,6 @@ #include -#include #include #include #include @@ -1653,32 +1652,6 @@ static void do_unregister_framebuffer(struct fb_info *fb_info) put_fb_info(fb_info); } -static int fb_aperture_acquire_for_platform_device(struct fb_info *fb_info) -{ - struct apertures_struct *ap = fb_info->apertures; - struct device *dev = fb_info->device; - struct platform_device *pdev; - unsigned int i; - int ret; - - if (!ap) - return 0; - - if (!dev_is_platform(dev)) - return 0; - - pdev = to_platform_device(dev); - - for (ret = 0, i = 0; i < ap->count; ++i) { - ret = devm_aperture_acquire_for_platform_device(pdev, ap->ranges[i].base, - ap->ranges[i].size); - if (ret) - break; - } - - return ret; -} - /** * register_framebuffer - registers a frame buffer device * @fb_info: frame buffer info structure @@ -1693,12 +1666,6 @@ register_framebuffer(struct fb_info *fb_info) { int ret; - if (fb_info->flags & FBINFO_MISC_FIRMWARE) { - ret = fb_aperture_acquire_for_platform_device(fb_info); - if (ret) - return ret; - } - mutex_lock(®istration_lock); ret = do_register_framebuffer(fb_info); mutex_unlock(®istration_lock); diff --git a/drivers/video/fbdev/core/fbsysfs.c b/drivers/video/fbdev/core/fbsysfs.c index 4d7f63892dcc..0c33c4adcd79 100644 --- a/drivers/video/fbdev/core/fbsysfs.c +++ b/drivers/video/fbdev/core/fbsysfs.c @@ -88,7 +88,6 @@ void framebuffer_release(struct fb_info *info) mutex_destroy(&info->bl_curve_mutex); #endif - kfree(info->apertures); kfree(info); } EXPORT_SYMBOL(framebuffer_release); diff --git a/include/linux/fb.h b/include/linux/fb.h index 96b96323e9cb..30183fd259ae 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -423,8 +423,6 @@ struct fb_tile_ops { */ #define FBINFO_MISC_ALWAYS_SETPAR 0x40000 -/* where the fb is a firmware driver, and can be replaced with a proper one */ -#define FBINFO_MISC_FIRMWARE 0x80000 /* * Host and GPU endianness differ. */ @@ -499,30 +497,10 @@ struct fb_info { void *fbcon_par; /* fbcon use-only private area */ /* From here on everything is device dependent */ void *par; - /* we need the PCI or similar aperture base/size not - smem_start/size as smem_start may just be an object - allocated inside the aperture so may not actually overlap */ - struct apertures_struct { - unsigned int count; - struct aperture { - resource_size_t base; - resource_size_t size; - } ranges[0]; - } *apertures; bool skip_vt_switch; /* no VT switch on suspend/resume required */ }; -static inline struct apertures_struct *alloc_apertures(unsigned int max_num) { - struct apertures_struct *a; - - a = kzalloc(struct_size(a, ranges, max_num), GFP_KERNEL); - if (!a) - return NULL; - a->count = max_num; - return a; -} - #define FBINFO_FLAG_DEFAULT FBINFO_DEFAULT /* This will go away -- cgit v1.2.3 From 6caeb33fa986151f745fc62190bc28a593b8a0d2 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Tue, 10 Jan 2023 10:54:05 +0800 Subject: iommu: Add set_platform_dma_ops iommu ops When VFIO finishes assigning a device to user space and calls iommu_group_release_dma_owner() to return the device to kernel, the IOMMU core will attach the default domain to the device. Unfortunately, some IOMMU drivers don't support default domain, hence in the end, the core calls .detach_dev instead. This adds set_platform_dma_ops iommu ops to make it clear that what it does is returning control back to the platform DMA ops. Suggested-by: Jason Gunthorpe Reviewed-by: Jason Gunthorpe Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20230110025408.667767-3-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/iommu.c | 28 ++++++++++++++++++++++++---- include/linux/iommu.h | 4 ++++ 2 files changed, 28 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index de91dd88705b..1c8b2c7678f7 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -2163,6 +2163,16 @@ static int iommu_group_do_detach_device(struct device *dev, void *data) return 0; } +static int iommu_group_do_set_platform_dma(struct device *dev, void *data) +{ + const struct iommu_ops *ops = dev_iommu_ops(dev); + + if (!WARN_ON(!ops->set_platform_dma_ops)) + ops->set_platform_dma_ops(dev); + + return 0; +} + static int __iommu_group_set_domain(struct iommu_group *group, struct iommu_domain *new_domain) { @@ -2177,10 +2187,20 @@ static int __iommu_group_set_domain(struct iommu_group *group, * platform specific behavior. */ if (!new_domain) { - if (WARN_ON(!group->domain->ops->detach_dev)) - return -EINVAL; - __iommu_group_for_each_dev(group, group->domain, - iommu_group_do_detach_device); + struct group_device *grp_dev; + + grp_dev = list_first_entry(&group->devices, + struct group_device, list); + + if (dev_iommu_ops(grp_dev->dev)->set_platform_dma_ops) + __iommu_group_for_each_dev(group, NULL, + iommu_group_do_set_platform_dma); + else if (group->domain->ops->detach_dev) + __iommu_group_for_each_dev(group, group->domain, + iommu_group_do_detach_device); + else + WARN_ON_ONCE(1); + group->domain = NULL; return 0; } diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 46e1347bfa22..7b3e3775b069 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -228,6 +228,9 @@ struct iommu_iotlb_gather { * @release_device: Remove device from iommu driver handling * @probe_finalize: Do final setup work after the device is added to an IOMMU * group and attached to the groups domain + * @set_platform_dma_ops: Returning control back to the platform DMA ops. This op + * is to support old IOMMU drivers, new drivers should use + * default domains, and the common IOMMU DMA ops. * @device_group: find iommu group for a particular device * @get_resv_regions: Request list of reserved regions for a device * @of_xlate: add OF master IDs to iommu grouping @@ -256,6 +259,7 @@ struct iommu_ops { struct iommu_device *(*probe_device)(struct device *dev); void (*release_device)(struct device *dev); void (*probe_finalize)(struct device *dev); + void (*set_platform_dma_ops)(struct device *dev); struct iommu_group *(*device_group)(struct device *dev); /* Request/Free a list of reserved regions for a device */ -- cgit v1.2.3 From dd8a25c557e109f868430bd2e3e8f394cb40eaa7 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Tue, 10 Jan 2023 10:54:07 +0800 Subject: iommu: Remove deferred attach check from __iommu_detach_device() At the current moment, __iommu_detach_device() is only called via call chains that are after the device driver is attached - eg via explicit attach APIs called by the device driver. Commit bd421264ed30 ("iommu: Fix deferred domain attachment") has removed deferred domain attachment check from __iommu_attach_device() path, so it should just unconditionally work in the __iommu_detach_device() path. It actually looks like a bug that we were blocking detach on these paths since the attach was unconditional and the caller is going to free the (probably) UNAMANGED domain once this returns. The only place we should be testing for deferred attach is during the initial point the dma device is linked to the group, and then again during the dma api calls. Signed-off-by: Jason Gunthorpe Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20230110025408.667767-5-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/iommu.c | 70 ++++++++++++++++++++++++++------------------------- include/linux/iommu.h | 2 ++ 2 files changed, 38 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 1c8b2c7678f7..85ae20c8ff5e 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -371,6 +371,30 @@ err_unlock: return ret; } +static bool iommu_is_attach_deferred(struct device *dev) +{ + const struct iommu_ops *ops = dev_iommu_ops(dev); + + if (ops->is_attach_deferred) + return ops->is_attach_deferred(dev); + + return false; +} + +static int iommu_group_do_dma_first_attach(struct device *dev, void *data) +{ + struct iommu_domain *domain = data; + + lockdep_assert_held(&dev->iommu_group->mutex); + + if (iommu_is_attach_deferred(dev)) { + dev->iommu->attach_deferred = 1; + return 0; + } + + return __iommu_attach_device(domain, dev); +} + int iommu_probe_device(struct device *dev) { const struct iommu_ops *ops; @@ -401,7 +425,7 @@ int iommu_probe_device(struct device *dev) * attach the default domain. */ if (group->default_domain && !group->owner) { - ret = __iommu_attach_device(group->default_domain, dev); + ret = iommu_group_do_dma_first_attach(dev, group->default_domain); if (ret) { mutex_unlock(&group->mutex); iommu_group_put(group); @@ -947,16 +971,6 @@ out: return ret; } -static bool iommu_is_attach_deferred(struct device *dev) -{ - const struct iommu_ops *ops = dev_iommu_ops(dev); - - if (ops->is_attach_deferred) - return ops->is_attach_deferred(dev); - - return false; -} - /** * iommu_group_add_device - add a device to an iommu group * @group: the group into which to add the device (reference should be held) @@ -1009,8 +1023,8 @@ rename: mutex_lock(&group->mutex); list_add_tail(&device->list, &group->devices); - if (group->domain && !iommu_is_attach_deferred(dev)) - ret = __iommu_attach_device(group->domain, dev); + if (group->domain) + ret = iommu_group_do_dma_first_attach(dev, group->domain); mutex_unlock(&group->mutex); if (ret) goto err_put_group; @@ -1776,21 +1790,10 @@ static void probe_alloc_default_domain(struct bus_type *bus, } -static int iommu_group_do_dma_attach(struct device *dev, void *data) -{ - struct iommu_domain *domain = data; - int ret = 0; - - if (!iommu_is_attach_deferred(dev)) - ret = __iommu_attach_device(domain, dev); - - return ret; -} - -static int __iommu_group_dma_attach(struct iommu_group *group) +static int __iommu_group_dma_first_attach(struct iommu_group *group) { return __iommu_group_for_each_dev(group, group->default_domain, - iommu_group_do_dma_attach); + iommu_group_do_dma_first_attach); } static int iommu_group_do_probe_finalize(struct device *dev, void *data) @@ -1855,7 +1858,7 @@ int bus_iommu_probe(struct bus_type *bus) iommu_group_create_direct_mappings(group); - ret = __iommu_group_dma_attach(group); + ret = __iommu_group_dma_first_attach(group); mutex_unlock(&group->mutex); @@ -1987,9 +1990,11 @@ static int __iommu_attach_device(struct iommu_domain *domain, return -ENODEV; ret = domain->ops->attach_dev(domain, dev); - if (!ret) - trace_attach_device_to_domain(dev); - return ret; + if (ret) + return ret; + dev->iommu->attach_deferred = 0; + trace_attach_device_to_domain(dev); + return 0; } /** @@ -2034,7 +2039,7 @@ EXPORT_SYMBOL_GPL(iommu_attach_device); int iommu_deferred_attach(struct device *dev, struct iommu_domain *domain) { - if (iommu_is_attach_deferred(dev)) + if (dev->iommu && dev->iommu->attach_deferred) return __iommu_attach_device(domain, dev); return 0; @@ -2043,9 +2048,6 @@ int iommu_deferred_attach(struct device *dev, struct iommu_domain *domain) static void __iommu_detach_device(struct iommu_domain *domain, struct device *dev) { - if (iommu_is_attach_deferred(dev)) - return; - domain->ops->detach_dev(domain, dev); trace_detach_device_from_domain(dev); } diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 7b3e3775b069..0d10566b3cb2 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -405,6 +405,7 @@ struct iommu_fault_param { * @iommu_dev: IOMMU device this device is linked to * @priv: IOMMU Driver private data * @max_pasids: number of PASIDs this device can consume + * @attach_deferred: the dma domain attachment is deferred * * TODO: migrate other per device data pointers under iommu_dev_data, e.g. * struct iommu_group *iommu_group; @@ -417,6 +418,7 @@ struct dev_iommu { struct iommu_device *iommu_dev; void *priv; u32 max_pasids; + u32 attach_deferred:1; }; int iommu_device_register(struct iommu_device *iommu, -- cgit v1.2.3 From 8f9930fa016134ea07db4775ec596b16c3d03f05 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Tue, 10 Jan 2023 10:54:08 +0800 Subject: iommu: Remove detach_dev callback The detach_dev callback of domain ops is not called in the IOMMU core. Remove this callback to avoid dead code. The trace event for detaching domain from device is removed accordingly. Reviewed-by: Jason Gunthorpe Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20230110025408.667767-6-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/iommu-traces.c | 1 - drivers/iommu/iommu.c | 36 ++++-------------------------------- include/linux/iommu.h | 2 -- include/trace/events/iommu.h | 7 ------- 4 files changed, 4 insertions(+), 42 deletions(-) (limited to 'include/linux') diff --git a/drivers/iommu/iommu-traces.c b/drivers/iommu/iommu-traces.c index 1e9ca7789de1..23416bf76df9 100644 --- a/drivers/iommu/iommu-traces.c +++ b/drivers/iommu/iommu-traces.c @@ -18,7 +18,6 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(remove_device_from_group); /* iommu_device_event */ EXPORT_TRACEPOINT_SYMBOL_GPL(attach_device_to_domain); -EXPORT_TRACEPOINT_SYMBOL_GPL(detach_device_from_domain); /* iommu_map_unmap */ EXPORT_TRACEPOINT_SYMBOL_GPL(map); diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 85ae20c8ff5e..9135540d7d59 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -2045,13 +2045,6 @@ int iommu_deferred_attach(struct device *dev, struct iommu_domain *domain) return 0; } -static void __iommu_detach_device(struct iommu_domain *domain, - struct device *dev) -{ - domain->ops->detach_dev(domain, dev); - trace_detach_device_from_domain(dev); -} - void iommu_detach_device(struct iommu_domain *domain, struct device *dev) { struct iommu_group *group; @@ -2156,15 +2149,6 @@ int iommu_attach_group(struct iommu_domain *domain, struct iommu_group *group) } EXPORT_SYMBOL_GPL(iommu_attach_group); -static int iommu_group_do_detach_device(struct device *dev, void *data) -{ - struct iommu_domain *domain = data; - - __iommu_detach_device(domain, dev); - - return 0; -} - static int iommu_group_do_set_platform_dma(struct device *dev, void *data) { const struct iommu_ops *ops = dev_iommu_ops(dev); @@ -2184,25 +2168,13 @@ static int __iommu_group_set_domain(struct iommu_group *group, return 0; /* - * New drivers should support default domains and so the detach_dev() op - * will never be called. Otherwise the NULL domain represents some + * New drivers should support default domains, so set_platform_dma() + * op will never be called. Otherwise the NULL domain represents some * platform specific behavior. */ if (!new_domain) { - struct group_device *grp_dev; - - grp_dev = list_first_entry(&group->devices, - struct group_device, list); - - if (dev_iommu_ops(grp_dev->dev)->set_platform_dma_ops) - __iommu_group_for_each_dev(group, NULL, - iommu_group_do_set_platform_dma); - else if (group->domain->ops->detach_dev) - __iommu_group_for_each_dev(group, group->domain, - iommu_group_do_detach_device); - else - WARN_ON_ONCE(1); - + __iommu_group_for_each_dev(group, NULL, + iommu_group_do_set_platform_dma); group->domain = NULL; return 0; } diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 0d10566b3cb2..a8063f26ff69 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -299,7 +299,6 @@ struct iommu_ops { * * EBUSY - device is attached to a domain and cannot be changed * * ENODEV - device specific errors, not able to be attached * * - treated as ENODEV by the caller. Use is discouraged - * @detach_dev: detach an iommu domain from a device * @set_dev_pasid: set an iommu domain to a pasid of device * @map: map a physically contiguous memory region to an iommu domain * @map_pages: map a physically contiguous set of pages of the same size to @@ -320,7 +319,6 @@ struct iommu_ops { */ struct iommu_domain_ops { int (*attach_dev)(struct iommu_domain *domain, struct device *dev); - void (*detach_dev)(struct iommu_domain *domain, struct device *dev); int (*set_dev_pasid)(struct iommu_domain *domain, struct device *dev, ioasid_t pasid); diff --git a/include/trace/events/iommu.h b/include/trace/events/iommu.h index 29096fe12623..70743db1fb75 100644 --- a/include/trace/events/iommu.h +++ b/include/trace/events/iommu.h @@ -76,13 +76,6 @@ DEFINE_EVENT(iommu_device_event, attach_device_to_domain, TP_ARGS(dev) ); -DEFINE_EVENT(iommu_device_event, detach_device_from_domain, - - TP_PROTO(struct device *dev), - - TP_ARGS(dev) -); - TRACE_EVENT(map, TP_PROTO(unsigned long iova, phys_addr_t paddr, size_t size), -- cgit v1.2.3 From 9f820fc0651c32f8dde26b8e3ad93e1b9fdb62c4 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 12 Jan 2023 10:36:35 +0100 Subject: mtd: rawnand: Check the data only read pattern only once Instead of checking if a pattern is supported each time we need it, let's create a bitfield that only the core would be allowed to fill at startup time. The core and the individual drivers may then use it in order to check what operation they should use. This bitfield is supposed to grow over time. Signed-off-by: Miquel Raynal Tested-by: Liao Jaime Link: https://lore.kernel.org/linux-mtd/20230112093637.987838-2-miquel.raynal@bootlin.com --- drivers/mtd/nand/raw/nand_base.c | 20 ++++++++++++++++++++ drivers/mtd/nand/raw/nand_jedec.c | 3 +-- drivers/mtd/nand/raw/nand_onfi.c | 3 +-- include/linux/mtd/rawnand.h | 8 ++++++++ 4 files changed, 30 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c index c3cc66039925..7b87e2e70484 100644 --- a/drivers/mtd/nand/raw/nand_base.c +++ b/drivers/mtd/nand/raw/nand_base.c @@ -4991,6 +4991,24 @@ nand_manufacturer_name(const struct nand_manufacturer_desc *manufacturer_desc) return manufacturer_desc ? manufacturer_desc->name : "Unknown"; } +static void rawnand_check_data_only_read_support(struct nand_chip *chip) +{ + /* Use an arbitrary size for the check */ + if (!nand_read_data_op(chip, NULL, SZ_512, true, true)) + chip->controller->supported_op.data_only_read = 1; +} + +static void rawnand_early_check_supported_ops(struct nand_chip *chip) +{ + /* The supported_op fields should not be set by individual drivers */ + WARN_ON_ONCE(chip->controller->supported_op.data_only_read); + + if (!nand_has_exec_op(chip)) + return; + + rawnand_check_data_only_read_support(chip); +} + /* * Get the flash and manufacturer id and lookup if the type is supported. */ @@ -5023,6 +5041,8 @@ static int nand_detect(struct nand_chip *chip, struct nand_flash_dev *type) /* Select the device */ nand_select_target(chip, 0); + rawnand_early_check_supported_ops(chip); + /* Send the command for reading device ID */ ret = nand_readid_op(chip, 0, id_data, 2); if (ret) diff --git a/drivers/mtd/nand/raw/nand_jedec.c b/drivers/mtd/nand/raw/nand_jedec.c index 85b6d9372d80..836757717660 100644 --- a/drivers/mtd/nand/raw/nand_jedec.c +++ b/drivers/mtd/nand/raw/nand_jedec.c @@ -46,8 +46,7 @@ int nand_jedec_detect(struct nand_chip *chip) if (!p) return -ENOMEM; - if (!nand_has_exec_op(chip) || - !nand_read_data_op(chip, p, sizeof(*p), true, true)) + if (!nand_has_exec_op(chip) || chip->controller->supported_op.data_only_read) use_datain = true; for (i = 0; i < JEDEC_PARAM_PAGES; i++) { diff --git a/drivers/mtd/nand/raw/nand_onfi.c b/drivers/mtd/nand/raw/nand_onfi.c index 7586befce7f9..f15ef90aec8c 100644 --- a/drivers/mtd/nand/raw/nand_onfi.c +++ b/drivers/mtd/nand/raw/nand_onfi.c @@ -166,8 +166,7 @@ int nand_onfi_detect(struct nand_chip *chip) if (!pbuf) return -ENOMEM; - if (!nand_has_exec_op(chip) || - !nand_read_data_op(chip, &pbuf[0], sizeof(*pbuf), true, true)) + if (!nand_has_exec_op(chip) || chip->controller->supported_op.data_only_read) use_datain = true; for (i = 0; i < ONFI_PARAM_PAGES; i++) { diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index dcf90144d70b..28c5dce782dd 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1094,10 +1094,18 @@ struct nand_controller_ops { * * @lock: lock used to serialize accesses to the NAND controller * @ops: NAND controller operations. + * @supported_op: NAND controller known-to-be-supported operations, + * only writable by the core after initial checking. + * @supported_op.data_only_read: The controller supports reading more data from + * the bus without restarting an entire read operation nor + * changing the column. */ struct nand_controller { struct mutex lock; const struct nand_controller_ops *ops; + struct { + unsigned int data_only_read: 1; + } supported_op; }; static inline void nand_controller_init(struct nand_controller *nfc) -- cgit v1.2.3 From 003fe4b9545b83cca4f7a7633695d1f69a0b0011 Mon Sep 17 00:00:00 2001 From: JaimeLiao Date: Thu, 12 Jan 2023 10:36:37 +0100 Subject: mtd: rawnand: Support for sequential cache reads Add support for sequential cache reads for controllers using the generic core helpers for their fast read/write helpers. Sequential reads may reduce the overhead when accessing physically continuous data by loading in cache the next page while the previous page gets sent out on the NAND bus. The ONFI specification provides the following additional commands to handle sequential cached reads: * 0x31 - READ CACHE SEQUENTIAL: Requires the NAND chip to load the next page into cache while keeping the current cache available for host reads. * 0x3F - READ CACHE END: Tells the NAND chip this is the end of the sequential cache read, the current cache shall remain accessible for the host but no more internal cache loading operation is required. On the bus, a multi page read operation is currently handled like this: 00 -- ADDR1 -- 30 -- WAIT_RDY (tR+tRR) -- DATA1_IN 00 -- ADDR2 -- 30 -- WAIT_RDY (tR+tRR) -- DATA2_IN 00 -- ADDR3 -- 30 -- WAIT_RDY (tR+tRR) -- DATA3_IN Sequential cached reads may instead be achieved with: 00 -- ADDR1 -- 30 -- WAIT_RDY (tR) -- \ 31 -- WAIT_RDY (tRCBSY+tRR) -- DATA1_IN \ 31 -- WAIT_RDY (tRCBSY+tRR) -- DATA2_IN \ 3F -- WAIT_RDY (tRCBSY+tRR) -- DATA3_IN Below are the read speed test results with regular reads and sequential cached reads, on NXP i.MX6 VAR-SOM-SOLO in mapping mode with a NAND chip characterized with the following timings: * tR: 20 µs * tRCBSY: 5 µs * tRR: 20 ns and the following geometry: * device size: 2 MiB * eraseblock size: 128 kiB * page size: 2 kiB ============= Normal read @ 33MHz ================= mtd_speedtest: eraseblock read speed is 15633 KiB/s mtd_speedtest: page read speed is 15515 KiB/s mtd_speedtest: 2 page read speed is 15398 KiB/s =================================================== ========= Sequential cache read @ 33MHz =========== mtd_speedtest: eraseblock read speed is 18285 KiB/s mtd_speedtest: page read speed is 15875 KiB/s mtd_speedtest: 2 page read speed is 16253 KiB/s =================================================== We observe an overall speed improvement of about 5% when reading 2 pages, up to 15% when reading an entire block. This is due to the ~14us gain on each additional page read (tR - (tRCBSY + tRR)). Co-developed-by: Miquel Raynal Signed-off-by: Miquel Raynal Signed-off-by: JaimeLiao Tested-by: Liao Jaime Link: https://lore.kernel.org/linux-mtd/20230112093637.987838-4-miquel.raynal@bootlin.com --- drivers/mtd/nand/raw/nand_base.c | 119 +++++++++++++++++++++++++++++++++++++-- include/linux/mtd/rawnand.h | 9 +++ 2 files changed, 124 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c index e1f74e2fa415..a6af521832aa 100644 --- a/drivers/mtd/nand/raw/nand_base.c +++ b/drivers/mtd/nand/raw/nand_base.c @@ -1208,6 +1208,73 @@ static int nand_lp_exec_read_page_op(struct nand_chip *chip, unsigned int page, return nand_exec_op(chip, &op); } +static int nand_lp_exec_cont_read_page_op(struct nand_chip *chip, unsigned int page, + unsigned int offset_in_page, void *buf, + unsigned int len, bool check_only) +{ + const struct nand_interface_config *conf = + nand_get_interface_config(chip); + u8 addrs[5]; + struct nand_op_instr start_instrs[] = { + NAND_OP_CMD(NAND_CMD_READ0, 0), + NAND_OP_ADDR(4, addrs, 0), + NAND_OP_CMD(NAND_CMD_READSTART, NAND_COMMON_TIMING_NS(conf, tWB_max)), + NAND_OP_WAIT_RDY(NAND_COMMON_TIMING_MS(conf, tR_max), 0), + NAND_OP_CMD(NAND_CMD_READCACHESEQ, NAND_COMMON_TIMING_NS(conf, tWB_max)), + NAND_OP_WAIT_RDY(NAND_COMMON_TIMING_MS(conf, tR_max), + NAND_COMMON_TIMING_NS(conf, tRR_min)), + NAND_OP_DATA_IN(len, buf, 0), + }; + struct nand_op_instr cont_instrs[] = { + NAND_OP_CMD(page == chip->cont_read.last_page ? + NAND_CMD_READCACHEEND : NAND_CMD_READCACHESEQ, + NAND_COMMON_TIMING_NS(conf, tWB_max)), + NAND_OP_WAIT_RDY(NAND_COMMON_TIMING_MS(conf, tR_max), + NAND_COMMON_TIMING_NS(conf, tRR_min)), + NAND_OP_DATA_IN(len, buf, 0), + }; + struct nand_operation start_op = NAND_OPERATION(chip->cur_cs, start_instrs); + struct nand_operation cont_op = NAND_OPERATION(chip->cur_cs, cont_instrs); + int ret; + + if (!len) { + start_op.ninstrs--; + cont_op.ninstrs--; + } + + ret = nand_fill_column_cycles(chip, addrs, offset_in_page); + if (ret < 0) + return ret; + + addrs[2] = page; + addrs[3] = page >> 8; + + if (chip->options & NAND_ROW_ADDR_3) { + addrs[4] = page >> 16; + start_instrs[1].ctx.addr.naddrs++; + } + + /* Check if cache reads are supported */ + if (check_only) { + if (nand_check_op(chip, &start_op) || nand_check_op(chip, &cont_op)) + return -EOPNOTSUPP; + + return 0; + } + + if (page == chip->cont_read.first_page) + return nand_exec_op(chip, &start_op); + else + return nand_exec_op(chip, &cont_op); +} + +static bool rawnand_cont_read_ongoing(struct nand_chip *chip, unsigned int page) +{ + return chip->cont_read.ongoing && + page >= chip->cont_read.first_page && + page <= chip->cont_read.last_page; +} + /** * nand_read_page_op - Do a READ PAGE operation * @chip: The NAND chip @@ -1233,10 +1300,16 @@ int nand_read_page_op(struct nand_chip *chip, unsigned int page, return -EINVAL; if (nand_has_exec_op(chip)) { - if (mtd->writesize > 512) - return nand_lp_exec_read_page_op(chip, page, - offset_in_page, buf, - len); + if (mtd->writesize > 512) { + if (rawnand_cont_read_ongoing(chip, page)) + return nand_lp_exec_cont_read_page_op(chip, page, + offset_in_page, + buf, len, false); + else + return nand_lp_exec_read_page_op(chip, page, + offset_in_page, buf, + len); + } return nand_sp_exec_read_page_op(chip, page, offset_in_page, buf, len); @@ -3353,6 +3426,27 @@ static uint8_t *nand_transfer_oob(struct nand_chip *chip, uint8_t *oob, return NULL; } +static void rawnand_enable_cont_reads(struct nand_chip *chip, unsigned int page, + u32 readlen, int col) +{ + struct mtd_info *mtd = nand_to_mtd(chip); + + if (!chip->controller->supported_op.cont_read) + return; + + if ((col && col + readlen < (3 * mtd->writesize)) || + (!col && readlen < (2 * mtd->writesize))) { + chip->cont_read.ongoing = false; + return; + } + + chip->cont_read.ongoing = true; + chip->cont_read.first_page = page; + if (col) + chip->cont_read.first_page++; + chip->cont_read.last_page = page + ((readlen >> chip->page_shift) & chip->pagemask); +} + /** * nand_setup_read_retry - [INTERN] Set the READ RETRY mode * @chip: NAND chip object @@ -3426,6 +3520,8 @@ static int nand_do_read_ops(struct nand_chip *chip, loff_t from, oob = ops->oobbuf; oob_required = oob ? 1 : 0; + rawnand_enable_cont_reads(chip, page, readlen, col); + while (1) { struct mtd_ecc_stats ecc_stats = mtd->ecc_stats; @@ -5009,12 +5105,27 @@ static void rawnand_early_check_supported_ops(struct nand_chip *chip) rawnand_check_data_only_read_support(chip); } +static void rawnand_check_cont_read_support(struct nand_chip *chip) +{ + struct mtd_info *mtd = nand_to_mtd(chip); + + if (chip->read_retries) + return; + + if (!nand_lp_exec_cont_read_page_op(chip, 0, 0, NULL, + mtd->writesize, true)) + chip->controller->supported_op.cont_read = 1; +} + static void rawnand_late_check_supported_ops(struct nand_chip *chip) { /* The supported_op fields should not be set by individual drivers */ + WARN_ON_ONCE(chip->controller->supported_op.cont_read); if (!nand_has_exec_op(chip)) return; + + rawnand_check_cont_read_support(chip); } /* diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 28c5dce782dd..1b0936fe3c6e 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -67,6 +67,8 @@ struct gpio_desc; /* Extended commands for large page devices */ #define NAND_CMD_READSTART 0x30 +#define NAND_CMD_READCACHESEQ 0x31 +#define NAND_CMD_READCACHEEND 0x3f #define NAND_CMD_RNDOUTSTART 0xE0 #define NAND_CMD_CACHEDPROG 0x15 @@ -1099,12 +1101,14 @@ struct nand_controller_ops { * @supported_op.data_only_read: The controller supports reading more data from * the bus without restarting an entire read operation nor * changing the column. + * @supported_op.cont_read: The controller supports sequential cache reads. */ struct nand_controller { struct mutex lock; const struct nand_controller_ops *ops; struct { unsigned int data_only_read: 1; + unsigned int cont_read: 1; } supported_op; }; @@ -1308,6 +1312,11 @@ struct nand_chip { int read_retries; struct nand_secure_region *secure_regions; u8 nr_secure_regions; + struct { + bool ongoing; + unsigned int first_page; + unsigned int last_page; + } cont_read; /* Externals */ struct nand_controller *controller; -- cgit v1.2.3 From fa5bde139ee43ab91087c01e690c61aec957c339 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Thu, 27 Oct 2022 13:07:55 +0900 Subject: ata: libata: Introduce ata_ncq_supported() Introduce the inline helper function ata_ncq_supported() to test if a device supports NCQ commands. The function ata_ncq_enabled() is also rewritten using this new helper function. Signed-off-by: Damien Le Moal Reviewed-by: Hannes Reinecke Reviewed-by: Chaitanya Kulkarni Reviewed-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Reviewed-by: Niklas Cassel --- include/linux/libata.h | 28 +++++++++++++++++++++------- 1 file changed, 21 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 3b7f5d9e2f87..059ca7f2b69c 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1691,21 +1691,35 @@ extern struct ata_device *ata_dev_next(struct ata_device *dev, (dev) = ata_dev_next((dev), (link), ATA_DITER_##mode)) /** - * ata_ncq_enabled - Test whether NCQ is enabled - * @dev: ATA device to test for + * ata_ncq_supported - Test whether NCQ is supported + * @dev: ATA device to test * * LOCKING: * spin_lock_irqsave(host lock) * * RETURNS: - * 1 if NCQ is enabled for @dev, 0 otherwise. + * true if @dev supports NCQ, false otherwise. */ -static inline int ata_ncq_enabled(struct ata_device *dev) +static inline bool ata_ncq_supported(struct ata_device *dev) { if (!IS_ENABLED(CONFIG_SATA_HOST)) - return 0; - return (dev->flags & (ATA_DFLAG_PIO | ATA_DFLAG_NCQ_OFF | - ATA_DFLAG_NCQ)) == ATA_DFLAG_NCQ; + return false; + return (dev->flags & (ATA_DFLAG_PIO | ATA_DFLAG_NCQ)) == ATA_DFLAG_NCQ; +} + +/** + * ata_ncq_enabled - Test whether NCQ is enabled + * @dev: ATA device to test + * + * LOCKING: + * spin_lock_irqsave(host lock) + * + * RETURNS: + * true if NCQ is enabled for @dev, false otherwise. + */ +static inline bool ata_ncq_enabled(struct ata_device *dev) +{ + return ata_ncq_supported(dev) && !(dev->flags & ATA_DFLAG_NCQ_OFF); } static inline bool ata_fpdma_dsm_supported(struct ata_device *dev) -- cgit v1.2.3 From 4d2e4980a5289ae31a1cff40d258b68573182a37 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Fri, 14 Oct 2022 18:05:38 +0900 Subject: ata: libata: cleanup fua support detection Move the detection of a device FUA support from ata_scsiop_mode_sense()/ata_dev_supports_fua() to device scan time in ata_dev_configure(). The function ata_dev_config_fua() is introduced to detect if a device supports FUA and this support is indicated using the new device flag ATA_DFLAG_FUA. In order to blacklist known buggy devices, the horkage flag ATA_HORKAGE_NO_FUA is introduced. Similarly to other horkage flags, the libata.force= arguments "fua" and "nofua" are also introduced to allow a user to control this horkage flag through the "force" libata module parameter. The ATA_DFLAG_FUA device flag is set only and only if all the following conditions are met: * libata.fua module parameter is set to 1 * The device supports the WRITE DMA FUA EXT command, * The device is not marked with the ATA_HORKAGE_NO_FUA flag, either from the blacklist or set by the user with libata.force=nofua * The device supports NCQ (while this is not mandated by the standards, this restriction is introduced to avoid problems with older non-NCQ devices). Enabling or diabling libata FUA support for all devices can now also be done using the "force=[no]fua" module parameter when libata.fua is set to 1. Signed-off-by: Damien Le Moal Reviewed-by: Hannes Reinecke Reviewed-by: Chaitanya Kulkarni Reviewed-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Reviewed-by: Niklas Cassel --- Documentation/admin-guide/kernel-parameters.txt | 3 +++ drivers/ata/libata-core.c | 30 ++++++++++++++++++++++++- drivers/ata/libata-scsi.c | 30 ++----------------------- include/linux/libata.h | 8 ++++--- 4 files changed, 39 insertions(+), 32 deletions(-) (limited to 'include/linux') diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 6cfa6e3996cf..3d0f2de7dc03 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -2816,6 +2816,9 @@ * [no]setxfer: Indicate if transfer speed mode setting should be skipped. + * [no]fua: Disable or enable FUA (Force Unit Access) + support for devices supporting this feature. + * dump_id: Dump IDENTIFY data. * disable: Disable this device. diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 1c16342dda08..d25a53a873dc 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -2422,6 +2422,28 @@ static void ata_dev_config_chs(struct ata_device *dev) dev->heads, dev->sectors); } +static void ata_dev_config_fua(struct ata_device *dev) +{ + /* Ignore FUA support if its use is disabled globally */ + if (!libata_fua) + goto nofua; + + /* Ignore devices without support for WRITE DMA FUA EXT */ + if (!(dev->flags & ATA_DFLAG_LBA48) || !ata_id_has_fua(dev->id)) + goto nofua; + + /* Ignore known bad devices and devices that lack NCQ support */ + if (!ata_ncq_supported(dev) || (dev->horkage & ATA_HORKAGE_NO_FUA)) + goto nofua; + + dev->flags |= ATA_DFLAG_FUA; + + return; + +nofua: + dev->flags &= ~ATA_DFLAG_FUA; +} + static void ata_dev_config_devslp(struct ata_device *dev) { u8 *sata_setting = dev->link->ap->sector_buf; @@ -2510,7 +2532,8 @@ static void ata_dev_print_features(struct ata_device *dev) return; ata_dev_info(dev, - "Features:%s%s%s%s%s%s\n", + "Features:%s%s%s%s%s%s%s\n", + dev->flags & ATA_DFLAG_FUA ? " FUA" : "", dev->flags & ATA_DFLAG_TRUSTED ? " Trust" : "", dev->flags & ATA_DFLAG_DA ? " Dev-Attention" : "", dev->flags & ATA_DFLAG_DEVSLP ? " Dev-Sleep" : "", @@ -2671,6 +2694,7 @@ int ata_dev_configure(struct ata_device *dev) ata_dev_config_chs(dev); } + ata_dev_config_fua(dev); ata_dev_config_devslp(dev); ata_dev_config_sense_reporting(dev); ata_dev_config_zac(dev); @@ -4105,6 +4129,9 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { */ { "SATADOM-ML 3ME", NULL, ATA_HORKAGE_NO_LOG_DIR }, + /* Buggy FUA */ + { "Maxtor", "BANC1G10", ATA_HORKAGE_NO_FUA }, + /* End Marker */ { } }; @@ -6216,6 +6243,7 @@ static const struct ata_force_param force_tbl[] __initconst = { force_horkage_onoff(lpm, ATA_HORKAGE_NOLPM), force_horkage_onoff(setxfer, ATA_HORKAGE_NOSETXFER), force_horkage_on(dump_id, ATA_HORKAGE_DUMP_ID), + force_horkage_onoff(fua, ATA_HORKAGE_NO_FUA), force_horkage_on(disable, ATA_HORKAGE_DISABLE), }; diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 46109bde8a04..aa338f10cef2 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -2240,30 +2240,6 @@ static unsigned int ata_msense_rw_recovery(u8 *buf, bool changeable) return sizeof(def_rw_recovery_mpage); } -/* - * We can turn this into a real blacklist if it's needed, for now just - * blacklist any Maxtor BANC1G10 revision firmware - */ -static int ata_dev_supports_fua(u16 *id) -{ - unsigned char model[ATA_ID_PROD_LEN + 1], fw[ATA_ID_FW_REV_LEN + 1]; - - if (!libata_fua) - return 0; - if (!ata_id_has_fua(id)) - return 0; - - ata_id_c_string(id, model, ATA_ID_PROD, sizeof(model)); - ata_id_c_string(id, fw, ATA_ID_FW_REV, sizeof(fw)); - - if (strcmp(model, "Maxtor")) - return 1; - if (strcmp(fw, "BANC1G10")) - return 1; - - return 0; /* blacklisted */ -} - /** * ata_scsiop_mode_sense - Simulate MODE SENSE 6, 10 commands * @args: device IDENTIFY data / SCSI command of interest. @@ -2287,7 +2263,7 @@ static unsigned int ata_scsiop_mode_sense(struct ata_scsi_args *args, u8 *rbuf) }; u8 pg, spg; unsigned int ebd, page_control, six_byte; - u8 dpofua, bp = 0xff; + u8 dpofua = 0, bp = 0xff; u16 fp; six_byte = (scsicmd[0] == MODE_SENSE); @@ -2350,9 +2326,7 @@ static unsigned int ata_scsiop_mode_sense(struct ata_scsi_args *args, u8 *rbuf) goto invalid_fld; } - dpofua = 0; - if (ata_dev_supports_fua(args->id) && (dev->flags & ATA_DFLAG_LBA48) && - (!(dev->flags & ATA_DFLAG_PIO) || dev->multi_count)) + if (dev->flags & ATA_DFLAG_FUA) dpofua = 1 << 4; if (six_byte) { diff --git a/include/linux/libata.h b/include/linux/libata.h index 059ca7f2b69c..a759dfbdcc91 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -90,6 +90,7 @@ enum { ATA_DFLAG_ACPI_FAILED = (1 << 6), /* ACPI on devcfg has failed */ ATA_DFLAG_AN = (1 << 7), /* AN configured */ ATA_DFLAG_TRUSTED = (1 << 8), /* device supports trusted send/recv */ + ATA_DFLAG_FUA = (1 << 9), /* device supports FUA */ ATA_DFLAG_DMADIR = (1 << 10), /* device requires DMADIR */ ATA_DFLAG_NCQ_SEND_RECV = (1 << 11), /* device supports NCQ SEND and RECV */ ATA_DFLAG_NCQ_PRIO = (1 << 12), /* device supports NCQ priority */ @@ -112,9 +113,9 @@ enum { ATA_DFLAG_D_SENSE = (1 << 29), /* Descriptor sense requested */ ATA_DFLAG_ZAC = (1 << 30), /* ZAC device */ - ATA_DFLAG_FEATURES_MASK = ATA_DFLAG_TRUSTED | ATA_DFLAG_DA | \ - ATA_DFLAG_DEVSLP | ATA_DFLAG_NCQ_SEND_RECV | \ - ATA_DFLAG_NCQ_PRIO, + ATA_DFLAG_FEATURES_MASK = (ATA_DFLAG_TRUSTED | ATA_DFLAG_DA | \ + ATA_DFLAG_DEVSLP | ATA_DFLAG_NCQ_SEND_RECV | \ + ATA_DFLAG_NCQ_PRIO | ATA_DFLAG_FUA), ATA_DEV_UNKNOWN = 0, /* unknown device */ ATA_DEV_ATA = 1, /* ATA device */ @@ -381,6 +382,7 @@ enum { ATA_HORKAGE_NO_NCQ_ON_ATI = (1 << 27), /* Disable NCQ on ATI chipset */ ATA_HORKAGE_NO_ID_DEV_LOG = (1 << 28), /* Identify device log missing */ ATA_HORKAGE_NO_LOG_DIR = (1 << 29), /* Do not read log directory */ + ATA_HORKAGE_NO_FUA = (1 << 30), /* Do not use FUA */ /* DMA mask for user DMA control: User visible values; DO NOT renumber */ -- cgit v1.2.3 From 312b8f79eb05479628ee71357749815b2eeeeea8 Mon Sep 17 00:00:00 2001 From: Mark Zhang Date: Wed, 4 Jan 2023 11:43:34 +0200 Subject: RDMA/mlx: Calling qp event handler in workqueue context Move the call of qp event handler from atomic to workqueue context, so that the handler is able to block. This is needed by following patches. Signed-off-by: Mark Zhang Reviewed-by: Patrisious Haddad Link: https://lore.kernel.org/r/0cd17b8331e445f03942f4bb28d447f24ac5669d.1672821186.git.leonro@nvidia.com Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/mlx4/main.c | 8 +++ drivers/infiniband/hw/mlx4/mlx4_ib.h | 3 + drivers/infiniband/hw/mlx4/qp.c | 121 ++++++++++++++++++++++---------- drivers/infiniband/hw/mlx5/main.c | 7 ++ drivers/infiniband/hw/mlx5/qp.c | 119 ++++++++++++++++++++++--------- drivers/infiniband/hw/mlx5/qp.h | 2 + drivers/infiniband/hw/mlx5/qpc.c | 3 +- drivers/net/ethernet/mellanox/mlx4/qp.c | 14 ++-- include/linux/mlx4/qp.h | 1 + include/rdma/ib_verbs.h | 2 +- 10 files changed, 202 insertions(+), 78 deletions(-) (limited to 'include/linux') diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index dceebcd885bb..b18e9f2adc82 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -3303,6 +3303,10 @@ static int __init mlx4_ib_init(void) if (!wq) return -ENOMEM; + err = mlx4_ib_qp_event_init(); + if (err) + goto clean_qp_event; + err = mlx4_ib_cm_init(); if (err) goto clean_wq; @@ -3324,6 +3328,9 @@ clean_cm: mlx4_ib_cm_destroy(); clean_wq: + mlx4_ib_qp_event_cleanup(); + +clean_qp_event: destroy_workqueue(wq); return err; } @@ -3333,6 +3340,7 @@ static void __exit mlx4_ib_cleanup(void) mlx4_unregister_interface(&mlx4_ib_interface); mlx4_ib_mcg_destroy(); mlx4_ib_cm_destroy(); + mlx4_ib_qp_event_cleanup(); destroy_workqueue(wq); } diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h index 6a3b0f121045..17fee1e73a45 100644 --- a/drivers/infiniband/hw/mlx4/mlx4_ib.h +++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h @@ -940,4 +940,7 @@ int mlx4_ib_umem_calc_optimal_mtt_size(struct ib_umem *umem, u64 start_va, int mlx4_ib_cm_init(void); void mlx4_ib_cm_destroy(void); +int mlx4_ib_qp_event_init(void); +void mlx4_ib_qp_event_cleanup(void); + #endif /* MLX4_IB_H */ diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c index b17d6ebc5b70..884825b2e5f7 100644 --- a/drivers/infiniband/hw/mlx4/qp.c +++ b/drivers/infiniband/hw/mlx4/qp.c @@ -102,6 +102,14 @@ enum mlx4_ib_source_type { MLX4_IB_RWQ_SRC = 1, }; +struct mlx4_ib_qp_event_work { + struct work_struct work; + struct mlx4_qp *qp; + enum mlx4_event type; +}; + +static struct workqueue_struct *mlx4_ib_qp_event_wq; + static int is_tunnel_qp(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp) { if (!mlx4_is_master(dev->dev)) @@ -200,50 +208,77 @@ static void stamp_send_wqe(struct mlx4_ib_qp *qp, int n) } } +static void mlx4_ib_handle_qp_event(struct work_struct *_work) +{ + struct mlx4_ib_qp_event_work *qpe_work = + container_of(_work, struct mlx4_ib_qp_event_work, work); + struct ib_qp *ibqp = &to_mibqp(qpe_work->qp)->ibqp; + struct ib_event event = {}; + + event.device = ibqp->device; + event.element.qp = ibqp; + + switch (qpe_work->type) { + case MLX4_EVENT_TYPE_PATH_MIG: + event.event = IB_EVENT_PATH_MIG; + break; + case MLX4_EVENT_TYPE_COMM_EST: + event.event = IB_EVENT_COMM_EST; + break; + case MLX4_EVENT_TYPE_SQ_DRAINED: + event.event = IB_EVENT_SQ_DRAINED; + break; + case MLX4_EVENT_TYPE_SRQ_QP_LAST_WQE: + event.event = IB_EVENT_QP_LAST_WQE_REACHED; + break; + case MLX4_EVENT_TYPE_WQ_CATAS_ERROR: + event.event = IB_EVENT_QP_FATAL; + break; + case MLX4_EVENT_TYPE_PATH_MIG_FAILED: + event.event = IB_EVENT_PATH_MIG_ERR; + break; + case MLX4_EVENT_TYPE_WQ_INVAL_REQ_ERROR: + event.event = IB_EVENT_QP_REQ_ERR; + break; + case MLX4_EVENT_TYPE_WQ_ACCESS_ERROR: + event.event = IB_EVENT_QP_ACCESS_ERR; + break; + default: + pr_warn("Unexpected event type %d on QP %06x\n", + qpe_work->type, qpe_work->qp->qpn); + goto out; + } + + ibqp->event_handler(&event, ibqp->qp_context); + +out: + mlx4_put_qp(qpe_work->qp); + kfree(qpe_work); +} + static void mlx4_ib_qp_event(struct mlx4_qp *qp, enum mlx4_event type) { - struct ib_event event; struct ib_qp *ibqp = &to_mibqp(qp)->ibqp; + struct mlx4_ib_qp_event_work *qpe_work; if (type == MLX4_EVENT_TYPE_PATH_MIG) to_mibqp(qp)->port = to_mibqp(qp)->alt_port; - if (ibqp->event_handler) { - event.device = ibqp->device; - event.element.qp = ibqp; - switch (type) { - case MLX4_EVENT_TYPE_PATH_MIG: - event.event = IB_EVENT_PATH_MIG; - break; - case MLX4_EVENT_TYPE_COMM_EST: - event.event = IB_EVENT_COMM_EST; - break; - case MLX4_EVENT_TYPE_SQ_DRAINED: - event.event = IB_EVENT_SQ_DRAINED; - break; - case MLX4_EVENT_TYPE_SRQ_QP_LAST_WQE: - event.event = IB_EVENT_QP_LAST_WQE_REACHED; - break; - case MLX4_EVENT_TYPE_WQ_CATAS_ERROR: - event.event = IB_EVENT_QP_FATAL; - break; - case MLX4_EVENT_TYPE_PATH_MIG_FAILED: - event.event = IB_EVENT_PATH_MIG_ERR; - break; - case MLX4_EVENT_TYPE_WQ_INVAL_REQ_ERROR: - event.event = IB_EVENT_QP_REQ_ERR; - break; - case MLX4_EVENT_TYPE_WQ_ACCESS_ERROR: - event.event = IB_EVENT_QP_ACCESS_ERR; - break; - default: - pr_warn("Unexpected event type %d " - "on QP %06x\n", type, qp->qpn); - return; - } + if (!ibqp->event_handler) + goto out_no_handler; - ibqp->event_handler(&event, ibqp->qp_context); - } + qpe_work = kzalloc(sizeof(*qpe_work), GFP_ATOMIC); + if (!qpe_work) + goto out_no_handler; + + qpe_work->qp = qp; + qpe_work->type = type; + INIT_WORK(&qpe_work->work, mlx4_ib_handle_qp_event); + queue_work(mlx4_ib_qp_event_wq, &qpe_work->work); + return; + +out_no_handler: + mlx4_put_qp(qp); } static void mlx4_ib_wq_event(struct mlx4_qp *qp, enum mlx4_event type) @@ -4468,3 +4503,17 @@ void mlx4_ib_drain_rq(struct ib_qp *qp) handle_drain_completion(cq, &rdrain, dev); } + +int mlx4_ib_qp_event_init(void) +{ + mlx4_ib_qp_event_wq = alloc_ordered_workqueue("mlx4_ib_qp_event_wq", 0); + if (!mlx4_ib_qp_event_wq) + return -ENOMEM; + + return 0; +} + +void mlx4_ib_qp_event_cleanup(void) +{ + destroy_workqueue(mlx4_ib_qp_event_wq); +} diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index c669ef6e47e7..8588f2fc0cba 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -4403,6 +4403,10 @@ static int __init mlx5_ib_init(void) return -ENOMEM; } + ret = mlx5_ib_qp_event_init(); + if (ret) + goto qp_event_err; + mlx5_ib_odp_init(); ret = mlx5r_rep_init(); if (ret) @@ -4420,6 +4424,8 @@ drv_err: mp_err: mlx5r_rep_cleanup(); rep_err: + mlx5_ib_qp_event_cleanup(); +qp_event_err: destroy_workqueue(mlx5_ib_event_wq); free_page((unsigned long)xlt_emergency_page); return ret; @@ -4431,6 +4437,7 @@ static void __exit mlx5_ib_cleanup(void) auxiliary_driver_unregister(&mlx5r_mp_driver); mlx5r_rep_cleanup(); + mlx5_ib_qp_event_cleanup(); destroy_workqueue(mlx5_ib_event_wq); free_page((unsigned long)xlt_emergency_page); } diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index cf953d23d18d..9b85e1be0aed 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -71,6 +71,14 @@ struct mlx5_modify_raw_qp_param { u32 port; }; +struct mlx5_ib_qp_event_work { + struct work_struct work; + struct mlx5_core_qp *qp; + int type; +}; + +static struct workqueue_struct *mlx5_ib_qp_event_wq; + static void get_cqs(enum ib_qp_type qp_type, struct ib_cq *ib_send_cq, struct ib_cq *ib_recv_cq, struct mlx5_ib_cq **send_cq, struct mlx5_ib_cq **recv_cq); @@ -302,51 +310,78 @@ int mlx5_ib_read_wqe_srq(struct mlx5_ib_srq *srq, int wqe_index, void *buffer, return mlx5_ib_read_user_wqe_srq(srq, wqe_index, buffer, buflen, bc); } +static void mlx5_ib_handle_qp_event(struct work_struct *_work) +{ + struct mlx5_ib_qp_event_work *qpe_work = + container_of(_work, struct mlx5_ib_qp_event_work, work); + struct ib_qp *ibqp = &to_mibqp(qpe_work->qp)->ibqp; + struct ib_event event = {}; + + event.device = ibqp->device; + event.element.qp = ibqp; + switch (qpe_work->type) { + case MLX5_EVENT_TYPE_PATH_MIG: + event.event = IB_EVENT_PATH_MIG; + break; + case MLX5_EVENT_TYPE_COMM_EST: + event.event = IB_EVENT_COMM_EST; + break; + case MLX5_EVENT_TYPE_SQ_DRAINED: + event.event = IB_EVENT_SQ_DRAINED; + break; + case MLX5_EVENT_TYPE_SRQ_LAST_WQE: + event.event = IB_EVENT_QP_LAST_WQE_REACHED; + break; + case MLX5_EVENT_TYPE_WQ_CATAS_ERROR: + event.event = IB_EVENT_QP_FATAL; + break; + case MLX5_EVENT_TYPE_PATH_MIG_FAILED: + event.event = IB_EVENT_PATH_MIG_ERR; + break; + case MLX5_EVENT_TYPE_WQ_INVAL_REQ_ERROR: + event.event = IB_EVENT_QP_REQ_ERR; + break; + case MLX5_EVENT_TYPE_WQ_ACCESS_ERROR: + event.event = IB_EVENT_QP_ACCESS_ERR; + break; + default: + pr_warn("mlx5_ib: Unexpected event type %d on QP %06x\n", + qpe_work->type, qpe_work->qp->qpn); + goto out; + } + + ibqp->event_handler(&event, ibqp->qp_context); + +out: + mlx5_core_res_put(&qpe_work->qp->common); + kfree(qpe_work); +} + static void mlx5_ib_qp_event(struct mlx5_core_qp *qp, int type) { struct ib_qp *ibqp = &to_mibqp(qp)->ibqp; - struct ib_event event; + struct mlx5_ib_qp_event_work *qpe_work; if (type == MLX5_EVENT_TYPE_PATH_MIG) { /* This event is only valid for trans_qps */ to_mibqp(qp)->port = to_mibqp(qp)->trans_qp.alt_port; } - if (ibqp->event_handler) { - event.device = ibqp->device; - event.element.qp = ibqp; - switch (type) { - case MLX5_EVENT_TYPE_PATH_MIG: - event.event = IB_EVENT_PATH_MIG; - break; - case MLX5_EVENT_TYPE_COMM_EST: - event.event = IB_EVENT_COMM_EST; - break; - case MLX5_EVENT_TYPE_SQ_DRAINED: - event.event = IB_EVENT_SQ_DRAINED; - break; - case MLX5_EVENT_TYPE_SRQ_LAST_WQE: - event.event = IB_EVENT_QP_LAST_WQE_REACHED; - break; - case MLX5_EVENT_TYPE_WQ_CATAS_ERROR: - event.event = IB_EVENT_QP_FATAL; - break; - case MLX5_EVENT_TYPE_PATH_MIG_FAILED: - event.event = IB_EVENT_PATH_MIG_ERR; - break; - case MLX5_EVENT_TYPE_WQ_INVAL_REQ_ERROR: - event.event = IB_EVENT_QP_REQ_ERR; - break; - case MLX5_EVENT_TYPE_WQ_ACCESS_ERROR: - event.event = IB_EVENT_QP_ACCESS_ERR; - break; - default: - pr_warn("mlx5_ib: Unexpected event type %d on QP %06x\n", type, qp->qpn); - return; - } + if (!ibqp->event_handler) + goto out_no_handler; - ibqp->event_handler(&event, ibqp->qp_context); - } + qpe_work = kzalloc(sizeof(*qpe_work), GFP_ATOMIC); + if (!qpe_work) + goto out_no_handler; + + qpe_work->qp = qp; + qpe_work->type = type; + INIT_WORK(&qpe_work->work, mlx5_ib_handle_qp_event); + queue_work(mlx5_ib_qp_event_wq, &qpe_work->work); + return; + +out_no_handler: + mlx5_core_res_put(&qp->common); } static int set_rq_size(struct mlx5_ib_dev *dev, struct ib_qp_cap *cap, @@ -5720,3 +5755,17 @@ out: mutex_unlock(&mqp->mutex); return err; } + +int mlx5_ib_qp_event_init(void) +{ + mlx5_ib_qp_event_wq = alloc_ordered_workqueue("mlx5_ib_qp_event_wq", 0); + if (!mlx5_ib_qp_event_wq) + return -ENOMEM; + + return 0; +} + +void mlx5_ib_qp_event_cleanup(void) +{ + destroy_workqueue(mlx5_ib_qp_event_wq); +} diff --git a/drivers/infiniband/hw/mlx5/qp.h b/drivers/infiniband/hw/mlx5/qp.h index 5d4e140db99c..fb2f4e030bb8 100644 --- a/drivers/infiniband/hw/mlx5/qp.h +++ b/drivers/infiniband/hw/mlx5/qp.h @@ -44,4 +44,6 @@ void mlx5_core_res_put(struct mlx5_core_rsc_common *res); int mlx5_core_xrcd_alloc(struct mlx5_ib_dev *dev, u32 *xrcdn); int mlx5_core_xrcd_dealloc(struct mlx5_ib_dev *dev, u32 xrcdn); int mlx5_ib_qp_set_counter(struct ib_qp *qp, struct rdma_counter *counter); +int mlx5_ib_qp_event_init(void); +void mlx5_ib_qp_event_cleanup(void); #endif /* _MLX5_IB_QP_H */ diff --git a/drivers/infiniband/hw/mlx5/qpc.c b/drivers/infiniband/hw/mlx5/qpc.c index 542e4c63a8de..604af1fd6397 100644 --- a/drivers/infiniband/hw/mlx5/qpc.c +++ b/drivers/infiniband/hw/mlx5/qpc.c @@ -135,7 +135,8 @@ static int rsc_event_notifier(struct notifier_block *nb, case MLX5_RES_SQ: qp = (struct mlx5_core_qp *)common; qp->event(qp, event_type); - break; + /* Need to put resource in event handler */ + return NOTIFY_OK; case MLX5_RES_DCT: dct = (struct mlx5_core_dct *)common; if (event_type == MLX5_EVENT_TYPE_DCT_DRAINED) diff --git a/drivers/net/ethernet/mellanox/mlx4/qp.c b/drivers/net/ethernet/mellanox/mlx4/qp.c index 48cfaa7eaf50..913ed255990f 100644 --- a/drivers/net/ethernet/mellanox/mlx4/qp.c +++ b/drivers/net/ethernet/mellanox/mlx4/qp.c @@ -46,6 +46,13 @@ #define MLX4_BF_QP_SKIP_MASK 0xc0 #define MLX4_MAX_BF_QP_RANGE 0x40 +void mlx4_put_qp(struct mlx4_qp *qp) +{ + if (refcount_dec_and_test(&qp->refcount)) + complete(&qp->free); +} +EXPORT_SYMBOL_GPL(mlx4_put_qp); + void mlx4_qp_event(struct mlx4_dev *dev, u32 qpn, int event_type) { struct mlx4_qp_table *qp_table = &mlx4_priv(dev)->qp_table; @@ -64,10 +71,8 @@ void mlx4_qp_event(struct mlx4_dev *dev, u32 qpn, int event_type) return; } + /* Need to call mlx4_put_qp() in event handler */ qp->event(qp, event_type); - - if (refcount_dec_and_test(&qp->refcount)) - complete(&qp->free); } /* used for INIT/CLOSE port logic */ @@ -523,8 +528,7 @@ EXPORT_SYMBOL_GPL(mlx4_qp_remove); void mlx4_qp_free(struct mlx4_dev *dev, struct mlx4_qp *qp) { - if (refcount_dec_and_test(&qp->refcount)) - complete(&qp->free); + mlx4_put_qp(qp); wait_for_completion(&qp->free); mlx4_qp_free_icm(dev, qp->qpn); diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h index 9db93e487496..c78b90f2e9a1 100644 --- a/include/linux/mlx4/qp.h +++ b/include/linux/mlx4/qp.h @@ -503,4 +503,5 @@ static inline u16 folded_qp(u32 q) u16 mlx4_qp_roce_entropy(struct mlx4_dev *dev, u32 qpn); +void mlx4_put_qp(struct mlx4_qp *qp); #endif /* MLX4_QP_H */ diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index a9a429172c0a..949cf4ffc536 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -1168,7 +1168,7 @@ enum ib_qp_create_flags { */ struct ib_qp_init_attr { - /* Consumer's event_handler callback must not block */ + /* This callback occurs in workqueue context */ void (*event_handler)(struct ib_event *, void *); void *qp_context; -- cgit v1.2.3 From ade7fd908d710d0ab865c273df782c75528636ef Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Tue, 17 Jan 2023 13:43:09 +0100 Subject: efi: efivars: drop kobject from efivars_register() Since commit 0f5b2c69a4cb ("efi: vars: Remove deprecated 'efivars' sysfs interface") and the removal of the sysfs interface there are no users of the efivars kobject. Drop the kobject argument from efivars_register() and add a new efivar_is_available() helper in favour of the old efivars_kobject(). Note that the new helper uses the prefix 'efivar' (i.e. without an 's') for consistency with efivar_supports_writes() and the rest of the interface (except the registration functions). For the benefit of drivers with optional EFI support, also provide a dummy implementation of efivar_is_available(). Signed-off-by: Johan Hovold Signed-off-by: Ard Biesheuvel --- drivers/firmware/efi/efi.c | 2 +- drivers/firmware/efi/vars.c | 19 ++++++------------- drivers/firmware/google/gsmi.c | 2 +- fs/efivarfs/super.c | 2 +- include/linux/efi.h | 11 +++++++---- 5 files changed, 16 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index 09716eebe8ac..e7ff692f111d 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -197,7 +197,7 @@ static int generic_ops_register(void) generic_ops.set_variable = efi.set_variable; generic_ops.set_variable_nonblocking = efi.set_variable_nonblocking; } - return efivars_register(&generic_efivars, &generic_ops, efi_kobj); + return efivars_register(&generic_efivars, &generic_ops); } static void generic_ops_unregister(void) diff --git a/drivers/firmware/efi/vars.c b/drivers/firmware/efi/vars.c index 0ba9f18312f5..d6b2c4f9a575 100644 --- a/drivers/firmware/efi/vars.c +++ b/drivers/firmware/efi/vars.c @@ -40,37 +40,30 @@ static efi_status_t check_var_size(bool nonblocking, u32 attributes, } /** - * efivars_kobject - get the kobject for the registered efivars + * efivar_is_available - check if efivars is available * - * If efivars_register() has not been called we return NULL, - * otherwise return the kobject used at registration time. + * @return true iff evivars is currently registered */ -struct kobject *efivars_kobject(void) +bool efivar_is_available(void) { - if (!__efivars) - return NULL; - - return __efivars->kobject; + return __efivars != NULL; } -EXPORT_SYMBOL_GPL(efivars_kobject); +EXPORT_SYMBOL_GPL(efivar_is_available); /** * efivars_register - register an efivars * @efivars: efivars to register * @ops: efivars operations - * @kobject: @efivars-specific kobject * * Only a single efivars can be registered at any time. */ int efivars_register(struct efivars *efivars, - const struct efivar_operations *ops, - struct kobject *kobject) + const struct efivar_operations *ops) { if (down_interruptible(&efivars_lock)) return -EINTR; efivars->ops = ops; - efivars->kobject = kobject; __efivars = efivars; diff --git a/drivers/firmware/google/gsmi.c b/drivers/firmware/google/gsmi.c index 4e2575dfeb90..60054a5d5de7 100644 --- a/drivers/firmware/google/gsmi.c +++ b/drivers/firmware/google/gsmi.c @@ -1029,7 +1029,7 @@ static __init int gsmi_init(void) } #ifdef CONFIG_EFI - ret = efivars_register(&efivars, &efivar_ops, gsmi_kobj); + ret = efivars_register(&efivars, &efivar_ops); if (ret) { printk(KERN_INFO "gsmi: Failed to register efivars\n"); sysfs_remove_files(gsmi_kobj, gsmi_attrs); diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c index 07e82e246666..f72c529c8ec3 100644 --- a/fs/efivarfs/super.c +++ b/fs/efivarfs/super.c @@ -256,7 +256,7 @@ static struct file_system_type efivarfs_type = { static __init int efivarfs_init(void) { - if (!efivars_kobject()) + if (!efivar_is_available()) return -ENODEV; return register_filesystem(&efivarfs_type); diff --git a/include/linux/efi.h b/include/linux/efi.h index 4b27519143f5..2124e55c02d6 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1039,7 +1039,6 @@ struct efivar_operations { struct efivars { struct kset *kset; - struct kobject *kobject; const struct efivar_operations *ops; }; @@ -1053,10 +1052,14 @@ struct efivars { #define EFI_VAR_NAME_LEN 1024 int efivars_register(struct efivars *efivars, - const struct efivar_operations *ops, - struct kobject *kobject); + const struct efivar_operations *ops); int efivars_unregister(struct efivars *efivars); -struct kobject *efivars_kobject(void); + +#ifdef CONFIG_EFI +bool efivar_is_available(void); +#else +static inline bool efivar_is_available(void) { return false; } +#endif int efivar_supports_writes(void); -- cgit v1.2.3 From 2cf9e278efeff8f8bbb9580e2d6760e19795e310 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Tue, 17 Jan 2023 13:43:10 +0100 Subject: efi: efivars: make efivar_supports_writes() return bool For consistency with the new efivar_is_available() function, change the return type of efivar_supports_writes() to bool. Signed-off-by: Johan Hovold Signed-off-by: Ard Biesheuvel --- drivers/firmware/efi/vars.c | 2 +- include/linux/efi.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/firmware/efi/vars.c b/drivers/firmware/efi/vars.c index d6b2c4f9a575..aa5ba38f81ff 100644 --- a/drivers/firmware/efi/vars.c +++ b/drivers/firmware/efi/vars.c @@ -110,7 +110,7 @@ out: } EXPORT_SYMBOL_GPL(efivars_unregister); -int efivar_supports_writes(void) +bool efivar_supports_writes(void) { return __efivars && __efivars->ops->set_variable; } diff --git a/include/linux/efi.h b/include/linux/efi.h index 2124e55c02d6..f6b107da1cbc 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1061,7 +1061,7 @@ bool efivar_is_available(void); static inline bool efivar_is_available(void) { return false; } #endif -int efivar_supports_writes(void); +bool efivar_supports_writes(void); int efivar_lock(void); int efivar_trylock(void); -- cgit v1.2.3 From 28e1ff70a08d331703f115534bd4278e11451439 Mon Sep 17 00:00:00 2001 From: Ricardo Ribalda Date: Wed, 21 Dec 2022 20:34:51 +0100 Subject: USB: Improve usb_fill_* documentation Document the transfer buffer requirement. That is, the buffer must be DMAble - otherwise data corruption might occur. Acked-by: Randy Dunlap Reviewed-by: Laurent Pinchart Signed-off-by: Ricardo Ribalda Acked-by: Alan Stern Link: https://lore.kernel.org/r/20221220-usb-dmadoc-v4-0-74a045bf14f4@chromium.org Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 27 +++++++++++++++++++++++---- 1 file changed, 23 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index 7d5325d47c45..4e98ebacec96 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -1626,14 +1626,25 @@ struct urb { * @urb: pointer to the urb to initialize. * @dev: pointer to the struct usb_device for this urb. * @pipe: the endpoint pipe - * @setup_packet: pointer to the setup_packet buffer - * @transfer_buffer: pointer to the transfer buffer + * @setup_packet: pointer to the setup_packet buffer. The buffer must be + * suitable for DMA. + * @transfer_buffer: pointer to the transfer buffer. The buffer must be + * suitable for DMA. * @buffer_length: length of the transfer buffer * @complete_fn: pointer to the usb_complete_t function * @context: what to set the urb context to. * * Initializes a control urb with the proper information needed to submit * it to a device. + * + * The transfer buffer and the setup_packet buffer will most likely be filled + * or read via DMA. The simplest way to get a buffer that can be DMAed to is + * allocating it via kmalloc() or equivalent, even for very small buffers. + * If the buffers are embedded in a bigger structure, there is a risk that + * the buffer itself, the previous fields and/or the next fields are corrupted + * due to cache incoherencies; or slowed down if they are evicted from the + * cache. For more information, check &struct urb. + * */ static inline void usb_fill_control_urb(struct urb *urb, struct usb_device *dev, @@ -1658,13 +1669,17 @@ static inline void usb_fill_control_urb(struct urb *urb, * @urb: pointer to the urb to initialize. * @dev: pointer to the struct usb_device for this urb. * @pipe: the endpoint pipe - * @transfer_buffer: pointer to the transfer buffer + * @transfer_buffer: pointer to the transfer buffer. The buffer must be + * suitable for DMA. * @buffer_length: length of the transfer buffer * @complete_fn: pointer to the usb_complete_t function * @context: what to set the urb context to. * * Initializes a bulk urb with the proper information needed to submit it * to a device. + * + * Refer to usb_fill_control_urb() for a description of the requirements for + * transfer_buffer. */ static inline void usb_fill_bulk_urb(struct urb *urb, struct usb_device *dev, @@ -1687,7 +1702,8 @@ static inline void usb_fill_bulk_urb(struct urb *urb, * @urb: pointer to the urb to initialize. * @dev: pointer to the struct usb_device for this urb. * @pipe: the endpoint pipe - * @transfer_buffer: pointer to the transfer buffer + * @transfer_buffer: pointer to the transfer buffer. The buffer must be + * suitable for DMA. * @buffer_length: length of the transfer buffer * @complete_fn: pointer to the usb_complete_t function * @context: what to set the urb context to. @@ -1697,6 +1713,9 @@ static inline void usb_fill_bulk_urb(struct urb *urb, * Initializes a interrupt urb with the proper information needed to submit * it to a device. * + * Refer to usb_fill_control_urb() for a description of the requirements for + * transfer_buffer. + * * Note that High Speed and SuperSpeed(+) interrupt endpoints use a logarithmic * encoding of the endpoint interval, and express polling intervals in * microframes (eight per millisecond) rather than in frames (one per -- cgit v1.2.3 From 599f008c257d913674b2b2f2fa9e273c1058ec2e Mon Sep 17 00:00:00 2001 From: Badhri Jagan Sridharan Date: Sat, 14 Jan 2023 01:32:44 -0800 Subject: usb: typec: tcpm: Add callbacks to mitigate wakeups due to contaminant On some of the TCPC implementations, when the Type-C port is exposed to contaminants, such as water, TCPC stops toggling while reporting OPEN either by the time TCPM reads CC pin status or during CC debounce window. This causes TCPM to be stuck in TOGGLING state. If TCPM is made to restart toggling, the behavior recurs causing redundant CPU wakeups till the USB-C port is free of contaminant. [206199.287817] CC1: 0 -> 0, CC2: 0 -> 0 [state TOGGLING, polarity 0, disconnected] [206199.640337] CC1: 0 -> 0, CC2: 0 -> 0 [state TOGGLING, polarity 0, disconnected] [206199.985789] CC1: 0 -> 0, CC2: 0 -> 0 [state TOGGLING, polarity 0, disconnected] (or) [ 7853.867577] Start toggling [ 7853.889921] CC1: 0 -> 0, CC2: 0 -> 0 [state TOGGLING, polarity 0, disconnected] [ 7855.698765] CC1: 0 -> 0, CC2: 0 -> 5 [state TOGGLING, polarity 0, connected] [ 7855.698790] state change TOGGLING -> SNK_ATTACH_WAIT [rev3 NONE_AMS] [ 7855.698826] pending state change SNK_ATTACH_WAIT -> SNK_DEBOUNCED @ 170 ms [rev3 NONE_AMS] [ 7855.703559] CC1: 0 -> 0, CC2: 5 -> 5 [state SNK_ATTACH_WAIT, polarity 0, connected] [ 7855.856555] CC1: 0 -> 0, CC2: 5 -> 0 [state SNK_ATTACH_WAIT, polarity 0, disconnected] [ 7855.856581] state change SNK_ATTACH_WAIT -> SNK_ATTACH_WAIT [rev3 NONE_AMS] [ 7855.856613] pending state change SNK_ATTACH_WAIT -> SNK_UNATTACHED @ 170 ms [rev3 NONE_AMS] [ 7856.027744] state change SNK_ATTACH_WAIT -> SNK_UNATTACHED [delayed 170 ms] [ 7856.181949] CC1: 0 -> 0, CC2: 0 -> 0 [state TOGGLING, polarity 0, disconnected] [ 7856.187896] CC1: 0 -> 0, CC2: 0 -> 0 [state TOGGLING, polarity 0, disconnected] [ 7857.645630] CC1: 0 -> 0, CC2: 0 -> 0 [state TOGGLING, polarity 0, disconnected] [ 7857.647291] CC1: 0 -> 0, CC2: 0 -> 5 [state TOGGLING, polarity 0, connected] [ 7857.647298] state change TOGGLING -> SNK_ATTACH_WAIT [rev3 NONE_AMS] [ 7857.647310] pending state change SNK_ATTACH_WAIT -> SNK_DEBOUNCED @ 170 ms [rev3 NONE_AMS] [ 7857.808106] CC1: 0 -> 0, CC2: 5 -> 0 [state SNK_ATTACH_WAIT, polarity 0, disconnected] [ 7857.808123] state change SNK_ATTACH_WAIT -> SNK_ATTACH_WAIT [rev3 NONE_AMS] [ 7857.808150] pending state change SNK_ATTACH_WAIT -> SNK_UNATTACHED @ 170 ms [rev3 NONE_AMS] [ 7857.978727] state change SNK_ATTACH_WAIT -> SNK_UNATTACHED [delayed 170 ms] To mitigate redundant TCPM wakeups, TCPCs which do have the needed hardware can implement the check_contaminant callback which is invoked by TCPM to evaluate for presence of contaminant. Lower level TCPC driver can restart toggling through TCPM_PORT_CLEAN event when the driver detects that USB-C port is free of contaminant. check_contaminant callback also passes the disconnect_while_debounce flag which when true denotes that the CC pins transitioned to OPEN state during the CC debounce window. Signed-off-by: Badhri Jagan Sridharan Acked-by: Heikki Krogerus Link: https://lore.kernel.org/r/20230114093246.1933321-1-badhri@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/tcpm/tcpm.c | 55 ++++++++++++++++++++++++++++++++++++++++++- include/linux/usb/tcpm.h | 8 +++++++ 2 files changed, 62 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index 904c7b4ce2f0..c624747f32df 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -36,6 +36,7 @@ #define FOREACH_STATE(S) \ S(INVALID_STATE), \ S(TOGGLING), \ + S(CHECK_CONTAMINANT), \ S(SRC_UNATTACHED), \ S(SRC_ATTACH_WAIT), \ S(SRC_ATTACHED), \ @@ -249,6 +250,7 @@ enum frs_typec_current { #define TCPM_RESET_EVENT BIT(2) #define TCPM_FRS_EVENT BIT(3) #define TCPM_SOURCING_VBUS BIT(4) +#define TCPM_PORT_CLEAN BIT(5) #define LOG_BUFFER_ENTRIES 1024 #define LOG_BUFFER_ENTRY_SIZE 128 @@ -483,6 +485,13 @@ struct tcpm_port { * SNK_READY for non-pd link. */ bool slow_charger_loop; + + /* + * When true indicates that the lower level drivers indicate potential presence + * of contaminant in the connector pins based on the tcpm state machine + * transitions. + */ + bool potential_contaminant; #ifdef CONFIG_DEBUG_FS struct dentry *dentry; struct mutex logbuffer_lock; /* log buffer access lock */ @@ -647,7 +656,7 @@ static void tcpm_log(struct tcpm_port *port, const char *fmt, ...) /* Do not log while disconnected and unattached */ if (tcpm_port_is_disconnected(port) && (port->state == SRC_UNATTACHED || port->state == SNK_UNATTACHED || - port->state == TOGGLING)) + port->state == TOGGLING || port->state == CHECK_CONTAMINANT)) return; va_start(args, fmt); @@ -3904,15 +3913,28 @@ static void run_state_machine(struct tcpm_port *port) unsigned int msecs; enum tcpm_state upcoming_state; + if (port->tcpc->check_contaminant && port->state != CHECK_CONTAMINANT) + port->potential_contaminant = ((port->enter_state == SRC_ATTACH_WAIT && + port->state == SRC_UNATTACHED) || + (port->enter_state == SNK_ATTACH_WAIT && + port->state == SNK_UNATTACHED)); + port->enter_state = port->state; switch (port->state) { case TOGGLING: break; + case CHECK_CONTAMINANT: + port->tcpc->check_contaminant(port->tcpc); + break; /* SRC states */ case SRC_UNATTACHED: if (!port->non_pd_role_swap) tcpm_swap_complete(port, -ENOTCONN); tcpm_src_detach(port); + if (port->potential_contaminant) { + tcpm_set_state(port, CHECK_CONTAMINANT, 0); + break; + } if (tcpm_start_toggling(port, tcpm_rp_cc(port))) { tcpm_set_state(port, TOGGLING, 0); break; @@ -4150,6 +4172,10 @@ static void run_state_machine(struct tcpm_port *port) tcpm_swap_complete(port, -ENOTCONN); tcpm_pps_complete(port, -ENOTCONN); tcpm_snk_detach(port); + if (port->potential_contaminant) { + tcpm_set_state(port, CHECK_CONTAMINANT, 0); + break; + } if (tcpm_start_toggling(port, TYPEC_CC_RD)) { tcpm_set_state(port, TOGGLING, 0); break; @@ -4926,6 +4952,9 @@ static void _tcpm_cc_change(struct tcpm_port *port, enum typec_cc_status cc1, else if (tcpm_port_is_sink(port)) tcpm_set_state(port, SNK_ATTACH_WAIT, 0); break; + case CHECK_CONTAMINANT: + /* Wait for Toggling to be resumed */ + break; case SRC_UNATTACHED: case ACC_UNATTACHED: if (tcpm_port_is_debug(port) || tcpm_port_is_audio(port) || @@ -5425,6 +5454,15 @@ static void tcpm_pd_event_handler(struct kthread_work *work) port->vbus_source = true; _tcpm_pd_vbus_on(port); } + if (events & TCPM_PORT_CLEAN) { + tcpm_log(port, "port clean"); + if (port->state == CHECK_CONTAMINANT) { + if (tcpm_start_toggling(port, tcpm_rp_cc(port))) + tcpm_set_state(port, TOGGLING, 0); + else + tcpm_set_state(port, tcpm_default_state(port), 0); + } + } spin_lock(&port->pd_event_lock); } @@ -5477,6 +5515,21 @@ void tcpm_sourcing_vbus(struct tcpm_port *port) } EXPORT_SYMBOL_GPL(tcpm_sourcing_vbus); +void tcpm_port_clean(struct tcpm_port *port) +{ + spin_lock(&port->pd_event_lock); + port->pd_events |= TCPM_PORT_CLEAN; + spin_unlock(&port->pd_event_lock); + kthread_queue_work(port->wq, &port->event_work); +} +EXPORT_SYMBOL_GPL(tcpm_port_clean); + +bool tcpm_port_is_toggling(struct tcpm_port *port) +{ + return port->port_type == TYPEC_PORT_DRP && port->state == TOGGLING; +} +EXPORT_SYMBOL_GPL(tcpm_port_is_toggling); + static void tcpm_enable_frs_work(struct kthread_work *work) { struct tcpm_port *port = container_of(work, struct tcpm_port, enable_frs); diff --git a/include/linux/usb/tcpm.h b/include/linux/usb/tcpm.h index bffc8d3e14ad..ab7ca872950b 100644 --- a/include/linux/usb/tcpm.h +++ b/include/linux/usb/tcpm.h @@ -114,6 +114,11 @@ enum tcpm_transmit_type { * Optional; The USB Communications Capable bit indicates if port * partner is capable of communication over the USB data lines * (e.g. D+/- or SS Tx/Rx). Called to notify the status of the bit. + * @check_contaminant: + * Optional; The callback is called when CC pins report open status + * at the end of the deboumce period or when the port is still + * toggling. Chip level drivers are expected to check for contaminant + * and call tcpm_clean_port when the port is clean. */ struct tcpc_dev { struct fwnode_handle *fwnode; @@ -148,6 +153,7 @@ struct tcpc_dev { bool pps_active, u32 requested_vbus_voltage); bool (*is_vbus_vsafe0v)(struct tcpc_dev *dev); void (*set_partner_usb_comm_capable)(struct tcpc_dev *dev, bool enable); + void (*check_contaminant)(struct tcpc_dev *dev); }; struct tcpm_port; @@ -165,5 +171,7 @@ void tcpm_pd_transmit_complete(struct tcpm_port *port, enum tcpm_transmit_status status); void tcpm_pd_hard_reset(struct tcpm_port *port); void tcpm_tcpc_reset(struct tcpm_port *port); +void tcpm_port_clean(struct tcpm_port *port); +bool tcpm_port_is_toggling(struct tcpm_port *port); #endif /* __LINUX_USB_TCPM_H */ -- cgit v1.2.3 From abc028a270f47f86060ef479395d1bb8c2ab6e7e Mon Sep 17 00:00:00 2001 From: Badhri Jagan Sridharan Date: Sat, 14 Jan 2023 01:32:45 -0800 Subject: usb: typec: tcpci: Add callback for evaluating contaminant presence This change adds callback to evaluate presence of contaminant in the TCPCI layer. Signed-off-by: Badhri Jagan Sridharan Link: https://lore.kernel.org/r/20230114093246.1933321-2-badhri@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/tcpm/tcpci.c | 11 +++++++++++ include/linux/usb/tcpci.h | 7 +++++++ 2 files changed, 18 insertions(+) (limited to 'include/linux') diff --git a/drivers/usb/typec/tcpm/tcpci.c b/drivers/usb/typec/tcpm/tcpci.c index c7796511695d..8da23240afbe 100644 --- a/drivers/usb/typec/tcpm/tcpci.c +++ b/drivers/usb/typec/tcpm/tcpci.c @@ -404,6 +404,14 @@ static void tcpci_frs_sourcing_vbus(struct tcpc_dev *dev) tcpci->data->frs_sourcing_vbus(tcpci, tcpci->data); } +static void tcpci_check_contaminant(struct tcpc_dev *dev) +{ + struct tcpci *tcpci = tcpc_to_tcpci(dev); + + if (tcpci->data->check_contaminant) + tcpci->data->check_contaminant(tcpci, tcpci->data); +} + static int tcpci_set_bist_data(struct tcpc_dev *tcpc, bool enable) { struct tcpci *tcpci = tcpc_to_tcpci(tcpc); @@ -782,6 +790,9 @@ struct tcpci *tcpci_register_port(struct device *dev, struct tcpci_data *data) tcpci->tcpc.frs_sourcing_vbus = tcpci_frs_sourcing_vbus; tcpci->tcpc.set_partner_usb_comm_capable = tcpci_set_partner_usb_comm_capable; + if (tcpci->data->check_contaminant) + tcpci->tcpc.check_contaminant = tcpci_check_contaminant; + if (tcpci->data->auto_discharge_disconnect) { tcpci->tcpc.enable_auto_vbus_discharge = tcpci_enable_auto_vbus_discharge; tcpci->tcpc.set_auto_vbus_discharge_threshold = diff --git a/include/linux/usb/tcpci.h b/include/linux/usb/tcpci.h index 17657451c762..85e95a3251d3 100644 --- a/include/linux/usb/tcpci.h +++ b/include/linux/usb/tcpci.h @@ -188,6 +188,12 @@ struct tcpci; * Optional; The USB Communications Capable bit indicates if port * partner is capable of communication over the USB data lines * (e.g. D+/- or SS Tx/Rx). Called to notify the status of the bit. + * @check_contaminant: + * Optional; The callback is invoked when chiplevel drivers indicated + * that the USB port needs to be checked for contaminant presence. + * Chip level drivers are expected to check for contaminant and call + * tcpm_clean_port when the port is clean to put the port back into + * toggling state. */ struct tcpci_data { struct regmap *regmap; @@ -204,6 +210,7 @@ struct tcpci_data { void (*frs_sourcing_vbus)(struct tcpci *tcpci, struct tcpci_data *data); void (*set_partner_usb_comm_capable)(struct tcpci *tcpci, struct tcpci_data *data, bool capable); + void (*check_contaminant)(struct tcpci *tcpci, struct tcpci_data *data); }; struct tcpci *tcpci_register_port(struct device *dev, struct tcpci_data *data); -- cgit v1.2.3 From 5c5a7680e67ba6fbbb5f4d79fa41485450c1985c Mon Sep 17 00:00:00 2001 From: Uwe Kleine-König Date: Fri, 9 Dec 2022 16:09:14 +0100 Subject: platform: Provide a remove callback that returns no value struct platform_driver::remove returning an integer made driver authors expect that returning an error code was proper error handling. However the driver core ignores the error and continues to remove the device because there is nothing the core could do anyhow and reentering the remove callback again is only calling for trouble. So this is an source for errors typically yielding resource leaks in the error path. As there are too many platform drivers to neatly convert them all to return void in a single go, do it in several steps after this patch: a) Convert all drivers to implement .remove_new() returning void instead of .remove() returning int; b) Change struct platform_driver::remove() to return void and so make it identical to .remove_new(); c) Change all drivers back to .remove() now with the better prototype; d) drop struct platform_driver::remove_new(). While this touches all drivers eventually twice, steps a) and c) can be done one driver after another and so reduces coordination efforts immensely and simplifies review. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20221209150914.3557650-1-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/base/platform.c | 4 +++- include/linux/platform_device.h | 11 +++++++++++ 2 files changed, 14 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/base/platform.c b/drivers/base/platform.c index 968f3d71eeab..a4938d1c8fe1 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -1416,7 +1416,9 @@ static void platform_remove(struct device *_dev) struct platform_driver *drv = to_platform_driver(_dev->driver); struct platform_device *dev = to_platform_device(_dev); - if (drv->remove) { + if (drv->remove_new) { + drv->remove_new(dev); + } else if (drv->remove) { int ret = drv->remove(dev); if (ret) diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index b0d5a253156e..b845fd83f429 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -207,7 +207,18 @@ extern void platform_device_put(struct platform_device *pdev); struct platform_driver { int (*probe)(struct platform_device *); + + /* + * Traditionally the remove callback returned an int which however is + * ignored by the driver core. This led to wrong expectations by driver + * authors who thought returning an error code was a valid error + * handling strategy. To convert to a callback returning void, new + * drivers should implement .remove_new() until the conversion it done + * that eventually makes .remove() return void. + */ int (*remove)(struct platform_device *); + void (*remove_new)(struct platform_device *); + void (*shutdown)(struct platform_device *); int (*suspend)(struct platform_device *, pm_message_t state); int (*resume)(struct platform_device *); -- cgit v1.2.3 From 3dbdd92014a410778de8406e9e3253e353f51c2b Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 28 Dec 2022 11:49:22 +0200 Subject: software node: Remove unused APIs There are no more users of software_node_register_nodes() and software_node_unregister_nodes(). Remove them. Signed-off-by: Andy Shevchenko Acked-by: Greg Kroah-Hartman Acked-by: Sakari Ailus Tested-by: Daniel Scally Acked-by: Heikki Krogerus Link: https://lore.kernel.org/r/20221228094922.84119-5-andriy.shevchenko@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/base/swnode.c | 61 ------------------------------------------------ include/linux/property.h | 3 --- 2 files changed, 64 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/swnode.c b/drivers/base/swnode.c index 0a482212c7e8..da3c1c2cb9a8 100644 --- a/drivers/base/swnode.c +++ b/drivers/base/swnode.c @@ -819,67 +819,6 @@ swnode_register(const struct software_node *node, struct swnode *parent, return &swnode->fwnode; } -/** - * software_node_register_nodes - Register an array of software nodes - * @nodes: Zero terminated array of software nodes to be registered - * - * Register multiple software nodes at once. If any node in the array - * has its .parent pointer set (which can only be to another software_node), - * then its parent **must** have been registered before it is; either outside - * of this function or by ordering the array such that parent comes before - * child. - */ -int software_node_register_nodes(const struct software_node *nodes) -{ - int ret; - int i; - - for (i = 0; nodes[i].name; i++) { - const struct software_node *parent = nodes[i].parent; - - if (parent && !software_node_to_swnode(parent)) { - ret = -EINVAL; - goto err_unregister_nodes; - } - - ret = software_node_register(&nodes[i]); - if (ret) - goto err_unregister_nodes; - } - - return 0; - -err_unregister_nodes: - software_node_unregister_nodes(nodes); - return ret; -} -EXPORT_SYMBOL_GPL(software_node_register_nodes); - -/** - * software_node_unregister_nodes - Unregister an array of software nodes - * @nodes: Zero terminated array of software nodes to be unregistered - * - * Unregister multiple software nodes at once. If parent pointers are set up - * in any of the software nodes then the array **must** be ordered such that - * parents come before their children. - * - * NOTE: If you are uncertain whether the array is ordered such that - * parents will be unregistered before their children, it is wiser to - * remove the nodes individually, in the correct order (child before - * parent). - */ -void software_node_unregister_nodes(const struct software_node *nodes) -{ - unsigned int i = 0; - - while (nodes[i].name) - i++; - - while (i--) - software_node_unregister(&nodes[i]); -} -EXPORT_SYMBOL_GPL(software_node_unregister_nodes); - /** * software_node_register_node_group - Register a group of software nodes * @node_group: NULL terminated array of software node pointers to be registered diff --git a/include/linux/property.h b/include/linux/property.h index 37179e3abad5..1ffd4f9bb67b 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -486,9 +486,6 @@ const struct software_node * software_node_find_by_name(const struct software_node *parent, const char *name); -int software_node_register_nodes(const struct software_node *nodes); -void software_node_unregister_nodes(const struct software_node *nodes); - int software_node_register_node_group(const struct software_node **node_group); void software_node_unregister_node_group(const struct software_node **node_group); -- cgit v1.2.3 From c3719bd9eeb2edf84bd263d662e36ca0ba262a23 Mon Sep 17 00:00:00 2001 From: Pierre Gondois Date: Wed, 4 Jan 2023 19:30:24 +0100 Subject: cacheinfo: Use RISC-V's init_cache_level() as generic OF implementation RISC-V's implementation of init_of_cache_level() is following the Devicetree Specification v0.3 regarding caches, cf.: - s3.7.3 'Internal (L1) Cache Properties' - s3.8 'Multi-level and Shared Cache Nodes' Allow reusing the implementation by moving it. Also make 'levels', 'leaves' and 'level' unsigned int. Signed-off-by: Pierre Gondois Reviewed-by: Conor Dooley Acked-by: Palmer Dabbelt Link: https://lore.kernel.org/r/20230104183033.755668-2-pierre.gondois@arm.com Signed-off-by: Sudeep Holla --- arch/riscv/kernel/cacheinfo.c | 39 +------------------------------------- drivers/base/cacheinfo.c | 44 +++++++++++++++++++++++++++++++++++++++++++ include/linux/cacheinfo.h | 1 + 3 files changed, 46 insertions(+), 38 deletions(-) (limited to 'include/linux') diff --git a/arch/riscv/kernel/cacheinfo.c b/arch/riscv/kernel/cacheinfo.c index 90deabfe63ea..440a3df5944c 100644 --- a/arch/riscv/kernel/cacheinfo.c +++ b/arch/riscv/kernel/cacheinfo.c @@ -115,44 +115,7 @@ static void fill_cacheinfo(struct cacheinfo **this_leaf, int init_cache_level(unsigned int cpu) { - struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu); - struct device_node *np = of_cpu_device_node_get(cpu); - struct device_node *prev = NULL; - int levels = 0, leaves = 0, level; - - if (of_property_read_bool(np, "cache-size")) - ++leaves; - if (of_property_read_bool(np, "i-cache-size")) - ++leaves; - if (of_property_read_bool(np, "d-cache-size")) - ++leaves; - if (leaves > 0) - levels = 1; - - prev = np; - while ((np = of_find_next_cache_node(np))) { - of_node_put(prev); - prev = np; - if (!of_device_is_compatible(np, "cache")) - break; - if (of_property_read_u32(np, "cache-level", &level)) - break; - if (level <= levels) - break; - if (of_property_read_bool(np, "cache-size")) - ++leaves; - if (of_property_read_bool(np, "i-cache-size")) - ++leaves; - if (of_property_read_bool(np, "d-cache-size")) - ++leaves; - levels = level; - } - - of_node_put(np); - this_cpu_ci->num_levels = levels; - this_cpu_ci->num_leaves = leaves; - - return 0; + return init_of_cache_level(cpu); } int populate_cache_leaves(unsigned int cpu) diff --git a/drivers/base/cacheinfo.c b/drivers/base/cacheinfo.c index 950b22cdb5f7..b60788aacfef 100644 --- a/drivers/base/cacheinfo.c +++ b/drivers/base/cacheinfo.c @@ -229,8 +229,52 @@ static int cache_setup_of_node(unsigned int cpu) return 0; } + +int init_of_cache_level(unsigned int cpu) +{ + struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu); + struct device_node *np = of_cpu_device_node_get(cpu); + struct device_node *prev = NULL; + unsigned int levels = 0, leaves = 0, level; + + if (of_property_read_bool(np, "cache-size")) + ++leaves; + if (of_property_read_bool(np, "i-cache-size")) + ++leaves; + if (of_property_read_bool(np, "d-cache-size")) + ++leaves; + if (leaves > 0) + levels = 1; + + prev = np; + while ((np = of_find_next_cache_node(np))) { + of_node_put(prev); + prev = np; + if (!of_device_is_compatible(np, "cache")) + break; + if (of_property_read_u32(np, "cache-level", &level)) + break; + if (level <= levels) + break; + if (of_property_read_bool(np, "cache-size")) + ++leaves; + if (of_property_read_bool(np, "i-cache-size")) + ++leaves; + if (of_property_read_bool(np, "d-cache-size")) + ++leaves; + levels = level; + } + + of_node_put(np); + this_cpu_ci->num_levels = levels; + this_cpu_ci->num_leaves = leaves; + + return 0; +} + #else static inline int cache_setup_of_node(unsigned int cpu) { return 0; } +int init_of_cache_level(unsigned int cpu) { return 0; } #endif int __weak cache_setup_acpi(unsigned int cpu) diff --git a/include/linux/cacheinfo.h b/include/linux/cacheinfo.h index 00b7a6ae8617..ff0328f3fbb0 100644 --- a/include/linux/cacheinfo.h +++ b/include/linux/cacheinfo.h @@ -80,6 +80,7 @@ struct cpu_cacheinfo { struct cpu_cacheinfo *get_cpu_cacheinfo(unsigned int cpu); int init_cache_level(unsigned int cpu); +int init_of_cache_level(unsigned int cpu); int populate_cache_leaves(unsigned int cpu); int cache_setup_acpi(unsigned int cpu); bool last_level_cache_is_valid(unsigned int cpu); -- cgit v1.2.3 From 504450d05c545a839b22542c72ddc388740462ac Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 11 Jan 2023 10:23:30 +0100 Subject: driver core: bus.h: document bus notifiers better The bus notifier values are not documented all that well, so clean this up and make a real enumerated type for them and document them much better. When doing this, remove the hex values and just rely on the enumerated type instead as that is all that is needed. Reviewed-by: Randy Dunlap Reviewed-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20230111092331.3946745-1-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/device/bus.h | 42 ++++++++++++++++++++++++++++-------------- 1 file changed, 28 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h index d529f644e92b..7b4a48b5159b 100644 --- a/include/linux/device/bus.h +++ b/include/linux/device/bus.h @@ -257,21 +257,35 @@ extern int bus_register_notifier(struct bus_type *bus, extern int bus_unregister_notifier(struct bus_type *bus, struct notifier_block *nb); -/* All 4 notifers below get called with the target struct device * - * as an argument. Note that those functions are likely to be called - * with the device lock held in the core, so be careful. +/** + * enum bus_notifier_event - Bus Notifier events that have happened + * @BUS_NOTIFY_ADD_DEVICE: device is added to this bus + * @BUS_NOTIFY_DEL_DEVICE: device is about to be removed from this bus + * @BUS_NOTIFY_REMOVED_DEVICE: device is successfully removed from this bus + * @BUS_NOTIFY_BIND_DRIVER: a driver is about to be bound to this device on this bus + * @BUS_NOTIFY_BOUND_DRIVER: a driver is successfully bound to this device on this bus + * @BUS_NOTIFY_UNBIND_DRIVER: a driver is about to be unbound from this device on this bus + * @BUS_NOTIFY_UNBOUND_DRIVER: a driver is successfully unbound from this device on this bus + * @BUS_NOTIFY_DRIVER_NOT_BOUND: a driver failed to be bound to this device on this bus + * + * These are the value passed to a bus notifier when a specific event happens. + * + * Note that bus notifiers are likely to be called with the device lock already + * held by the driver core, so be careful in any notifier callback as to what + * you do with the device structure. + * + * All bus notifiers are called with the target struct device * as an argument. */ -#define BUS_NOTIFY_ADD_DEVICE 0x00000001 /* device added */ -#define BUS_NOTIFY_DEL_DEVICE 0x00000002 /* device to be removed */ -#define BUS_NOTIFY_REMOVED_DEVICE 0x00000003 /* device removed */ -#define BUS_NOTIFY_BIND_DRIVER 0x00000004 /* driver about to be - bound */ -#define BUS_NOTIFY_BOUND_DRIVER 0x00000005 /* driver bound to device */ -#define BUS_NOTIFY_UNBIND_DRIVER 0x00000006 /* driver about to be - unbound */ -#define BUS_NOTIFY_UNBOUND_DRIVER 0x00000007 /* driver is unbound - from the device */ -#define BUS_NOTIFY_DRIVER_NOT_BOUND 0x00000008 /* driver fails to be bound */ +enum bus_notifier_event { + BUS_NOTIFY_ADD_DEVICE, + BUS_NOTIFY_DEL_DEVICE, + BUS_NOTIFY_REMOVED_DEVICE, + BUS_NOTIFY_BIND_DRIVER, + BUS_NOTIFY_BOUND_DRIVER, + BUS_NOTIFY_UNBIND_DRIVER, + BUS_NOTIFY_UNBOUND_DRIVER, + BUS_NOTIFY_DRIVER_NOT_BOUND, +}; extern struct kset *bus_get_kset(struct bus_type *bus); -- cgit v1.2.3 From bd500361a937c03a3da57178287ce543c8f3681b Mon Sep 17 00:00:00 2001 From: Pierre Gondois Date: Wed, 4 Jan 2023 19:30:28 +0100 Subject: ACPI: PPTT: Update acpi_find_last_cache_level() to acpi_get_cache_info() acpi_find_last_cache_level() allows to find the last level of cache for a given CPU. The function is only called on arm64 ACPI based platforms to check for cache information that would be missing in the CLIDR_EL1 register. To allow populating (struct cpu_cacheinfo).num_leaves by only parsing a PPTT, update acpi_find_last_cache_level() to get the 'split_levels', i.e. the number of cache levels being split in data/instruction caches. It is assumed that there will not be data/instruction caches above a unified cache. If a split level consist of one data cache and no instruction cache (or opposite), then the missing cache will still be populated by default with minimal cache information, and maximal cpumask (all non-existing caches have the same fw_token). Suggested-by: Jeremy Linton Signed-off-by: Pierre Gondois Reviewed-by: Jeremy Linton Acked-by: Rafael J. Wysocki Acked-by: Palmer Dabbelt Link: https://lore.kernel.org/r/20230104183033.755668-6-pierre.gondois@arm.com Signed-off-by: Sudeep Holla --- arch/arm64/kernel/cacheinfo.c | 11 ++++--- drivers/acpi/pptt.c | 76 ++++++++++++++++++++++++++++--------------- include/linux/cacheinfo.h | 9 +++-- 3 files changed, 63 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/kernel/cacheinfo.c b/arch/arm64/kernel/cacheinfo.c index 97c42be71338..36c3b07cdf2d 100644 --- a/arch/arm64/kernel/cacheinfo.c +++ b/arch/arm64/kernel/cacheinfo.c @@ -46,7 +46,7 @@ static void ci_leaf_init(struct cacheinfo *this_leaf, int init_cache_level(unsigned int cpu) { unsigned int ctype, level, leaves; - int fw_level; + int fw_level, ret; struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu); for (level = 1, leaves = 0; level <= MAX_CACHE_LEVEL; level++) { @@ -59,10 +59,13 @@ int init_cache_level(unsigned int cpu) leaves += (ctype == CACHE_TYPE_SEPARATE) ? 2 : 1; } - if (acpi_disabled) + if (acpi_disabled) { fw_level = of_find_last_cache_level(cpu); - else - fw_level = acpi_find_last_cache_level(cpu); + } else { + ret = acpi_get_cache_info(cpu, &fw_level, NULL); + if (ret < 0) + return ret; + } if (fw_level < 0) return fw_level; diff --git a/drivers/acpi/pptt.c b/drivers/acpi/pptt.c index 97c1d33822d1..10975bb603fb 100644 --- a/drivers/acpi/pptt.c +++ b/drivers/acpi/pptt.c @@ -81,6 +81,7 @@ static inline bool acpi_pptt_match_type(int table_type, int type) * acpi_pptt_walk_cache() - Attempt to find the requested acpi_pptt_cache * @table_hdr: Pointer to the head of the PPTT table * @local_level: passed res reflects this cache level + * @split_levels: Number of split cache levels (data/instruction). * @res: cache resource in the PPTT we want to walk * @found: returns a pointer to the requested level if found * @level: the requested cache level @@ -100,6 +101,7 @@ static inline bool acpi_pptt_match_type(int table_type, int type) */ static unsigned int acpi_pptt_walk_cache(struct acpi_table_header *table_hdr, unsigned int local_level, + unsigned int *split_levels, struct acpi_subtable_header *res, struct acpi_pptt_cache **found, unsigned int level, int type) @@ -113,8 +115,17 @@ static unsigned int acpi_pptt_walk_cache(struct acpi_table_header *table_hdr, while (cache) { local_level++; + if (!(cache->flags & ACPI_PPTT_CACHE_TYPE_VALID)) { + cache = fetch_pptt_cache(table_hdr, cache->next_level_of_cache); + continue; + } + + if (split_levels && + (acpi_pptt_match_type(cache->attributes, ACPI_PPTT_CACHE_TYPE_DATA) || + acpi_pptt_match_type(cache->attributes, ACPI_PPTT_CACHE_TYPE_INSTR))) + *split_levels = local_level; + if (local_level == level && - cache->flags & ACPI_PPTT_CACHE_TYPE_VALID && acpi_pptt_match_type(cache->attributes, type)) { if (*found != NULL && cache != *found) pr_warn("Found duplicate cache level/type unable to determine uniqueness\n"); @@ -135,8 +146,8 @@ static unsigned int acpi_pptt_walk_cache(struct acpi_table_header *table_hdr, static struct acpi_pptt_cache * acpi_find_cache_level(struct acpi_table_header *table_hdr, struct acpi_pptt_processor *cpu_node, - unsigned int *starting_level, unsigned int level, - int type) + unsigned int *starting_level, unsigned int *split_levels, + unsigned int level, int type) { struct acpi_subtable_header *res; unsigned int number_of_levels = *starting_level; @@ -149,7 +160,8 @@ acpi_find_cache_level(struct acpi_table_header *table_hdr, resource++; local_level = acpi_pptt_walk_cache(table_hdr, *starting_level, - res, &ret, level, type); + split_levels, res, &ret, + level, type); /* * we are looking for the max depth. Since its potentially * possible for a given node to have resources with differing @@ -165,29 +177,29 @@ acpi_find_cache_level(struct acpi_table_header *table_hdr, } /** - * acpi_count_levels() - Given a PPTT table, and a CPU node, count the caches + * acpi_count_levels() - Given a PPTT table, and a CPU node, count the cache + * levels and split cache levels (data/instruction). * @table_hdr: Pointer to the head of the PPTT table * @cpu_node: processor node we wish to count caches for + * @levels: Number of levels if success. + * @split_levels: Number of split cache levels (data/instruction) if + * success. Can by NULL. * * Given a processor node containing a processing unit, walk into it and count * how many levels exist solely for it, and then walk up each level until we hit * the root node (ignore the package level because it may be possible to have - * caches that exist across packages). Count the number of cache levels that - * exist at each level on the way up. - * - * Return: Total number of levels found. + * caches that exist across packages). Count the number of cache levels and + * split cache levels (data/instruction) that exist at each level on the way + * up. */ -static int acpi_count_levels(struct acpi_table_header *table_hdr, - struct acpi_pptt_processor *cpu_node) +static void acpi_count_levels(struct acpi_table_header *table_hdr, + struct acpi_pptt_processor *cpu_node, + unsigned int *levels, unsigned int *split_levels) { - int total_levels = 0; - do { - acpi_find_cache_level(table_hdr, cpu_node, &total_levels, 0, 0); + acpi_find_cache_level(table_hdr, cpu_node, levels, split_levels, 0, 0); cpu_node = fetch_pptt_node(table_hdr, cpu_node->parent); } while (cpu_node); - - return total_levels; } /** @@ -321,7 +333,7 @@ static struct acpi_pptt_cache *acpi_find_cache_node(struct acpi_table_header *ta while (cpu_node && !found) { found = acpi_find_cache_level(table_hdr, cpu_node, - &total_levels, level, acpi_type); + &total_levels, NULL, level, acpi_type); *node = cpu_node; cpu_node = fetch_pptt_node(table_hdr, cpu_node->parent); } @@ -589,36 +601,48 @@ static int check_acpi_cpu_flag(unsigned int cpu, int rev, u32 flag) } /** - * acpi_find_last_cache_level() - Determines the number of cache levels for a PE + * acpi_get_cache_info() - Determine the number of cache levels and + * split cache levels (data/instruction) and for a PE. * @cpu: Kernel logical CPU number + * @levels: Number of levels if success. + * @split_levels: Number of levels being split (i.e. data/instruction) + * if success. Can by NULL. * * Given a logical CPU number, returns the number of levels of cache represented * in the PPTT. Errors caused by lack of a PPTT table, or otherwise, return 0 * indicating we didn't find any cache levels. * - * Return: Cache levels visible to this core. + * Return: -ENOENT if no PPTT table or no PPTT processor struct found. + * 0 on success. */ -int acpi_find_last_cache_level(unsigned int cpu) +int acpi_get_cache_info(unsigned int cpu, unsigned int *levels, + unsigned int *split_levels) { struct acpi_pptt_processor *cpu_node; struct acpi_table_header *table; - int number_of_levels = 0; u32 acpi_cpu_id; + *levels = 0; + if (split_levels) + *split_levels = 0; + table = acpi_get_pptt(); if (!table) return -ENOENT; - pr_debug("Cache Setup find last level CPU=%d\n", cpu); + pr_debug("Cache Setup: find cache levels for CPU=%d\n", cpu); acpi_cpu_id = get_acpi_id_for_cpu(cpu); cpu_node = acpi_find_processor_node(table, acpi_cpu_id); - if (cpu_node) - number_of_levels = acpi_count_levels(table, cpu_node); + if (!cpu_node) + return -ENOENT; - pr_debug("Cache Setup find last level level=%d\n", number_of_levels); + acpi_count_levels(table, cpu_node, levels, split_levels); - return number_of_levels; + pr_debug("Cache Setup: last_level=%d split_levels=%d\n", + *levels, split_levels ? *split_levels : -1); + + return 0; } /** diff --git a/include/linux/cacheinfo.h b/include/linux/cacheinfo.h index ff0328f3fbb0..00d8e7f9d1c6 100644 --- a/include/linux/cacheinfo.h +++ b/include/linux/cacheinfo.h @@ -88,19 +88,22 @@ bool last_level_cache_is_shared(unsigned int cpu_x, unsigned int cpu_y); int detect_cache_attributes(unsigned int cpu); #ifndef CONFIG_ACPI_PPTT /* - * acpi_find_last_cache_level is only called on ACPI enabled + * acpi_get_cache_info() is only called on ACPI enabled * platforms using the PPTT for topology. This means that if * the platform supports other firmware configuration methods * we need to stub out the call when ACPI is disabled. * ACPI enabled platforms not using PPTT won't be making calls * to this function so we need not worry about them. */ -static inline int acpi_find_last_cache_level(unsigned int cpu) +static inline +int acpi_get_cache_info(unsigned int cpu, + unsigned int *levels, unsigned int *split_levels) { return 0; } #else -int acpi_find_last_cache_level(unsigned int cpu); +int acpi_get_cache_info(unsigned int cpu, + unsigned int *levels, unsigned int *split_levels); #endif const struct attribute_group *cache_get_priv_group(struct cacheinfo *this_leaf); -- cgit v1.2.3 From 5944ce092b97caed5d86d961e963b883b5c44ee2 Mon Sep 17 00:00:00 2001 From: Pierre Gondois Date: Wed, 4 Jan 2023 19:30:29 +0100 Subject: arch_topology: Build cacheinfo from primary CPU commit 3fcbf1c77d08 ("arch_topology: Fix cache attributes detection in the CPU hotplug path") adds a call to detect_cache_attributes() to populate the cacheinfo before updating the siblings mask. detect_cache_attributes() allocates memory and can take the PPTT mutex (on ACPI platforms). On PREEMPT_RT kernels, on secondary CPUs, this triggers a: 'BUG: sleeping function called from invalid context' [1] as the code is executed with preemption and interrupts disabled. The primary CPU was previously storing the cache information using the now removed (struct cpu_topology).llc_id: commit 5b8dc787ce4a ("arch_topology: Drop LLC identifier stash from the CPU topology") allocate_cache_info() tries to build the cacheinfo from the primary CPU prior secondary CPUs boot, if the DT/ACPI description contains cache information. If allocate_cache_info() fails, then fallback to the current state for the cacheinfo allocation. [1] will be triggered in such case. When unplugging a CPU, the cacheinfo memory cannot be freed. If it was, then the memory would be allocated early by the re-plugged CPU and would trigger [1]. Note that populate_cache_leaves() might be called multiple times due to populate_leaves being moved up. This is required since detect_cache_attributes() might be called with per_cpu_cacheinfo(cpu) being allocated but not populated. [1]: | BUG: sleeping function called from invalid context at kernel/locking/spinlock_rt.c:46 | in_atomic(): 1, irqs_disabled(): 128, non_block: 0, pid: 0, name: swapper/111 | preempt_count: 1, expected: 0 | RCU nest depth: 1, expected: 1 | 3 locks held by swapper/111/0: | #0: (&pcp->lock){+.+.}-{3:3}, at: get_page_from_freelist+0x218/0x12c8 | #1: (rcu_read_lock){....}-{1:3}, at: rt_spin_trylock+0x48/0xf0 | #2: (&zone->lock){+.+.}-{3:3}, at: rmqueue_bulk+0x64/0xa80 | irq event stamp: 0 | hardirqs last enabled at (0): 0x0 | hardirqs last disabled at (0): copy_process+0x5dc/0x1ab8 | softirqs last enabled at (0): copy_process+0x5dc/0x1ab8 | softirqs last disabled at (0): 0x0 | Preemption disabled at: | migrate_enable+0x30/0x130 | CPU: 111 PID: 0 Comm: swapper/111 Tainted: G W 6.0.0-rc4-rt6-[...] | Call trace: | __kmalloc+0xbc/0x1e8 | detect_cache_attributes+0x2d4/0x5f0 | update_siblings_masks+0x30/0x368 | store_cpu_topology+0x78/0xb8 | secondary_start_kernel+0xd0/0x198 | __secondary_switched+0xb0/0xb4 Signed-off-by: Pierre Gondois Reviewed-by: Sudeep Holla Acked-by: Palmer Dabbelt Link: https://lore.kernel.org/r/20230104183033.755668-7-pierre.gondois@arm.com Signed-off-by: Sudeep Holla --- arch/riscv/kernel/cacheinfo.c | 5 --- drivers/base/arch_topology.c | 12 ++++++-- drivers/base/cacheinfo.c | 71 ++++++++++++++++++++++++++++++++----------- include/linux/cacheinfo.h | 1 + 4 files changed, 65 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/arch/riscv/kernel/cacheinfo.c b/arch/riscv/kernel/cacheinfo.c index 440a3df5944c..3a13113f1b29 100644 --- a/arch/riscv/kernel/cacheinfo.c +++ b/arch/riscv/kernel/cacheinfo.c @@ -113,11 +113,6 @@ static void fill_cacheinfo(struct cacheinfo **this_leaf, } } -int init_cache_level(unsigned int cpu) -{ - return init_of_cache_level(cpu); -} - int populate_cache_leaves(unsigned int cpu) { struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu); diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c index e7d6e6657ffa..b1c1dd38ab01 100644 --- a/drivers/base/arch_topology.c +++ b/drivers/base/arch_topology.c @@ -736,7 +736,7 @@ void update_siblings_masks(unsigned int cpuid) ret = detect_cache_attributes(cpuid); if (ret && ret != -ENOENT) - pr_info("Early cacheinfo failed, ret = %d\n", ret); + pr_info("Early cacheinfo allocation failed, ret = %d\n", ret); /* update core and thread sibling masks */ for_each_online_cpu(cpu) { @@ -825,7 +825,7 @@ __weak int __init parse_acpi_topology(void) #if defined(CONFIG_ARM64) || defined(CONFIG_RISCV) void __init init_cpu_topology(void) { - int ret; + int cpu, ret; reset_cpu_topology(); ret = parse_acpi_topology(); @@ -840,6 +840,14 @@ void __init init_cpu_topology(void) reset_cpu_topology(); return; } + + for_each_possible_cpu(cpu) { + ret = fetch_cache_info(cpu); + if (ret) { + pr_err("Early cacheinfo failed, ret = %d\n", ret); + break; + } + } } void store_cpu_topology(unsigned int cpuid) diff --git a/drivers/base/cacheinfo.c b/drivers/base/cacheinfo.c index 9ad4403f2dab..c9bcecf76c7f 100644 --- a/drivers/base/cacheinfo.c +++ b/drivers/base/cacheinfo.c @@ -389,10 +389,6 @@ static void free_cache_attributes(unsigned int cpu) return; cache_shared_cpu_map_remove(cpu); - - kfree(per_cpu_cacheinfo(cpu)); - per_cpu_cacheinfo(cpu) = NULL; - cache_leaves(cpu) = 0; } int __weak init_cache_level(unsigned int cpu) @@ -405,29 +401,71 @@ int __weak populate_cache_leaves(unsigned int cpu) return -ENOENT; } +static inline +int allocate_cache_info(int cpu) +{ + per_cpu_cacheinfo(cpu) = kcalloc(cache_leaves(cpu), + sizeof(struct cacheinfo), GFP_ATOMIC); + if (!per_cpu_cacheinfo(cpu)) { + cache_leaves(cpu) = 0; + return -ENOMEM; + } + + return 0; +} + +int fetch_cache_info(unsigned int cpu) +{ + struct cpu_cacheinfo *this_cpu_ci; + unsigned int levels, split_levels; + int ret; + + if (acpi_disabled) { + ret = init_of_cache_level(cpu); + if (ret < 0) + return ret; + } else { + ret = acpi_get_cache_info(cpu, &levels, &split_levels); + if (ret < 0) + return ret; + + this_cpu_ci = get_cpu_cacheinfo(cpu); + this_cpu_ci->num_levels = levels; + /* + * This assumes that: + * - there cannot be any split caches (data/instruction) + * above a unified cache + * - data/instruction caches come by pair + */ + this_cpu_ci->num_leaves = levels + split_levels; + } + if (!cache_leaves(cpu)) + return -ENOENT; + + return allocate_cache_info(cpu); +} + int detect_cache_attributes(unsigned int cpu) { int ret; - /* Since early detection of the cacheinfo is allowed via this - * function and this also gets called as CPU hotplug callbacks via - * cacheinfo_cpu_online, the initialisation can be skipped and only - * CPU maps can be updated as the CPU online status would be update - * if called via cacheinfo_cpu_online path. + /* Since early initialization/allocation of the cacheinfo is allowed + * via fetch_cache_info() and this also gets called as CPU hotplug + * callbacks via cacheinfo_cpu_online, the init/alloc can be skipped + * as it will happen only once (the cacheinfo memory is never freed). + * Just populate the cacheinfo. */ if (per_cpu_cacheinfo(cpu)) - goto update_cpu_map; + goto populate_leaves; if (init_cache_level(cpu) || !cache_leaves(cpu)) return -ENOENT; - per_cpu_cacheinfo(cpu) = kcalloc(cache_leaves(cpu), - sizeof(struct cacheinfo), GFP_ATOMIC); - if (per_cpu_cacheinfo(cpu) == NULL) { - cache_leaves(cpu) = 0; - return -ENOMEM; - } + ret = allocate_cache_info(cpu); + if (ret) + return ret; +populate_leaves: /* * populate_cache_leaves() may completely setup the cache leaves and * shared_cpu_map or it may leave it partially setup. @@ -436,7 +474,6 @@ int detect_cache_attributes(unsigned int cpu) if (ret) goto free_ci; -update_cpu_map: /* * For systems using DT for cache hierarchy, fw_token * and shared_cpu_map will be set up here only if they are diff --git a/include/linux/cacheinfo.h b/include/linux/cacheinfo.h index 00d8e7f9d1c6..dfef57077cd0 100644 --- a/include/linux/cacheinfo.h +++ b/include/linux/cacheinfo.h @@ -85,6 +85,7 @@ int populate_cache_leaves(unsigned int cpu); int cache_setup_acpi(unsigned int cpu); bool last_level_cache_is_valid(unsigned int cpu); bool last_level_cache_is_shared(unsigned int cpu_x, unsigned int cpu_y); +int fetch_cache_info(unsigned int cpu); int detect_cache_attributes(unsigned int cpu); #ifndef CONFIG_ACPI_PPTT /* -- cgit v1.2.3 From 80baab88bb93eeaa133b426d24dfc0775a8cf824 Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Sun, 15 Jan 2023 08:45:51 -0800 Subject: iomap/gfs2: Unlock and put folio in page_done handler When an iomap defines a ->page_done() handler in its page_ops, delegate unlocking the folio and putting the folio reference to that handler. This allows to fix a race between journaled data writes and folio writeback in gfs2: before this change, gfs2_iomap_page_done() was called after unlocking the folio, so writeback could start writing back the folio's buffers before they could be marked for writing to the journal. Also, try_to_free_buffers() could free the buffers before gfs2_iomap_page_done() was done adding the buffers to the current current transaction. With this change, gfs2_iomap_page_done() adds the buffers to the current transaction while the folio is still locked, so the problems described above can no longer occur. The only current user of ->page_done() is gfs2, so other filesystems are not affected. To catch out any out-of-tree users, switch from a page to a folio in ->page_done(). Signed-off-by: Andreas Gruenbacher Reviewed-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Signed-off-by: Darrick J. Wong --- fs/gfs2/bmap.c | 15 ++++++++++++--- fs/iomap/buffered-io.c | 8 ++++---- include/linux/iomap.h | 7 ++++--- 3 files changed, 20 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index e7537fd305dd..46206286ad42 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -968,14 +968,23 @@ static int gfs2_iomap_page_prepare(struct inode *inode, loff_t pos, } static void gfs2_iomap_page_done(struct inode *inode, loff_t pos, - unsigned copied, struct page *page) + unsigned copied, struct folio *folio) { struct gfs2_trans *tr = current->journal_info; struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_sbd *sdp = GFS2_SB(inode); - if (page && !gfs2_is_stuffed(ip)) - gfs2_page_add_databufs(ip, page, offset_in_page(pos), copied); + if (!folio) { + gfs2_trans_end(sdp); + return; + } + + if (!gfs2_is_stuffed(ip)) + gfs2_page_add_databufs(ip, &folio->page, offset_in_page(pos), + copied); + + folio_unlock(folio); + folio_put(folio); if (tr->tr_num_buf_new) __mark_inode_dirty(inode, I_DIRTY_DATASYNC); diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index c045689b6af8..a9082078e4ed 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -580,12 +580,12 @@ static void __iomap_put_folio(struct iomap_iter *iter, loff_t pos, size_t ret, { const struct iomap_page_ops *page_ops = iter->iomap.page_ops; - if (folio) + if (page_ops && page_ops->page_done) { + page_ops->page_done(iter->inode, pos, ret, folio); + } else if (folio) { folio_unlock(folio); - if (page_ops && page_ops->page_done) - page_ops->page_done(iter->inode, pos, ret, &folio->page); - if (folio) folio_put(folio); + } } static int iomap_write_begin_inline(const struct iomap_iter *iter, diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 0983dfc9a203..743e2a909162 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -131,13 +131,14 @@ static inline bool iomap_inline_data_valid(const struct iomap *iomap) * associated with them. * * When page_prepare succeeds, page_done will always be called to do any - * cleanup work necessary. In that page_done call, @page will be NULL if the - * associated page could not be obtained. + * cleanup work necessary. In that page_done call, @folio will be NULL if the + * associated folio could not be obtained. When folio is not NULL, page_done + * is responsible for unlocking and putting the folio. */ struct iomap_page_ops { int (*page_prepare)(struct inode *inode, loff_t pos, unsigned len); void (*page_done)(struct inode *inode, loff_t pos, unsigned copied, - struct page *page); + struct folio *folio); /* * Check that the cached iomap still maps correctly to the filesystem's -- cgit v1.2.3 From 40405dddd98a9a95585482af46b8e269f5ebe5df Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Sun, 15 Jan 2023 08:45:51 -0800 Subject: iomap: Rename page_done handler to put_folio The ->page_done() handler in struct iomap_page_ops is now somewhat misnamed in that it mainly deals with unlocking and putting a folio, so rename it to ->put_folio(). Signed-off-by: Andreas Gruenbacher Reviewed-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Signed-off-by: Darrick J. Wong --- fs/gfs2/bmap.c | 4 ++-- fs/iomap/buffered-io.c | 4 ++-- include/linux/iomap.h | 12 ++++++------ 3 files changed, 10 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index 46206286ad42..0c041459677b 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -967,7 +967,7 @@ static int gfs2_iomap_page_prepare(struct inode *inode, loff_t pos, return gfs2_trans_begin(sdp, RES_DINODE + blocks, 0); } -static void gfs2_iomap_page_done(struct inode *inode, loff_t pos, +static void gfs2_iomap_put_folio(struct inode *inode, loff_t pos, unsigned copied, struct folio *folio) { struct gfs2_trans *tr = current->journal_info; @@ -994,7 +994,7 @@ static void gfs2_iomap_page_done(struct inode *inode, loff_t pos, static const struct iomap_page_ops gfs2_iomap_page_ops = { .page_prepare = gfs2_iomap_page_prepare, - .page_done = gfs2_iomap_page_done, + .put_folio = gfs2_iomap_put_folio, }; static int gfs2_iomap_begin_write(struct inode *inode, loff_t pos, diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index a9082078e4ed..d4b444e44861 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -580,8 +580,8 @@ static void __iomap_put_folio(struct iomap_iter *iter, loff_t pos, size_t ret, { const struct iomap_page_ops *page_ops = iter->iomap.page_ops; - if (page_ops && page_ops->page_done) { - page_ops->page_done(iter->inode, pos, ret, folio); + if (page_ops && page_ops->put_folio) { + page_ops->put_folio(iter->inode, pos, ret, folio); } else if (folio) { folio_unlock(folio); folio_put(folio); diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 743e2a909162..ecf815b34d51 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -126,18 +126,18 @@ static inline bool iomap_inline_data_valid(const struct iomap *iomap) /* * When a filesystem sets page_ops in an iomap mapping it returns, page_prepare - * and page_done will be called for each page written to. This only applies to - * buffered writes as unbuffered writes will not typically have pages + * and put_folio will be called for each folio written to. This only applies + * to buffered writes as unbuffered writes will not typically have folios * associated with them. * - * When page_prepare succeeds, page_done will always be called to do any - * cleanup work necessary. In that page_done call, @folio will be NULL if the - * associated folio could not be obtained. When folio is not NULL, page_done + * When page_prepare succeeds, put_folio will always be called to do any + * cleanup work necessary. In that put_folio call, @folio will be NULL if the + * associated folio could not be obtained. When folio is not NULL, put_folio * is responsible for unlocking and putting the folio. */ struct iomap_page_ops { int (*page_prepare)(struct inode *inode, loff_t pos, unsigned len); - void (*page_done)(struct inode *inode, loff_t pos, unsigned copied, + void (*put_folio)(struct inode *inode, loff_t pos, unsigned copied, struct folio *folio); /* -- cgit v1.2.3 From 98321b5139f92a736a426404fb6e23bfb8feb9cc Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Sun, 15 Jan 2023 08:49:04 -0800 Subject: iomap: Add iomap_get_folio helper Add an iomap_get_folio() helper that gets a folio reference based on an iomap iterator and an offset into the address space. Use it in iomap_write_begin(). Signed-off-by: Andreas Gruenbacher Reviewed-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Signed-off-by: Darrick J. Wong --- fs/iomap/buffered-io.c | 39 ++++++++++++++++++++++++++++++--------- include/linux/iomap.h | 1 + 2 files changed, 31 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index d4b444e44861..de4a8e5f721a 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -457,6 +457,33 @@ bool iomap_is_partially_uptodate(struct folio *folio, size_t from, size_t count) } EXPORT_SYMBOL_GPL(iomap_is_partially_uptodate); +/** + * iomap_get_folio - get a folio reference for writing + * @iter: iteration structure + * @pos: start offset of write + * + * Returns a locked reference to the folio at @pos, or an error pointer if the + * folio could not be obtained. + */ +struct folio *iomap_get_folio(struct iomap_iter *iter, loff_t pos) +{ + unsigned fgp = FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE | FGP_NOFS; + struct folio *folio; + + if (iter->flags & IOMAP_NOWAIT) + fgp |= FGP_NOWAIT; + + folio = __filemap_get_folio(iter->inode->i_mapping, pos >> PAGE_SHIFT, + fgp, mapping_gfp_mask(iter->inode->i_mapping)); + if (folio) + return folio; + + if (iter->flags & IOMAP_NOWAIT) + return ERR_PTR(-EAGAIN); + return ERR_PTR(-ENOMEM); +} +EXPORT_SYMBOL_GPL(iomap_get_folio); + bool iomap_release_folio(struct folio *folio, gfp_t gfp_flags) { trace_iomap_release_folio(folio->mapping->host, folio_pos(folio), @@ -603,12 +630,8 @@ static int iomap_write_begin(struct iomap_iter *iter, loff_t pos, const struct iomap_page_ops *page_ops = iter->iomap.page_ops; const struct iomap *srcmap = iomap_iter_srcmap(iter); struct folio *folio; - unsigned fgp = FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE | FGP_NOFS; int status = 0; - if (iter->flags & IOMAP_NOWAIT) - fgp |= FGP_NOWAIT; - BUG_ON(pos + len > iter->iomap.offset + iter->iomap.length); if (srcmap != &iter->iomap) BUG_ON(pos + len > srcmap->offset + srcmap->length); @@ -625,12 +648,10 @@ static int iomap_write_begin(struct iomap_iter *iter, loff_t pos, return status; } - folio = __filemap_get_folio(iter->inode->i_mapping, pos >> PAGE_SHIFT, - fgp, mapping_gfp_mask(iter->inode->i_mapping)); - if (!folio) { - status = (iter->flags & IOMAP_NOWAIT) ? -EAGAIN : -ENOMEM; + folio = iomap_get_folio(iter, pos); + if (IS_ERR(folio)) { __iomap_put_folio(iter, pos, 0, NULL); - return status; + return PTR_ERR(folio); } /* diff --git a/include/linux/iomap.h b/include/linux/iomap.h index ecf815b34d51..188d14e786a4 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -261,6 +261,7 @@ int iomap_file_buffered_write_punch_delalloc(struct inode *inode, int iomap_read_folio(struct folio *folio, const struct iomap_ops *ops); void iomap_readahead(struct readahead_control *, const struct iomap_ops *ops); bool iomap_is_partially_uptodate(struct folio *, size_t from, size_t count); +struct folio *iomap_get_folio(struct iomap_iter *iter, loff_t pos); bool iomap_release_folio(struct folio *folio, gfp_t gfp_flags); void iomap_invalidate_folio(struct folio *folio, size_t offset, size_t len); int iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len, -- cgit v1.2.3 From 9060bc4d3aca6106bbe72891efba391d9d6b86e7 Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Sun, 15 Jan 2023 08:49:12 -0800 Subject: iomap/gfs2: Get page in page_prepare handler Change the iomap ->page_prepare() handler to get and return a locked folio instead of doing that in iomap_write_begin(). This allows to recover from out-of-memory situations in ->page_prepare(), which eliminates the corresponding error handling code in iomap_write_begin(). The ->put_folio() handler now also isn't called with NULL as the folio value anymore. Filesystems are expected to use the iomap_get_folio() helper for getting locked folios in their ->page_prepare() handlers. Signed-off-by: Andreas Gruenbacher Reviewed-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Signed-off-by: Darrick J. Wong --- fs/gfs2/bmap.c | 21 +++++++++++++-------- fs/iomap/buffered-io.c | 17 ++++++----------- include/linux/iomap.h | 9 +++++---- 3 files changed, 24 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index 0c041459677b..41349e09558b 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -956,15 +956,25 @@ hole_found: goto out; } -static int gfs2_iomap_page_prepare(struct inode *inode, loff_t pos, - unsigned len) +static struct folio * +gfs2_iomap_page_prepare(struct iomap_iter *iter, loff_t pos, unsigned len) { + struct inode *inode = iter->inode; unsigned int blockmask = i_blocksize(inode) - 1; struct gfs2_sbd *sdp = GFS2_SB(inode); unsigned int blocks; + struct folio *folio; + int status; blocks = ((pos & blockmask) + len + blockmask) >> inode->i_blkbits; - return gfs2_trans_begin(sdp, RES_DINODE + blocks, 0); + status = gfs2_trans_begin(sdp, RES_DINODE + blocks, 0); + if (status) + return ERR_PTR(status); + + folio = iomap_get_folio(iter, pos); + if (IS_ERR(folio)) + gfs2_trans_end(sdp); + return folio; } static void gfs2_iomap_put_folio(struct inode *inode, loff_t pos, @@ -974,11 +984,6 @@ static void gfs2_iomap_put_folio(struct inode *inode, loff_t pos, struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_sbd *sdp = GFS2_SB(inode); - if (!folio) { - gfs2_trans_end(sdp); - return; - } - if (!gfs2_is_stuffed(ip)) gfs2_page_add_databufs(ip, &folio->page, offset_in_page(pos), copied); diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index de4a8e5f721a..418519dea2ce 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -609,7 +609,7 @@ static void __iomap_put_folio(struct iomap_iter *iter, loff_t pos, size_t ret, if (page_ops && page_ops->put_folio) { page_ops->put_folio(iter->inode, pos, ret, folio); - } else if (folio) { + } else { folio_unlock(folio); folio_put(folio); } @@ -642,17 +642,12 @@ static int iomap_write_begin(struct iomap_iter *iter, loff_t pos, if (!mapping_large_folio_support(iter->inode->i_mapping)) len = min_t(size_t, len, PAGE_SIZE - offset_in_page(pos)); - if (page_ops && page_ops->page_prepare) { - status = page_ops->page_prepare(iter->inode, pos, len); - if (status) - return status; - } - - folio = iomap_get_folio(iter, pos); - if (IS_ERR(folio)) { - __iomap_put_folio(iter, pos, 0, NULL); + if (page_ops && page_ops->page_prepare) + folio = page_ops->page_prepare(iter, pos, len); + else + folio = iomap_get_folio(iter, pos); + if (IS_ERR(folio)) return PTR_ERR(folio); - } /* * Now we have a locked folio, before we do anything with it we need to diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 188d14e786a4..d50501781856 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -13,6 +13,7 @@ struct address_space; struct fiemap_extent_info; struct inode; +struct iomap_iter; struct iomap_dio; struct iomap_writepage_ctx; struct iov_iter; @@ -131,12 +132,12 @@ static inline bool iomap_inline_data_valid(const struct iomap *iomap) * associated with them. * * When page_prepare succeeds, put_folio will always be called to do any - * cleanup work necessary. In that put_folio call, @folio will be NULL if the - * associated folio could not be obtained. When folio is not NULL, put_folio - * is responsible for unlocking and putting the folio. + * cleanup work necessary. put_folio is responsible for unlocking and putting + * @folio. */ struct iomap_page_ops { - int (*page_prepare)(struct inode *inode, loff_t pos, unsigned len); + struct folio *(*page_prepare)(struct iomap_iter *iter, loff_t pos, + unsigned len); void (*put_folio)(struct inode *inode, loff_t pos, unsigned copied, struct folio *folio); -- cgit v1.2.3 From c82abc2394642490da736b1ba78671bbcef81150 Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Sun, 15 Jan 2023 08:50:25 -0800 Subject: iomap: Rename page_prepare handler to get_folio The ->page_prepare() handler in struct iomap_page_ops is now somewhat misnamed, so rename it to ->get_folio(). Signed-off-by: Andreas Gruenbacher Reviewed-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Signed-off-by: Darrick J. Wong --- fs/gfs2/bmap.c | 6 +++--- fs/iomap/buffered-io.c | 4 ++-- include/linux/iomap.h | 6 +++--- 3 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index 41349e09558b..d3adb715ac8c 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -957,7 +957,7 @@ hole_found: } static struct folio * -gfs2_iomap_page_prepare(struct iomap_iter *iter, loff_t pos, unsigned len) +gfs2_iomap_get_folio(struct iomap_iter *iter, loff_t pos, unsigned len) { struct inode *inode = iter->inode; unsigned int blockmask = i_blocksize(inode) - 1; @@ -998,7 +998,7 @@ static void gfs2_iomap_put_folio(struct inode *inode, loff_t pos, } static const struct iomap_page_ops gfs2_iomap_page_ops = { - .page_prepare = gfs2_iomap_page_prepare, + .get_folio = gfs2_iomap_get_folio, .put_folio = gfs2_iomap_put_folio, }; @@ -1291,7 +1291,7 @@ int gfs2_alloc_extent(struct inode *inode, u64 lblock, u64 *dblock, /* * NOTE: Never call gfs2_block_zero_range with an open transaction because it * uses iomap write to perform its actions, which begin their own transactions - * (iomap_begin, page_prepare, etc.) + * (iomap_begin, get_folio, etc.) */ static int gfs2_block_zero_range(struct inode *inode, loff_t from, unsigned int length) diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 666107c3a385..006ddf933948 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -607,8 +607,8 @@ static struct folio *__iomap_get_folio(struct iomap_iter *iter, loff_t pos, { const struct iomap_page_ops *page_ops = iter->iomap.page_ops; - if (page_ops && page_ops->page_prepare) - return page_ops->page_prepare(iter, pos, len); + if (page_ops && page_ops->get_folio) + return page_ops->get_folio(iter, pos, len); else return iomap_get_folio(iter, pos); } diff --git a/include/linux/iomap.h b/include/linux/iomap.h index d50501781856..da226032aedc 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -126,17 +126,17 @@ static inline bool iomap_inline_data_valid(const struct iomap *iomap) } /* - * When a filesystem sets page_ops in an iomap mapping it returns, page_prepare + * When a filesystem sets page_ops in an iomap mapping it returns, get_folio * and put_folio will be called for each folio written to. This only applies * to buffered writes as unbuffered writes will not typically have folios * associated with them. * - * When page_prepare succeeds, put_folio will always be called to do any + * When get_folio succeeds, put_folio will always be called to do any * cleanup work necessary. put_folio is responsible for unlocking and putting * @folio. */ struct iomap_page_ops { - struct folio *(*page_prepare)(struct iomap_iter *iter, loff_t pos, + struct folio *(*get_folio)(struct iomap_iter *iter, loff_t pos, unsigned len); void (*put_folio)(struct inode *inode, loff_t pos, unsigned copied, struct folio *folio); -- cgit v1.2.3 From 471859f57d42537626a56312cfb50cd6acee09ae Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Sun, 15 Jan 2023 08:50:44 -0800 Subject: iomap: Rename page_ops to folio_ops The operations in struct page_ops all operate on folios, so rename struct page_ops to struct folio_ops. Signed-off-by: Andreas Gruenbacher Reviewed-by: Darrick J. Wong Reviewed-by: Christoph Hellwig [djwong: port around not removing iomap_valid] Signed-off-by: Darrick J. Wong --- fs/gfs2/bmap.c | 4 ++-- fs/iomap/buffered-io.c | 20 ++++++++++---------- fs/xfs/xfs_iomap.c | 4 ++-- include/linux/iomap.h | 8 ++++---- 4 files changed, 18 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index d3adb715ac8c..e191ecfb1fde 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -997,7 +997,7 @@ static void gfs2_iomap_put_folio(struct inode *inode, loff_t pos, gfs2_trans_end(sdp); } -static const struct iomap_page_ops gfs2_iomap_page_ops = { +static const struct iomap_folio_ops gfs2_iomap_folio_ops = { .get_folio = gfs2_iomap_get_folio, .put_folio = gfs2_iomap_put_folio, }; @@ -1075,7 +1075,7 @@ static int gfs2_iomap_begin_write(struct inode *inode, loff_t pos, } if (gfs2_is_stuffed(ip) || gfs2_is_jdata(ip)) - iomap->page_ops = &gfs2_iomap_page_ops; + iomap->folio_ops = &gfs2_iomap_folio_ops; return 0; out_trans_end: diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 006ddf933948..d3c300563eb8 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -605,10 +605,10 @@ static int __iomap_write_begin(const struct iomap_iter *iter, loff_t pos, static struct folio *__iomap_get_folio(struct iomap_iter *iter, loff_t pos, size_t len) { - const struct iomap_page_ops *page_ops = iter->iomap.page_ops; + const struct iomap_folio_ops *folio_ops = iter->iomap.folio_ops; - if (page_ops && page_ops->get_folio) - return page_ops->get_folio(iter, pos, len); + if (folio_ops && folio_ops->get_folio) + return folio_ops->get_folio(iter, pos, len); else return iomap_get_folio(iter, pos); } @@ -616,10 +616,10 @@ static struct folio *__iomap_get_folio(struct iomap_iter *iter, loff_t pos, static void __iomap_put_folio(struct iomap_iter *iter, loff_t pos, size_t ret, struct folio *folio) { - const struct iomap_page_ops *page_ops = iter->iomap.page_ops; + const struct iomap_folio_ops *folio_ops = iter->iomap.folio_ops; - if (page_ops && page_ops->put_folio) { - page_ops->put_folio(iter->inode, pos, ret, folio); + if (folio_ops && folio_ops->put_folio) { + folio_ops->put_folio(iter->inode, pos, ret, folio); } else { folio_unlock(folio); folio_put(folio); @@ -638,7 +638,7 @@ static int iomap_write_begin_inline(const struct iomap_iter *iter, static int iomap_write_begin(struct iomap_iter *iter, loff_t pos, size_t len, struct folio **foliop) { - const struct iomap_page_ops *page_ops = iter->iomap.page_ops; + const struct iomap_folio_ops *folio_ops = iter->iomap.folio_ops; const struct iomap *srcmap = iomap_iter_srcmap(iter); struct folio *folio; int status = 0; @@ -667,9 +667,9 @@ static int iomap_write_begin(struct iomap_iter *iter, loff_t pos, * could do the wrong thing here (zero a page range incorrectly or fail * to zero) and corrupt data. */ - if (page_ops && page_ops->iomap_valid) { - bool iomap_valid = page_ops->iomap_valid(iter->inode, - &iter->iomap); + if (folio_ops && folio_ops->iomap_valid) { + bool iomap_valid = folio_ops->iomap_valid(iter->inode, + &iter->iomap); if (!iomap_valid) { iter->iomap.flags |= IOMAP_F_STALE; status = 0; diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index fc1946f80a4a..69dbe7814128 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -83,7 +83,7 @@ xfs_iomap_valid( return true; } -static const struct iomap_page_ops xfs_iomap_page_ops = { +static const struct iomap_folio_ops xfs_iomap_folio_ops = { .iomap_valid = xfs_iomap_valid, }; @@ -133,7 +133,7 @@ xfs_bmbt_to_iomap( iomap->flags |= IOMAP_F_DIRTY; iomap->validity_cookie = sequence_cookie; - iomap->page_ops = &xfs_iomap_page_ops; + iomap->folio_ops = &xfs_iomap_folio_ops; return 0; } diff --git a/include/linux/iomap.h b/include/linux/iomap.h index da226032aedc..c70a9d4fb447 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -86,7 +86,7 @@ struct vm_fault; */ #define IOMAP_NULL_ADDR -1ULL /* addr is not valid */ -struct iomap_page_ops; +struct iomap_folio_ops; struct iomap { u64 addr; /* disk offset of mapping, bytes */ @@ -98,7 +98,7 @@ struct iomap { struct dax_device *dax_dev; /* dax_dev for dax operations */ void *inline_data; void *private; /* filesystem private */ - const struct iomap_page_ops *page_ops; + const struct iomap_folio_ops *folio_ops; u64 validity_cookie; /* used with .iomap_valid() */ }; @@ -126,7 +126,7 @@ static inline bool iomap_inline_data_valid(const struct iomap *iomap) } /* - * When a filesystem sets page_ops in an iomap mapping it returns, get_folio + * When a filesystem sets folio_ops in an iomap mapping it returns, get_folio * and put_folio will be called for each folio written to. This only applies * to buffered writes as unbuffered writes will not typically have folios * associated with them. @@ -135,7 +135,7 @@ static inline bool iomap_inline_data_valid(const struct iomap *iomap) * cleanup work necessary. put_folio is responsible for unlocking and putting * @folio. */ -struct iomap_page_ops { +struct iomap_folio_ops { struct folio *(*get_folio)(struct iomap_iter *iter, loff_t pos, unsigned len); void (*put_folio)(struct inode *inode, loff_t pos, unsigned copied, -- cgit v1.2.3 From 04a42e72d77a93a166b79c34b7bc862f55a53967 Mon Sep 17 00:00:00 2001 From: Sidhartha Kumar Date: Wed, 14 Dec 2022 22:17:57 -0800 Subject: mm: move folio_set_compound_order() to mm/internal.h folio_set_compound_order() is moved to an mm-internal location so external folio users cannot misuse this function. Change the name of the function to folio_set_order() and use WARN_ON_ONCE() rather than BUG_ON. Also, handle the case if a non-large folio is passed and add clarifying comments to the function. Link: https://lore.kernel.org/lkml/20221207223731.32784-1-sidhartha.kumar@oracle.com/T/ Link: https://lkml.kernel.org/r/20221215061757.223440-1-sidhartha.kumar@oracle.com Fixes: 9fd330582b2f ("mm: add folio dtor and order setter functions") Signed-off-by: Sidhartha Kumar Suggested-by: Mike Kravetz Suggested-by: Muchun Song Suggested-by: Matthew Wilcox Suggested-by: John Hubbard Reviewed-by: John Hubbard Reviewed-by: Muchun Song Signed-off-by: Andrew Morton --- include/linux/mm.h | 16 ---------------- mm/hugetlb.c | 6 +++--- mm/internal.h | 19 +++++++++++++++++++ 3 files changed, 22 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 8f857163ac89..253b2d7489e6 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1019,22 +1019,6 @@ static inline void set_compound_order(struct page *page, unsigned int order) #endif } -/* - * folio_set_compound_order is generally passed a non-zero order to - * initialize a large folio. However, hugetlb code abuses this by - * passing in zero when 'dissolving' a large folio. - */ -static inline void folio_set_compound_order(struct folio *folio, - unsigned int order) -{ - VM_BUG_ON_FOLIO(!folio_test_large(folio), folio); - - folio->_folio_order = order; -#ifdef CONFIG_64BIT - folio->_folio_nr_pages = order ? 1U << order : 0; -#endif -} - /* Returns the number of pages in this potentially compound page. */ static inline unsigned long compound_nr(struct page *page) { diff --git a/mm/hugetlb.c b/mm/hugetlb.c index bdbfeb6fb393..cfd47a66ded0 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1492,7 +1492,7 @@ static void __destroy_compound_gigantic_folio(struct folio *folio, set_page_refcounted(p); } - folio_set_compound_order(folio, 0); + folio_set_order(folio, 0); __folio_clear_head(folio); } @@ -1956,7 +1956,7 @@ static bool __prep_compound_gigantic_folio(struct folio *folio, __folio_clear_reserved(folio); __folio_set_head(folio); /* we rely on prep_new_hugetlb_folio to set the destructor */ - folio_set_compound_order(folio, order); + folio_set_order(folio, order); for (i = 0; i < nr_pages; i++) { p = folio_page(folio, i); @@ -2020,7 +2020,7 @@ out_error: p = folio_page(folio, j); __ClearPageReserved(p); } - folio_set_compound_order(folio, 0); + folio_set_order(folio, 0); __folio_clear_head(folio); return false; } diff --git a/mm/internal.h b/mm/internal.h index bcf75a8b032d..1d6f4e168510 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -378,6 +378,25 @@ extern void *memmap_alloc(phys_addr_t size, phys_addr_t align, int split_free_page(struct page *free_page, unsigned int order, unsigned long split_pfn_offset); +/* + * This will have no effect, other than possibly generating a warning, if the + * caller passes in a non-large folio. + */ +static inline void folio_set_order(struct folio *folio, unsigned int order) +{ + if (WARN_ON_ONCE(!folio_test_large(folio))) + return; + + folio->_folio_order = order; +#ifdef CONFIG_64BIT + /* + * When hugetlb dissolves a folio, we need to clear the tail + * page, rather than setting nr_pages to 1. + */ + folio->_folio_nr_pages = order ? 1U << order : 0; +#endif +} + #if defined CONFIG_COMPACTION || defined CONFIG_CMA /* -- cgit v1.2.3 From 105ff5339f498af74e60d7662c8f1c4d21f1342d Mon Sep 17 00:00:00 2001 From: Jeff Xu Date: Thu, 15 Dec 2022 00:12:03 +0000 Subject: mm/memfd: add MFD_NOEXEC_SEAL and MFD_EXEC The new MFD_NOEXEC_SEAL and MFD_EXEC flags allows application to set executable bit at creation time (memfd_create). When MFD_NOEXEC_SEAL is set, memfd is created without executable bit (mode:0666), and sealed with F_SEAL_EXEC, so it can't be chmod to be executable (mode: 0777) after creation. when MFD_EXEC flag is set, memfd is created with executable bit (mode:0777), this is the same as the old behavior of memfd_create. The new pid namespaced sysctl vm.memfd_noexec has 3 values: 0: memfd_create() without MFD_EXEC nor MFD_NOEXEC_SEAL acts like MFD_EXEC was set. 1: memfd_create() without MFD_EXEC nor MFD_NOEXEC_SEAL acts like MFD_NOEXEC_SEAL was set. 2: memfd_create() without MFD_NOEXEC_SEAL will be rejected. The sysctl allows finer control of memfd_create for old-software that doesn't set the executable bit, for example, a container with vm.memfd_noexec=1 means the old-software will create non-executable memfd by default. Also, the value of memfd_noexec is passed to child namespace at creation time. For example, if the init namespace has vm.memfd_noexec=2, all its children namespaces will be created with 2. [akpm@linux-foundation.org: add stub functions to fix build] [akpm@linux-foundation.org: remove unneeded register_pid_ns_ctl_table_vm() stub, per Jeff] [akpm@linux-foundation.org: s/pr_warn_ratelimited/pr_warn_once/, per review] [akpm@linux-foundation.org: fix CONFIG_SYSCTL=n warning] Link: https://lkml.kernel.org/r/20221215001205.51969-4-jeffxu@google.com Signed-off-by: Jeff Xu Co-developed-by: Daniel Verkamp Signed-off-by: Daniel Verkamp Reported-by: kernel test robot Reviewed-by: Kees Cook Cc: David Herrmann Cc: Dmitry Torokhov Cc: Hugh Dickins Cc: Jann Horn Cc: Jorge Lucangeli Obes Cc: Shuah Khan Signed-off-by: Andrew Morton --- include/linux/pid_namespace.h | 19 ++++++++++++++ include/uapi/linux/memfd.h | 4 +++ kernel/pid_namespace.c | 5 ++++ kernel/pid_sysctl.h | 60 +++++++++++++++++++++++++++++++++++++++++++ mm/memfd.c | 48 ++++++++++++++++++++++++++++++++-- 5 files changed, 134 insertions(+), 2 deletions(-) create mode 100644 kernel/pid_sysctl.h (limited to 'include/linux') diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h index 07481bb87d4e..c758809d5bcf 100644 --- a/include/linux/pid_namespace.h +++ b/include/linux/pid_namespace.h @@ -16,6 +16,21 @@ struct fs_pin; +#if defined(CONFIG_SYSCTL) && defined(CONFIG_MEMFD_CREATE) +/* + * sysctl for vm.memfd_noexec + * 0: memfd_create() without MFD_EXEC nor MFD_NOEXEC_SEAL + * acts like MFD_EXEC was set. + * 1: memfd_create() without MFD_EXEC nor MFD_NOEXEC_SEAL + * acts like MFD_NOEXEC_SEAL was set. + * 2: memfd_create() without MFD_NOEXEC_SEAL will be + * rejected. + */ +#define MEMFD_NOEXEC_SCOPE_EXEC 0 +#define MEMFD_NOEXEC_SCOPE_NOEXEC_SEAL 1 +#define MEMFD_NOEXEC_SCOPE_NOEXEC_ENFORCED 2 +#endif + struct pid_namespace { struct idr idr; struct rcu_head rcu; @@ -31,6 +46,10 @@ struct pid_namespace { struct ucounts *ucounts; int reboot; /* group exit code if this pidns was rebooted */ struct ns_common ns; +#if defined(CONFIG_SYSCTL) && defined(CONFIG_MEMFD_CREATE) + /* sysctl for vm.memfd_noexec */ + int memfd_noexec_scope; +#endif } __randomize_layout; extern struct pid_namespace init_pid_ns; diff --git a/include/uapi/linux/memfd.h b/include/uapi/linux/memfd.h index 7a8a26751c23..273a4e15dfcf 100644 --- a/include/uapi/linux/memfd.h +++ b/include/uapi/linux/memfd.h @@ -8,6 +8,10 @@ #define MFD_CLOEXEC 0x0001U #define MFD_ALLOW_SEALING 0x0002U #define MFD_HUGETLB 0x0004U +/* not executable and sealed to prevent changing to executable. */ +#define MFD_NOEXEC_SEAL 0x0008U +/* executable */ +#define MFD_EXEC 0x0010U /* * Huge page size encoding when MFD_HUGETLB is specified, and a huge page diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c index f4f8cb0435b4..8a98b1af9376 100644 --- a/kernel/pid_namespace.c +++ b/kernel/pid_namespace.c @@ -23,6 +23,7 @@ #include #include #include +#include "pid_sysctl.h" static DEFINE_MUTEX(pid_caches_mutex); static struct kmem_cache *pid_ns_cachep; @@ -110,6 +111,8 @@ static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns ns->ucounts = ucounts; ns->pid_allocated = PIDNS_ADDING; + initialize_memfd_noexec_scope(ns); + return ns; out_free_idr: @@ -455,6 +458,8 @@ static __init int pid_namespaces_init(void) #ifdef CONFIG_CHECKPOINT_RESTORE register_sysctl_paths(kern_path, pid_ns_ctl_table); #endif + + register_pid_ns_sysctl_table_vm(); return 0; } diff --git a/kernel/pid_sysctl.h b/kernel/pid_sysctl.h new file mode 100644 index 000000000000..e22d072e1e24 --- /dev/null +++ b/kernel/pid_sysctl.h @@ -0,0 +1,60 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef LINUX_PID_SYSCTL_H +#define LINUX_PID_SYSCTL_H + +#include + +#if defined(CONFIG_SYSCTL) && defined(CONFIG_MEMFD_CREATE) +static inline void initialize_memfd_noexec_scope(struct pid_namespace *ns) +{ + ns->memfd_noexec_scope = + task_active_pid_ns(current)->memfd_noexec_scope; +} + +static int pid_mfd_noexec_dointvec_minmax(struct ctl_table *table, + int write, void *buf, size_t *lenp, loff_t *ppos) +{ + struct pid_namespace *ns = task_active_pid_ns(current); + struct ctl_table table_copy; + + if (write && !ns_capable(ns->user_ns, CAP_SYS_ADMIN)) + return -EPERM; + + table_copy = *table; + if (ns != &init_pid_ns) + table_copy.data = &ns->memfd_noexec_scope; + + /* + * set minimum to current value, the effect is only bigger + * value is accepted. + */ + if (*(int *)table_copy.data > *(int *)table_copy.extra1) + table_copy.extra1 = table_copy.data; + + return proc_dointvec_minmax(&table_copy, write, buf, lenp, ppos); +} + +static struct ctl_table pid_ns_ctl_table_vm[] = { + { + .procname = "memfd_noexec", + .data = &init_pid_ns.memfd_noexec_scope, + .maxlen = sizeof(init_pid_ns.memfd_noexec_scope), + .mode = 0644, + .proc_handler = pid_mfd_noexec_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_TWO, + }, + { } +}; +static struct ctl_path vm_path[] = { { .procname = "vm", }, { } }; +static inline void register_pid_ns_sysctl_table_vm(void) +{ + register_sysctl_paths(vm_path, pid_ns_ctl_table_vm); +} +#else +static inline void initialize_memfd_noexec_scope(struct pid_namespace *ns) {} +static inline void set_memfd_noexec_scope(struct pid_namespace *ns) {} +static inline void register_pid_ns_sysctl_table_vm(void) {} +#endif + +#endif /* LINUX_PID_SYSCTL_H */ diff --git a/mm/memfd.c b/mm/memfd.c index 4ebeab94aa74..bc214390e28d 100644 --- a/mm/memfd.c +++ b/mm/memfd.c @@ -18,6 +18,7 @@ #include #include #include +#include #include /* @@ -263,12 +264,13 @@ long memfd_fcntl(struct file *file, unsigned int cmd, unsigned long arg) #define MFD_NAME_PREFIX_LEN (sizeof(MFD_NAME_PREFIX) - 1) #define MFD_NAME_MAX_LEN (NAME_MAX - MFD_NAME_PREFIX_LEN) -#define MFD_ALL_FLAGS (MFD_CLOEXEC | MFD_ALLOW_SEALING | MFD_HUGETLB) +#define MFD_ALL_FLAGS (MFD_CLOEXEC | MFD_ALLOW_SEALING | MFD_HUGETLB | MFD_NOEXEC_SEAL | MFD_EXEC) SYSCALL_DEFINE2(memfd_create, const char __user *, uname, unsigned int, flags) { + char comm[TASK_COMM_LEN]; unsigned int *file_seals; struct file *file; int fd, error; @@ -285,6 +287,40 @@ SYSCALL_DEFINE2(memfd_create, return -EINVAL; } + /* Invalid if both EXEC and NOEXEC_SEAL are set.*/ + if ((flags & MFD_EXEC) && (flags & MFD_NOEXEC_SEAL)) + return -EINVAL; + + if (!(flags & (MFD_EXEC | MFD_NOEXEC_SEAL))) { +#ifdef CONFIG_SYSCTL + int sysctl = MEMFD_NOEXEC_SCOPE_EXEC; + struct pid_namespace *ns; + + ns = task_active_pid_ns(current); + if (ns) + sysctl = ns->memfd_noexec_scope; + + switch (sysctl) { + case MEMFD_NOEXEC_SCOPE_EXEC: + flags |= MFD_EXEC; + break; + case MEMFD_NOEXEC_SCOPE_NOEXEC_SEAL: + flags |= MFD_NOEXEC_SEAL; + break; + default: + pr_warn_once( + "memfd_create(): MFD_NOEXEC_SEAL is enforced, pid=%d '%s'\n", + task_pid_nr(current), get_task_comm(comm, current)); + return -EINVAL; + } +#else + flags |= MFD_EXEC; +#endif + pr_warn_once( + "memfd_create() without MFD_EXEC nor MFD_NOEXEC_SEAL, pid=%d '%s'\n", + task_pid_nr(current), get_task_comm(comm, current)); + } + /* length includes terminating zero */ len = strnlen_user(uname, MFD_NAME_MAX_LEN + 1); if (len <= 0) @@ -328,7 +364,15 @@ SYSCALL_DEFINE2(memfd_create, file->f_mode |= FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE; file->f_flags |= O_LARGEFILE; - if (flags & MFD_ALLOW_SEALING) { + if (flags & MFD_NOEXEC_SEAL) { + struct inode *inode = file_inode(file); + + inode->i_mode &= ~0111; + file_seals = memfd_file_seals_ptr(file); + *file_seals &= ~F_SEAL_SEAL; + *file_seals |= F_SEAL_EXEC; + } else if (flags & MFD_ALLOW_SEALING) { + /* MFD_EXEC and MFD_ALLOW_SEALING are set */ file_seals = memfd_file_seals_ptr(file); *file_seals &= ~F_SEAL_SEAL; } -- cgit v1.2.3 From fe7d4c6d5a42f5bdc63fdfdca2cad32c8a779e23 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Fri, 16 Dec 2022 10:50:54 -0500 Subject: mm/hugetlb: document huge_pte_offset usage huge_pte_offset() is potentially a pgtable walker, looking up pte_t* for a hugetlb address. Normally, it's always safe to walk a generic pgtable as long as we're with the mmap lock held for either read or write, because that guarantees the pgtable pages will always be valid during the process. But it's not true for hugetlbfs, especially shared: hugetlbfs can have its pgtable freed by pmd unsharing, it means that even with mmap lock held for current mm, the PMD pgtable page can still go away from under us if pmd unsharing is possible during the walk. So we have two ways to make it safe even for a shared mapping: (1) If we're with the hugetlb vma lock held for either read/write, it's okay because pmd unshare cannot happen at all. (2) If we're with the i_mmap_rwsem lock held for either read/write, it's okay because even if pmd unshare can happen, the pgtable page cannot be freed from under us. Document it. Link: https://lkml.kernel.org/r/20221216155100.2043537-4-peterx@redhat.com Signed-off-by: Peter Xu Reviewed-by: John Hubbard Reviewed-by: David Hildenbrand Cc: Andrea Arcangeli Cc: James Houghton Cc: Jann Horn Cc: Miaohe Lin Cc: Mike Kravetz Cc: Muchun Song Cc: Nadav Amit Cc: Rik van Riel Signed-off-by: Andrew Morton --- include/linux/hugetlb.h | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 551834cd5299..d755e2a7c0db 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -192,6 +192,38 @@ extern struct list_head huge_boot_pages; pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, unsigned long sz); +/* + * huge_pte_offset(): Walk the hugetlb pgtable until the last level PTE. + * Returns the pte_t* if found, or NULL if the address is not mapped. + * + * Since this function will walk all the pgtable pages (including not only + * high-level pgtable page, but also PUD entry that can be unshared + * concurrently for VM_SHARED), the caller of this function should be + * responsible of its thread safety. One can follow this rule: + * + * (1) For private mappings: pmd unsharing is not possible, so holding the + * mmap_lock for either read or write is sufficient. Most callers + * already hold the mmap_lock, so normally, no special action is + * required. + * + * (2) For shared mappings: pmd unsharing is possible (so the PUD-ranged + * pgtable page can go away from under us! It can be done by a pmd + * unshare with a follow up munmap() on the other process), then we + * need either: + * + * (2.1) hugetlb vma lock read or write held, to make sure pmd unshare + * won't happen upon the range (it also makes sure the pte_t we + * read is the right and stable one), or, + * + * (2.2) hugetlb mapping i_mmap_rwsem lock held read or write, to make + * sure even if unshare happened the racy unmap() will wait until + * i_mmap_rwsem is released. + * + * Option (2.1) is the safest, which guarantees pte stability from pmd + * sharing pov, until the vma lock released. Option (2.2) doesn't protect + * a concurrent pmd unshare, but it makes sure the pgtable page is safe to + * access. + */ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz); unsigned long hugetlb_mask_last_page(struct hstate *h); -- cgit v1.2.3 From fcd48540d188876c917a377d81cd24c100332a62 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Fri, 16 Dec 2022 10:50:55 -0500 Subject: mm/hugetlb: move swap entry handling into vma lock when faulted In hugetlb_fault(), there used to have a special path to handle swap entry at the entrance using huge_pte_offset(). That's unsafe because huge_pte_offset() for a pmd sharable range can access freed pgtables if without any lock to protect the pgtable from being freed after pmd unshare. Here the simplest solution to make it safe is to move the swap handling to be after the vma lock being held. We may need to take the fault mutex on either migration or hwpoison entries now (also the vma lock, but that's really needed), however neither of them is hot path. Note that the vma lock cannot be released in hugetlb_fault() when the migration entry is detected, because in migration_entry_wait_huge() the pgtable page will be used again (by taking the pgtable lock), so that also need to be protected by the vma lock. Modify migration_entry_wait_huge() so that it must be called with vma read lock held, and properly release the lock in __migration_entry_wait_huge(). Link: https://lkml.kernel.org/r/20221216155100.2043537-5-peterx@redhat.com Signed-off-by: Peter Xu Reviewed-by: Mike Kravetz Reviewed-by: John Hubbard Cc: Andrea Arcangeli Cc: David Hildenbrand Cc: James Houghton Cc: Jann Horn Cc: Miaohe Lin Cc: Muchun Song Cc: Nadav Amit Cc: Rik van Riel Signed-off-by: Andrew Morton --- include/linux/swapops.h | 6 ++++-- mm/hugetlb.c | 37 ++++++++++++++++--------------------- mm/migrate.c | 25 +++++++++++++++++++++---- 3 files changed, 41 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swapops.h b/include/linux/swapops.h index b982dd614572..3a451b7afcb3 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -337,7 +337,8 @@ extern void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, extern void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, unsigned long address); #ifdef CONFIG_HUGETLB_PAGE -extern void __migration_entry_wait_huge(pte_t *ptep, spinlock_t *ptl); +extern void __migration_entry_wait_huge(struct vm_area_struct *vma, + pte_t *ptep, spinlock_t *ptl); extern void migration_entry_wait_huge(struct vm_area_struct *vma, pte_t *pte); #endif /* CONFIG_HUGETLB_PAGE */ #else /* CONFIG_MIGRATION */ @@ -366,7 +367,8 @@ static inline void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, static inline void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, unsigned long address) { } #ifdef CONFIG_HUGETLB_PAGE -static inline void __migration_entry_wait_huge(pte_t *ptep, spinlock_t *ptl) { } +static inline void __migration_entry_wait_huge(struct vm_area_struct *vma, + pte_t *ptep, spinlock_t *ptl) { } static inline void migration_entry_wait_huge(struct vm_area_struct *vma, pte_t *pte) { } #endif /* CONFIG_HUGETLB_PAGE */ static inline int is_writable_migration_entry(swp_entry_t entry) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 549f79668756..7f9db1d9f6a5 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5993,22 +5993,6 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, int need_wait_lock = 0; unsigned long haddr = address & huge_page_mask(h); - ptep = huge_pte_offset(mm, haddr, huge_page_size(h)); - if (ptep) { - /* - * Since we hold no locks, ptep could be stale. That is - * OK as we are only making decisions based on content and - * not actually modifying content here. - */ - entry = huge_ptep_get(ptep); - if (unlikely(is_hugetlb_entry_migration(entry))) { - migration_entry_wait_huge(vma, ptep); - return 0; - } else if (unlikely(is_hugetlb_entry_hwpoisoned(entry))) - return VM_FAULT_HWPOISON_LARGE | - VM_FAULT_SET_HINDEX(hstate_index(h)); - } - /* * Serialize hugepage allocation and instantiation, so that we don't * get spurious allocation failures if two CPUs race to instantiate @@ -6023,10 +6007,6 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, * Acquire vma lock before calling huge_pte_alloc and hold * until finished with ptep. This prevents huge_pmd_unshare from * being called elsewhere and making the ptep no longer valid. - * - * ptep could have already be assigned via huge_pte_offset. That - * is OK, as huge_pte_alloc will return the same value unless - * something has changed. */ hugetlb_vma_lock_read(vma); ptep = huge_pte_alloc(mm, vma, haddr, huge_page_size(h)); @@ -6055,8 +6035,23 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, * fault, and is_hugetlb_entry_(migration|hwpoisoned) check will * properly handle it. */ - if (!pte_present(entry)) + if (!pte_present(entry)) { + if (unlikely(is_hugetlb_entry_migration(entry))) { + /* + * Release the hugetlb fault lock now, but retain + * the vma lock, because it is needed to guard the + * huge_pte_lockptr() later in + * migration_entry_wait_huge(). The vma lock will + * be released there. + */ + mutex_unlock(&hugetlb_fault_mutex_table[hash]); + migration_entry_wait_huge(vma, ptep); + return 0; + } else if (unlikely(is_hugetlb_entry_hwpoisoned(entry))) + ret = VM_FAULT_HWPOISON_LARGE | + VM_FAULT_SET_HINDEX(hstate_index(h)); goto out_mutex; + } /* * If we are going to COW/unshare the mapping later, we examine the diff --git a/mm/migrate.c b/mm/migrate.c index a4d3fc65085f..98de7ce2b576 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -329,24 +329,41 @@ void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, } #ifdef CONFIG_HUGETLB_PAGE -void __migration_entry_wait_huge(pte_t *ptep, spinlock_t *ptl) +/* + * The vma read lock must be held upon entry. Holding that lock prevents either + * the pte or the ptl from being freed. + * + * This function will release the vma lock before returning. + */ +void __migration_entry_wait_huge(struct vm_area_struct *vma, + pte_t *ptep, spinlock_t *ptl) { pte_t pte; + hugetlb_vma_assert_locked(vma); spin_lock(ptl); pte = huge_ptep_get(ptep); - if (unlikely(!is_hugetlb_entry_migration(pte))) + if (unlikely(!is_hugetlb_entry_migration(pte))) { spin_unlock(ptl); - else + hugetlb_vma_unlock_read(vma); + } else { + /* + * If migration entry existed, safe to release vma lock + * here because the pgtable page won't be freed without the + * pgtable lock released. See comment right above pgtable + * lock release in migration_entry_wait_on_locked(). + */ + hugetlb_vma_unlock_read(vma); migration_entry_wait_on_locked(pte_to_swp_entry(pte), NULL, ptl); + } } void migration_entry_wait_huge(struct vm_area_struct *vma, pte_t *pte) { spinlock_t *ptl = huge_pte_lockptr(hstate_vma(vma), vma->vm_mm, pte); - __migration_entry_wait_huge(pte, ptl); + __migration_entry_wait_huge(vma, pte, ptl); } #endif -- cgit v1.2.3 From dd361e5033cf36c51acab996ea17748b81cedb38 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Fri, 16 Dec 2022 10:52:26 -0500 Subject: mm/hugetlb: make walk_hugetlb_range() safe to pmd unshare Since walk_hugetlb_range() walks the pgtable, it needs the vma lock to make sure the pgtable page will not be freed concurrently. Link: https://lkml.kernel.org/r/20221216155226.2043738-1-peterx@redhat.com Signed-off-by: Peter Xu Reviewed-by: Mike Kravetz Reviewed-by: John Hubbard Cc: Andrea Arcangeli Cc: David Hildenbrand Cc: James Houghton Cc: Jann Horn Cc: Miaohe Lin Cc: Muchun Song Cc: Nadav Amit Cc: Rik van Riel Signed-off-by: Andrew Morton --- include/linux/pagewalk.h | 11 ++++++++++- mm/hmm.c | 15 ++++++++++++++- mm/pagewalk.c | 2 ++ 3 files changed, 26 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagewalk.h b/include/linux/pagewalk.h index 959f52e5867d..27a6df448ee5 100644 --- a/include/linux/pagewalk.h +++ b/include/linux/pagewalk.h @@ -21,7 +21,16 @@ struct mm_walk; * depth is -1 if not known, 0:PGD, 1:P4D, 2:PUD, 3:PMD. * Any folded depths (where PTRS_PER_P?D is equal to 1) * are skipped. - * @hugetlb_entry: if set, called for each hugetlb entry + * @hugetlb_entry: if set, called for each hugetlb entry. This hook + * function is called with the vma lock held, in order to + * protect against a concurrent freeing of the pte_t* or + * the ptl. In some cases, the hook function needs to drop + * and retake the vma lock in order to avoid deadlocks + * while calling other functions. In such cases the hook + * function must either refrain from accessing the pte or + * ptl after dropping the vma lock, or else revalidate + * those items after re-acquiring the vma lock and before + * accessing them. * @test_walk: caller specific callback function to determine whether * we walk over the current vma or not. Returning 0 means * "do page table walk over the current vma", returning diff --git a/mm/hmm.c b/mm/hmm.c index 601a99ce3c84..6a151c09de5e 100644 --- a/mm/hmm.c +++ b/mm/hmm.c @@ -492,8 +492,21 @@ static int hmm_vma_walk_hugetlb_entry(pte_t *pte, unsigned long hmask, required_fault = hmm_pte_need_fault(hmm_vma_walk, pfn_req_flags, cpu_flags); if (required_fault) { + int ret; + spin_unlock(ptl); - return hmm_vma_fault(addr, end, required_fault, walk); + hugetlb_vma_unlock_read(vma); + /* + * Avoid deadlock: drop the vma lock before calling + * hmm_vma_fault(), which will itself potentially take and + * drop the vma lock. This is also correct from a + * protection point of view, because there is no further + * use here of either pte or ptl after dropping the vma + * lock. + */ + ret = hmm_vma_fault(addr, end, required_fault, walk); + hugetlb_vma_lock_read(vma); + return ret; } pfn = pte_pfn(entry) + ((start & ~hmask) >> PAGE_SHIFT); diff --git a/mm/pagewalk.c b/mm/pagewalk.c index 7f1c9b274906..d98564a7be57 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -302,6 +302,7 @@ static int walk_hugetlb_range(unsigned long addr, unsigned long end, const struct mm_walk_ops *ops = walk->ops; int err = 0; + hugetlb_vma_lock_read(vma); do { next = hugetlb_entry_end(h, addr, end); pte = huge_pte_offset(walk->mm, addr & hmask, sz); @@ -314,6 +315,7 @@ static int walk_hugetlb_range(unsigned long addr, unsigned long end, if (err) break; } while (addr = next, addr != end); + hugetlb_vma_unlock_read(vma); return err; } -- cgit v1.2.3 From 9c67a20704e763f9cb8cd262c3e45de7bd2816bc Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Fri, 16 Dec 2022 10:52:29 -0500 Subject: mm/hugetlb: introduce hugetlb_walk() huge_pte_offset() is the main walker function for hugetlb pgtables. The name is not really representing what it does, though. Instead of renaming it, introduce a wrapper function called hugetlb_walk() which will use huge_pte_offset() inside. Assert on the locks when walking the pgtable. Note, the vma lock assertion will be a no-op for private mappings. Document the last special case in the page_vma_mapped_walk() path where we don't need any more lock to call hugetlb_walk(). Taking vma lock there is not needed because either: (1) potential callers of hugetlb pvmw holds i_mmap_rwsem already (from one rmap_walk()), or (2) the caller will not walk a hugetlb vma at all so the hugetlb code path not reachable (e.g. in ksm or uprobe paths). It's slightly implicit for future page_vma_mapped_walk() callers on that lock requirement. But anyway, when one day this rule breaks, one will get a straightforward warning in hugetlb_walk() with lockdep, then there'll be a way out. [akpm@linux-foundation.org: coding-style cleanups] Link: https://lkml.kernel.org/r/20221216155229.2043750-1-peterx@redhat.com Signed-off-by: Peter Xu Reviewed-by: Mike Kravetz Reviewed-by: John Hubbard Reviewed-by: David Hildenbrand Cc: Andrea Arcangeli Cc: James Houghton Cc: Jann Horn Cc: Miaohe Lin Cc: Muchun Song Cc: Nadav Amit Cc: Rik van Riel Signed-off-by: Andrew Morton --- fs/hugetlbfs/inode.c | 4 +--- fs/userfaultfd.c | 6 ++---- include/linux/hugetlb.h | 37 +++++++++++++++++++++++++++++++++++++ mm/hugetlb.c | 31 +++++++++++++------------------ mm/page_vma_mapped.c | 9 ++++++--- mm/pagewalk.c | 4 +--- 6 files changed, 60 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index fdb16246f46e..48f1a8ad2243 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -388,9 +388,7 @@ static bool hugetlb_vma_maps_page(struct vm_area_struct *vma, { pte_t *ptep, pte; - ptep = huge_pte_offset(vma->vm_mm, addr, - huge_page_size(hstate_vma(vma))); - + ptep = hugetlb_walk(vma, addr, huge_page_size(hstate_vma(vma))); if (!ptep) return false; diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 3b1797e0448a..15a5bf765d43 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -252,14 +252,12 @@ static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx, unsigned long flags, unsigned long reason) { - struct mm_struct *mm = ctx->mm; pte_t *ptep, pte; bool ret = true; - mmap_assert_locked(mm); - - ptep = huge_pte_offset(mm, address, vma_mmu_pagesize(vma)); + mmap_assert_locked(ctx->mm); + ptep = hugetlb_walk(vma, address, vma_mmu_pagesize(vma)); if (!ptep) goto out; diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index d755e2a7c0db..b6b10101bea7 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -2,6 +2,7 @@ #ifndef _LINUX_HUGETLB_H #define _LINUX_HUGETLB_H +#include #include #include #include @@ -196,6 +197,11 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, * huge_pte_offset(): Walk the hugetlb pgtable until the last level PTE. * Returns the pte_t* if found, or NULL if the address is not mapped. * + * IMPORTANT: we should normally not directly call this function, instead + * this is only a common interface to implement arch-specific + * walker. Please use hugetlb_walk() instead, because that will attempt to + * verify the locking for you. + * * Since this function will walk all the pgtable pages (including not only * high-level pgtable page, but also PUD entry that can be unshared * concurrently for VM_SHARED), the caller of this function should be @@ -1229,4 +1235,35 @@ bool want_pmd_share(struct vm_area_struct *vma, unsigned long addr); #define flush_hugetlb_tlb_range(vma, addr, end) flush_tlb_range(vma, addr, end) #endif +static inline bool __vma_shareable_lock(struct vm_area_struct *vma) +{ + return (vma->vm_flags & VM_MAYSHARE) && vma->vm_private_data; +} + +/* + * Safe version of huge_pte_offset() to check the locks. See comments + * above huge_pte_offset(). + */ +static inline pte_t * +hugetlb_walk(struct vm_area_struct *vma, unsigned long addr, unsigned long sz) +{ +#if defined(CONFIG_HUGETLB_PAGE) && \ + defined(CONFIG_ARCH_WANT_HUGE_PMD_SHARE) && defined(CONFIG_LOCKDEP) + struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; + + /* + * If pmd sharing possible, locking needed to safely walk the + * hugetlb pgtables. More information can be found at the comment + * above huge_pte_offset() in the same file. + * + * NOTE: lockdep_is_held() is only defined with CONFIG_LOCKDEP. + */ + if (__vma_shareable_lock(vma)) + WARN_ON_ONCE(!lockdep_is_held(&vma_lock->rw_sema) && + !lockdep_is_held( + &vma->vm_file->f_mapping->i_mmap_rwsem)); +#endif + return huge_pte_offset(vma->vm_mm, addr, sz); +} + #endif /* _LINUX_HUGETLB_H */ diff --git a/mm/hugetlb.c b/mm/hugetlb.c index da4c37553c08..0e5441d6890a 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -260,11 +260,6 @@ static inline struct hugepage_subpool *subpool_vma(struct vm_area_struct *vma) /* * hugetlb vma_lock helper routines */ -static bool __vma_shareable_lock(struct vm_area_struct *vma) -{ - return vma->vm_flags & VM_MAYSHARE && vma->vm_private_data; -} - void hugetlb_vma_lock_read(struct vm_area_struct *vma) { if (__vma_shareable_lock(vma)) { @@ -4980,7 +4975,7 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, } else { /* * For shared mappings the vma lock must be held before - * calling huge_pte_offset in the src vma. Otherwise, the + * calling hugetlb_walk() in the src vma. Otherwise, the * returned ptep could go away if part of a shared pmd and * another thread calls huge_pmd_unshare. */ @@ -4990,7 +4985,7 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, last_addr_mask = hugetlb_mask_last_page(h); for (addr = src_vma->vm_start; addr < src_vma->vm_end; addr += sz) { spinlock_t *src_ptl, *dst_ptl; - src_pte = huge_pte_offset(src, addr, sz); + src_pte = hugetlb_walk(src_vma, addr, sz); if (!src_pte) { addr |= last_addr_mask; continue; @@ -5197,7 +5192,7 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma, hugetlb_vma_lock_write(vma); i_mmap_lock_write(mapping); for (; old_addr < old_end; old_addr += sz, new_addr += sz) { - src_pte = huge_pte_offset(mm, old_addr, sz); + src_pte = hugetlb_walk(vma, old_addr, sz); if (!src_pte) { old_addr |= last_addr_mask; new_addr |= last_addr_mask; @@ -5260,7 +5255,7 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct last_addr_mask = hugetlb_mask_last_page(h); address = start; for (; address < end; address += sz) { - ptep = huge_pte_offset(mm, address, sz); + ptep = hugetlb_walk(vma, address, sz); if (!ptep) { address |= last_addr_mask; continue; @@ -5573,7 +5568,7 @@ retry_avoidcopy: mutex_lock(&hugetlb_fault_mutex_table[hash]); hugetlb_vma_lock_read(vma); spin_lock(ptl); - ptep = huge_pte_offset(mm, haddr, huge_page_size(h)); + ptep = hugetlb_walk(vma, haddr, huge_page_size(h)); if (likely(ptep && pte_same(huge_ptep_get(ptep), pte))) goto retry_avoidcopy; @@ -5611,7 +5606,7 @@ retry_avoidcopy: * before the page tables are altered */ spin_lock(ptl); - ptep = huge_pte_offset(mm, haddr, huge_page_size(h)); + ptep = hugetlb_walk(vma, haddr, huge_page_size(h)); if (likely(ptep && pte_same(huge_ptep_get(ptep), pte))) { /* Break COW or unshare */ huge_ptep_clear_flush(vma, haddr, ptep); @@ -6397,7 +6392,7 @@ struct page *hugetlb_follow_page_mask(struct vm_area_struct *vma, return NULL; hugetlb_vma_lock_read(vma); - pte = huge_pte_offset(mm, haddr, huge_page_size(h)); + pte = hugetlb_walk(vma, haddr, huge_page_size(h)); if (!pte) goto out_unlock; @@ -6462,8 +6457,8 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, * * Note that page table lock is not held when pte is null. */ - pte = huge_pte_offset(mm, vaddr & huge_page_mask(h), - huge_page_size(h)); + pte = hugetlb_walk(vma, vaddr & huge_page_mask(h), + huge_page_size(h)); if (pte) ptl = huge_pte_lock(h, mm, pte); absent = !pte || huge_pte_none(huge_ptep_get(pte)); @@ -6654,7 +6649,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, last_addr_mask = hugetlb_mask_last_page(h); for (; address < end; address += psize) { spinlock_t *ptl; - ptep = huge_pte_offset(mm, address, psize); + ptep = hugetlb_walk(vma, address, psize); if (!ptep) { if (!uffd_wp) { address |= last_addr_mask; @@ -7064,8 +7059,8 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, saddr = page_table_shareable(svma, vma, addr, idx); if (saddr) { - spte = huge_pte_offset(svma->vm_mm, saddr, - vma_mmu_pagesize(svma)); + spte = hugetlb_walk(svma, saddr, + vma_mmu_pagesize(svma)); if (spte) { get_page(virt_to_page(spte)); break; @@ -7377,7 +7372,7 @@ static void hugetlb_unshare_pmds(struct vm_area_struct *vma, hugetlb_vma_lock_write(vma); i_mmap_lock_write(vma->vm_file->f_mapping); for (address = start; address < end; address += PUD_SIZE) { - ptep = huge_pte_offset(mm, address, sz); + ptep = hugetlb_walk(vma, address, sz); if (!ptep) continue; ptl = huge_pte_lock(h, mm, ptep); diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c index 93e13fc17d3c..4e448cfbc6ef 100644 --- a/mm/page_vma_mapped.c +++ b/mm/page_vma_mapped.c @@ -168,9 +168,12 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) /* The only possible mapping was handled on last iteration */ if (pvmw->pte) return not_found(pvmw); - - /* when pud is not present, pte will be NULL */ - pvmw->pte = huge_pte_offset(mm, pvmw->address, size); + /* + * All callers that get here will already hold the + * i_mmap_rwsem. Therefore, no additional locks need to be + * taken before calling hugetlb_walk(). + */ + pvmw->pte = hugetlb_walk(vma, pvmw->address, size); if (!pvmw->pte) return false; diff --git a/mm/pagewalk.c b/mm/pagewalk.c index d98564a7be57..cb23f8a15c13 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -305,13 +305,11 @@ static int walk_hugetlb_range(unsigned long addr, unsigned long end, hugetlb_vma_lock_read(vma); do { next = hugetlb_entry_end(h, addr, end); - pte = huge_pte_offset(walk->mm, addr & hmask, sz); - + pte = hugetlb_walk(vma, addr & hmask, sz); if (pte) err = ops->hugetlb_entry(pte, hmask, addr, next, walk); else if (ops->pte_hole) err = ops->pte_hole(addr, next, -1, walk); - if (err) break; } while (addr = next, addr != end); -- cgit v1.2.3 From d685c668b0695dff927c85e27ef27d4f404f16a3 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox (Oracle) Date: Thu, 15 Dec 2022 21:43:51 +0000 Subject: buffer: add b_folio as an alias of b_page Patch series "Start converting buffer_heads to use folios". I was hoping that filesystems would convert from buffer_heads to iomap, but that's not happening particularly quickly. So the buffer_head infrastructure needs to be converted from being page-based to being folio-based. This patch (of 12): Buffer heads point to the allocation (ie the folio), not the page. This is currently the same thing for all filesystems that use buffer heads, so this is a safe transitional step. Link: https://lkml.kernel.org/r/20221215214402.3522366-1-willy@infradead.org Link: https://lkml.kernel.org/r/20221215214402.3522366-2-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Jan Kara Signed-off-by: Andrew Morton --- include/linux/buffer_head.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 33fa5e94aa80..8f14dca5fed7 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -61,7 +61,10 @@ typedef void (bh_end_io_t)(struct buffer_head *bh, int uptodate); struct buffer_head { unsigned long b_state; /* buffer state bitmap (see above) */ struct buffer_head *b_this_page;/* circular list of page's buffers */ - struct page *b_page; /* the page this bh is mapped to */ + union { + struct page *b_page; /* the page this bh is mapped to */ + struct folio *b_folio; /* the folio this bh is mapped to */ + }; sector_t b_blocknr; /* start block number */ size_t b_size; /* size of mapping */ -- cgit v1.2.3 From 6a6fe9ebd571a4092b7d5c1f11e4e1e15d296fa5 Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Fri, 9 Dec 2022 10:06:18 +0800 Subject: mm: swap: convert mark_page_lazyfree() to folio_mark_lazyfree() mark_page_lazyfree() and the callers are converted to use folio, this rename and make it to take in a folio argument instead of calling page_folio(). Link: https://lkml.kernel.org/r/20221209020618.190306-1-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang Reviewed-by: Vishal Moola (Oracle) Cc: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- include/linux/swap.h | 2 +- mm/huge_memory.c | 2 +- mm/madvise.c | 2 +- mm/swap.c | 12 +++++------- 4 files changed, 8 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 2787b84eaf12..93f1cebd8545 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -402,7 +402,7 @@ extern void lru_add_drain_cpu(int cpu); extern void lru_add_drain_cpu_zone(struct zone *zone); extern void lru_add_drain_all(void); extern void deactivate_page(struct page *page); -extern void mark_page_lazyfree(struct page *page); +void folio_mark_lazyfree(struct folio *folio); extern void swap_setup(void); extern void lru_cache_add_inactive_or_unevictable(struct page *page, diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 3de266e0aeb2..266c4b557946 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1660,7 +1660,7 @@ bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, tlb_remove_pmd_tlb_entry(tlb, pmd, addr); } - mark_page_lazyfree(&folio->page); + folio_mark_lazyfree(folio); ret = true; out: spin_unlock(ptl); diff --git a/mm/madvise.c b/mm/madvise.c index b6ea204d4e23..479d9a32e44a 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -728,7 +728,7 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr, set_pte_at(mm, addr, pte, ptent); tlb_remove_tlb_entry(tlb, pte, addr); } - mark_page_lazyfree(&folio->page); + folio_mark_lazyfree(folio); } out: if (nr_swap) { diff --git a/mm/swap.c b/mm/swap.c index 70e2063ef43a..5e5eba186930 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -757,16 +757,14 @@ void deactivate_page(struct page *page) } /** - * mark_page_lazyfree - make an anon page lazyfree - * @page: page to deactivate + * folio_mark_lazyfree - make an anon folio lazyfree + * @folio: folio to deactivate * - * mark_page_lazyfree() moves @page to the inactive file list. - * This is done to accelerate the reclaim of @page. + * folio_mark_lazyfree() moves @folio to the inactive file list. + * This is done to accelerate the reclaim of @folio. */ -void mark_page_lazyfree(struct page *page) +void folio_mark_lazyfree(struct folio *folio) { - struct folio *folio = page_folio(page); - if (folio_test_lru(folio) && folio_test_anon(folio) && folio_test_swapbacked(folio) && !folio_test_swapcache(folio) && !folio_test_unevictable(folio)) { -- cgit v1.2.3 From 98def236f63c66629fb6b2d4b69cecffc5b46539 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Mon, 5 Dec 2022 23:08:20 +0000 Subject: mm/damon/core: implement damos filter Patch series "implement DAMOS filtering for anon pages and/or specific memory cgroups" DAMOS let users do system operations in a data access pattern oriented way. The data access pattern, which is extracted by DAMON, is somewhat accurate more than what user space could know in many cases. However, in some situation, users could know something more than the kernel about the pattern or some special requirements for some types of memory or processes. For example, some users would have slow swap devices and knows latency-ciritical processes and therefore want to use DAMON-based proactive reclamation (DAMON_RECLAIM) for only non-anonymous pages of non-latency-critical processes. For such restriction, users could exclude the memory regions from the initial monitoring regions and use non-dynamic monitoring regions update monitoring operations set including fvaddr and paddr. They could also adjust the DAMOS target access pattern. For dynamically changing memory layout and access pattern, those would be not enough. To help the case, add an interface, namely DAMOS filters, which can be used to avoid the DAMOS actions be applied to specific types of memory, to DAMON kernel API (damon.h). At the moment, it supports filtering anonymous pages and/or specific memory cgroups in or out for each DAMOS scheme. This patchset adds the support for all DAMOS actions that 'paddr' monitoring operations set supports ('pageout', 'lru_prio', and 'lru_deprio'), and the functionality is exposed via DAMON kernel API (damon.h) the DAMON sysfs interface (/sys/kernel/mm/damon/admins/), and DAMON_RECLAIM module parameters. Patches Sequence ---------------- First patch implements DAMOS filter interface to DAMON kernel API. Second patch makes the physical address space monitoring operations set to support the filters from all supporting DAMOS actions. Third patch adds anonymous pages filter support to DAMON_RECLAIM, and the fourth patch documents the DAMON_RECLAIM's new feature. Fifth to seventh patches implement DAMON sysfs files for support of the filters, and eighth patch connects the file to use DAMOS filters feature. Ninth patch adds simple self test cases for DAMOS filters of the sysfs interface. Finally, following two patches (tenth and eleventh) document the new features and interfaces. This patch (of 11): DAMOS lets users do system operation in a data access pattern oriented way. The data access pattern, which is extracted by DAMON, is somewhat accurate more than what user space could know in many cases. However, in some situation, users could know something more than the kernel about the pattern or some special requirements for some types of memory or processes. For example, some users would have slow swap devices and knows latency-ciritical processes and therefore want to use DAMON-based proactive reclamation (DAMON_RECLAIM) for only non-anonymous pages of non-latency-critical processes. For such restriction, users could exclude the memory regions from the initial monitoring regions and use non-dynamic monitoring regions update monitoring operations set including fvaddr and paddr. They could also adjust the DAMOS target access pattern. For dynamically changing memory layout and access pattern, those would be not enough. To help the case, add an interface, namely DAMOS filters, which can be used to avoid the DAMOS actions be applied to specific types of memory, to DAMON kernel API (damon.h). At the moment, it supports filtering anonymous pages and/or specific memory cgroups in or out for each DAMOS scheme. Note that this commit adds only the interface to the DAMON kernel API. The impelmentation should be made in the monitoring operations sets, and following commits will add that. Link: https://lkml.kernel.org/r/20221205230830.144349-1-sj@kernel.org Link: https://lkml.kernel.org/r/20221205230830.144349-2-sj@kernel.org Signed-off-by: SeongJae Park Cc: Jonathan Corbet Cc: Shuah Khan Signed-off-by: Andrew Morton --- include/linux/damon.h | 51 +++++++++++++++++++++++++++++++++++++++++++++++++++ mm/damon/core.c | 39 +++++++++++++++++++++++++++++++++++++++ 2 files changed, 90 insertions(+) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index ad15a5b88e3a..7907918ad2e0 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -8,6 +8,7 @@ #ifndef _DAMON_H_ #define _DAMON_H_ +#include #include #include #include @@ -215,6 +216,39 @@ struct damos_stat { unsigned long qt_exceeds; }; +/** + * enum damos_filter_type - Type of memory for &struct damos_filter + * @DAMOS_FILTER_TYPE_ANON: Anonymous pages. + * @DAMOS_FILTER_TYPE_MEMCG: Specific memcg's pages. + * @NR_DAMOS_FILTER_TYPES: Number of filter types. + */ +enum damos_filter_type { + DAMOS_FILTER_TYPE_ANON, + DAMOS_FILTER_TYPE_MEMCG, + NR_DAMOS_FILTER_TYPES, +}; + +/** + * struct damos_filter - DAMOS action target memory filter. + * @type: Type of the page. + * @matching: If the matching page should filtered out or in. + * @memcg_id: Memcg id of the question if @type is DAMOS_FILTER_MEMCG. + * @list: List head for siblings. + * + * Before applying the &damos->action to a memory region, DAMOS checks if each + * page of the region matches to this and avoid applying the action if so. + * Note that the check support is up to &struct damon_operations + * implementation. + */ +struct damos_filter { + enum damos_filter_type type; + bool matching; + union { + unsigned short memcg_id; + }; + struct list_head list; +}; + /** * struct damos_access_pattern - Target access pattern of the given scheme. * @min_sz_region: Minimum size of target regions. @@ -239,6 +273,7 @@ struct damos_access_pattern { * @action: &damo_action to be applied to the target regions. * @quota: Control the aggressiveness of this scheme. * @wmarks: Watermarks for automated (in)activation of this scheme. + * @filters: Additional set of &struct damos_filter for &action. * @stat: Statistics of this scheme. * @list: List head for siblings. * @@ -254,6 +289,10 @@ struct damos_access_pattern { * If all schemes that registered to a &struct damon_ctx are inactive, DAMON * stops monitoring and just repeatedly checks the watermarks. * + * Before applying the &action to a memory region, &struct damon_operations + * implementation could check pages of the region and skip &action to respect + * &filters + * * After applying the &action to each region, &stat_count and &stat_sz is * updated to reflect the number of regions and total size of regions that the * &action is applied. @@ -263,6 +302,7 @@ struct damos { enum damos_action action; struct damos_quota quota; struct damos_watermarks wmarks; + struct list_head filters; struct damos_stat stat; struct list_head list; }; @@ -516,6 +556,12 @@ static inline unsigned long damon_sz_region(struct damon_region *r) #define damon_for_each_scheme_safe(s, next, ctx) \ list_for_each_entry_safe(s, next, &(ctx)->schemes, list) +#define damos_for_each_filter(f, scheme) \ + list_for_each_entry(f, &(scheme)->filters, list) + +#define damos_for_each_filter_safe(f, next, scheme) \ + list_for_each_entry_safe(f, next, &(scheme)->filters, list) + #ifdef CONFIG_DAMON struct damon_region *damon_new_region(unsigned long start, unsigned long end); @@ -536,6 +582,11 @@ void damon_destroy_region(struct damon_region *r, struct damon_target *t); int damon_set_regions(struct damon_target *t, struct damon_addr_range *ranges, unsigned int nr_ranges); +struct damos_filter *damos_new_filter(enum damos_filter_type type, + bool matching); +void damos_add_filter(struct damos *s, struct damos_filter *f); +void damos_destroy_filter(struct damos_filter *f); + struct damos *damon_new_scheme(struct damos_access_pattern *pattern, enum damos_action action, struct damos_quota *quota, struct damos_watermarks *wmarks); diff --git a/mm/damon/core.c b/mm/damon/core.c index ceec75b88ef9..1bf0654ae189 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -263,6 +263,40 @@ int damon_set_regions(struct damon_target *t, struct damon_addr_range *ranges, return 0; } +struct damos_filter *damos_new_filter(enum damos_filter_type type, + bool matching) +{ + struct damos_filter *filter; + + filter = kmalloc(sizeof(*filter), GFP_KERNEL); + if (!filter) + return NULL; + filter->type = type; + filter->matching = matching; + return filter; +} + +void damos_add_filter(struct damos *s, struct damos_filter *f) +{ + list_add_tail(&f->list, &s->filters); +} + +static void damos_del_filter(struct damos_filter *f) +{ + list_del(&f->list); +} + +static void damos_free_filter(struct damos_filter *f) +{ + kfree(f); +} + +void damos_destroy_filter(struct damos_filter *f) +{ + damos_del_filter(f); + damos_free_filter(f); +} + /* initialize private fields of damos_quota and return the pointer */ static struct damos_quota *damos_quota_init_priv(struct damos_quota *quota) { @@ -287,6 +321,7 @@ struct damos *damon_new_scheme(struct damos_access_pattern *pattern, return NULL; scheme->pattern = *pattern; scheme->action = action; + INIT_LIST_HEAD(&scheme->filters); scheme->stat = (struct damos_stat){}; INIT_LIST_HEAD(&scheme->list); @@ -315,6 +350,10 @@ static void damon_free_scheme(struct damos *s) void damon_destroy_scheme(struct damos *s) { + struct damos_filter *f, *next; + + damos_for_each_filter_safe(f, next, s) + damos_destroy_filter(f); damon_del_scheme(s); damon_free_scheme(s); } -- cgit v1.2.3 From 44383cef54c0ce1201f884d83cc2b367bc5aa4f7 Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Mon, 19 Dec 2022 19:09:18 +0100 Subject: kasan: allow sampling page_alloc allocations for HW_TAGS As Hardware Tag-Based KASAN is intended to be used in production, its performance impact is crucial. As page_alloc allocations tend to be big, tagging and checking all such allocations can introduce a significant slowdown. Add two new boot parameters that allow to alleviate that slowdown: - kasan.page_alloc.sample, which makes Hardware Tag-Based KASAN tag only every Nth page_alloc allocation with the order configured by the second added parameter (default: tag every such allocation). - kasan.page_alloc.sample.order, which makes sampling enabled by the first parameter only affect page_alloc allocations with the order equal or greater than the specified value (default: 3, see below). The exact performance improvement caused by using the new parameters depends on their values and the applied workload. The chosen default value for kasan.page_alloc.sample.order is 3, which matches both PAGE_ALLOC_COSTLY_ORDER and SKB_FRAG_PAGE_ORDER. This is done for two reasons: 1. PAGE_ALLOC_COSTLY_ORDER is "the order at which allocations are deemed costly to service", which corresponds to the idea that only large and thus costly allocations are supposed to sampled. 2. One of the workloads targeted by this patch is a benchmark that sends a large amount of data over a local loopback connection. Most multi-page data allocations in the networking subsystem have the order of SKB_FRAG_PAGE_ORDER (or PAGE_ALLOC_COSTLY_ORDER). When running a local loopback test on a testing MTE-enabled device in sync mode, enabling Hardware Tag-Based KASAN introduces a ~50% slowdown. Applying this patch and setting kasan.page_alloc.sampling to a value higher than 1 allows to lower the slowdown. The performance improvement saturates around the sampling interval value of 10 with the default sampling page order of 3. This lowers the slowdown to ~20%. The slowdown in real scenarios involving the network will likely be better. Enabling page_alloc sampling has a downside: KASAN misses bad accesses to a page_alloc allocation that has not been tagged. This lowers the value of KASAN as a security mitigation. However, based on measuring the number of page_alloc allocations of different orders during boot in a test build, sampling with the default kasan.page_alloc.sample.order value affects only ~7% of allocations. The rest ~93% of allocations are still checked deterministically. Link: https://lkml.kernel.org/r/129da0614123bb85ed4dd61ae30842b2dd7c903f.1671471846.git.andreyknvl@google.com Signed-off-by: Andrey Konovalov Reviewed-by: Marco Elver Cc: Alexander Potapenko Cc: Andrey Ryabinin Cc: Dmitry Vyukov Cc: Evgenii Stepanov Cc: Jann Horn Cc: Mark Brand Cc: Peter Collingbourne Signed-off-by: Andrew Morton --- Documentation/dev-tools/kasan.rst | 17 +++++++++++ include/linux/kasan.h | 14 +++++---- mm/kasan/common.c | 9 ++++-- mm/kasan/hw_tags.c | 60 +++++++++++++++++++++++++++++++++++++++ mm/kasan/kasan.h | 27 ++++++++++++++++++ mm/page_alloc.c | 43 +++++++++++++++++++--------- 6 files changed, 149 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/Documentation/dev-tools/kasan.rst b/Documentation/dev-tools/kasan.rst index 5c93ab915049..e66916a483cd 100644 --- a/Documentation/dev-tools/kasan.rst +++ b/Documentation/dev-tools/kasan.rst @@ -140,6 +140,23 @@ disabling KASAN altogether or controlling its features: - ``kasan.vmalloc=off`` or ``=on`` disables or enables tagging of vmalloc allocations (default: ``on``). +- ``kasan.page_alloc.sample=`` makes KASAN tag only every + Nth page_alloc allocation with the order equal or greater than + ``kasan.page_alloc.sample.order``, where N is the value of the ``sample`` + parameter (default: ``1``, or tag every such allocation). + This parameter is intended to mitigate the performance overhead introduced + by KASAN. + Note that enabling this parameter makes Hardware Tag-Based KASAN skip checks + of allocations chosen by sampling and thus miss bad accesses to these + allocations. Use the default value for accurate bug detection. + +- ``kasan.page_alloc.sample.order=`` specifies the minimum + order of allocations that are affected by sampling (default: ``3``). + Only applies when ``kasan.page_alloc.sample`` is set to a value greater + than ``1``. + This parameter is intended to allow sampling only large page_alloc + allocations, which is the biggest source of the performance overhead. + Error reports ~~~~~~~~~~~~~ diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 96c9d56e5510..5ebbaf672009 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -120,12 +120,13 @@ static __always_inline void kasan_poison_pages(struct page *page, __kasan_poison_pages(page, order, init); } -void __kasan_unpoison_pages(struct page *page, unsigned int order, bool init); -static __always_inline void kasan_unpoison_pages(struct page *page, +bool __kasan_unpoison_pages(struct page *page, unsigned int order, bool init); +static __always_inline bool kasan_unpoison_pages(struct page *page, unsigned int order, bool init) { if (kasan_enabled()) - __kasan_unpoison_pages(page, order, init); + return __kasan_unpoison_pages(page, order, init); + return false; } void __kasan_cache_create_kmalloc(struct kmem_cache *cache); @@ -249,8 +250,11 @@ static __always_inline bool kasan_check_byte(const void *addr) static inline void kasan_unpoison_range(const void *address, size_t size) {} static inline void kasan_poison_pages(struct page *page, unsigned int order, bool init) {} -static inline void kasan_unpoison_pages(struct page *page, unsigned int order, - bool init) {} +static inline bool kasan_unpoison_pages(struct page *page, unsigned int order, + bool init) +{ + return false; +} static inline void kasan_cache_create_kmalloc(struct kmem_cache *cache) {} static inline void kasan_poison_slab(struct slab *slab) {} static inline void kasan_unpoison_object_data(struct kmem_cache *cache, diff --git a/mm/kasan/common.c b/mm/kasan/common.c index 833bf2cfd2a3..1d0008e1c420 100644 --- a/mm/kasan/common.c +++ b/mm/kasan/common.c @@ -95,19 +95,24 @@ asmlinkage void kasan_unpoison_task_stack_below(const void *watermark) } #endif /* CONFIG_KASAN_STACK */ -void __kasan_unpoison_pages(struct page *page, unsigned int order, bool init) +bool __kasan_unpoison_pages(struct page *page, unsigned int order, bool init) { u8 tag; unsigned long i; if (unlikely(PageHighMem(page))) - return; + return false; + + if (!kasan_sample_page_alloc(order)) + return false; tag = kasan_random_tag(); kasan_unpoison(set_tag(page_address(page), tag), PAGE_SIZE << order, init); for (i = 0; i < (1 << order); i++) page_kasan_tag_set(page + i, tag); + + return true; } void __kasan_poison_pages(struct page *page, unsigned int order, bool init) diff --git a/mm/kasan/hw_tags.c b/mm/kasan/hw_tags.c index b22c4f461cb0..d1bcb0205327 100644 --- a/mm/kasan/hw_tags.c +++ b/mm/kasan/hw_tags.c @@ -59,6 +59,24 @@ EXPORT_SYMBOL_GPL(kasan_mode); /* Whether to enable vmalloc tagging. */ DEFINE_STATIC_KEY_TRUE(kasan_flag_vmalloc); +#define PAGE_ALLOC_SAMPLE_DEFAULT 1 +#define PAGE_ALLOC_SAMPLE_ORDER_DEFAULT 3 + +/* + * Sampling interval of page_alloc allocation (un)poisoning. + * Defaults to no sampling. + */ +unsigned long kasan_page_alloc_sample = PAGE_ALLOC_SAMPLE_DEFAULT; + +/* + * Minimum order of page_alloc allocations to be affected by sampling. + * The default value is chosen to match both + * PAGE_ALLOC_COSTLY_ORDER and SKB_FRAG_PAGE_ORDER. + */ +unsigned int kasan_page_alloc_sample_order = PAGE_ALLOC_SAMPLE_ORDER_DEFAULT; + +DEFINE_PER_CPU(long, kasan_page_alloc_skip); + /* kasan=off/on */ static int __init early_kasan_flag(char *arg) { @@ -122,6 +140,48 @@ static inline const char *kasan_mode_info(void) return "sync"; } +/* kasan.page_alloc.sample= */ +static int __init early_kasan_flag_page_alloc_sample(char *arg) +{ + int rv; + + if (!arg) + return -EINVAL; + + rv = kstrtoul(arg, 0, &kasan_page_alloc_sample); + if (rv) + return rv; + + if (!kasan_page_alloc_sample || kasan_page_alloc_sample > LONG_MAX) { + kasan_page_alloc_sample = PAGE_ALLOC_SAMPLE_DEFAULT; + return -EINVAL; + } + + return 0; +} +early_param("kasan.page_alloc.sample", early_kasan_flag_page_alloc_sample); + +/* kasan.page_alloc.sample.order= */ +static int __init early_kasan_flag_page_alloc_sample_order(char *arg) +{ + int rv; + + if (!arg) + return -EINVAL; + + rv = kstrtouint(arg, 0, &kasan_page_alloc_sample_order); + if (rv) + return rv; + + if (kasan_page_alloc_sample_order > INT_MAX) { + kasan_page_alloc_sample_order = PAGE_ALLOC_SAMPLE_ORDER_DEFAULT; + return -EINVAL; + } + + return 0; +} +early_param("kasan.page_alloc.sample.order", early_kasan_flag_page_alloc_sample_order); + /* * kasan_init_hw_tags_cpu() is called for each CPU. * Not marked as __init as a CPU can be hot-plugged after boot. diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h index ea8cf1310b1e..32413f22aa82 100644 --- a/mm/kasan/kasan.h +++ b/mm/kasan/kasan.h @@ -42,6 +42,10 @@ enum kasan_mode { extern enum kasan_mode kasan_mode __ro_after_init; +extern unsigned long kasan_page_alloc_sample; +extern unsigned int kasan_page_alloc_sample_order; +DECLARE_PER_CPU(long, kasan_page_alloc_skip); + static inline bool kasan_vmalloc_enabled(void) { return static_branch_likely(&kasan_flag_vmalloc); @@ -57,6 +61,24 @@ static inline bool kasan_sync_fault_possible(void) return kasan_mode == KASAN_MODE_SYNC || kasan_mode == KASAN_MODE_ASYMM; } +static inline bool kasan_sample_page_alloc(unsigned int order) +{ + /* Fast-path for when sampling is disabled. */ + if (kasan_page_alloc_sample == 1) + return true; + + if (order < kasan_page_alloc_sample_order) + return true; + + if (this_cpu_dec_return(kasan_page_alloc_skip) < 0) { + this_cpu_write(kasan_page_alloc_skip, + kasan_page_alloc_sample - 1); + return true; + } + + return false; +} + #else /* CONFIG_KASAN_HW_TAGS */ static inline bool kasan_async_fault_possible(void) @@ -69,6 +91,11 @@ static inline bool kasan_sync_fault_possible(void) return true; } +static inline bool kasan_sample_page_alloc(unsigned int order) +{ + return true; +} + #endif /* CONFIG_KASAN_HW_TAGS */ #ifdef CONFIG_KASAN_GENERIC diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 0745aedebb37..7d980dc0000e 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1356,6 +1356,8 @@ out: * see the comment next to it. * 3. Skipping poisoning is requested via __GFP_SKIP_KASAN_POISON, * see the comment next to it. + * 4. The allocation is excluded from being checked due to sampling, + * see the call to kasan_unpoison_pages. * * Poisoning pages during deferred memory init will greatly lengthen the * process and cause problem in large memory systems as the deferred pages @@ -2468,7 +2470,8 @@ inline void post_alloc_hook(struct page *page, unsigned int order, { bool init = !want_init_on_free() && want_init_on_alloc(gfp_flags) && !should_skip_init(gfp_flags); - bool init_tags = init && (gfp_flags & __GFP_ZEROTAGS); + bool zero_tags = init && (gfp_flags & __GFP_ZEROTAGS); + bool reset_tags = !zero_tags; int i; set_page_private(page, 0); @@ -2491,30 +2494,42 @@ inline void post_alloc_hook(struct page *page, unsigned int order, */ /* - * If memory tags should be zeroed (which happens only when memory - * should be initialized as well). + * If memory tags should be zeroed + * (which happens only when memory should be initialized as well). */ - if (init_tags) { + if (zero_tags) { /* Initialize both memory and tags. */ for (i = 0; i != 1 << order; ++i) tag_clear_highpage(page + i); - /* Note that memory is already initialized by the loop above. */ + /* Take note that memory was initialized by the loop above. */ init = false; } if (!should_skip_kasan_unpoison(gfp_flags)) { - /* Unpoison shadow memory or set memory tags. */ - kasan_unpoison_pages(page, order, init); - - /* Note that memory is already initialized by KASAN. */ - if (kasan_has_integrated_init()) - init = false; - } else { - /* Ensure page_address() dereferencing does not fault. */ + /* Try unpoisoning (or setting tags) and initializing memory. */ + if (kasan_unpoison_pages(page, order, init)) { + /* Take note that memory was initialized by KASAN. */ + if (kasan_has_integrated_init()) + init = false; + /* Take note that memory tags were set by KASAN. */ + reset_tags = false; + } else { + /* + * KASAN decided to exclude this allocation from being + * poisoned due to sampling. Skip poisoning as well. + */ + SetPageSkipKASanPoison(page); + } + } + /* + * If memory tags have not been set, reset the page tags to ensure + * page_address() dereferencing does not fault. + */ + if (reset_tags) { for (i = 0; i != 1 << order; ++i) page_kasan_tag_reset(page + i); } - /* If memory is still not initialized, do it now. */ + /* If memory is still not initialized, initialize it now. */ if (init) kernel_init_pages(page, 1 << order); /* Propagate __GFP_SKIP_KASAN_POISON to page flags. */ -- cgit v1.2.3 From 831978e37e93bd3e36612917a4b193278950daff Mon Sep 17 00:00:00 2001 From: Vernon Yang Date: Wed, 21 Dec 2022 14:00:52 +0800 Subject: maple_tree: remove extra space and blank line Patch series "Clean up and refinement for maple tree", v2. This patchset cleans up and refines some maple tree code. A few small changes make the code easier to understand and for better readability. This patch (of 7): These extra space and blank lines are unnecessary, so drop them. Link: https://lkml.kernel.org/r/20221221060058.609003-1-vernon2gm@gmail.com Link: https://lkml.kernel.org/r/20221221060058.609003-2-vernon2gm@gmail.com Signed-off-by: Vernon Yang Reviewed-by: Liam R. Howlett Signed-off-by: Andrew Morton --- include/linux/maple_tree.h | 2 -- lib/maple_tree.c | 14 ++++---------- 2 files changed, 4 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/maple_tree.h b/include/linux/maple_tree.h index e594db58a0f1..4ee5a969441c 100644 --- a/include/linux/maple_tree.h +++ b/include/linux/maple_tree.h @@ -517,7 +517,6 @@ static inline void mas_reset(struct ma_state *mas) * entry. * * Note: may return the zero entry. - * */ #define mas_for_each(__mas, __entry, __max) \ while (((__entry) = mas_find((__mas), (__max))) != NULL) @@ -639,7 +638,6 @@ static inline void mt_set_in_rcu(struct maple_tree *mt) } static inline unsigned int mt_height(const struct maple_tree *mt) - { return (mt->ma_flags & MT_FLAGS_HEIGHT_MASK) >> MT_FLAGS_HEIGHT_OFFSET; } diff --git a/lib/maple_tree.c b/lib/maple_tree.c index 26e2045d3cda..975358bec754 100644 --- a/lib/maple_tree.c +++ b/lib/maple_tree.c @@ -183,7 +183,6 @@ static void ma_free_rcu(struct maple_node *node) call_rcu(&node->rcu, mt_free_rcu); } - static void mas_set_height(struct ma_state *mas) { unsigned int new_flags = mas->tree->ma_flags; @@ -468,7 +467,7 @@ static inline void mte_set_parent(struct maple_enode *enode, const struct maple_enode *parent, unsigned char slot) { - unsigned long val = (unsigned long) parent; + unsigned long val = (unsigned long)parent; unsigned long shift; unsigned long type; enum maple_type p_type = mte_node_type(parent); @@ -502,7 +501,7 @@ void mte_set_parent(struct maple_enode *enode, const struct maple_enode *parent, */ static inline unsigned int mte_parent_slot(const struct maple_enode *enode) { - unsigned long val = (unsigned long) mte_to_node(enode)->parent; + unsigned long val = (unsigned long)mte_to_node(enode)->parent; /* Root. */ if (val & 1) @@ -1278,7 +1277,6 @@ nomem_one: mas->alloc->total = success; mas_set_err(mas, -ENOMEM); return; - } /* @@ -2946,7 +2944,7 @@ next: mas->min = prev_min; mas->max = prev_max; mas->node = last; - return (void *) next; + return (void *)next; dead_node: mas_reset(mas); @@ -3466,7 +3464,6 @@ static inline bool mas_push_data(struct ma_state *mas, int height, */ static int mas_split(struct ma_state *mas, struct maple_big_node *b_node) { - struct maple_subtree_state mast; int height = 0; unsigned char mid_split, split = 0; @@ -3892,7 +3889,7 @@ next: goto dead_node; } while (!ma_is_leaf(type)); - return (void *) next; + return (void *)next; dead_node: mas_reset(mas); @@ -4710,7 +4707,6 @@ found: static inline void mas_rewalk(struct ma_state *mas, unsigned long index) { - retry: mas_set(mas, index); mas_state_walk(mas); @@ -4718,7 +4714,6 @@ retry: goto retry; return; - } /* @@ -5620,7 +5615,6 @@ static void mas_wr_store_setup(struct ma_wr_state *wr_mas) mas_reset(wr_mas->mas); } } - } /* Interface */ -- cgit v1.2.3 From eabb305293835b191ffe60234587ae8bf5e4e9fd Mon Sep 17 00:00:00 2001 From: Vernon Yang Date: Wed, 21 Dec 2022 14:00:56 +0800 Subject: maple_tree: remove the redundant code The macros CONFIG_DEBUG_MAPLE_TREE_VERBOSE no one uses, functions mas_dup_tree() and mas_dup_store() are not implemented, just function declaration, so drop it. Link: https://lkml.kernel.org/r/20221221060058.609003-6-vernon2gm@gmail.com Signed-off-by: Vernon Yang Reviewed-by: Liam R. Howlett Signed-off-by: Andrew Morton --- include/linux/maple_tree.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/maple_tree.h b/include/linux/maple_tree.h index 4ee5a969441c..815a27661517 100644 --- a/include/linux/maple_tree.h +++ b/include/linux/maple_tree.h @@ -12,7 +12,6 @@ #include #include /* #define CONFIG_MAPLE_RCU_DISABLED */ -/* #define CONFIG_DEBUG_MAPLE_TREE_VERBOSE */ /* * Allocated nodes are mutable until they have been inserted into the tree, @@ -483,9 +482,6 @@ static inline bool mas_is_paused(struct ma_state *mas) return mas->node == MAS_PAUSE; } -void mas_dup_tree(struct ma_state *oldmas, struct ma_state *mas); -void mas_dup_store(struct ma_state *mas, void *entry); - /* * This finds an empty area from the highest address to the lowest. * AKA "Topdown" version, -- cgit v1.2.3 From 318e9342fbbb6888d903d86e83865609901a1c65 Mon Sep 17 00:00:00 2001 From: Vishal Moola (Oracle) Date: Wed, 21 Dec 2022 10:08:45 -0800 Subject: mm/memory: add vm_normal_folio() Patch series "Convert deactivate_page() to folio_deactivate()", v4. Deactivate_page() has already been converted to use folios. This patch series modifies the callers of deactivate_page() to use folios. It also introduces vm_normal_folio() to assist with folio conversions, and converts deactivate_page() to folio_deactivate() which takes in a folio. This patch (of 4): Introduce a wrapper function called vm_normal_folio(). This function calls vm_normal_page() and returns the folio of the page found, or null if no page is found. This function allows callers to get a folio from a pte, which will eventually allow them to completely replace their struct page variables with struct folio instead. Link: https://lkml.kernel.org/r/20221221180848.20774-1-vishal.moola@gmail.com Link: https://lkml.kernel.org/r/20221221180848.20774-2-vishal.moola@gmail.com Signed-off-by: Vishal Moola (Oracle) Reviewed-by: Matthew Wilcox (Oracle) Cc: SeongJae Park Signed-off-by: Andrew Morton --- include/linux/mm.h | 2 ++ mm/memory.c | 10 ++++++++++ 2 files changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 253b2d7489e6..8e14183dfc58 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1968,6 +1968,8 @@ static inline bool can_do_mlock(void) { return false; } extern int user_shm_lock(size_t, struct ucounts *); extern void user_shm_unlock(size_t, struct ucounts *); +struct folio *vm_normal_folio(struct vm_area_struct *vma, unsigned long addr, + pte_t pte); struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, pte_t pte); struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, diff --git a/mm/memory.c b/mm/memory.c index ca490596b36f..1598051a2a24 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -625,6 +625,16 @@ out: return pfn_to_page(pfn); } +struct folio *vm_normal_folio(struct vm_area_struct *vma, unsigned long addr, + pte_t pte) +{ + struct page *page = vm_normal_page(vma, addr, pte); + + if (page) + return page_folio(page); + return NULL; +} + #ifdef CONFIG_TRANSPARENT_HUGEPAGE struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t pmd) -- cgit v1.2.3 From 5a9e34747c9f731bbb6b7fd7521c4fec0d840593 Mon Sep 17 00:00:00 2001 From: Vishal Moola (Oracle) Date: Wed, 21 Dec 2022 10:08:48 -0800 Subject: mm/swap: convert deactivate_page() to folio_deactivate() Deactivate_page() has already been converted to use folios, this change converts it to take in a folio argument instead of calling page_folio(). It also renames the function folio_deactivate() to be more consistent with other folio functions. [akpm@linux-foundation.org: fix left-over comments, per Yu Zhao] Link: https://lkml.kernel.org/r/20221221180848.20774-5-vishal.moola@gmail.com Signed-off-by: Vishal Moola (Oracle) Reviewed-by: Matthew Wilcox (Oracle) Reviewed-by: SeongJae Park Signed-off-by: Andrew Morton --- include/linux/swap.h | 2 +- mm/damon/paddr.c | 2 +- mm/madvise.c | 4 ++-- mm/page-writeback.c | 4 ++-- mm/swap.c | 14 ++++++-------- mm/vmscan.c | 2 +- 6 files changed, 13 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 93f1cebd8545..87cecb8c0bdc 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -401,7 +401,7 @@ extern void lru_add_drain(void); extern void lru_add_drain_cpu(int cpu); extern void lru_add_drain_cpu_zone(struct zone *zone); extern void lru_add_drain_all(void); -extern void deactivate_page(struct page *page); +void folio_deactivate(struct folio *folio); void folio_mark_lazyfree(struct folio *folio); extern void swap_setup(void); diff --git a/mm/damon/paddr.c b/mm/damon/paddr.c index 884c8bf18b12..6334c99e5152 100644 --- a/mm/damon/paddr.c +++ b/mm/damon/paddr.c @@ -297,7 +297,7 @@ static inline unsigned long damon_pa_mark_accessed_or_deactivate( if (mark_accessed) folio_mark_accessed(folio); else - deactivate_page(&folio->page); + folio_deactivate(folio); folio_put(folio); applied += folio_nr_pages(folio); } diff --git a/mm/madvise.c b/mm/madvise.c index 575ebf0363b8..e407d335e614 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -416,7 +416,7 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd, list_add(&folio->lru, &folio_list); } } else - deactivate_page(&folio->page); + folio_deactivate(folio); huge_unlock: spin_unlock(ptl); if (pageout) @@ -510,7 +510,7 @@ regular_folio: list_add(&folio->lru, &folio_list); } } else - deactivate_page(&folio->page); + folio_deactivate(folio); } arch_leave_lazy_mmu_mode(); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index ad608ef2a243..41128ea9c997 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2846,11 +2846,11 @@ bool folio_mark_dirty(struct folio *folio) if (likely(mapping)) { /* - * readahead/lru_deactivate_page could remain + * readahead/folio_deactivate could remain * PG_readahead/PG_reclaim due to race with folio_end_writeback * About readahead, if the folio is written, the flags would be * reset. So no problem. - * About lru_deactivate_page, if the folio is redirtied, + * About folio_deactivate, if the folio is redirtied, * the flag will be reset. So no problem. but if the * folio is used by readahead it will confuse readahead * and make it restart the size rampup process. But it's diff --git a/mm/swap.c b/mm/swap.c index 5e5eba186930..e54e2a252e27 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -733,17 +733,15 @@ void deactivate_file_folio(struct folio *folio) } /* - * deactivate_page - deactivate a page - * @page: page to deactivate + * folio_deactivate - deactivate a folio + * @folio: folio to deactivate * - * deactivate_page() moves @page to the inactive list if @page was on the active - * list and was not an unevictable page. This is done to accelerate the reclaim - * of @page. + * folio_deactivate() moves @folio to the inactive list if @folio was on the + * active list and was not unevictable. This is done to accelerate the + * reclaim of @folio. */ -void deactivate_page(struct page *page) +void folio_deactivate(struct folio *folio) { - struct folio *folio = page_folio(page); - if (folio_test_lru(folio) && !folio_test_unevictable(folio) && (folio_test_active(folio) || lru_gen_enabled())) { struct folio_batch *fbatch; diff --git a/mm/vmscan.c b/mm/vmscan.c index bd6637fcd8f9..aa8c252949da 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1920,7 +1920,7 @@ retry: !test_bit(PGDAT_DIRTY, &pgdat->flags))) { /* * Immediately reclaim when written back. - * Similar in principle to deactivate_page() + * Similar in principle to folio_deactivate() * except we already have the folio isolated * and know it's dirty */ -- cgit v1.2.3 From 0b7b8704ddcee372099a2bc6781db6ab273a85d5 Mon Sep 17 00:00:00 2001 From: Hao Sun Date: Wed, 21 Dec 2022 22:42:45 +0800 Subject: mm: new primitive kvmemdup() Similar to kmemdup(), but support large amount of bytes with kvmalloc() and does *not* guarantee that the result will be physically contiguous. Use only in cases where kvmalloc() is needed and free it with kvfree(). Also adapt policy_unpack.c in case someone bisect into this. Link: https://lkml.kernel.org/r/20221221144245.27164-1-sunhao.th@gmail.com Signed-off-by: Hao Sun Suggested-by: Daniel Borkmann Cc: Nick Terrell Cc: John Johansen Cc: Paul Moore Cc: James Morris Cc: "Serge E. Hallyn" Signed-off-by: Andrew Morton --- include/linux/string.h | 1 + mm/util.c | 24 +++++++++++++++++++++++- security/apparmor/policy_unpack.c | 11 +---------- 3 files changed, 25 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/string.h b/include/linux/string.h index db28802ab0a6..c062c581a98b 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -177,6 +177,7 @@ extern char *kstrdup(const char *s, gfp_t gfp) __malloc; extern const char *kstrdup_const(const char *s, gfp_t gfp); extern char *kstrndup(const char *s, size_t len, gfp_t gfp); extern void *kmemdup(const void *src, size_t len, gfp_t gfp) __realloc_size(2); +extern void *kvmemdup(const void *src, size_t len, gfp_t gfp) __realloc_size(2); extern char *kmemdup_nul(const char *s, size_t len, gfp_t gfp); extern char **argv_split(gfp_t gfp, const char *str, int *argcp); diff --git a/mm/util.c b/mm/util.c index b56c92fb910f..cec9327b27b4 100644 --- a/mm/util.c +++ b/mm/util.c @@ -120,7 +120,8 @@ EXPORT_SYMBOL(kstrndup); * @len: memory region length * @gfp: GFP mask to use * - * Return: newly allocated copy of @src or %NULL in case of error + * Return: newly allocated copy of @src or %NULL in case of error, + * result is physically contiguous. Use kfree() to free. */ void *kmemdup(const void *src, size_t len, gfp_t gfp) { @@ -133,6 +134,27 @@ void *kmemdup(const void *src, size_t len, gfp_t gfp) } EXPORT_SYMBOL(kmemdup); +/** + * kvmemdup - duplicate region of memory + * + * @src: memory region to duplicate + * @len: memory region length + * @gfp: GFP mask to use + * + * Return: newly allocated copy of @src or %NULL in case of error, + * result may be not physically contiguous. Use kvfree() to free. + */ +void *kvmemdup(const void *src, size_t len, gfp_t gfp) +{ + void *p; + + p = kvmalloc(len, gfp); + if (p) + memcpy(p, src, len); + return p; +} +EXPORT_SYMBOL(kvmemdup); + /** * kmemdup_nul - Create a NUL-terminated string from unterminated data * @s: The data to stringify diff --git a/security/apparmor/policy_unpack.c b/security/apparmor/policy_unpack.c index 66915653108c..5e9949832af6 100644 --- a/security/apparmor/policy_unpack.c +++ b/security/apparmor/policy_unpack.c @@ -161,15 +161,6 @@ VISIBLE_IF_KUNIT bool aa_inbounds(struct aa_ext *e, size_t size) } EXPORT_SYMBOL_IF_KUNIT(aa_inbounds); -static void *kvmemdup(const void *src, size_t len) -{ - void *p = kvmalloc(len, GFP_KERNEL); - - if (p) - memcpy(p, src, len); - return p; -} - /** * aa_unpack_u16_chunk - test and do bounds checking for a u16 size based chunk * @e: serialized data read head (NOT NULL) @@ -1027,7 +1018,7 @@ static struct aa_profile *unpack_profile(struct aa_ext *e, char **ns_name) data->key = key; data->size = aa_unpack_blob(e, &data->data, NULL); - data->data = kvmemdup(data->data, data->size); + data->data = kvmemdup(data->data, data->size, GFP_KERNEL); if (data->size && !data->data) { kfree_sensitive(data->key); kfree_sensitive(data); -- cgit v1.2.3 From b5054174ac7c7d8fae15deee7ddc0e20fd604f30 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 21 Dec 2022 21:24:54 +0000 Subject: mm: move FOLL_* defs to mm_types.h Move FOLL_* definitions to linux/mm_types.h to make them more accessible without having to drag in all of linux/mm.h and everything that drags in too[1]. Link: https://lkml.kernel.org/r/2161258.1671657894@warthog.procyon.org.uk Signed-off-by: David Howells Suggested-by: Matthew Wilcox Reviewed-by: John Hubbard Cc: Christoph Hellwig Cc: Al Viro Signed-off-by: Andrew Morton --- include/linux/mm.h | 75 ------------------------------------------------ include/linux/mm_types.h | 75 ++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 75 insertions(+), 75 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 8e14183dfc58..d68579bf8484 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3057,81 +3057,6 @@ static inline vm_fault_t vmf_error(int err) struct page *follow_page(struct vm_area_struct *vma, unsigned long address, unsigned int foll_flags); -#define FOLL_WRITE 0x01 /* check pte is writable */ -#define FOLL_TOUCH 0x02 /* mark page accessed */ -#define FOLL_GET 0x04 /* do get_page on page */ -#define FOLL_DUMP 0x08 /* give error on hole if it would be zero */ -#define FOLL_FORCE 0x10 /* get_user_pages read/write w/o permission */ -#define FOLL_NOWAIT 0x20 /* if a disk transfer is needed, start the IO - * and return without waiting upon it */ -#define FOLL_NOFAULT 0x80 /* do not fault in pages */ -#define FOLL_HWPOISON 0x100 /* check page is hwpoisoned */ -#define FOLL_TRIED 0x800 /* a retry, previous pass started an IO */ -#define FOLL_REMOTE 0x2000 /* we are working on non-current tsk/mm */ -#define FOLL_ANON 0x8000 /* don't do file mappings */ -#define FOLL_LONGTERM 0x10000 /* mapping lifetime is indefinite: see below */ -#define FOLL_SPLIT_PMD 0x20000 /* split huge pmd before returning */ -#define FOLL_PIN 0x40000 /* pages must be released via unpin_user_page */ -#define FOLL_FAST_ONLY 0x80000 /* gup_fast: prevent fall-back to slow gup */ -#define FOLL_PCI_P2PDMA 0x100000 /* allow returning PCI P2PDMA pages */ -#define FOLL_INTERRUPTIBLE 0x200000 /* allow interrupts from generic signals */ - -/* - * FOLL_PIN and FOLL_LONGTERM may be used in various combinations with each - * other. Here is what they mean, and how to use them: - * - * FOLL_LONGTERM indicates that the page will be held for an indefinite time - * period _often_ under userspace control. This is in contrast to - * iov_iter_get_pages(), whose usages are transient. - * - * FIXME: For pages which are part of a filesystem, mappings are subject to the - * lifetime enforced by the filesystem and we need guarantees that longterm - * users like RDMA and V4L2 only establish mappings which coordinate usage with - * the filesystem. Ideas for this coordination include revoking the longterm - * pin, delaying writeback, bounce buffer page writeback, etc. As FS DAX was - * added after the problem with filesystems was found FS DAX VMAs are - * specifically failed. Filesystem pages are still subject to bugs and use of - * FOLL_LONGTERM should be avoided on those pages. - * - * FIXME: Also NOTE that FOLL_LONGTERM is not supported in every GUP call. - * Currently only get_user_pages() and get_user_pages_fast() support this flag - * and calls to get_user_pages_[un]locked are specifically not allowed. This - * is due to an incompatibility with the FS DAX check and - * FAULT_FLAG_ALLOW_RETRY. - * - * In the CMA case: long term pins in a CMA region would unnecessarily fragment - * that region. And so, CMA attempts to migrate the page before pinning, when - * FOLL_LONGTERM is specified. - * - * FOLL_PIN indicates that a special kind of tracking (not just page->_refcount, - * but an additional pin counting system) will be invoked. This is intended for - * anything that gets a page reference and then touches page data (for example, - * Direct IO). This lets the filesystem know that some non-file-system entity is - * potentially changing the pages' data. In contrast to FOLL_GET (whose pages - * are released via put_page()), FOLL_PIN pages must be released, ultimately, by - * a call to unpin_user_page(). - * - * FOLL_PIN is similar to FOLL_GET: both of these pin pages. They use different - * and separate refcounting mechanisms, however, and that means that each has - * its own acquire and release mechanisms: - * - * FOLL_GET: get_user_pages*() to acquire, and put_page() to release. - * - * FOLL_PIN: pin_user_pages*() to acquire, and unpin_user_pages to release. - * - * FOLL_PIN and FOLL_GET are mutually exclusive for a given function call. - * (The underlying pages may experience both FOLL_GET-based and FOLL_PIN-based - * calls applied to them, and that's perfectly OK. This is a constraint on the - * callers, not on the pages.) - * - * FOLL_PIN should be set internally by the pin_user_pages*() APIs, never - * directly by the caller. That's in order to help avoid mismatches when - * releasing pages: get_user_pages*() pages must be released via put_page(), - * while pin_user_pages*() pages must be released via unpin_user_page(). - * - * Please see Documentation/core-api/pin_user_pages.rst for more information. - */ - static inline int vm_fault_to_errno(vm_fault_t vm_fault, int foll_flags) { if (vm_fault & VM_FAULT_OOM) diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 9757067c3053..1118e381fcdc 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -1085,4 +1085,79 @@ enum fault_flag { typedef unsigned int __bitwise zap_flags_t; +/* + * FOLL_PIN and FOLL_LONGTERM may be used in various combinations with each + * other. Here is what they mean, and how to use them: + * + * FOLL_LONGTERM indicates that the page will be held for an indefinite time + * period _often_ under userspace control. This is in contrast to + * iov_iter_get_pages(), whose usages are transient. + * + * FIXME: For pages which are part of a filesystem, mappings are subject to the + * lifetime enforced by the filesystem and we need guarantees that longterm + * users like RDMA and V4L2 only establish mappings which coordinate usage with + * the filesystem. Ideas for this coordination include revoking the longterm + * pin, delaying writeback, bounce buffer page writeback, etc. As FS DAX was + * added after the problem with filesystems was found FS DAX VMAs are + * specifically failed. Filesystem pages are still subject to bugs and use of + * FOLL_LONGTERM should be avoided on those pages. + * + * FIXME: Also NOTE that FOLL_LONGTERM is not supported in every GUP call. + * Currently only get_user_pages() and get_user_pages_fast() support this flag + * and calls to get_user_pages_[un]locked are specifically not allowed. This + * is due to an incompatibility with the FS DAX check and + * FAULT_FLAG_ALLOW_RETRY. + * + * In the CMA case: long term pins in a CMA region would unnecessarily fragment + * that region. And so, CMA attempts to migrate the page before pinning, when + * FOLL_LONGTERM is specified. + * + * FOLL_PIN indicates that a special kind of tracking (not just page->_refcount, + * but an additional pin counting system) will be invoked. This is intended for + * anything that gets a page reference and then touches page data (for example, + * Direct IO). This lets the filesystem know that some non-file-system entity is + * potentially changing the pages' data. In contrast to FOLL_GET (whose pages + * are released via put_page()), FOLL_PIN pages must be released, ultimately, by + * a call to unpin_user_page(). + * + * FOLL_PIN is similar to FOLL_GET: both of these pin pages. They use different + * and separate refcounting mechanisms, however, and that means that each has + * its own acquire and release mechanisms: + * + * FOLL_GET: get_user_pages*() to acquire, and put_page() to release. + * + * FOLL_PIN: pin_user_pages*() to acquire, and unpin_user_pages to release. + * + * FOLL_PIN and FOLL_GET are mutually exclusive for a given function call. + * (The underlying pages may experience both FOLL_GET-based and FOLL_PIN-based + * calls applied to them, and that's perfectly OK. This is a constraint on the + * callers, not on the pages.) + * + * FOLL_PIN should be set internally by the pin_user_pages*() APIs, never + * directly by the caller. That's in order to help avoid mismatches when + * releasing pages: get_user_pages*() pages must be released via put_page(), + * while pin_user_pages*() pages must be released via unpin_user_page(). + * + * Please see Documentation/core-api/pin_user_pages.rst for more information. + */ + +#define FOLL_WRITE 0x01 /* check pte is writable */ +#define FOLL_TOUCH 0x02 /* mark page accessed */ +#define FOLL_GET 0x04 /* do get_page on page */ +#define FOLL_DUMP 0x08 /* give error on hole if it would be zero */ +#define FOLL_FORCE 0x10 /* get_user_pages read/write w/o permission */ +#define FOLL_NOWAIT 0x20 /* if a disk transfer is needed, start the IO + * and return without waiting upon it */ +#define FOLL_NOFAULT 0x80 /* do not fault in pages */ +#define FOLL_HWPOISON 0x100 /* check page is hwpoisoned */ +#define FOLL_TRIED 0x800 /* a retry, previous pass started an IO */ +#define FOLL_REMOTE 0x2000 /* we are working on non-current tsk/mm */ +#define FOLL_ANON 0x8000 /* don't do file mappings */ +#define FOLL_LONGTERM 0x10000 /* mapping lifetime is indefinite: see below */ +#define FOLL_SPLIT_PMD 0x20000 /* split huge pmd before returning */ +#define FOLL_PIN 0x40000 /* pages must be released via unpin_user_page */ +#define FOLL_FAST_ONLY 0x80000 /* gup_fast: prevent fall-back to slow gup */ +#define FOLL_PCI_P2PDMA 0x100000 /* allow returning PCI P2PDMA pages */ +#define FOLL_INTERRUPTIBLE 0x200000 /* allow interrupts from generic signals */ + #endif /* _LINUX_MM_TYPES_H */ -- cgit v1.2.3 From 391655fe08d1f942359a11148aa9aaf3f99d6d6f Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Wed, 21 Dec 2022 21:18:59 -0700 Subject: mm: multi-gen LRU: rename lru_gen_struct to lru_gen_folio Patch series "mm: multi-gen LRU: memcg LRU", v3. Overview ======== An memcg LRU is a per-node LRU of memcgs. It is also an LRU of LRUs, since each node and memcg combination has an LRU of folios (see mem_cgroup_lruvec()). Its goal is to improve the scalability of global reclaim, which is critical to system-wide memory overcommit in data centers. Note that memcg reclaim is currently out of scope. Its memory bloat is a pointer to each lruvec and negligible to each pglist_data. In terms of traversing memcgs during global reclaim, it improves the best-case complexity from O(n) to O(1) and does not affect the worst-case complexity O(n). Therefore, on average, it has a sublinear complexity in contrast to the current linear complexity. The basic structure of an memcg LRU can be understood by an analogy to the active/inactive LRU (of folios): 1. It has the young and the old (generations), i.e., the counterparts to the active and the inactive; 2. The increment of max_seq triggers promotion, i.e., the counterpart to activation; 3. Other events trigger similar operations, e.g., offlining an memcg triggers demotion, i.e., the counterpart to deactivation. In terms of global reclaim, it has two distinct features: 1. Sharding, which allows each thread to start at a random memcg (in the old generation) and improves parallelism; 2. Eventual fairness, which allows direct reclaim to bail out at will and reduces latency without affecting fairness over some time. The commit message in patch 6 details the workflow: https://lore.kernel.org/r/20221222041905.2431096-7-yuzhao@google.com/ The following is a simple test to quickly verify its effectiveness. Test design: 1. Create multiple memcgs. 2. Each memcg contains a job (fio). 3. All jobs access the same amount of memory randomly. 4. The system does not experience global memory pressure. 5. Periodically write to the root memory.reclaim. Desired outcome: 1. All memcgs have similar pgsteal counts, i.e., stddev(pgsteal) over mean(pgsteal) is close to 0%. 2. The total pgsteal is close to the total requested through memory.reclaim, i.e., sum(pgsteal) over sum(requested) is close to 100%. Actual outcome [1]: MGLRU off MGLRU on stddev(pgsteal) / mean(pgsteal) 75% 20% sum(pgsteal) / sum(requested) 425% 95% #################################################################### MEMCGS=128 for ((memcg = 0; memcg < $MEMCGS; memcg++)); do mkdir /sys/fs/cgroup/memcg$memcg done start() { echo $BASHPID > /sys/fs/cgroup/memcg$memcg/cgroup.procs fio -name=memcg$memcg --numjobs=1 --ioengine=mmap \ --filename=/dev/zero --size=1920M --rw=randrw \ --rate=64m,64m --random_distribution=random \ --fadvise_hint=0 --time_based --runtime=10h \ --group_reporting --minimal } for ((memcg = 0; memcg < $MEMCGS; memcg++)); do start & done sleep 600 for ((i = 0; i < 600; i++)); do echo 256m >/sys/fs/cgroup/memory.reclaim sleep 6 done for ((memcg = 0; memcg < $MEMCGS; memcg++)); do grep "pgsteal " /sys/fs/cgroup/memcg$memcg/memory.stat done #################################################################### [1]: This was obtained from running the above script (touches less than 256GB memory) on an EPYC 7B13 with 512GB DRAM for over an hour. This patch (of 8): The new name lru_gen_folio will be more distinct from the coming lru_gen_memcg. Link: https://lkml.kernel.org/r/20221222041905.2431096-1-yuzhao@google.com Link: https://lkml.kernel.org/r/20221222041905.2431096-2-yuzhao@google.com Signed-off-by: Yu Zhao Cc: Johannes Weiner Cc: Jonathan Corbet Cc: Michael Larabel Cc: Michal Hocko Cc: Mike Rapoport Cc: Roman Gushchin Cc: Suren Baghdasaryan Signed-off-by: Andrew Morton --- include/linux/mm_inline.h | 4 ++-- include/linux/mmzone.h | 6 +++--- mm/vmscan.c | 34 +++++++++++++++++----------------- mm/workingset.c | 4 ++-- 4 files changed, 24 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index ff3f3f23f649..177b8b1dd43c 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -178,7 +178,7 @@ static inline void lru_gen_update_size(struct lruvec *lruvec, struct folio *foli int zone = folio_zonenum(folio); int delta = folio_nr_pages(folio); enum lru_list lru = type * LRU_INACTIVE_FILE; - struct lru_gen_struct *lrugen = &lruvec->lrugen; + struct lru_gen_folio *lrugen = &lruvec->lrugen; VM_WARN_ON_ONCE(old_gen != -1 && old_gen >= MAX_NR_GENS); VM_WARN_ON_ONCE(new_gen != -1 && new_gen >= MAX_NR_GENS); @@ -224,7 +224,7 @@ static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, int gen = folio_lru_gen(folio); int type = folio_is_file_lru(folio); int zone = folio_zonenum(folio); - struct lru_gen_struct *lrugen = &lruvec->lrugen; + struct lru_gen_folio *lrugen = &lruvec->lrugen; VM_WARN_ON_ONCE_FOLIO(gen != -1, folio); diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index cd28a100d9e4..1686fcc4ed01 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -404,7 +404,7 @@ enum { * The number of pages in each generation is eventually consistent and therefore * can be transiently negative when reset_batch_size() is pending. */ -struct lru_gen_struct { +struct lru_gen_folio { /* the aging increments the youngest generation number */ unsigned long max_seq; /* the eviction increments the oldest generation numbers */ @@ -461,7 +461,7 @@ struct lru_gen_mm_state { struct lru_gen_mm_walk { /* the lruvec under reclaim */ struct lruvec *lruvec; - /* unstable max_seq from lru_gen_struct */ + /* unstable max_seq from lru_gen_folio */ unsigned long max_seq; /* the next address within an mm to scan */ unsigned long next_addr; @@ -524,7 +524,7 @@ struct lruvec { unsigned long flags; #ifdef CONFIG_LRU_GEN /* evictable pages divided into generations */ - struct lru_gen_struct lrugen; + struct lru_gen_folio lrugen; /* to concurrently iterate lru_gen_mm_list */ struct lru_gen_mm_state mm_state; #endif diff --git a/mm/vmscan.c b/mm/vmscan.c index aa8c252949da..5505f54871c9 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -3215,7 +3215,7 @@ static int get_nr_gens(struct lruvec *lruvec, int type) static bool __maybe_unused seq_is_valid(struct lruvec *lruvec) { - /* see the comment on lru_gen_struct */ + /* see the comment on lru_gen_folio */ return get_nr_gens(lruvec, LRU_GEN_FILE) >= MIN_NR_GENS && get_nr_gens(lruvec, LRU_GEN_FILE) <= get_nr_gens(lruvec, LRU_GEN_ANON) && get_nr_gens(lruvec, LRU_GEN_ANON) <= MAX_NR_GENS; @@ -3612,7 +3612,7 @@ struct ctrl_pos { static void read_ctrl_pos(struct lruvec *lruvec, int type, int tier, int gain, struct ctrl_pos *pos) { - struct lru_gen_struct *lrugen = &lruvec->lrugen; + struct lru_gen_folio *lrugen = &lruvec->lrugen; int hist = lru_hist_from_seq(lrugen->min_seq[type]); pos->refaulted = lrugen->avg_refaulted[type][tier] + @@ -3627,7 +3627,7 @@ static void read_ctrl_pos(struct lruvec *lruvec, int type, int tier, int gain, static void reset_ctrl_pos(struct lruvec *lruvec, int type, bool carryover) { int hist, tier; - struct lru_gen_struct *lrugen = &lruvec->lrugen; + struct lru_gen_folio *lrugen = &lruvec->lrugen; bool clear = carryover ? NR_HIST_GENS == 1 : NR_HIST_GENS > 1; unsigned long seq = carryover ? lrugen->min_seq[type] : lrugen->max_seq + 1; @@ -3704,7 +3704,7 @@ static int folio_update_gen(struct folio *folio, int gen) static int folio_inc_gen(struct lruvec *lruvec, struct folio *folio, bool reclaiming) { int type = folio_is_file_lru(folio); - struct lru_gen_struct *lrugen = &lruvec->lrugen; + struct lru_gen_folio *lrugen = &lruvec->lrugen; int new_gen, old_gen = lru_gen_from_seq(lrugen->min_seq[type]); unsigned long new_flags, old_flags = READ_ONCE(folio->flags); @@ -3749,7 +3749,7 @@ static void update_batch_size(struct lru_gen_mm_walk *walk, struct folio *folio, static void reset_batch_size(struct lruvec *lruvec, struct lru_gen_mm_walk *walk) { int gen, type, zone; - struct lru_gen_struct *lrugen = &lruvec->lrugen; + struct lru_gen_folio *lrugen = &lruvec->lrugen; walk->batched = 0; @@ -4263,7 +4263,7 @@ static bool inc_min_seq(struct lruvec *lruvec, int type, bool can_swap) { int zone; int remaining = MAX_LRU_BATCH; - struct lru_gen_struct *lrugen = &lruvec->lrugen; + struct lru_gen_folio *lrugen = &lruvec->lrugen; int new_gen, old_gen = lru_gen_from_seq(lrugen->min_seq[type]); if (type == LRU_GEN_ANON && !can_swap) @@ -4299,7 +4299,7 @@ static bool try_to_inc_min_seq(struct lruvec *lruvec, bool can_swap) { int gen, type, zone; bool success = false; - struct lru_gen_struct *lrugen = &lruvec->lrugen; + struct lru_gen_folio *lrugen = &lruvec->lrugen; DEFINE_MIN_SEQ(lruvec); VM_WARN_ON_ONCE(!seq_is_valid(lruvec)); @@ -4320,7 +4320,7 @@ next: ; } - /* see the comment on lru_gen_struct */ + /* see the comment on lru_gen_folio */ if (can_swap) { min_seq[LRU_GEN_ANON] = min(min_seq[LRU_GEN_ANON], min_seq[LRU_GEN_FILE]); min_seq[LRU_GEN_FILE] = max(min_seq[LRU_GEN_ANON], lrugen->min_seq[LRU_GEN_FILE]); @@ -4342,7 +4342,7 @@ static void inc_max_seq(struct lruvec *lruvec, bool can_swap, bool force_scan) { int prev, next; int type, zone; - struct lru_gen_struct *lrugen = &lruvec->lrugen; + struct lru_gen_folio *lrugen = &lruvec->lrugen; spin_lock_irq(&lruvec->lru_lock); @@ -4400,7 +4400,7 @@ static bool try_to_inc_max_seq(struct lruvec *lruvec, unsigned long max_seq, bool success; struct lru_gen_mm_walk *walk; struct mm_struct *mm = NULL; - struct lru_gen_struct *lrugen = &lruvec->lrugen; + struct lru_gen_folio *lrugen = &lruvec->lrugen; VM_WARN_ON_ONCE(max_seq > READ_ONCE(lrugen->max_seq)); @@ -4465,7 +4465,7 @@ static bool should_run_aging(struct lruvec *lruvec, unsigned long max_seq, unsig unsigned long old = 0; unsigned long young = 0; unsigned long total = 0; - struct lru_gen_struct *lrugen = &lruvec->lrugen; + struct lru_gen_folio *lrugen = &lruvec->lrugen; struct mem_cgroup *memcg = lruvec_memcg(lruvec); for (type = !can_swap; type < ANON_AND_FILE; type++) { @@ -4750,7 +4750,7 @@ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, int tier_idx) int delta = folio_nr_pages(folio); int refs = folio_lru_refs(folio); int tier = lru_tier_from_refs(refs); - struct lru_gen_struct *lrugen = &lruvec->lrugen; + struct lru_gen_folio *lrugen = &lruvec->lrugen; VM_WARN_ON_ONCE_FOLIO(gen >= MAX_NR_GENS, folio); @@ -4850,7 +4850,7 @@ static int scan_folios(struct lruvec *lruvec, struct scan_control *sc, int scanned = 0; int isolated = 0; int remaining = MAX_LRU_BATCH; - struct lru_gen_struct *lrugen = &lruvec->lrugen; + struct lru_gen_folio *lrugen = &lruvec->lrugen; struct mem_cgroup *memcg = lruvec_memcg(lruvec); VM_WARN_ON_ONCE(!list_empty(list)); @@ -5251,7 +5251,7 @@ done: static bool __maybe_unused state_is_valid(struct lruvec *lruvec) { - struct lru_gen_struct *lrugen = &lruvec->lrugen; + struct lru_gen_folio *lrugen = &lruvec->lrugen; if (lrugen->enabled) { enum lru_list lru; @@ -5530,7 +5530,7 @@ static void lru_gen_seq_show_full(struct seq_file *m, struct lruvec *lruvec, int i; int type, tier; int hist = lru_hist_from_seq(seq); - struct lru_gen_struct *lrugen = &lruvec->lrugen; + struct lru_gen_folio *lrugen = &lruvec->lrugen; for (tier = 0; tier < MAX_NR_TIERS; tier++) { seq_printf(m, " %10d", tier); @@ -5580,7 +5580,7 @@ static int lru_gen_seq_show(struct seq_file *m, void *v) unsigned long seq; bool full = !debugfs_real_fops(m->file)->write; struct lruvec *lruvec = v; - struct lru_gen_struct *lrugen = &lruvec->lrugen; + struct lru_gen_folio *lrugen = &lruvec->lrugen; int nid = lruvec_pgdat(lruvec)->node_id; struct mem_cgroup *memcg = lruvec_memcg(lruvec); DEFINE_MAX_SEQ(lruvec); @@ -5834,7 +5834,7 @@ void lru_gen_init_lruvec(struct lruvec *lruvec) { int i; int gen, type, zone; - struct lru_gen_struct *lrugen = &lruvec->lrugen; + struct lru_gen_folio *lrugen = &lruvec->lrugen; lrugen->max_seq = MIN_NR_GENS + 1; lrugen->enabled = lru_gen_enabled(); diff --git a/mm/workingset.c b/mm/workingset.c index 1a86645b7b3c..fd666584515c 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -223,7 +223,7 @@ static void *lru_gen_eviction(struct folio *folio) unsigned long token; unsigned long min_seq; struct lruvec *lruvec; - struct lru_gen_struct *lrugen; + struct lru_gen_folio *lrugen; int type = folio_is_file_lru(folio); int delta = folio_nr_pages(folio); int refs = folio_lru_refs(folio); @@ -252,7 +252,7 @@ static void lru_gen_refault(struct folio *folio, void *shadow) unsigned long token; unsigned long min_seq; struct lruvec *lruvec; - struct lru_gen_struct *lrugen; + struct lru_gen_folio *lrugen; struct mem_cgroup *memcg; struct pglist_data *pgdat; int type = folio_is_file_lru(folio); -- cgit v1.2.3 From 6df1b2212950aae2b2188c6645ea18e2a9e3fdd5 Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Wed, 21 Dec 2022 21:19:00 -0700 Subject: mm: multi-gen LRU: rename lrugen->lists[] to lrugen->folios[] lru_gen_folio will be chained into per-node lists by the coming lrugen->list. Link: https://lkml.kernel.org/r/20221222041905.2431096-3-yuzhao@google.com Signed-off-by: Yu Zhao Cc: Johannes Weiner Cc: Jonathan Corbet Cc: Michael Larabel Cc: Michal Hocko Cc: Mike Rapoport Cc: Roman Gushchin Cc: Suren Baghdasaryan Signed-off-by: Andrew Morton --- Documentation/mm/multigen_lru.rst | 8 ++++---- include/linux/mm_inline.h | 4 ++-- include/linux/mmzone.h | 8 ++++---- mm/vmscan.c | 20 ++++++++++---------- 4 files changed, 20 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/Documentation/mm/multigen_lru.rst b/Documentation/mm/multigen_lru.rst index d7062c6a8946..d8f721f98868 100644 --- a/Documentation/mm/multigen_lru.rst +++ b/Documentation/mm/multigen_lru.rst @@ -89,15 +89,15 @@ variables are monotonically increasing. Generation numbers are truncated into ``order_base_2(MAX_NR_GENS+1)`` bits in order to fit into the gen counter in ``folio->flags``. Each -truncated generation number is an index to ``lrugen->lists[]``. The +truncated generation number is an index to ``lrugen->folios[]``. The sliding window technique is used to track at least ``MIN_NR_GENS`` and at most ``MAX_NR_GENS`` generations. The gen counter stores a value within ``[1, MAX_NR_GENS]`` while a page is on one of -``lrugen->lists[]``; otherwise it stores zero. +``lrugen->folios[]``; otherwise it stores zero. Each generation is divided into multiple tiers. A page accessed ``N`` times through file descriptors is in tier ``order_base_2(N)``. Unlike -generations, tiers do not have dedicated ``lrugen->lists[]``. In +generations, tiers do not have dedicated ``lrugen->folios[]``. In contrast to moving across generations, which requires the LRU lock, moving across tiers only involves atomic operations on ``folio->flags`` and therefore has a negligible cost. A feedback loop @@ -127,7 +127,7 @@ page mapped by this PTE to ``(max_seq%MAX_NR_GENS)+1``. Eviction -------- The eviction consumes old generations. Given an ``lruvec``, it -increments ``min_seq`` when ``lrugen->lists[]`` indexed by +increments ``min_seq`` when ``lrugen->folios[]`` indexed by ``min_seq%MAX_NR_GENS`` becomes empty. To select a type and a tier to evict from, it first compares ``min_seq[]`` to select the older type. If both types are equally old, it selects the one whose first tier has diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index 177b8b1dd43c..eb8a2435ee80 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -256,9 +256,9 @@ static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, lru_gen_update_size(lruvec, folio, -1, gen); /* for folio_rotate_reclaimable() */ if (reclaiming) - list_add_tail(&folio->lru, &lrugen->lists[gen][type][zone]); + list_add_tail(&folio->lru, &lrugen->folios[gen][type][zone]); else - list_add(&folio->lru, &lrugen->lists[gen][type][zone]); + list_add(&folio->lru, &lrugen->folios[gen][type][zone]); return true; } diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 1686fcc4ed01..6c96ee823dbd 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -312,7 +312,7 @@ enum lruvec_flags { * They form a sliding window of a variable size [MIN_NR_GENS, MAX_NR_GENS]. An * offset within MAX_NR_GENS, i.e., gen, indexes the LRU list of the * corresponding generation. The gen counter in folio->flags stores gen+1 while - * a page is on one of lrugen->lists[]. Otherwise it stores 0. + * a page is on one of lrugen->folios[]. Otherwise it stores 0. * * A page is added to the youngest generation on faulting. The aging needs to * check the accessed bit at least twice before handing this page over to the @@ -324,8 +324,8 @@ enum lruvec_flags { * rest of generations, if they exist, are considered inactive. See * lru_gen_is_active(). * - * PG_active is always cleared while a page is on one of lrugen->lists[] so that - * the aging needs not to worry about it. And it's set again when a page + * PG_active is always cleared while a page is on one of lrugen->folios[] so + * that the aging needs not to worry about it. And it's set again when a page * considered active is isolated for non-reclaiming purposes, e.g., migration. * See lru_gen_add_folio() and lru_gen_del_folio(). * @@ -412,7 +412,7 @@ struct lru_gen_folio { /* the birth time of each generation in jiffies */ unsigned long timestamps[MAX_NR_GENS]; /* the multi-gen LRU lists, lazily sorted on eviction */ - struct list_head lists[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES]; + struct list_head folios[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES]; /* the multi-gen LRU sizes, eventually consistent */ long nr_pages[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES]; /* the exponential moving average of refaulted */ diff --git a/mm/vmscan.c b/mm/vmscan.c index 5505f54871c9..d8a53b7443d4 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -4271,7 +4271,7 @@ static bool inc_min_seq(struct lruvec *lruvec, int type, bool can_swap) /* prevent cold/hot inversion if force_scan is true */ for (zone = 0; zone < MAX_NR_ZONES; zone++) { - struct list_head *head = &lrugen->lists[old_gen][type][zone]; + struct list_head *head = &lrugen->folios[old_gen][type][zone]; while (!list_empty(head)) { struct folio *folio = lru_to_folio(head); @@ -4282,7 +4282,7 @@ static bool inc_min_seq(struct lruvec *lruvec, int type, bool can_swap) VM_WARN_ON_ONCE_FOLIO(folio_zonenum(folio) != zone, folio); new_gen = folio_inc_gen(lruvec, folio, false); - list_move_tail(&folio->lru, &lrugen->lists[new_gen][type][zone]); + list_move_tail(&folio->lru, &lrugen->folios[new_gen][type][zone]); if (!--remaining) return false; @@ -4310,7 +4310,7 @@ static bool try_to_inc_min_seq(struct lruvec *lruvec, bool can_swap) gen = lru_gen_from_seq(min_seq[type]); for (zone = 0; zone < MAX_NR_ZONES; zone++) { - if (!list_empty(&lrugen->lists[gen][type][zone])) + if (!list_empty(&lrugen->folios[gen][type][zone])) goto next; } @@ -4775,7 +4775,7 @@ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, int tier_idx) /* promoted */ if (gen != lru_gen_from_seq(lrugen->min_seq[type])) { - list_move(&folio->lru, &lrugen->lists[gen][type][zone]); + list_move(&folio->lru, &lrugen->folios[gen][type][zone]); return true; } @@ -4784,7 +4784,7 @@ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, int tier_idx) int hist = lru_hist_from_seq(lrugen->min_seq[type]); gen = folio_inc_gen(lruvec, folio, false); - list_move_tail(&folio->lru, &lrugen->lists[gen][type][zone]); + list_move_tail(&folio->lru, &lrugen->folios[gen][type][zone]); WRITE_ONCE(lrugen->protected[hist][type][tier - 1], lrugen->protected[hist][type][tier - 1] + delta); @@ -4796,7 +4796,7 @@ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, int tier_idx) if (folio_test_locked(folio) || folio_test_writeback(folio) || (type == LRU_GEN_FILE && folio_test_dirty(folio))) { gen = folio_inc_gen(lruvec, folio, true); - list_move(&folio->lru, &lrugen->lists[gen][type][zone]); + list_move(&folio->lru, &lrugen->folios[gen][type][zone]); return true; } @@ -4863,7 +4863,7 @@ static int scan_folios(struct lruvec *lruvec, struct scan_control *sc, for (zone = sc->reclaim_idx; zone >= 0; zone--) { LIST_HEAD(moved); int skipped = 0; - struct list_head *head = &lrugen->lists[gen][type][zone]; + struct list_head *head = &lrugen->folios[gen][type][zone]; while (!list_empty(head)) { struct folio *folio = lru_to_folio(head); @@ -5264,7 +5264,7 @@ static bool __maybe_unused state_is_valid(struct lruvec *lruvec) int gen, type, zone; for_each_gen_type_zone(gen, type, zone) { - if (!list_empty(&lrugen->lists[gen][type][zone])) + if (!list_empty(&lrugen->folios[gen][type][zone])) return false; } } @@ -5309,7 +5309,7 @@ static bool drain_evictable(struct lruvec *lruvec) int remaining = MAX_LRU_BATCH; for_each_gen_type_zone(gen, type, zone) { - struct list_head *head = &lruvec->lrugen.lists[gen][type][zone]; + struct list_head *head = &lruvec->lrugen.folios[gen][type][zone]; while (!list_empty(head)) { bool success; @@ -5843,7 +5843,7 @@ void lru_gen_init_lruvec(struct lruvec *lruvec) lrugen->timestamps[i] = jiffies; for_each_gen_type_zone(gen, type, zone) - INIT_LIST_HEAD(&lrugen->lists[gen][type][zone]); + INIT_LIST_HEAD(&lrugen->folios[gen][type][zone]); lruvec->mm_state.seq = MIN_NR_GENS; init_waitqueue_head(&lruvec->mm_state.wait); -- cgit v1.2.3 From e4dde56cd208674ce899b47589f263499e5b8cdc Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Wed, 21 Dec 2022 21:19:04 -0700 Subject: mm: multi-gen LRU: per-node lru_gen_folio lists For each node, memcgs are divided into two generations: the old and the young. For each generation, memcgs are randomly sharded into multiple bins to improve scalability. For each bin, an RCU hlist_nulls is virtually divided into three segments: the head, the tail and the default. An onlining memcg is added to the tail of a random bin in the old generation. The eviction starts at the head of a random bin in the old generation. The per-node memcg generation counter, whose reminder (mod 2) indexes the old generation, is incremented when all its bins become empty. There are four operations: 1. MEMCG_LRU_HEAD, which moves an memcg to the head of a random bin in its current generation (old or young) and updates its "seg" to "head"; 2. MEMCG_LRU_TAIL, which moves an memcg to the tail of a random bin in its current generation (old or young) and updates its "seg" to "tail"; 3. MEMCG_LRU_OLD, which moves an memcg to the head of a random bin in the old generation, updates its "gen" to "old" and resets its "seg" to "default"; 4. MEMCG_LRU_YOUNG, which moves an memcg to the tail of a random bin in the young generation, updates its "gen" to "young" and resets its "seg" to "default". The events that trigger the above operations are: 1. Exceeding the soft limit, which triggers MEMCG_LRU_HEAD; 2. The first attempt to reclaim an memcg below low, which triggers MEMCG_LRU_TAIL; 3. The first attempt to reclaim an memcg below reclaimable size threshold, which triggers MEMCG_LRU_TAIL; 4. The second attempt to reclaim an memcg below reclaimable size threshold, which triggers MEMCG_LRU_YOUNG; 5. Attempting to reclaim an memcg below min, which triggers MEMCG_LRU_YOUNG; 6. Finishing the aging on the eviction path, which triggers MEMCG_LRU_YOUNG; 7. Offlining an memcg, which triggers MEMCG_LRU_OLD. Note that memcg LRU only applies to global reclaim, and the round-robin incrementing of their max_seq counters ensures the eventual fairness to all eligible memcgs. For memcg reclaim, it still relies on mem_cgroup_iter(). Link: https://lkml.kernel.org/r/20221222041905.2431096-7-yuzhao@google.com Signed-off-by: Yu Zhao Cc: Johannes Weiner Cc: Jonathan Corbet Cc: Michael Larabel Cc: Michal Hocko Cc: Mike Rapoport Cc: Roman Gushchin Cc: Suren Baghdasaryan Signed-off-by: Andrew Morton --- include/linux/memcontrol.h | 10 ++ include/linux/mm_inline.h | 17 +++ include/linux/mmzone.h | 117 +++++++++++++- mm/memcontrol.c | 16 ++ mm/page_alloc.c | 1 + mm/vmscan.c | 374 +++++++++++++++++++++++++++++++++++++++++---- 6 files changed, 500 insertions(+), 35 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index d3c8203cab6c..2e08b05bc6bf 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -794,6 +794,11 @@ static inline void obj_cgroup_put(struct obj_cgroup *objcg) percpu_ref_put(&objcg->refcnt); } +static inline bool mem_cgroup_tryget(struct mem_cgroup *memcg) +{ + return !memcg || css_tryget(&memcg->css); +} + static inline void mem_cgroup_put(struct mem_cgroup *memcg) { if (memcg) @@ -1301,6 +1306,11 @@ static inline void obj_cgroup_put(struct obj_cgroup *objcg) { } +static inline bool mem_cgroup_tryget(struct mem_cgroup *memcg) +{ + return true; +} + static inline void mem_cgroup_put(struct mem_cgroup *memcg) { } diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index eb8a2435ee80..acf03147fff8 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -122,6 +122,18 @@ static inline bool lru_gen_in_fault(void) return current->in_lru_fault; } +#ifdef CONFIG_MEMCG +static inline int lru_gen_memcg_seg(struct lruvec *lruvec) +{ + return READ_ONCE(lruvec->lrugen.seg); +} +#else +static inline int lru_gen_memcg_seg(struct lruvec *lruvec) +{ + return 0; +} +#endif + static inline int lru_gen_from_seq(unsigned long seq) { return seq % MAX_NR_GENS; @@ -297,6 +309,11 @@ static inline bool lru_gen_in_fault(void) return false; } +static inline int lru_gen_memcg_seg(struct lruvec *lruvec) +{ + return 0; +} + static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) { return false; diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 6c96ee823dbd..815c7c2edf45 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -7,6 +7,7 @@ #include #include +#include #include #include #include @@ -367,6 +368,15 @@ struct page_vma_mapped_walk; #define LRU_GEN_MASK ((BIT(LRU_GEN_WIDTH) - 1) << LRU_GEN_PGOFF) #define LRU_REFS_MASK ((BIT(LRU_REFS_WIDTH) - 1) << LRU_REFS_PGOFF) +/* see the comment on MEMCG_NR_GENS */ +enum { + MEMCG_LRU_NOP, + MEMCG_LRU_HEAD, + MEMCG_LRU_TAIL, + MEMCG_LRU_OLD, + MEMCG_LRU_YOUNG, +}; + #ifdef CONFIG_LRU_GEN enum { @@ -426,6 +436,14 @@ struct lru_gen_folio { atomic_long_t refaulted[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS]; /* whether the multi-gen LRU is enabled */ bool enabled; +#ifdef CONFIG_MEMCG + /* the memcg generation this lru_gen_folio belongs to */ + u8 gen; + /* the list segment this lru_gen_folio belongs to */ + u8 seg; + /* per-node lru_gen_folio list for global reclaim */ + struct hlist_nulls_node list; +#endif }; enum { @@ -479,12 +497,87 @@ void lru_gen_init_lruvec(struct lruvec *lruvec); void lru_gen_look_around(struct page_vma_mapped_walk *pvmw); #ifdef CONFIG_MEMCG + +/* + * For each node, memcgs are divided into two generations: the old and the + * young. For each generation, memcgs are randomly sharded into multiple bins + * to improve scalability. For each bin, the hlist_nulls is virtually divided + * into three segments: the head, the tail and the default. + * + * An onlining memcg is added to the tail of a random bin in the old generation. + * The eviction starts at the head of a random bin in the old generation. The + * per-node memcg generation counter, whose reminder (mod MEMCG_NR_GENS) indexes + * the old generation, is incremented when all its bins become empty. + * + * There are four operations: + * 1. MEMCG_LRU_HEAD, which moves an memcg to the head of a random bin in its + * current generation (old or young) and updates its "seg" to "head"; + * 2. MEMCG_LRU_TAIL, which moves an memcg to the tail of a random bin in its + * current generation (old or young) and updates its "seg" to "tail"; + * 3. MEMCG_LRU_OLD, which moves an memcg to the head of a random bin in the old + * generation, updates its "gen" to "old" and resets its "seg" to "default"; + * 4. MEMCG_LRU_YOUNG, which moves an memcg to the tail of a random bin in the + * young generation, updates its "gen" to "young" and resets its "seg" to + * "default". + * + * The events that trigger the above operations are: + * 1. Exceeding the soft limit, which triggers MEMCG_LRU_HEAD; + * 2. The first attempt to reclaim an memcg below low, which triggers + * MEMCG_LRU_TAIL; + * 3. The first attempt to reclaim an memcg below reclaimable size threshold, + * which triggers MEMCG_LRU_TAIL; + * 4. The second attempt to reclaim an memcg below reclaimable size threshold, + * which triggers MEMCG_LRU_YOUNG; + * 5. Attempting to reclaim an memcg below min, which triggers MEMCG_LRU_YOUNG; + * 6. Finishing the aging on the eviction path, which triggers MEMCG_LRU_YOUNG; + * 7. Offlining an memcg, which triggers MEMCG_LRU_OLD. + * + * Note that memcg LRU only applies to global reclaim, and the round-robin + * incrementing of their max_seq counters ensures the eventual fairness to all + * eligible memcgs. For memcg reclaim, it still relies on mem_cgroup_iter(). + */ +#define MEMCG_NR_GENS 2 +#define MEMCG_NR_BINS 8 + +struct lru_gen_memcg { + /* the per-node memcg generation counter */ + unsigned long seq; + /* each memcg has one lru_gen_folio per node */ + unsigned long nr_memcgs[MEMCG_NR_GENS]; + /* per-node lru_gen_folio list for global reclaim */ + struct hlist_nulls_head fifo[MEMCG_NR_GENS][MEMCG_NR_BINS]; + /* protects the above */ + spinlock_t lock; +}; + +void lru_gen_init_pgdat(struct pglist_data *pgdat); + void lru_gen_init_memcg(struct mem_cgroup *memcg); void lru_gen_exit_memcg(struct mem_cgroup *memcg); -#endif +void lru_gen_online_memcg(struct mem_cgroup *memcg); +void lru_gen_offline_memcg(struct mem_cgroup *memcg); +void lru_gen_release_memcg(struct mem_cgroup *memcg); +void lru_gen_rotate_memcg(struct lruvec *lruvec, int op); + +#else /* !CONFIG_MEMCG */ + +#define MEMCG_NR_GENS 1 + +struct lru_gen_memcg { +}; + +static inline void lru_gen_init_pgdat(struct pglist_data *pgdat) +{ +} + +#endif /* CONFIG_MEMCG */ #else /* !CONFIG_LRU_GEN */ +static inline void lru_gen_init_pgdat(struct pglist_data *pgdat) +{ +} + static inline void lru_gen_init_lruvec(struct lruvec *lruvec) { } @@ -494,6 +587,7 @@ static inline void lru_gen_look_around(struct page_vma_mapped_walk *pvmw) } #ifdef CONFIG_MEMCG + static inline void lru_gen_init_memcg(struct mem_cgroup *memcg) { } @@ -501,7 +595,24 @@ static inline void lru_gen_init_memcg(struct mem_cgroup *memcg) static inline void lru_gen_exit_memcg(struct mem_cgroup *memcg) { } -#endif + +static inline void lru_gen_online_memcg(struct mem_cgroup *memcg) +{ +} + +static inline void lru_gen_offline_memcg(struct mem_cgroup *memcg) +{ +} + +static inline void lru_gen_release_memcg(struct mem_cgroup *memcg) +{ +} + +static inline void lru_gen_rotate_memcg(struct lruvec *lruvec, int op) +{ +} + +#endif /* CONFIG_MEMCG */ #endif /* CONFIG_LRU_GEN */ @@ -1243,6 +1354,8 @@ typedef struct pglist_data { #ifdef CONFIG_LRU_GEN /* kswap mm walk data */ struct lru_gen_mm_walk mm_walk; + /* lru_gen_folio list */ + struct lru_gen_memcg memcg_lru; #endif CACHELINE_PADDING(_pad2_); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 49f67176a1a2..2758b67eb169 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -478,6 +478,16 @@ static void mem_cgroup_update_tree(struct mem_cgroup *memcg, int nid) struct mem_cgroup_per_node *mz; struct mem_cgroup_tree_per_node *mctz; + if (lru_gen_enabled()) { + struct lruvec *lruvec = &memcg->nodeinfo[nid]->lruvec; + + /* see the comment on MEMCG_NR_GENS */ + if (soft_limit_excess(memcg) && lru_gen_memcg_seg(lruvec) != MEMCG_LRU_HEAD) + lru_gen_rotate_memcg(lruvec, MEMCG_LRU_HEAD); + + return; + } + mctz = soft_limit_tree.rb_tree_per_node[nid]; if (!mctz) return; @@ -3530,6 +3540,9 @@ unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, struct mem_cgroup_tree_per_node *mctz; unsigned long excess; + if (lru_gen_enabled()) + return 0; + if (order > 0) return 0; @@ -5391,6 +5404,7 @@ static int mem_cgroup_css_online(struct cgroup_subsys_state *css) if (unlikely(mem_cgroup_is_root(memcg))) queue_delayed_work(system_unbound_wq, &stats_flush_dwork, 2UL*HZ); + lru_gen_online_memcg(memcg); return 0; offline_kmem: memcg_offline_kmem(memcg); @@ -5422,6 +5436,7 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css) memcg_offline_kmem(memcg); reparent_shrinker_deferred(memcg); wb_memcg_offline(memcg); + lru_gen_offline_memcg(memcg); drain_all_stock(memcg); @@ -5433,6 +5448,7 @@ static void mem_cgroup_css_released(struct cgroup_subsys_state *css) struct mem_cgroup *memcg = mem_cgroup_from_css(css); invalidate_reclaim_iterators(memcg); + lru_gen_release_memcg(memcg); } static void mem_cgroup_css_free(struct cgroup_subsys_state *css) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 7d980dc0000e..5668c1a2de49 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -7941,6 +7941,7 @@ static void __init free_area_init_node(int nid) pgdat_set_deferred_range(pgdat); free_area_init_core(pgdat); + lru_gen_init_pgdat(pgdat); } static void __init free_area_init_memoryless_node(int nid) diff --git a/mm/vmscan.c b/mm/vmscan.c index 5a167f8efc38..178465a503db 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -55,6 +55,8 @@ #include #include #include +#include +#include #include #include @@ -135,11 +137,6 @@ struct scan_control { /* Always discard instead of demoting to lower tier memory */ unsigned int no_demotion:1; -#ifdef CONFIG_LRU_GEN - /* help kswapd make better choices among multiple memcgs */ - unsigned long last_reclaimed; -#endif - /* Allocation order */ s8 order; @@ -3185,6 +3182,9 @@ DEFINE_STATIC_KEY_ARRAY_FALSE(lru_gen_caps, NR_LRU_GEN_CAPS); for ((type) = 0; (type) < ANON_AND_FILE; (type)++) \ for ((zone) = 0; (zone) < MAX_NR_ZONES; (zone)++) +#define get_memcg_gen(seq) ((seq) % MEMCG_NR_GENS) +#define get_memcg_bin(bin) ((bin) % MEMCG_NR_BINS) + static struct lruvec *get_lruvec(struct mem_cgroup *memcg, int nid) { struct pglist_data *pgdat = NODE_DATA(nid); @@ -4453,8 +4453,7 @@ done: if (sc->priority <= DEF_PRIORITY - 2) wait_event_killable(lruvec->mm_state.wait, max_seq < READ_ONCE(lrugen->max_seq)); - - return max_seq < READ_ONCE(lrugen->max_seq); + return false; } VM_WARN_ON_ONCE(max_seq != READ_ONCE(lrugen->max_seq)); @@ -4527,8 +4526,6 @@ static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc) VM_WARN_ON_ONCE(!current_is_kswapd()); - sc->last_reclaimed = sc->nr_reclaimed; - /* check the order to exclude compaction-induced reclaim */ if (!min_ttl || sc->order || sc->priority == DEF_PRIORITY) return; @@ -5117,8 +5114,7 @@ static bool should_run_aging(struct lruvec *lruvec, unsigned long max_seq, * 1. Defer try_to_inc_max_seq() to workqueues to reduce latency for memcg * reclaim. */ -static unsigned long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *sc, - bool can_swap) +static long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *sc, bool can_swap) { unsigned long nr_to_scan; struct mem_cgroup *memcg = lruvec_memcg(lruvec); @@ -5136,10 +5132,8 @@ static unsigned long get_nr_to_scan(struct lruvec *lruvec, struct scan_control * if (sc->priority == DEF_PRIORITY) return nr_to_scan; - try_to_inc_max_seq(lruvec, max_seq, sc, can_swap, false); - /* skip this lruvec as it's low on cold folios */ - return 0; + return try_to_inc_max_seq(lruvec, max_seq, sc, can_swap, false) ? -1 : 0; } static unsigned long get_nr_to_reclaim(struct scan_control *sc) @@ -5148,29 +5142,18 @@ static unsigned long get_nr_to_reclaim(struct scan_control *sc) if (!global_reclaim(sc)) return -1; - /* discount the previous progress for kswapd */ - if (current_is_kswapd()) - return sc->nr_to_reclaim + sc->last_reclaimed; - return max(sc->nr_to_reclaim, compact_gap(sc->order)); } -static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) +static bool try_to_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) { - struct blk_plug plug; + long nr_to_scan; unsigned long scanned = 0; unsigned long nr_to_reclaim = get_nr_to_reclaim(sc); - lru_add_drain(); - - blk_start_plug(&plug); - - set_mm_walk(lruvec_pgdat(lruvec)); - while (true) { int delta; int swappiness; - unsigned long nr_to_scan; if (sc->may_swap) swappiness = get_swappiness(lruvec, sc); @@ -5180,7 +5163,7 @@ static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc swappiness = 0; nr_to_scan = get_nr_to_scan(lruvec, sc, swappiness); - if (!nr_to_scan) + if (nr_to_scan <= 0) break; delta = evict_folios(lruvec, sc, swappiness); @@ -5197,11 +5180,252 @@ static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc cond_resched(); } + /* whether try_to_inc_max_seq() was successful */ + return nr_to_scan < 0; +} + +static int shrink_one(struct lruvec *lruvec, struct scan_control *sc) +{ + bool success; + unsigned long scanned = sc->nr_scanned; + unsigned long reclaimed = sc->nr_reclaimed; + int seg = lru_gen_memcg_seg(lruvec); + struct mem_cgroup *memcg = lruvec_memcg(lruvec); + struct pglist_data *pgdat = lruvec_pgdat(lruvec); + + /* see the comment on MEMCG_NR_GENS */ + if (!lruvec_is_sizable(lruvec, sc)) + return seg != MEMCG_LRU_TAIL ? MEMCG_LRU_TAIL : MEMCG_LRU_YOUNG; + + mem_cgroup_calculate_protection(NULL, memcg); + + if (mem_cgroup_below_min(NULL, memcg)) + return MEMCG_LRU_YOUNG; + + if (mem_cgroup_below_low(NULL, memcg)) { + /* see the comment on MEMCG_NR_GENS */ + if (seg != MEMCG_LRU_TAIL) + return MEMCG_LRU_TAIL; + + memcg_memory_event(memcg, MEMCG_LOW); + } + + success = try_to_shrink_lruvec(lruvec, sc); + + shrink_slab(sc->gfp_mask, pgdat->node_id, memcg, sc->priority); + + if (!sc->proactive) + vmpressure(sc->gfp_mask, memcg, false, sc->nr_scanned - scanned, + sc->nr_reclaimed - reclaimed); + + sc->nr_reclaimed += current->reclaim_state->reclaimed_slab; + current->reclaim_state->reclaimed_slab = 0; + + return success ? MEMCG_LRU_YOUNG : 0; +} + +#ifdef CONFIG_MEMCG + +static void shrink_many(struct pglist_data *pgdat, struct scan_control *sc) +{ + int gen; + int bin; + int first_bin; + struct lruvec *lruvec; + struct lru_gen_folio *lrugen; + const struct hlist_nulls_node *pos; + int op = 0; + struct mem_cgroup *memcg = NULL; + unsigned long nr_to_reclaim = get_nr_to_reclaim(sc); + + bin = first_bin = get_random_u32_below(MEMCG_NR_BINS); +restart: + gen = get_memcg_gen(READ_ONCE(pgdat->memcg_lru.seq)); + + rcu_read_lock(); + + hlist_nulls_for_each_entry_rcu(lrugen, pos, &pgdat->memcg_lru.fifo[gen][bin], list) { + if (op) + lru_gen_rotate_memcg(lruvec, op); + + mem_cgroup_put(memcg); + + lruvec = container_of(lrugen, struct lruvec, lrugen); + memcg = lruvec_memcg(lruvec); + + if (!mem_cgroup_tryget(memcg)) { + op = 0; + memcg = NULL; + continue; + } + + rcu_read_unlock(); + + op = shrink_one(lruvec, sc); + + if (sc->nr_reclaimed >= nr_to_reclaim) + goto success; + + rcu_read_lock(); + } + + rcu_read_unlock(); + + /* restart if raced with lru_gen_rotate_memcg() */ + if (gen != get_nulls_value(pos)) + goto restart; + + /* try the rest of the bins of the current generation */ + bin = get_memcg_bin(bin + 1); + if (bin != first_bin) + goto restart; +success: + if (op) + lru_gen_rotate_memcg(lruvec, op); + + mem_cgroup_put(memcg); +} + +static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) +{ + struct blk_plug plug; + + VM_WARN_ON_ONCE(global_reclaim(sc)); + + lru_add_drain(); + + blk_start_plug(&plug); + + set_mm_walk(lruvec_pgdat(lruvec)); + + if (try_to_shrink_lruvec(lruvec, sc)) + lru_gen_rotate_memcg(lruvec, MEMCG_LRU_YOUNG); + clear_mm_walk(); blk_finish_plug(&plug); } +#else /* !CONFIG_MEMCG */ + +static void shrink_many(struct pglist_data *pgdat, struct scan_control *sc) +{ + BUILD_BUG(); +} + +static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) +{ + BUILD_BUG(); +} + +#endif + +static void set_initial_priority(struct pglist_data *pgdat, struct scan_control *sc) +{ + int priority; + unsigned long reclaimable; + struct lruvec *lruvec = mem_cgroup_lruvec(NULL, pgdat); + + if (sc->priority != DEF_PRIORITY || sc->nr_to_reclaim < MIN_LRU_BATCH) + return; + /* + * Determine the initial priority based on ((total / MEMCG_NR_GENS) >> + * priority) * reclaimed_to_scanned_ratio = nr_to_reclaim, where the + * estimated reclaimed_to_scanned_ratio = inactive / total. + */ + reclaimable = node_page_state(pgdat, NR_INACTIVE_FILE); + if (get_swappiness(lruvec, sc)) + reclaimable += node_page_state(pgdat, NR_INACTIVE_ANON); + + reclaimable /= MEMCG_NR_GENS; + + /* round down reclaimable and round up sc->nr_to_reclaim */ + priority = fls_long(reclaimable) - 1 - fls_long(sc->nr_to_reclaim - 1); + + sc->priority = clamp(priority, 0, DEF_PRIORITY); +} + +static void lru_gen_shrink_node(struct pglist_data *pgdat, struct scan_control *sc) +{ + struct blk_plug plug; + unsigned long reclaimed = sc->nr_reclaimed; + + VM_WARN_ON_ONCE(!global_reclaim(sc)); + + lru_add_drain(); + + blk_start_plug(&plug); + + set_mm_walk(pgdat); + + set_initial_priority(pgdat, sc); + + if (current_is_kswapd()) + sc->nr_reclaimed = 0; + + if (mem_cgroup_disabled()) + shrink_one(&pgdat->__lruvec, sc); + else + shrink_many(pgdat, sc); + + if (current_is_kswapd()) + sc->nr_reclaimed += reclaimed; + + clear_mm_walk(); + + blk_finish_plug(&plug); + + /* kswapd should never fail */ + pgdat->kswapd_failures = 0; +} + +#ifdef CONFIG_MEMCG +void lru_gen_rotate_memcg(struct lruvec *lruvec, int op) +{ + int seg; + int old, new; + int bin = get_random_u32_below(MEMCG_NR_BINS); + struct pglist_data *pgdat = lruvec_pgdat(lruvec); + + spin_lock(&pgdat->memcg_lru.lock); + + VM_WARN_ON_ONCE(hlist_nulls_unhashed(&lruvec->lrugen.list)); + + seg = 0; + new = old = lruvec->lrugen.gen; + + /* see the comment on MEMCG_NR_GENS */ + if (op == MEMCG_LRU_HEAD) + seg = MEMCG_LRU_HEAD; + else if (op == MEMCG_LRU_TAIL) + seg = MEMCG_LRU_TAIL; + else if (op == MEMCG_LRU_OLD) + new = get_memcg_gen(pgdat->memcg_lru.seq); + else if (op == MEMCG_LRU_YOUNG) + new = get_memcg_gen(pgdat->memcg_lru.seq + 1); + else + VM_WARN_ON_ONCE(true); + + hlist_nulls_del_rcu(&lruvec->lrugen.list); + + if (op == MEMCG_LRU_HEAD || op == MEMCG_LRU_OLD) + hlist_nulls_add_head_rcu(&lruvec->lrugen.list, &pgdat->memcg_lru.fifo[new][bin]); + else + hlist_nulls_add_tail_rcu(&lruvec->lrugen.list, &pgdat->memcg_lru.fifo[new][bin]); + + pgdat->memcg_lru.nr_memcgs[old]--; + pgdat->memcg_lru.nr_memcgs[new]++; + + lruvec->lrugen.gen = new; + WRITE_ONCE(lruvec->lrugen.seg, seg); + + if (!pgdat->memcg_lru.nr_memcgs[old] && old == get_memcg_gen(pgdat->memcg_lru.seq)) + WRITE_ONCE(pgdat->memcg_lru.seq, pgdat->memcg_lru.seq + 1); + + spin_unlock(&pgdat->memcg_lru.lock); +} +#endif + /****************************************************************************** * state change ******************************************************************************/ @@ -5655,11 +5879,11 @@ static int run_cmd(char cmd, int memcg_id, int nid, unsigned long seq, if (!mem_cgroup_disabled()) { rcu_read_lock(); + memcg = mem_cgroup_from_id(memcg_id); -#ifdef CONFIG_MEMCG - if (memcg && !css_tryget(&memcg->css)) + if (!mem_cgroup_tryget(memcg)) memcg = NULL; -#endif + rcu_read_unlock(); if (!memcg) @@ -5807,6 +6031,19 @@ void lru_gen_init_lruvec(struct lruvec *lruvec) } #ifdef CONFIG_MEMCG + +void lru_gen_init_pgdat(struct pglist_data *pgdat) +{ + int i, j; + + spin_lock_init(&pgdat->memcg_lru.lock); + + for (i = 0; i < MEMCG_NR_GENS; i++) { + for (j = 0; j < MEMCG_NR_BINS; j++) + INIT_HLIST_NULLS_HEAD(&pgdat->memcg_lru.fifo[i][j], i); + } +} + void lru_gen_init_memcg(struct mem_cgroup *memcg) { INIT_LIST_HEAD(&memcg->mm_list.fifo); @@ -5830,7 +6067,69 @@ void lru_gen_exit_memcg(struct mem_cgroup *memcg) } } } -#endif + +void lru_gen_online_memcg(struct mem_cgroup *memcg) +{ + int gen; + int nid; + int bin = get_random_u32_below(MEMCG_NR_BINS); + + for_each_node(nid) { + struct pglist_data *pgdat = NODE_DATA(nid); + struct lruvec *lruvec = get_lruvec(memcg, nid); + + spin_lock(&pgdat->memcg_lru.lock); + + VM_WARN_ON_ONCE(!hlist_nulls_unhashed(&lruvec->lrugen.list)); + + gen = get_memcg_gen(pgdat->memcg_lru.seq); + + hlist_nulls_add_tail_rcu(&lruvec->lrugen.list, &pgdat->memcg_lru.fifo[gen][bin]); + pgdat->memcg_lru.nr_memcgs[gen]++; + + lruvec->lrugen.gen = gen; + + spin_unlock(&pgdat->memcg_lru.lock); + } +} + +void lru_gen_offline_memcg(struct mem_cgroup *memcg) +{ + int nid; + + for_each_node(nid) { + struct lruvec *lruvec = get_lruvec(memcg, nid); + + lru_gen_rotate_memcg(lruvec, MEMCG_LRU_OLD); + } +} + +void lru_gen_release_memcg(struct mem_cgroup *memcg) +{ + int gen; + int nid; + + for_each_node(nid) { + struct pglist_data *pgdat = NODE_DATA(nid); + struct lruvec *lruvec = get_lruvec(memcg, nid); + + spin_lock(&pgdat->memcg_lru.lock); + + VM_WARN_ON_ONCE(hlist_nulls_unhashed(&lruvec->lrugen.list)); + + gen = lruvec->lrugen.gen; + + hlist_nulls_del_rcu(&lruvec->lrugen.list); + pgdat->memcg_lru.nr_memcgs[gen]--; + + if (!pgdat->memcg_lru.nr_memcgs[gen] && gen == get_memcg_gen(pgdat->memcg_lru.seq)) + WRITE_ONCE(pgdat->memcg_lru.seq, pgdat->memcg_lru.seq + 1); + + spin_unlock(&pgdat->memcg_lru.lock); + } +} + +#endif /* CONFIG_MEMCG */ static int __init init_lru_gen(void) { @@ -5857,6 +6156,10 @@ static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc { } +static void lru_gen_shrink_node(struct pglist_data *pgdat, struct scan_control *sc) +{ +} + #endif /* CONFIG_LRU_GEN */ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) @@ -5870,7 +6173,7 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) bool proportional_reclaim; struct blk_plug plug; - if (lru_gen_enabled()) { + if (lru_gen_enabled() && !global_reclaim(sc)) { lru_gen_shrink_lruvec(lruvec, sc); return; } @@ -6113,6 +6416,11 @@ static void shrink_node(pg_data_t *pgdat, struct scan_control *sc) struct lruvec *target_lruvec; bool reclaimable = false; + if (lru_gen_enabled() && global_reclaim(sc)) { + lru_gen_shrink_node(pgdat, sc); + return; + } + target_lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, pgdat); again: -- cgit v1.2.3 From 1ef488edd6c4d447784710974f049628c2890481 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 23 Dec 2022 16:56:16 +0100 Subject: mm/mprotect: drop pgprot_t parameter from change_protection() Being able to provide a custom protection opens the door for inconsistencies and BUGs: for example, accidentally allowing for more permissions than desired by other mechanisms (e.g., softdirty tracking). vma->vm_page_prot should be the single source of truth. Only PROT_NUMA is special: there is no way we can erroneously allow for more permissions when removing all permissions. Special-case using the MM_CP_PROT_NUMA flag. [david@redhat.com: PAGE_NONE might not be defined without CONFIG_NUMA_BALANCING] Link: https://lkml.kernel.org/r/5084ff1c-ebb3-f918-6a60-bacabf550a88@redhat.com Link: https://lkml.kernel.org/r/20221223155616.297723-3-david@redhat.com Signed-off-by: David Hildenbrand Cc: Andrea Arcangeli Cc: Hugh Dickins Cc: Nadav Amit Cc: Peter Xu Signed-off-by: Andrew Morton --- include/linux/mm.h | 3 +-- mm/mempolicy.c | 3 +-- mm/mprotect.c | 18 +++++++++++++++--- mm/userfaultfd.c | 3 +-- 4 files changed, 18 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index d68579bf8484..329ed67edd76 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2134,8 +2134,7 @@ bool can_change_pte_writable(struct vm_area_struct *vma, unsigned long addr, pte_t pte); extern unsigned long change_protection(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, - unsigned long end, pgprot_t newprot, - unsigned long cp_flags); + unsigned long end, unsigned long cp_flags); extern int mprotect_fixup(struct mmu_gather *tlb, struct vm_area_struct *vma, struct vm_area_struct **pprev, unsigned long start, unsigned long end, unsigned long newflags); diff --git a/mm/mempolicy.c b/mm/mempolicy.c index becf41e10076..d3558248a0f0 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -635,8 +635,7 @@ unsigned long change_prot_numa(struct vm_area_struct *vma, tlb_gather_mmu(&tlb, vma->vm_mm); - nr_updated = change_protection(&tlb, vma, addr, end, PAGE_NONE, - MM_CP_PROT_NUMA); + nr_updated = change_protection(&tlb, vma, addr, end, MM_CP_PROT_NUMA); if (nr_updated) count_vm_numa_events(NUMA_PTE_UPDATES, nr_updated); diff --git a/mm/mprotect.c b/mm/mprotect.c index bf8fa0af5a15..71358e45a742 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -507,13 +507,25 @@ static unsigned long change_protection_range(struct mmu_gather *tlb, unsigned long change_protection(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, - unsigned long end, pgprot_t newprot, - unsigned long cp_flags) + unsigned long end, unsigned long cp_flags) { + pgprot_t newprot = vma->vm_page_prot; unsigned long pages; BUG_ON((cp_flags & MM_CP_UFFD_WP_ALL) == MM_CP_UFFD_WP_ALL); +#ifdef CONFIG_NUMA_BALANCING + /* + * Ordinary protection updates (mprotect, uffd-wp, softdirty tracking) + * are expected to reflect their requirements via VMA flags such that + * vma_set_page_prot() will adjust vma->vm_page_prot accordingly. + */ + if (cp_flags & MM_CP_PROT_NUMA) + newprot = PAGE_NONE; +#else + WARN_ON_ONCE(cp_flags & MM_CP_PROT_NUMA); +#endif + if (is_vm_hugetlb_page(vma)) pages = hugetlb_change_protection(vma, start, end, newprot, cp_flags); @@ -642,7 +654,7 @@ success: mm_cp_flags |= MM_CP_TRY_CHANGE_WRITABLE; vma_set_page_prot(vma); - change_protection(tlb, vma, start, end, vma->vm_page_prot, mm_cp_flags); + change_protection(tlb, vma, start, end, mm_cp_flags); /* * Private VM_LOCKED VMA becoming writable: trigger COW to avoid major diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 46771362550f..65ad172add27 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -730,8 +730,7 @@ void uffd_wp_range(struct mm_struct *dst_mm, struct vm_area_struct *dst_vma, if (!enable_wp && vma_wants_manual_pte_write_upgrade(dst_vma)) mm_cp_flags |= MM_CP_TRY_CHANGE_WRITABLE; tlb_gather_mmu(&tlb, dst_mm); - change_protection(&tlb, dst_vma, start, start + len, vma->vm_page_prot, - mm_cp_flags); + change_protection(&tlb, dst_vma, start, start + len, mm_cp_flags); tlb_finish_mmu(&tlb); } -- cgit v1.2.3 From 3783e1721b650588938d28e4a084a1c9748361c8 Mon Sep 17 00:00:00 2001 From: Kele Huang Date: Sat, 24 Dec 2022 01:02:33 -0500 Subject: mm: fix comment of page table counter Commit af5b0f6a09e42 ("mm: consolidate page table accounting") consolidates page table accounting to a single counter in struct mm_struct {} as mm->pgtables_bytes. So the meanning of this counter should be the size of all page tables now. Link: https://lkml.kernel.org/r/20221224060233.417827-1-kele.huang@columbia.edu Signed-off-by: Kele Huang Cc: Arnd Bergmann Cc: Colin Cross Cc: David Hildenbrand Cc: Hugh Dickins Cc: Liam Howlett Cc: Matthew Wilcox (Oracle) Cc: Pasha Tatashin Cc: Peter Xu Cc: Vlastimil Babka Cc: Yu Zhao Signed-off-by: Andrew Morton --- include/linux/mm_types.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 1118e381fcdc..10b6eb311ede 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -647,7 +647,7 @@ struct mm_struct { atomic_t mm_count; #ifdef CONFIG_MMU - atomic_long_t pgtables_bytes; /* PTE page table pages */ + atomic_long_t pgtables_bytes; /* size of all page tables */ #endif int map_count; /* number of VMAs */ -- cgit v1.2.3 From cff61bbc717bfddd6e433fe142b8e70b21546a1d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 29 Dec 2022 06:10:29 -1000 Subject: jbd2,ocfs2: move jbd2_journal_submit_inode_data_buffers to ocfs2 jbd2_journal_submit_inode_data_buffers is only used by ocfs2, so move it there to prepare for removing generic_writepages. Link: https://lkml.kernel.org/r/20221229161031.391878-5-hch@lst.de Signed-off-by: Christoph Hellwig Cc: Jan Kara Cc: Joel Becker Cc: Joseph Qi Cc: Konstantin Komarov Cc: Mark Fasheh Cc: Matthew Wilcox Cc: Theodore Ts'o Signed-off-by: Andrew Morton --- fs/jbd2/commit.c | 25 ------------------------- fs/jbd2/journal.c | 1 - fs/ocfs2/journal.c | 16 +++++++++++++++- include/linux/jbd2.h | 2 -- 4 files changed, 15 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 96a1ebc6342d..b33155dd7001 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -177,31 +177,6 @@ static int journal_wait_on_commit_record(journal_t *journal, return ret; } -/* - * write the filemap data using writepage() address_space_operations. - * We don't do block allocation here even for delalloc. We don't - * use writepages() because with delayed allocation we may be doing - * block allocation in writepages(). - */ -int jbd2_journal_submit_inode_data_buffers(struct jbd2_inode *jinode) -{ - struct address_space *mapping = jinode->i_vfs_inode->i_mapping; - struct writeback_control wbc = { - .sync_mode = WB_SYNC_ALL, - .nr_to_write = mapping->nrpages * 2, - .range_start = jinode->i_dirty_start, - .range_end = jinode->i_dirty_end, - }; - - /* - * submit the inode data buffers. We use writepage - * instead of writepages. Because writepages can do - * block allocation with delalloc. We need to write - * only allocated blocks here. - */ - return generic_writepages(mapping, &wbc); -} - /* Send all the data buffers related to an inode */ int jbd2_submit_inode_data(journal_t *journal, struct jbd2_inode *jinode) { diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 4095fe91457f..e80c781731f8 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -89,7 +89,6 @@ EXPORT_SYMBOL(jbd2_journal_try_to_free_buffers); EXPORT_SYMBOL(jbd2_journal_force_commit); EXPORT_SYMBOL(jbd2_journal_inode_ranged_write); EXPORT_SYMBOL(jbd2_journal_inode_ranged_wait); -EXPORT_SYMBOL(jbd2_journal_submit_inode_data_buffers); EXPORT_SYMBOL(jbd2_journal_finish_inode_data_buffers); EXPORT_SYMBOL(jbd2_journal_init_jbd_inode); EXPORT_SYMBOL(jbd2_journal_release_jbd_inode); diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index 3fb98b4569a2..59f612684c51 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -15,6 +15,7 @@ #include #include #include +#include #include @@ -841,6 +842,19 @@ bail: return status; } +static int ocfs2_journal_submit_inode_data_buffers(struct jbd2_inode *jinode) +{ + struct address_space *mapping = jinode->i_vfs_inode->i_mapping; + struct writeback_control wbc = { + .sync_mode = WB_SYNC_ALL, + .nr_to_write = mapping->nrpages * 2, + .range_start = jinode->i_dirty_start, + .range_end = jinode->i_dirty_end, + }; + + return generic_writepages(mapping, &wbc); +} + int ocfs2_journal_init(struct ocfs2_super *osb, int *dirty) { int status = -1; @@ -910,7 +924,7 @@ int ocfs2_journal_init(struct ocfs2_super *osb, int *dirty) journal->j_journal = j_journal; journal->j_journal->j_submit_inode_data_buffers = - jbd2_journal_submit_inode_data_buffers; + ocfs2_journal_submit_inode_data_buffers; journal->j_journal->j_finish_inode_data_buffers = jbd2_journal_finish_inode_data_buffers; journal->j_inode = inode; diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 2170e0cc279d..5962072a4b19 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1570,8 +1570,6 @@ extern int jbd2_journal_inode_ranged_write(handle_t *handle, extern int jbd2_journal_inode_ranged_wait(handle_t *handle, struct jbd2_inode *inode, loff_t start_byte, loff_t length); -extern int jbd2_journal_submit_inode_data_buffers( - struct jbd2_inode *jinode); extern int jbd2_journal_finish_inode_data_buffers( struct jbd2_inode *jinode); extern int jbd2_journal_begin_ordered_truncate(journal_t *journal, -- cgit v1.2.3 From c2ca7a59a4199059556b57cfdf98fcf46039ca6b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 29 Dec 2022 06:10:31 -1000 Subject: mm: remove generic_writepages Now that all external callers are gone, just fold it into do_writepages. Link: https://lkml.kernel.org/r/20221229161031.391878-7-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Cc: Joel Becker Cc: Joseph Qi Cc: Konstantin Komarov Cc: Mark Fasheh Cc: Matthew Wilcox Cc: Theodore Ts'o Signed-off-by: Andrew Morton --- include/linux/writeback.h | 2 -- mm/page-writeback.c | 53 ++++++++++++++--------------------------------- 2 files changed, 15 insertions(+), 40 deletions(-) (limited to 'include/linux') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 06f9291b6fd5..2554b71765e9 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -369,8 +369,6 @@ bool wb_over_bg_thresh(struct bdi_writeback *wb); typedef int (*writepage_t)(struct page *page, struct writeback_control *wbc, void *data); -int generic_writepages(struct address_space *mapping, - struct writeback_control *wbc); void tag_pages_for_writeback(struct address_space *mapping, pgoff_t start, pgoff_t end); int write_cache_pages(struct address_space *mapping, diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 41128ea9c997..337cafe9978c 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2526,12 +2526,8 @@ continue_unlock: } EXPORT_SYMBOL(write_cache_pages); -/* - * Function used by generic_writepages to call the real writepage - * function and set the mapping flags on error - */ -static int __writepage(struct page *page, struct writeback_control *wbc, - void *data) +static int writepage_cb(struct page *page, struct writeback_control *wbc, + void *data) { struct address_space *mapping = data; int ret = mapping->a_ops->writepage(page, wbc); @@ -2539,34 +2535,6 @@ static int __writepage(struct page *page, struct writeback_control *wbc, return ret; } -/** - * generic_writepages - walk the list of dirty pages of the given address space and writepage() all of them. - * @mapping: address space structure to write - * @wbc: subtract the number of written pages from *@wbc->nr_to_write - * - * This is a library function, which implements the writepages() - * address_space_operation. - * - * Return: %0 on success, negative error code otherwise - */ -int generic_writepages(struct address_space *mapping, - struct writeback_control *wbc) -{ - struct blk_plug plug; - int ret; - - /* deal with chardevs and other special file */ - if (!mapping->a_ops->writepage) - return 0; - - blk_start_plug(&plug); - ret = write_cache_pages(mapping, wbc, __writepage, mapping); - blk_finish_plug(&plug); - return ret; -} - -EXPORT_SYMBOL(generic_writepages); - int do_writepages(struct address_space *mapping, struct writeback_control *wbc) { int ret; @@ -2577,11 +2545,20 @@ int do_writepages(struct address_space *mapping, struct writeback_control *wbc) wb = inode_to_wb_wbc(mapping->host, wbc); wb_bandwidth_estimate_start(wb); while (1) { - if (mapping->a_ops->writepages) + if (mapping->a_ops->writepages) { ret = mapping->a_ops->writepages(mapping, wbc); - else - ret = generic_writepages(mapping, wbc); - if ((ret != -ENOMEM) || (wbc->sync_mode != WB_SYNC_ALL)) + } else if (mapping->a_ops->writepage) { + struct blk_plug plug; + + blk_start_plug(&plug); + ret = write_cache_pages(mapping, wbc, writepage_cb, + mapping); + blk_finish_plug(&plug); + } else { + /* deal with chardevs and other special files */ + ret = 0; + } + if (ret != -ENOMEM || wbc->sync_mode != WB_SYNC_ALL) break; /* -- cgit v1.2.3 From becacb04fdd439d7d1f2a93739161706a2e3e947 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 30 Dec 2022 15:08:42 +0800 Subject: mm: memcg: add folio_memcg_check() Patch series "mm: convert page_idle/damon to use folios", v4. This patch (of 8): Convert page_memcg_check() into folio_memcg_check() and add a page_memcg_check() wrapper. The behaviour of page_memcg_check() is unchanged; tail pages always had a NULL ->memcg_data. Link: https://lkml.kernel.org/r/20221230070849.63358-1-wangkefeng.wang@huawei.com Link: https://lkml.kernel.org/r/20221230070849.63358-2-wangkefeng.wang@huawei.com Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Kefeng Wang Cc: David Hildenbrand Cc: SeongJae Park Cc: Vishal Moola (Oracle) Signed-off-by: Andrew Morton --- include/linux/memcontrol.h | 40 ++++++++++++++++++++++++++-------------- mm/memcontrol.c | 6 +++--- 2 files changed, 29 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 2e08b05bc6bf..26667bf16da5 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -466,34 +466,34 @@ static inline struct mem_cgroup *folio_memcg_rcu(struct folio *folio) } /* - * page_memcg_check - get the memory cgroup associated with a page - * @page: a pointer to the page struct + * folio_memcg_check - Get the memory cgroup associated with a folio. + * @folio: Pointer to the folio. * - * Returns a pointer to the memory cgroup associated with the page, - * or NULL. This function unlike page_memcg() can take any page - * as an argument. It has to be used in cases when it's not known if a page + * Returns a pointer to the memory cgroup associated with the folio, + * or NULL. This function unlike folio_memcg() can take any folio + * as an argument. It has to be used in cases when it's not known if a folio * has an associated memory cgroup pointer or an object cgroups vector or * an object cgroup. * - * For a non-kmem page any of the following ensures page and memcg binding + * For a non-kmem folio any of the following ensures folio and memcg binding * stability: * - * - the page lock + * - the folio lock * - LRU isolation - * - lock_page_memcg() + * - lock_folio_memcg() * - exclusive reference * - mem_cgroup_trylock_pages() * - * For a kmem page a caller should hold an rcu read lock to protect memcg - * associated with a kmem page from being released. + * For a kmem folio a caller should hold an rcu read lock to protect memcg + * associated with a kmem folio from being released. */ -static inline struct mem_cgroup *page_memcg_check(struct page *page) +static inline struct mem_cgroup *folio_memcg_check(struct folio *folio) { /* - * Because page->memcg_data might be changed asynchronously - * for slab pages, READ_ONCE() should be used here. + * Because folio->memcg_data might be changed asynchronously + * for slabs, READ_ONCE() should be used here. */ - unsigned long memcg_data = READ_ONCE(page->memcg_data); + unsigned long memcg_data = READ_ONCE(folio->memcg_data); if (memcg_data & MEMCG_DATA_OBJCGS) return NULL; @@ -508,6 +508,13 @@ static inline struct mem_cgroup *page_memcg_check(struct page *page) return (struct mem_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); } +static inline struct mem_cgroup *page_memcg_check(struct page *page) +{ + if (PageTail(page)) + return NULL; + return folio_memcg_check((struct folio *)page); +} + static inline struct mem_cgroup *get_mem_cgroup_from_objcg(struct obj_cgroup *objcg) { struct mem_cgroup *memcg; @@ -1170,6 +1177,11 @@ static inline struct mem_cgroup *folio_memcg_rcu(struct folio *folio) return NULL; } +static inline struct mem_cgroup *folio_memcg_check(struct folio *folio) +{ + return NULL; +} + static inline struct mem_cgroup *page_memcg_check(struct page *page) { return NULL; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 2758b67eb169..17965e558ab7 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2952,13 +2952,13 @@ struct mem_cgroup *mem_cgroup_from_obj_folio(struct folio *folio, void *p) } /* - * page_memcg_check() is used here, because in theory we can encounter + * folio_memcg_check() is used here, because in theory we can encounter * a folio where the slab flag has been cleared already, but * slab->memcg_data has not been freed yet - * page_memcg_check(page) will guarantee that a proper memory + * folio_memcg_check() will guarantee that a proper memory * cgroup pointer or NULL will be returned. */ - return page_memcg_check(folio_page(folio, 0)); + return folio_memcg_check(folio); } /* -- cgit v1.2.3 From a79390f5d6a78647fd70856bd42b22d994de0ba2 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Wed, 4 Jan 2023 17:52:06 -0500 Subject: mm/mprotect: use long for page accountings and retval Switch to use type "long" for page accountings and retval across the whole procedure of change_protection(). The change should have shrinked the possible maximum page number to be half comparing to previous (ULONG_MAX / 2), but it shouldn't overflow on any system either because the maximum possible pages touched by change protection should be ULONG_MAX / PAGE_SIZE. Two reasons to switch from "unsigned long" to "long": 1. It suites better on count_vm_numa_events(), whose 2nd parameter takes a long type. 2. It paves way for returning negative (error) values in the future. Currently the only caller that consumes this retval is change_prot_numa(), where the unsigned long was converted to an int. Since at it, touching up the numa code to also take a long, so it'll avoid any possible overflow too during the int-size convertion. Link: https://lkml.kernel.org/r/20230104225207.1066932-3-peterx@redhat.com Signed-off-by: Peter Xu Acked-by: Mike Kravetz Acked-by: James Houghton Cc: Andrea Arcangeli Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Muchun Song Cc: Nadav Amit Signed-off-by: Andrew Morton --- include/linux/hugetlb.h | 4 ++-- include/linux/mm.h | 2 +- mm/hugetlb.c | 4 ++-- mm/mempolicy.c | 2 +- mm/mprotect.c | 26 +++++++++++++------------- 5 files changed, 19 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index b6b10101bea7..e3aa336df900 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -248,7 +248,7 @@ void hugetlb_vma_lock_release(struct kref *kref); int pmd_huge(pmd_t pmd); int pud_huge(pud_t pud); -unsigned long hugetlb_change_protection(struct vm_area_struct *vma, +long hugetlb_change_protection(struct vm_area_struct *vma, unsigned long address, unsigned long end, pgprot_t newprot, unsigned long cp_flags); @@ -437,7 +437,7 @@ static inline void move_hugetlb_state(struct folio *old_folio, { } -static inline unsigned long hugetlb_change_protection( +static inline long hugetlb_change_protection( struct vm_area_struct *vma, unsigned long address, unsigned long end, pgprot_t newprot, unsigned long cp_flags) diff --git a/include/linux/mm.h b/include/linux/mm.h index 329ed67edd76..4ac5ea4b584c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2132,7 +2132,7 @@ static inline bool vma_wants_manual_pte_write_upgrade(struct vm_area_struct *vma } bool can_change_pte_writable(struct vm_area_struct *vma, unsigned long addr, pte_t pte); -extern unsigned long change_protection(struct mmu_gather *tlb, +extern long change_protection(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, unsigned long end, unsigned long cp_flags); extern int mprotect_fixup(struct mmu_gather *tlb, struct vm_area_struct *vma, diff --git a/mm/hugetlb.c b/mm/hugetlb.c index a82f41024167..a0d6d0980064 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -6615,7 +6615,7 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, return i ? i : err; } -unsigned long hugetlb_change_protection(struct vm_area_struct *vma, +long hugetlb_change_protection(struct vm_area_struct *vma, unsigned long address, unsigned long end, pgprot_t newprot, unsigned long cp_flags) { @@ -6624,7 +6624,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, pte_t *ptep; pte_t pte; struct hstate *h = hstate_vma(vma); - unsigned long pages = 0, psize = huge_page_size(h); + long pages = 0, psize = huge_page_size(h); bool shared_pmd = false; struct mmu_notifier_range range; unsigned long last_addr_mask; diff --git a/mm/mempolicy.c b/mm/mempolicy.c index d3558248a0f0..a86b8f15e2f0 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -631,7 +631,7 @@ unsigned long change_prot_numa(struct vm_area_struct *vma, unsigned long addr, unsigned long end) { struct mmu_gather tlb; - int nr_updated; + long nr_updated; tlb_gather_mmu(&tlb, vma->vm_mm); diff --git a/mm/mprotect.c b/mm/mprotect.c index 71358e45a742..0af22ab59ea8 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -80,13 +80,13 @@ bool can_change_pte_writable(struct vm_area_struct *vma, unsigned long addr, return pte_dirty(pte); } -static unsigned long change_pte_range(struct mmu_gather *tlb, +static long change_pte_range(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, pgprot_t newprot, unsigned long cp_flags) { pte_t *pte, oldpte; spinlock_t *ptl; - unsigned long pages = 0; + long pages = 0; int target_node = NUMA_NO_NODE; bool prot_numa = cp_flags & MM_CP_PROT_NUMA; bool uffd_wp = cp_flags & MM_CP_UFFD_WP; @@ -353,13 +353,13 @@ uffd_wp_protect_file(struct vm_area_struct *vma, unsigned long cp_flags) } \ } while (0) -static inline unsigned long change_pmd_range(struct mmu_gather *tlb, +static inline long change_pmd_range(struct mmu_gather *tlb, struct vm_area_struct *vma, pud_t *pud, unsigned long addr, unsigned long end, pgprot_t newprot, unsigned long cp_flags) { pmd_t *pmd; unsigned long next; - unsigned long pages = 0; + long pages = 0; unsigned long nr_huge_updates = 0; struct mmu_notifier_range range; @@ -367,7 +367,7 @@ static inline unsigned long change_pmd_range(struct mmu_gather *tlb, pmd = pmd_offset(pud, addr); do { - unsigned long this_pages; + long this_pages; next = pmd_addr_end(addr, end); @@ -437,13 +437,13 @@ next: return pages; } -static inline unsigned long change_pud_range(struct mmu_gather *tlb, +static inline long change_pud_range(struct mmu_gather *tlb, struct vm_area_struct *vma, p4d_t *p4d, unsigned long addr, unsigned long end, pgprot_t newprot, unsigned long cp_flags) { pud_t *pud; unsigned long next; - unsigned long pages = 0; + long pages = 0; pud = pud_offset(p4d, addr); do { @@ -458,13 +458,13 @@ static inline unsigned long change_pud_range(struct mmu_gather *tlb, return pages; } -static inline unsigned long change_p4d_range(struct mmu_gather *tlb, +static inline long change_p4d_range(struct mmu_gather *tlb, struct vm_area_struct *vma, pgd_t *pgd, unsigned long addr, unsigned long end, pgprot_t newprot, unsigned long cp_flags) { p4d_t *p4d; unsigned long next; - unsigned long pages = 0; + long pages = 0; p4d = p4d_offset(pgd, addr); do { @@ -479,14 +479,14 @@ static inline unsigned long change_p4d_range(struct mmu_gather *tlb, return pages; } -static unsigned long change_protection_range(struct mmu_gather *tlb, +static long change_protection_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long addr, unsigned long end, pgprot_t newprot, unsigned long cp_flags) { struct mm_struct *mm = vma->vm_mm; pgd_t *pgd; unsigned long next; - unsigned long pages = 0; + long pages = 0; BUG_ON(addr >= end); pgd = pgd_offset(mm, addr); @@ -505,12 +505,12 @@ static unsigned long change_protection_range(struct mmu_gather *tlb, return pages; } -unsigned long change_protection(struct mmu_gather *tlb, +long change_protection(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, unsigned long end, unsigned long cp_flags) { pgprot_t newprot = vma->vm_page_prot; - unsigned long pages; + long pages; BUG_ON((cp_flags & MM_CP_UFFD_WP_ALL) == MM_CP_UFFD_WP_ALL); -- cgit v1.2.3 From d1751118c88673fe5a948ad82277898e9e284c55 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Wed, 4 Jan 2023 17:52:07 -0500 Subject: mm/uffd: detect pgtable allocation failures Before this patch, when there's any pgtable allocation issues happened during change_protection(), the error will be ignored from the syscall. For shmem, there will be an error dumped into the host dmesg. Two issues with that: (1) Doing a trace dump when allocation fails is not anything close to grace. (2) The user should be notified with any kind of such error, so the user can trap it and decide what to do next, either by retrying, or stop the process properly, or anything else. For userfault users, this will change the API of UFFDIO_WRITEPROTECT when pgtable allocation failure happened. It should not normally break anyone, though. If it breaks, then in good ways. One man-page update will be on the way to introduce the new -ENOMEM for UFFDIO_WRITEPROTECT. Not marking stable so we keep the old behavior on the 5.19-till-now kernels. [akpm@linux-foundation.org: coding-style cleanups] Link: https://lkml.kernel.org/r/20230104225207.1066932-4-peterx@redhat.com Signed-off-by: Peter Xu Reported-by: James Houghton Acked-by: James Houghton Cc: Andrea Arcangeli Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Mike Kravetz Cc: Muchun Song Cc: Nadav Amit Signed-off-by: Andrew Morton --- include/linux/userfaultfd_k.h | 2 +- mm/hugetlb.c | 6 +++-- mm/mempolicy.c | 2 +- mm/mprotect.c | 63 ++++++++++++++++++++++++++++--------------- mm/userfaultfd.c | 16 +++++++---- 5 files changed, 59 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index 9df0b9a762cc..3767f18114ef 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -73,7 +73,7 @@ extern ssize_t mcopy_continue(struct mm_struct *dst_mm, unsigned long dst_start, extern int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start, unsigned long len, bool enable_wp, atomic_t *mmap_changing); -extern void uffd_wp_range(struct mm_struct *dst_mm, struct vm_area_struct *vma, +extern long uffd_wp_range(struct mm_struct *dst_mm, struct vm_area_struct *vma, unsigned long start, unsigned long len, bool enable_wp); /* mm helpers */ diff --git a/mm/hugetlb.c b/mm/hugetlb.c index a0d6d0980064..6fe65f14d33b 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -6660,8 +6660,10 @@ long hugetlb_change_protection(struct vm_area_struct *vma, * pre-allocations to install pte markers. */ ptep = huge_pte_alloc(mm, vma, address, psize); - if (!ptep) + if (!ptep) { + pages = -ENOMEM; break; + } } ptl = huge_pte_lock(h, mm, ptep); if (huge_pmd_unshare(mm, vma, address, ptep)) { @@ -6751,7 +6753,7 @@ long hugetlb_change_protection(struct vm_area_struct *vma, hugetlb_vma_unlock_write(vma); mmu_notifier_invalidate_range_end(&range); - return pages << h->order; + return pages > 0 ? (pages << h->order) : pages; } /* Return true if reservation was successful, false otherwise. */ diff --git a/mm/mempolicy.c b/mm/mempolicy.c index a86b8f15e2f0..85a34f1f3ab8 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -636,7 +636,7 @@ unsigned long change_prot_numa(struct vm_area_struct *vma, tlb_gather_mmu(&tlb, vma->vm_mm); nr_updated = change_protection(&tlb, vma, addr, end, MM_CP_PROT_NUMA); - if (nr_updated) + if (nr_updated > 0) count_vm_numa_events(NUMA_PTE_UPDATES, nr_updated); tlb_finish_mmu(&tlb); diff --git a/mm/mprotect.c b/mm/mprotect.c index 0af22ab59ea8..92fc6f3fa512 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -330,28 +330,34 @@ uffd_wp_protect_file(struct vm_area_struct *vma, unsigned long cp_flags) /* * If wr-protecting the range for file-backed, populate pgtable for the case * when pgtable is empty but page cache exists. When {pte|pmd|...}_alloc() - * failed it means no memory, we don't have a better option but stop. + * failed we treat it the same way as pgtable allocation failures during + * page faults by kicking OOM and returning error. */ #define change_pmd_prepare(vma, pmd, cp_flags) \ - do { \ + ({ \ + long err = 0; \ if (unlikely(uffd_wp_protect_file(vma, cp_flags))) { \ - if (WARN_ON_ONCE(pte_alloc(vma->vm_mm, pmd))) \ - break; \ + if (pte_alloc(vma->vm_mm, pmd)) \ + err = -ENOMEM; \ } \ - } while (0) + err; \ + }) + /* * This is the general pud/p4d/pgd version of change_pmd_prepare(). We need to * have separate change_pmd_prepare() because pte_alloc() returns 0 on success, * while {pmd|pud|p4d}_alloc() returns the valid pointer on success. */ #define change_prepare(vma, high, low, addr, cp_flags) \ - do { \ + ({ \ + long err = 0; \ if (unlikely(uffd_wp_protect_file(vma, cp_flags))) { \ low##_t *p = low##_alloc(vma->vm_mm, high, addr); \ - if (WARN_ON_ONCE(p == NULL)) \ - break; \ + if (p == NULL) \ + err = -ENOMEM; \ } \ - } while (0) + err; \ + }) static inline long change_pmd_range(struct mmu_gather *tlb, struct vm_area_struct *vma, pud_t *pud, unsigned long addr, @@ -367,11 +373,15 @@ static inline long change_pmd_range(struct mmu_gather *tlb, pmd = pmd_offset(pud, addr); do { - long this_pages; + long ret; next = pmd_addr_end(addr, end); - change_pmd_prepare(vma, pmd, cp_flags); + ret = change_pmd_prepare(vma, pmd, cp_flags); + if (ret) { + pages = ret; + break; + } /* * Automatic NUMA balancing walks the tables with mmap_lock * held for read. It's possible a parallel update to occur @@ -401,7 +411,11 @@ static inline long change_pmd_range(struct mmu_gather *tlb, * cleared; make sure pmd populated if * necessary, then fall-through to pte level. */ - change_pmd_prepare(vma, pmd, cp_flags); + ret = change_pmd_prepare(vma, pmd, cp_flags); + if (ret) { + pages = ret; + break; + } } else { /* * change_huge_pmd() does not defer TLB flushes, @@ -422,9 +436,8 @@ static inline long change_pmd_range(struct mmu_gather *tlb, } /* fall through, the trans huge pmd just split */ } - this_pages = change_pte_range(tlb, vma, pmd, addr, next, - newprot, cp_flags); - pages += this_pages; + pages += change_pte_range(tlb, vma, pmd, addr, next, + newprot, cp_flags); next: cond_resched(); } while (pmd++, addr = next, addr != end); @@ -443,12 +456,14 @@ static inline long change_pud_range(struct mmu_gather *tlb, { pud_t *pud; unsigned long next; - long pages = 0; + long pages = 0, ret; pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); - change_prepare(vma, pud, pmd, addr, cp_flags); + ret = change_prepare(vma, pud, pmd, addr, cp_flags); + if (ret) + return ret; if (pud_none_or_clear_bad(pud)) continue; pages += change_pmd_range(tlb, vma, pud, addr, next, newprot, @@ -464,12 +479,14 @@ static inline long change_p4d_range(struct mmu_gather *tlb, { p4d_t *p4d; unsigned long next; - long pages = 0; + long pages = 0, ret; p4d = p4d_offset(pgd, addr); do { next = p4d_addr_end(addr, end); - change_prepare(vma, p4d, pud, addr, cp_flags); + ret = change_prepare(vma, p4d, pud, addr, cp_flags); + if (ret) + return ret; if (p4d_none_or_clear_bad(p4d)) continue; pages += change_pud_range(tlb, vma, p4d, addr, next, newprot, @@ -486,14 +503,18 @@ static long change_protection_range(struct mmu_gather *tlb, struct mm_struct *mm = vma->vm_mm; pgd_t *pgd; unsigned long next; - long pages = 0; + long pages = 0, ret; BUG_ON(addr >= end); pgd = pgd_offset(mm, addr); tlb_start_vma(tlb, vma); do { next = pgd_addr_end(addr, end); - change_prepare(vma, pgd, p4d, addr, cp_flags); + ret = change_prepare(vma, pgd, p4d, addr, cp_flags); + if (ret) { + pages = ret; + break; + } if (pgd_none_or_clear_bad(pgd)) continue; pages += change_p4d_range(tlb, vma, pgd, addr, next, newprot, diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 65ad172add27..53c3d916ff66 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -710,11 +710,12 @@ ssize_t mcopy_continue(struct mm_struct *dst_mm, unsigned long start, mmap_changing, 0); } -void uffd_wp_range(struct mm_struct *dst_mm, struct vm_area_struct *dst_vma, +long uffd_wp_range(struct mm_struct *dst_mm, struct vm_area_struct *dst_vma, unsigned long start, unsigned long len, bool enable_wp) { unsigned int mm_cp_flags; struct mmu_gather tlb; + long ret; if (enable_wp) mm_cp_flags = MM_CP_UFFD_WP; @@ -730,8 +731,10 @@ void uffd_wp_range(struct mm_struct *dst_mm, struct vm_area_struct *dst_vma, if (!enable_wp && vma_wants_manual_pte_write_upgrade(dst_vma)) mm_cp_flags |= MM_CP_TRY_CHANGE_WRITABLE; tlb_gather_mmu(&tlb, dst_mm); - change_protection(&tlb, dst_vma, start, start + len, mm_cp_flags); + ret = change_protection(&tlb, dst_vma, start, start + len, mm_cp_flags); tlb_finish_mmu(&tlb); + + return ret; } int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start, @@ -740,7 +743,7 @@ int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start, { struct vm_area_struct *dst_vma; unsigned long page_mask; - int err; + long err; /* * Sanitize the command parameters: @@ -779,9 +782,12 @@ int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start, goto out_unlock; } - uffd_wp_range(dst_mm, dst_vma, start, len, enable_wp); + err = uffd_wp_range(dst_mm, dst_vma, start, len, enable_wp); + + /* Return 0 on success, <0 on failures */ + if (err > 0) + err = 0; - err = 0; out_unlock: mmap_read_unlock(dst_mm); return err; -- cgit v1.2.3 From 9eefefd835e451d340f5e95bc14ffd68b9b99268 Mon Sep 17 00:00:00 2001 From: Fabio M. De Francesco Date: Thu, 5 Jan 2023 13:04:24 +0100 Subject: mm: remove an ambiguous sentence from kmap_local_folio() kdocs In the kdocs of kmap_local_folio() there is a an ambiguous sentence which suggests to use this API "only when really necessary". On the contrary, since kmap() and kmap_atomic() are deprecated, both kmap_local_folio(), as well as kmap_local_page(), must be preferred to the previous ones. Therefore, remove the above-mentioned sentence exactly how it has previously been done for the kmap_local_page() kdocs in commit 72f1c55adf70 ("highmem: delete a sentence from kmap_local_page() kdocs"). Link: https://lkml.kernel.org/r/20230105120424.30055-1-fmdefrancesco@gmail.com Signed-off-by: Fabio M. De Francesco Reviewed-by: Ira Weiny Cc: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- include/linux/highmem.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 44242268f53b..daeb0d8e753a 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -119,9 +119,8 @@ static inline void *kmap_local_page(struct page *page); * virtual address of the direct mapping. Only real highmem pages are * temporarily mapped. * - * While it is significantly faster than kmap() for the higmem case it - * comes with restrictions about the pointer validity. Only use when really - * necessary. + * While it is significantly faster than kmap() for the highmem case it + * comes with restrictions about the pointer validity. * * On HIGHMEM enabled systems mapping a highmem page has the side effect of * disabling migration in order to keep the virtual address stable across -- cgit v1.2.3 From 1f8549fce525bc95df40ea3ddbfc6e8e719d188d Mon Sep 17 00:00:00 2001 From: Fabio M. De Francesco Date: Thu, 5 Jan 2023 13:13:05 +0100 Subject: mm: fix spelling mistake in highmem.h Substitute "higmem" with "highmem" in highmem.h. Link: https://lkml.kernel.org/r/20230105121305.30714-1-fmdefrancesco@gmail.com Signed-off-by: Fabio M. De Francesco Suggested-by: "Matthew Wilcox (Oracle)" Reviewed-by: Ira Weiny Signed-off-by: Andrew Morton --- include/linux/highmem.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/highmem.h b/include/linux/highmem.h index daeb0d8e753a..d7097b8158f2 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -86,8 +86,8 @@ static inline void kmap_flush_unused(void); * virtual address of the direct mapping. Only real highmem pages are * temporarily mapped. * - * While it is significantly faster than kmap() for the higmem case it - * comes with restrictions about the pointer validity. + * While kmap_local_page() is significantly faster than kmap() for the highmem + * case it comes with restrictions about the pointer validity. * * On HIGHMEM enabled systems mapping a highmem page has the side effect of * disabling migration in order to keep the virtual address stable across -- cgit v1.2.3 From bbc61844b4645d54c147a82654ac974bb7be85de Mon Sep 17 00:00:00 2001 From: Feng Tang Date: Wed, 4 Jan 2023 14:06:05 +0800 Subject: mm/kasan: simplify and refine kasan_cache code struct 'kasan_cache' has a member 'is_kmalloc' indicating whether its host kmem_cache is a kmalloc cache. With newly introduced is_kmalloc_cache() helper, 'is_kmalloc' and its related function can be replaced and removed. Also 'kasan_cache' is only needed by KASAN generic mode, and not by SW/HW tag modes, so refine its protection macro accordingly, suggested by Andrey Konoval. Link: https://lkml.kernel.org/r/20230104060605.930910-2-feng.tang@intel.com Signed-off-by: Feng Tang Reviewed-by: Andrey Konovalov Acked-by: Vlastimil Babka Acked-by: David Rientjes Cc: Alexander Potapenko Cc: Andrey Ryabinin Cc: Christoph Lameter Cc: Dmitry Vyukov Cc: Hyeonggon Yoo <42.hyeyoo@gmail.com> Cc: Joonsoo Kim Cc: Pekka Enberg Cc: Roman Gushchin Cc: Vincenzo Frascino Signed-off-by: Andrew Morton --- include/linux/kasan.h | 22 +++++----------------- include/linux/slab_def.h | 2 +- include/linux/slub_def.h | 2 +- mm/kasan/common.c | 9 ++------- mm/slab_common.c | 1 - 5 files changed, 9 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 5ebbaf672009..f7ef70661ce2 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -96,15 +96,6 @@ static inline bool kasan_has_integrated_init(void) } #ifdef CONFIG_KASAN - -struct kasan_cache { -#ifdef CONFIG_KASAN_GENERIC - int alloc_meta_offset; - int free_meta_offset; -#endif - bool is_kmalloc; -}; - void __kasan_unpoison_range(const void *addr, size_t size); static __always_inline void kasan_unpoison_range(const void *addr, size_t size) { @@ -129,13 +120,6 @@ static __always_inline bool kasan_unpoison_pages(struct page *page, return false; } -void __kasan_cache_create_kmalloc(struct kmem_cache *cache); -static __always_inline void kasan_cache_create_kmalloc(struct kmem_cache *cache) -{ - if (kasan_enabled()) - __kasan_cache_create_kmalloc(cache); -} - void __kasan_poison_slab(struct slab *slab); static __always_inline void kasan_poison_slab(struct slab *slab) { @@ -255,7 +239,6 @@ static inline bool kasan_unpoison_pages(struct page *page, unsigned int order, { return false; } -static inline void kasan_cache_create_kmalloc(struct kmem_cache *cache) {} static inline void kasan_poison_slab(struct slab *slab) {} static inline void kasan_unpoison_object_data(struct kmem_cache *cache, void *object) {} @@ -306,6 +289,11 @@ static inline void kasan_unpoison_task_stack(struct task_struct *task) {} #ifdef CONFIG_KASAN_GENERIC +struct kasan_cache { + int alloc_meta_offset; + int free_meta_offset; +}; + size_t kasan_metadata_size(struct kmem_cache *cache, bool in_object); slab_flags_t kasan_never_merge(void); void kasan_cache_create(struct kmem_cache *cache, unsigned int *size, diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h index 5834bad8ad78..a61e7d55d0d3 100644 --- a/include/linux/slab_def.h +++ b/include/linux/slab_def.h @@ -72,7 +72,7 @@ struct kmem_cache { int obj_offset; #endif /* CONFIG_DEBUG_SLAB */ -#ifdef CONFIG_KASAN +#ifdef CONFIG_KASAN_GENERIC struct kasan_cache kasan_info; #endif diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index aa0ee1678d29..f6df03f934e5 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -136,7 +136,7 @@ struct kmem_cache { unsigned int *random_seq; #endif -#ifdef CONFIG_KASAN +#ifdef CONFIG_KASAN_GENERIC struct kasan_cache kasan_info; #endif diff --git a/mm/kasan/common.c b/mm/kasan/common.c index 1d0008e1c420..6b8e9c848573 100644 --- a/mm/kasan/common.c +++ b/mm/kasan/common.c @@ -122,11 +122,6 @@ void __kasan_poison_pages(struct page *page, unsigned int order, bool init) KASAN_PAGE_FREE, init); } -void __kasan_cache_create_kmalloc(struct kmem_cache *cache) -{ - cache->kasan_info.is_kmalloc = true; -} - void __kasan_poison_slab(struct slab *slab) { struct page *page = slab_page(slab); @@ -326,7 +321,7 @@ void * __must_check __kasan_slab_alloc(struct kmem_cache *cache, kasan_unpoison(tagged_object, cache->object_size, init); /* Save alloc info (if possible) for non-kmalloc() allocations. */ - if (kasan_stack_collection_enabled() && !cache->kasan_info.is_kmalloc) + if (kasan_stack_collection_enabled() && !is_kmalloc_cache(cache)) kasan_save_alloc_info(cache, tagged_object, flags); return tagged_object; @@ -372,7 +367,7 @@ static inline void *____kasan_kmalloc(struct kmem_cache *cache, * Save alloc info (if possible) for kmalloc() allocations. * This also rewrites the alloc info when called from kasan_krealloc(). */ - if (kasan_stack_collection_enabled() && cache->kasan_info.is_kmalloc) + if (kasan_stack_collection_enabled() && is_kmalloc_cache(cache)) kasan_save_alloc_info(cache, (void *)object, flags); /* Keep the tag that was set by kasan_slab_alloc(). */ diff --git a/mm/slab_common.c b/mm/slab_common.c index 1cba98acc486..bf4e777cfe90 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -670,7 +670,6 @@ struct kmem_cache *__init create_kmalloc_cache(const char *name, create_boot_cache(s, name, size, flags | SLAB_KMALLOC, useroffset, usersize); - kasan_cache_create_kmalloc(s); list_add(&s->list, &slab_caches); s->refcount = 1; return s; -- cgit v1.2.3 From e9adcfecf572fcfaa9f8525904cf49c709974f73 Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Tue, 3 Jan 2023 16:27:32 -0800 Subject: mm: remove zap_page_range and create zap_vma_pages zap_page_range was originally designed to unmap pages within an address range that could span multiple vmas. While working on [1], it was discovered that all callers of zap_page_range pass a range entirely within a single vma. In addition, the mmu notification call within zap_page range does not correctly handle ranges that span multiple vmas. When crossing a vma boundary, a new mmu_notifier_range_init/end call pair with the new vma should be made. Instead of fixing zap_page_range, do the following: - Create a new routine zap_vma_pages() that will remove all pages within the passed vma. Most users of zap_page_range pass the entire vma and can use this new routine. - For callers of zap_page_range not passing the entire vma, instead call zap_page_range_single(). - Remove zap_page_range. [1] https://lore.kernel.org/linux-mm/20221114235507.294320-2-mike.kravetz@oracle.com/ Link: https://lkml.kernel.org/r/20230104002732.232573-1-mike.kravetz@oracle.com Signed-off-by: Mike Kravetz Suggested-by: Peter Xu Acked-by: Michal Hocko Acked-by: Peter Xu Acked-by: Heiko Carstens [s390] Reviewed-by: Christoph Hellwig Cc: Christian Borntraeger Cc: Christian Brauner Cc: Dave Hansen Cc: David Hildenbrand Cc: Eric Dumazet Cc: Matthew Wilcox Cc: Michael Ellerman Cc: Nadav Amit Cc: Palmer Dabbelt Cc: Rik van Riel Cc: Vlastimil Babka Cc: Will Deacon Signed-off-by: Andrew Morton --- arch/arm64/kernel/vdso.c | 6 ++---- arch/powerpc/kernel/vdso.c | 4 +--- arch/powerpc/platforms/book3s/vas-api.c | 2 +- arch/powerpc/platforms/pseries/vas.c | 3 +-- arch/riscv/kernel/vdso.c | 6 ++---- arch/s390/kernel/vdso.c | 4 +--- arch/s390/mm/gmap.c | 2 +- arch/x86/entry/vdso/vma.c | 4 +--- drivers/android/binder_alloc.c | 2 +- include/linux/mm.h | 7 +++++-- mm/memory.c | 30 ------------------------------ mm/page-writeback.c | 2 +- net/ipv4/tcp.c | 7 ++++--- 13 files changed, 21 insertions(+), 58 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c index e59a32aa0c49..0119dc91abb5 100644 --- a/arch/arm64/kernel/vdso.c +++ b/arch/arm64/kernel/vdso.c @@ -138,13 +138,11 @@ int vdso_join_timens(struct task_struct *task, struct time_namespace *ns) mmap_read_lock(mm); for_each_vma(vmi, vma) { - unsigned long size = vma->vm_end - vma->vm_start; - if (vma_is_special_mapping(vma, vdso_info[VDSO_ABI_AA64].dm)) - zap_page_range(vma, vma->vm_start, size); + zap_vma_pages(vma); #ifdef CONFIG_COMPAT_VDSO if (vma_is_special_mapping(vma, vdso_info[VDSO_ABI_AA32].dm)) - zap_page_range(vma, vma->vm_start, size); + zap_vma_pages(vma); #endif } diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c index 507f8228f983..7a2ff9010f17 100644 --- a/arch/powerpc/kernel/vdso.c +++ b/arch/powerpc/kernel/vdso.c @@ -120,10 +120,8 @@ int vdso_join_timens(struct task_struct *task, struct time_namespace *ns) mmap_read_lock(mm); for_each_vma(vmi, vma) { - unsigned long size = vma->vm_end - vma->vm_start; - if (vma_is_special_mapping(vma, &vvar_spec)) - zap_page_range(vma, vma->vm_start, size); + zap_vma_pages(vma); } mmap_read_unlock(mm); diff --git a/arch/powerpc/platforms/book3s/vas-api.c b/arch/powerpc/platforms/book3s/vas-api.c index eb5bed333750..9580e8e12165 100644 --- a/arch/powerpc/platforms/book3s/vas-api.c +++ b/arch/powerpc/platforms/book3s/vas-api.c @@ -414,7 +414,7 @@ static vm_fault_t vas_mmap_fault(struct vm_fault *vmf) /* * When the LPAR lost credits due to core removal or during * migration, invalidate the existing mapping for the current - * paste addresses and set windows in-active (zap_page_range in + * paste addresses and set windows in-active (zap_vma_pages in * reconfig_close_windows()). * New mapping will be done later after migration or new credits * available. So continue to receive faults if the user space diff --git a/arch/powerpc/platforms/pseries/vas.c b/arch/powerpc/platforms/pseries/vas.c index 4ad6e510d405..559112312810 100644 --- a/arch/powerpc/platforms/pseries/vas.c +++ b/arch/powerpc/platforms/pseries/vas.c @@ -760,8 +760,7 @@ static int reconfig_close_windows(struct vas_caps *vcap, int excess_creds, * is done before the original mmap() and after the ioctl. */ if (vma) - zap_page_range(vma, vma->vm_start, - vma->vm_end - vma->vm_start); + zap_vma_pages(vma); mmap_write_unlock(task_ref->mm); mutex_unlock(&task_ref->mmap_mutex); diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c index e410275918ac..5c30212d8d1c 100644 --- a/arch/riscv/kernel/vdso.c +++ b/arch/riscv/kernel/vdso.c @@ -124,13 +124,11 @@ int vdso_join_timens(struct task_struct *task, struct time_namespace *ns) mmap_read_lock(mm); for_each_vma(vmi, vma) { - unsigned long size = vma->vm_end - vma->vm_start; - if (vma_is_special_mapping(vma, vdso_info.dm)) - zap_page_range(vma, vma->vm_start, size); + zap_vma_pages(vma); #ifdef CONFIG_COMPAT if (vma_is_special_mapping(vma, compat_vdso_info.dm)) - zap_page_range(vma, vma->vm_start, size); + zap_vma_pages(vma); #endif } diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c index ff7bf4432229..bbaefd84f15e 100644 --- a/arch/s390/kernel/vdso.c +++ b/arch/s390/kernel/vdso.c @@ -59,11 +59,9 @@ int vdso_join_timens(struct task_struct *task, struct time_namespace *ns) mmap_read_lock(mm); for_each_vma(vmi, vma) { - unsigned long size = vma->vm_end - vma->vm_start; - if (!vma_is_special_mapping(vma, &vvar_mapping)) continue; - zap_page_range(vma, vma->vm_start, size); + zap_vma_pages(vma); break; } mmap_read_unlock(mm); diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c index 74e1d873dce0..69af6cdf1a2a 100644 --- a/arch/s390/mm/gmap.c +++ b/arch/s390/mm/gmap.c @@ -722,7 +722,7 @@ void gmap_discard(struct gmap *gmap, unsigned long from, unsigned long to) if (is_vm_hugetlb_page(vma)) continue; size = min(to - gaddr, PMD_SIZE - (gaddr & ~PMD_MASK)); - zap_page_range(vma, vmaddr, size); + zap_page_range_single(vma, vmaddr, size, NULL); } mmap_read_unlock(gmap->mm); } diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c index b8f3f9b9e53c..ec5e4d2048cb 100644 --- a/arch/x86/entry/vdso/vma.c +++ b/arch/x86/entry/vdso/vma.c @@ -113,10 +113,8 @@ int vdso_join_timens(struct task_struct *task, struct time_namespace *ns) mmap_read_lock(mm); for_each_vma(vmi, vma) { - unsigned long size = vma->vm_end - vma->vm_start; - if (vma_is_special_mapping(vma, &vvar_mapping)) - zap_page_range(vma, vma->vm_start, size); + zap_vma_pages(vma); } mmap_read_unlock(mm); diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c index 4ad42b0f75cd..55a3c3c2409f 100644 --- a/drivers/android/binder_alloc.c +++ b/drivers/android/binder_alloc.c @@ -1019,7 +1019,7 @@ enum lru_status binder_alloc_free_page(struct list_head *item, if (vma) { trace_binder_unmap_user_start(alloc, index); - zap_page_range(vma, page_addr, PAGE_SIZE); + zap_page_range_single(vma, page_addr, PAGE_SIZE, NULL); trace_binder_unmap_user_end(alloc, index); } diff --git a/include/linux/mm.h b/include/linux/mm.h index 4ac5ea4b584c..eb5bfc77c2c2 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1977,10 +1977,13 @@ struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, void zap_vma_ptes(struct vm_area_struct *vma, unsigned long address, unsigned long size); -void zap_page_range(struct vm_area_struct *vma, unsigned long address, - unsigned long size); void zap_page_range_single(struct vm_area_struct *vma, unsigned long address, unsigned long size, struct zap_details *details); +static inline void zap_vma_pages(struct vm_area_struct *vma) +{ + zap_page_range_single(vma, vma->vm_start, + vma->vm_end - vma->vm_start, NULL); +} void unmap_vmas(struct mmu_gather *tlb, struct maple_tree *mt, struct vm_area_struct *start_vma, unsigned long start, unsigned long end); diff --git a/mm/memory.c b/mm/memory.c index 1598051a2a24..b0dda866ffe6 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1693,36 +1693,6 @@ void unmap_vmas(struct mmu_gather *tlb, struct maple_tree *mt, mmu_notifier_invalidate_range_end(&range); } -/** - * zap_page_range - remove user pages in a given range - * @vma: vm_area_struct holding the applicable pages - * @start: starting address of pages to zap - * @size: number of bytes to zap - * - * Caller must protect the VMA list - */ -void zap_page_range(struct vm_area_struct *vma, unsigned long start, - unsigned long size) -{ - struct maple_tree *mt = &vma->vm_mm->mm_mt; - unsigned long end = start + size; - struct mmu_notifier_range range; - struct mmu_gather tlb; - MA_STATE(mas, mt, vma->vm_end, vma->vm_end); - - lru_add_drain(); - mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm, - start, start + size); - tlb_gather_mmu(&tlb, vma->vm_mm); - update_hiwater_rss(vma->vm_mm); - mmu_notifier_invalidate_range_start(&range); - do { - unmap_single_vma(&tlb, vma, start, range.end, NULL); - } while ((vma = mas_find(&mas, end - 1)) != NULL); - mmu_notifier_invalidate_range_end(&range); - tlb_finish_mmu(&tlb); -} - /** * zap_page_range_single - remove user pages in a given range * @vma: vm_area_struct holding the applicable pages diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 337cafe9978c..e91f94b3438b 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2690,7 +2690,7 @@ void folio_account_cleaned(struct folio *folio, struct bdi_writeback *wb) * * The caller must hold lock_page_memcg(). Most callers have the folio * locked. A few have the folio blocked from truncation through other - * means (eg zap_page_range() has it mapped and is holding the page table + * means (eg zap_vma_pages() has it mapped and is holding the page table * lock). This can also be called from mark_buffer_dirty(), which I * cannot prove is always protected against truncate. */ diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index c567d5e8053e..f713c0422f0f 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2092,7 +2092,7 @@ static int tcp_zerocopy_vm_insert_batch_error(struct vm_area_struct *vma, maybe_zap_len = total_bytes_to_map - /* All bytes to map */ *length + /* Mapped or pending */ (pages_remaining * PAGE_SIZE); /* Failed map. */ - zap_page_range(vma, *address, maybe_zap_len); + zap_page_range_single(vma, *address, maybe_zap_len, NULL); err = 0; } @@ -2100,7 +2100,7 @@ static int tcp_zerocopy_vm_insert_batch_error(struct vm_area_struct *vma, unsigned long leftover_pages = pages_remaining; int bytes_mapped; - /* We called zap_page_range, try to reinsert. */ + /* We called zap_page_range_single, try to reinsert. */ err = vm_insert_pages(vma, *address, pending_pages, &pages_remaining); @@ -2234,7 +2234,8 @@ static int tcp_zerocopy_receive(struct sock *sk, total_bytes_to_map = avail_len & ~(PAGE_SIZE - 1); if (total_bytes_to_map) { if (!(zc->flags & TCP_RECEIVE_ZEROCOPY_FLAG_TLB_CLEAN_HINT)) - zap_page_range(vma, address, total_bytes_to_map); + zap_page_range_single(vma, address, total_bytes_to_map, + NULL); zc->length = total_bytes_to_map; zc->recv_skip_hint = 0; } else { -- cgit v1.2.3 From fc4f4be9b5271e43eeb4c675d190fa9734de9ea3 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 2 Jan 2023 17:08:54 +0100 Subject: mm/nommu: factor out check for NOMMU shared mappings into is_nommu_shared_mapping() Patch series "mm/nommu: don't use VM_MAYSHARE for MAP_PRIVATE mappings". Trying to reduce the confusion around VM_SHARED and VM_MAYSHARE first requires !CONFIG_MMU to stop using VM_MAYSHARE for MAP_PRIVATE mappings. CONFIG_MMU only sets VM_MAYSHARE for MAP_SHARED mappings. This paves the way for further VM_MAYSHARE and VM_SHARED cleanups: for example, renaming VM_MAYSHARED to VM_MAP_SHARED to make it cleaner what is actually means. Let's first get the weird case out of the way and not use VM_MAYSHARE in MAP_PRIVATE mappings, using a new VM_MAYOVERLAY flag instead. This patch (of 3): We want to stop using VM_MAYSHARE in private mappings to pave the way for clarifying the semantics of VM_MAYSHARE vs. VM_SHARED and reduce the confusion. While CONFIG_MMU uses VM_MAYSHARE to represent MAP_SHARED, !CONFIG_MMU also sets VM_MAYSHARE for selected R/O private file mappings that are an effective overlay of a file mapping. Let's factor out all relevant VM_MAYSHARE checks in !CONFIG_MMU code into is_nommu_shared_mapping() first. Note that whenever VM_SHARED is set, VM_MAYSHARE must be set as well (unless there is a serious BUG). So there is not need to test for VM_SHARED manually. No functional change intended. Link: https://lkml.kernel.org/r/20230102160856.500584-1-david@redhat.com Link: https://lkml.kernel.org/r/20230102160856.500584-2-david@redhat.com Signed-off-by: David Hildenbrand Cc: Arnd Bergmann Cc: David Hildenbrand Cc: Greg Kroah-Hartman Cc: Jens Axboe Cc: Nicolas Pitre Cc: Pavel Begunkov Signed-off-by: Andrew Morton --- drivers/char/mem.c | 2 +- fs/cramfs/inode.c | 2 +- fs/proc/task_nommu.c | 2 +- fs/ramfs/file-nommu.c | 2 +- fs/romfs/mmap-nommu.c | 2 +- include/linux/mm.h | 15 +++++++++++++++ io_uring/io_uring.c | 2 +- mm/nommu.c | 11 ++++++----- 8 files changed, 27 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/drivers/char/mem.c b/drivers/char/mem.c index 83bf2a4dcb57..ffb101d349f0 100644 --- a/drivers/char/mem.c +++ b/drivers/char/mem.c @@ -343,7 +343,7 @@ static unsigned zero_mmap_capabilities(struct file *file) /* can't do an in-place private mapping if there's no MMU */ static inline int private_mapping_ok(struct vm_area_struct *vma) { - return vma->vm_flags & VM_MAYSHARE; + return is_nommu_shared_mapping(vma->vm_flags); } #else diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c index 61ccf7722fc3..50e4e060db68 100644 --- a/fs/cramfs/inode.c +++ b/fs/cramfs/inode.c @@ -437,7 +437,7 @@ bailout: static int cramfs_physmem_mmap(struct file *file, struct vm_area_struct *vma) { - return vma->vm_flags & (VM_SHARED | VM_MAYSHARE) ? 0 : -ENOSYS; + return is_nommu_shared_mapping(vma->vm_flags) ? 0 : -ENOSYS; } static unsigned long cramfs_physmem_get_unmapped_area(struct file *file, diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c index 2fd06f52b6a4..0ec35072a8e5 100644 --- a/fs/proc/task_nommu.c +++ b/fs/proc/task_nommu.c @@ -38,7 +38,7 @@ void task_mem(struct seq_file *m, struct mm_struct *mm) } if (atomic_read(&mm->mm_count) > 1 || - vma->vm_flags & VM_MAYSHARE) { + is_nommu_shared_mapping(vma->vm_flags)) { sbytes += size; } else { bytes += size; diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c index cb240eac5036..cd4537692751 100644 --- a/fs/ramfs/file-nommu.c +++ b/fs/ramfs/file-nommu.c @@ -264,7 +264,7 @@ out: */ static int ramfs_nommu_mmap(struct file *file, struct vm_area_struct *vma) { - if (!(vma->vm_flags & (VM_SHARED | VM_MAYSHARE))) + if (!is_nommu_shared_mapping(vma->vm_flags)) return -ENOSYS; file_accessed(file); diff --git a/fs/romfs/mmap-nommu.c b/fs/romfs/mmap-nommu.c index 2c4a23113fb5..4578dc45e50a 100644 --- a/fs/romfs/mmap-nommu.c +++ b/fs/romfs/mmap-nommu.c @@ -63,7 +63,7 @@ static unsigned long romfs_get_unmapped_area(struct file *file, */ static int romfs_mmap(struct file *file, struct vm_area_struct *vma) { - return vma->vm_flags & (VM_SHARED | VM_MAYSHARE) ? 0 : -ENOSYS; + return is_nommu_shared_mapping(vma->vm_flags) ? 0 : -ENOSYS; } static unsigned romfs_mmap_capabilities(struct file *file) diff --git a/include/linux/mm.h b/include/linux/mm.h index eb5bfc77c2c2..791bac40bf8e 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1347,6 +1347,21 @@ static inline bool is_cow_mapping(vm_flags_t flags) return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE; } +#ifndef CONFIG_MMU +static inline bool is_nommu_shared_mapping(vm_flags_t flags) +{ + /* + * NOMMU shared mappings are ordinary MAP_SHARED mappings and selected + * R/O MAP_PRIVATE file mappings that are an effective R/O overlay of + * a file mapping. R/O MAP_PRIVATE mappings might still modify + * underlying memory if ptrace is active, so this is only possible if + * ptrace does not apply. Note that there is no mprotect() to upgrade + * write permissions later. + */ + return flags & VM_MAYSHARE; +} +#endif + #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) #define SECTION_IN_PAGE_FLAGS #endif diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 2ac1cd8d23ea..3a934f733136 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -3206,7 +3206,7 @@ static __cold int io_uring_mmap(struct file *file, struct vm_area_struct *vma) static int io_uring_mmap(struct file *file, struct vm_area_struct *vma) { - return vma->vm_flags & (VM_SHARED | VM_MAYSHARE) ? 0 : -EINVAL; + return is_nommu_shared_mapping(vma->vm_flags) ? 0 : -EINVAL; } static unsigned int io_uring_nommu_mmap_capabilities(struct file *file) diff --git a/mm/nommu.c b/mm/nommu.c index 5b83938ecb67..1671ebbecb8d 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -958,9 +958,10 @@ static int do_mmap_private(struct vm_area_struct *vma, */ if (capabilities & NOMMU_MAP_DIRECT) { ret = call_mmap(vma->vm_file, vma); + /* shouldn't return success if we're not sharing */ + if (WARN_ON_ONCE(!is_nommu_shared_mapping(vma->vm_flags))) + ret = -ENOSYS; if (ret == 0) { - /* shouldn't return success if we're not sharing */ - BUG_ON(!(vma->vm_flags & VM_MAYSHARE)); vma->vm_region->vm_top = vma->vm_region->vm_end; return 0; } @@ -1106,7 +1107,7 @@ unsigned long do_mmap(struct file *file, * these cases, sharing is handled in the driver or filesystem rather * than here */ - if (vm_flags & VM_MAYSHARE) { + if (is_nommu_shared_mapping(vm_flags)) { struct vm_region *pregion; unsigned long pglen, rpglen, pgend, rpgend, start; @@ -1116,7 +1117,7 @@ unsigned long do_mmap(struct file *file, for (rb = rb_first(&nommu_region_tree); rb; rb = rb_next(rb)) { pregion = rb_entry(rb, struct vm_region, vm_rb); - if (!(pregion->vm_flags & VM_MAYSHARE)) + if (!is_nommu_shared_mapping(pregion->vm_flags)) continue; /* search for overlapping mappings on the same file */ @@ -1600,7 +1601,7 @@ static unsigned long do_mremap(unsigned long addr, if (vma->vm_end != vma->vm_start + old_len) return (unsigned long) -EFAULT; - if (vma->vm_flags & VM_MAYSHARE) + if (is_nommu_shared_mapping(vma->vm_flags)) return (unsigned long) -EPERM; if (new_len > vma->vm_region->vm_end - vma->vm_region->vm_start) -- cgit v1.2.3 From b6b7a8faf05c709cd9f63d3b7d9c66bd91bc3b0d Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 2 Jan 2023 17:08:55 +0100 Subject: mm/nommu: don't use VM_MAYSHARE for MAP_PRIVATE mappings Let's stop using VM_MAYSHARE for MAP_PRIVATE mappings and use VM_MAYOVERLAY instead. Rewrite determine_vm_flags() to make the whole logic easier to digest, and to cleanly separate MAP_PRIVATE vs. MAP_SHARED. No functional change intended. Link: https://lkml.kernel.org/r/20230102160856.500584-3-david@redhat.com Signed-off-by: David Hildenbrand Cc: Arnd Bergmann Cc: Greg Kroah-Hartman Cc: Jens Axboe Cc: Nicolas Pitre Cc: Pavel Begunkov Signed-off-by: Andrew Morton --- include/linux/mm.h | 7 ++++++- mm/nommu.c | 51 ++++++++++++++++++++++++++++++--------------------- 2 files changed, 36 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 791bac40bf8e..8a8563359946 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -276,7 +276,12 @@ extern unsigned int kobjsize(const void *objp); #define VM_MAYSHARE 0x00000080 #define VM_GROWSDOWN 0x00000100 /* general info on the segment */ +#ifdef CONFIG_MMU #define VM_UFFD_MISSING 0x00000200 /* missing pages tracking */ +#else /* CONFIG_MMU */ +#define VM_MAYOVERLAY 0x00000200 /* nommu: R/O MAP_PRIVATE mapping that might overlay a file mapping */ +#define VM_UFFD_MISSING 0 +#endif /* CONFIG_MMU */ #define VM_PFNMAP 0x00000400 /* Page-ranges managed without "struct page", just pure PFN */ #define VM_UFFD_WP 0x00001000 /* wrprotect pages tracking */ @@ -1358,7 +1363,7 @@ static inline bool is_nommu_shared_mapping(vm_flags_t flags) * ptrace does not apply. Note that there is no mprotect() to upgrade * write permissions later. */ - return flags & VM_MAYSHARE; + return flags & (VM_MAYSHARE | VM_MAYOVERLAY); } #endif diff --git a/mm/nommu.c b/mm/nommu.c index 1671ebbecb8d..df1711acdf5b 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -892,29 +892,36 @@ static unsigned long determine_vm_flags(struct file *file, unsigned long vm_flags; vm_flags = calc_vm_prot_bits(prot, 0) | calc_vm_flag_bits(flags); - /* vm_flags |= mm->def_flags; */ - if (!(capabilities & NOMMU_MAP_DIRECT)) { - /* attempt to share read-only copies of mapped file chunks */ + if (!file) { + /* + * MAP_ANONYMOUS. MAP_SHARED is mapped to MAP_PRIVATE, because + * there is no fork(). + */ vm_flags |= VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC; - if (file && !(prot & PROT_WRITE)) - vm_flags |= VM_MAYSHARE; + } else if (flags & MAP_PRIVATE) { + /* MAP_PRIVATE file mapping */ + if (capabilities & NOMMU_MAP_DIRECT) + vm_flags |= (capabilities & NOMMU_VMFLAGS); + else + vm_flags |= VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC; + + if (!(prot & PROT_WRITE) && !current->ptrace) + /* + * R/O private file mapping which cannot be used to + * modify memory, especially also not via active ptrace + * (e.g., set breakpoints) or later by upgrading + * permissions (no mprotect()). We can try overlaying + * the file mapping, which will work e.g., on chardevs, + * ramfs/tmpfs/shmfs and romfs/cramf. + */ + vm_flags |= VM_MAYOVERLAY; } else { - /* overlay a shareable mapping on the backing device or inode - * if possible - used for chardevs, ramfs/tmpfs/shmfs and - * romfs/cramfs */ - vm_flags |= VM_MAYSHARE | (capabilities & NOMMU_VMFLAGS); - if (flags & MAP_SHARED) - vm_flags |= VM_SHARED; + /* MAP_SHARED file mapping: NOMMU_MAP_DIRECT is set. */ + vm_flags |= VM_SHARED | VM_MAYSHARE | + (capabilities & NOMMU_VMFLAGS); } - /* refuse to let anyone share private mappings with this process if - * it's being traced - otherwise breakpoints set in it may interfere - * with another untraced process - */ - if ((flags & MAP_PRIVATE) && current->ptrace) - vm_flags &= ~VM_MAYSHARE; - return vm_flags; } @@ -952,9 +959,11 @@ static int do_mmap_private(struct vm_area_struct *vma, void *base; int ret, order; - /* invoke the file's mapping function so that it can keep track of - * shared mappings on devices or memory - * - VM_MAYSHARE will be set if it may attempt to share + /* + * Invoke the file's mapping function so that it can keep track of + * shared mappings on devices or memory. VM_MAYOVERLAY will be set if + * it may attempt to share, which will make is_nommu_shared_mapping() + * happy. */ if (capabilities & NOMMU_MAP_DIRECT) { ret = call_mmap(vma->vm_file, vma); -- cgit v1.2.3 From 8788f6781486769d9598dcaedc3fe0eb12fc3e59 Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Fri, 30 Dec 2022 14:52:51 -0700 Subject: mm: add vma_has_recency() Add vma_has_recency() to indicate whether a VMA may exhibit temporal locality that the LRU algorithm relies on. This function returns false for VMAs marked by VM_SEQ_READ or VM_RAND_READ. While the former flag indicates linear access, i.e., a special case of spatial locality, both flags indicate a lack of temporal locality, i.e., the reuse of an area within a relatively small duration. "Recency" is chosen over "locality" to avoid confusion between temporal and spatial localities. Before this patch, the active/inactive LRU only ignored the accessed bit from VMAs marked by VM_SEQ_READ. After this patch, the active/inactive LRU and MGLRU share the same logic: they both ignore the accessed bit if vma_has_recency() returns false. For the active/inactive LRU, the following fio test showed a [6, 8]% increase in IOPS when randomly accessing mapped files under memory pressure. kb=$(awk '/MemTotal/ { print $2 }' /proc/meminfo) kb=$((kb - 8*1024*1024)) modprobe brd rd_nr=1 rd_size=$kb dd if=/dev/zero of=/dev/ram0 bs=1M mkfs.ext4 /dev/ram0 mount /dev/ram0 /mnt/ swapoff -a fio --name=test --directory=/mnt/ --ioengine=mmap --numjobs=8 \ --size=8G --rw=randrw --time_based --runtime=10m \ --group_reporting The discussion that led to this patch is here [1]. Additional test results are available in that thread. [1] https://lore.kernel.org/r/Y31s%2FK8T85jh05wH@google.com/ Link: https://lkml.kernel.org/r/20221230215252.2628425-1-yuzhao@google.com Signed-off-by: Yu Zhao Cc: Alexander Viro Cc: Andrea Righi Cc: Johannes Weiner Cc: Michael Larabel Signed-off-by: Andrew Morton --- include/linux/mm_inline.h | 8 ++++++++ mm/memory.c | 7 +++---- mm/rmap.c | 42 ++++++++++++++++++------------------------ mm/vmscan.c | 5 ++++- 4 files changed, 33 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index acf03147fff8..4abebf2615a3 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -594,4 +594,12 @@ pte_install_uffd_wp_if_needed(struct vm_area_struct *vma, unsigned long addr, #endif } +static inline bool vma_has_recency(struct vm_area_struct *vma) +{ + if (vma->vm_flags & (VM_SEQ_READ | VM_RAND_READ)) + return false; + + return true; +} + #endif diff --git a/mm/memory.c b/mm/memory.c index b0dda866ffe6..90f8f72777c7 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1402,8 +1402,7 @@ again: force_flush = 1; } } - if (pte_young(ptent) && - likely(!(vma->vm_flags & VM_SEQ_READ))) + if (pte_young(ptent) && likely(vma_has_recency(vma))) mark_page_accessed(page); } rss[mm_counter(page)]--; @@ -5115,8 +5114,8 @@ static inline void mm_account_fault(struct pt_regs *regs, #ifdef CONFIG_LRU_GEN static void lru_gen_enter_fault(struct vm_area_struct *vma) { - /* the LRU algorithm doesn't apply to sequential or random reads */ - current->in_lru_fault = !(vma->vm_flags & (VM_SEQ_READ | VM_RAND_READ)); + /* the LRU algorithm only applies to accesses with recency */ + current->in_lru_fault = vma_has_recency(vma); } static void lru_gen_exit_fault(void) diff --git a/mm/rmap.c b/mm/rmap.c index 32e48b1c5847..ab74e0547a52 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -823,25 +823,14 @@ static bool folio_referenced_one(struct folio *folio, } if (pvmw.pte) { - if (lru_gen_enabled() && pte_young(*pvmw.pte) && - !(vma->vm_flags & (VM_SEQ_READ | VM_RAND_READ))) { + if (lru_gen_enabled() && pte_young(*pvmw.pte)) { lru_gen_look_around(&pvmw); referenced++; } if (ptep_clear_flush_young_notify(vma, address, - pvmw.pte)) { - /* - * Don't treat a reference through - * a sequentially read mapping as such. - * If the folio has been used in another mapping, - * we will catch it; if this other mapping is - * already gone, the unmap path will have set - * the referenced flag or activated the folio. - */ - if (likely(!(vma->vm_flags & VM_SEQ_READ))) - referenced++; - } + pvmw.pte)) + referenced++; } else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) { if (pmdp_clear_flush_young_notify(vma, address, pvmw.pmd)) @@ -875,7 +864,20 @@ static bool invalid_folio_referenced_vma(struct vm_area_struct *vma, void *arg) struct folio_referenced_arg *pra = arg; struct mem_cgroup *memcg = pra->memcg; - if (!mm_match_cgroup(vma->vm_mm, memcg)) + /* + * Ignore references from this mapping if it has no recency. If the + * folio has been used in another mapping, we will catch it; if this + * other mapping is already gone, the unmap path will have set the + * referenced flag or activated the folio in zap_pte_range(). + */ + if (!vma_has_recency(vma)) + return true; + + /* + * If we are reclaiming on behalf of a cgroup, skip counting on behalf + * of references from different cgroups. + */ + if (memcg && !mm_match_cgroup(vma->vm_mm, memcg)) return true; return false; @@ -906,6 +908,7 @@ int folio_referenced(struct folio *folio, int is_locked, .arg = (void *)&pra, .anon_lock = folio_lock_anon_vma_read, .try_lock = true, + .invalid_vma = invalid_folio_referenced_vma, }; *vm_flags = 0; @@ -921,15 +924,6 @@ int folio_referenced(struct folio *folio, int is_locked, return 1; } - /* - * If we are reclaiming on behalf of a cgroup, skip - * counting on behalf of references from different - * cgroups - */ - if (memcg) { - rwc.invalid_vma = invalid_folio_referenced_vma; - } - rmap_walk(folio, &rwc); *vm_flags = pra.vm_flags; diff --git a/mm/vmscan.c b/mm/vmscan.c index 7c3fd900a89d..fe30b8c43f92 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -3794,7 +3794,10 @@ static int should_skip_vma(unsigned long start, unsigned long end, struct mm_wal if (is_vm_hugetlb_page(vma)) return true; - if (vma->vm_flags & (VM_LOCKED | VM_SPECIAL | VM_SEQ_READ | VM_RAND_READ)) + if (!vma_has_recency(vma)) + return true; + + if (vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) return true; if (vma == get_gate_vma(vma->vm_mm)) -- cgit v1.2.3 From 17e810229cb3068b692fa078bd9b3a6527e0866a Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Fri, 30 Dec 2022 14:52:52 -0700 Subject: mm: support POSIX_FADV_NOREUSE This patch adds POSIX_FADV_NOREUSE to vma_has_recency() so that the LRU algorithm can ignore access to mapped files marked by this flag. The advantages of POSIX_FADV_NOREUSE are: 1. Unlike MADV_SEQUENTIAL and MADV_RANDOM, it does not alter the default readahead behavior. 2. Unlike MADV_SEQUENTIAL and MADV_RANDOM, it does not split VMAs and therefore does not take mmap_lock. 3. Unlike MADV_COLD, setting it has a negligible cost, regardless of how many pages it affects. Its limitations are: 1. Like POSIX_FADV_RANDOM and POSIX_FADV_SEQUENTIAL, it currently does not support range. IOW, its scope is the entire file. 2. It currently does not ignore access through file descriptors. Specifically, for the active/inactive LRU, given a file page shared by two users and one of them having set POSIX_FADV_NOREUSE on the file, this page will be activated upon the second user accessing it. This corner case can be covered by checking POSIX_FADV_NOREUSE before calling folio_mark_accessed() on the read path. But it is considered not worth the effort. There have been a few attempts to support POSIX_FADV_NOREUSE, e.g., [1]. This time the goal is to fill a niche: a few desktop applications, e.g., large file transferring and video encoding/decoding, want fast file streaming with mmap() rather than direct IO. Among those applications, an SVT-AV1 regression was reported when running with MGLRU [2]. The following test can reproduce that regression. kb=$(awk '/MemTotal/ { print $2 }' /proc/meminfo) kb=$((kb - 8*1024*1024)) modprobe brd rd_nr=1 rd_size=$kb dd if=/dev/zero of=/dev/ram0 bs=1M mkfs.ext4 /dev/ram0 mount /dev/ram0 /mnt/ swapoff -a fallocate -l 8G /mnt/swapfile mkswap /mnt/swapfile swapon /mnt/swapfile wget http://ultravideo.cs.tut.fi/video/Bosphorus_3840x2160_120fps_420_8bit_YUV_Y4M.7z 7z e -o/mnt/ Bosphorus_3840x2160_120fps_420_8bit_YUV_Y4M.7z SvtAv1EncApp --preset 12 -w 3840 -h 2160 \ -i /mnt/Bosphorus_3840x2160.y4m For MGLRU, the following change showed a [9-11]% increase in FPS, which makes it on par with the active/inactive LRU. patch Source/App/EncApp/EbAppMain.c < #include 35d35 < #include /* _O_BINARY */ 117a118 > posix_fadvise(config->mmap.fd, 0, 0, POSIX_FADV_NOREUSE); EOF [1] https://lore.kernel.org/r/1308923350-7932-1-git-send-email-andrea@betterlinux.com/ [2] https://openbenchmarking.org/result/2209259-PTS-MGLRU8GB57 Link: https://lkml.kernel.org/r/20221230215252.2628425-2-yuzhao@google.com Signed-off-by: Yu Zhao Cc: Alexander Viro Cc: Andrea Righi Cc: Johannes Weiner Cc: Michael Larabel Signed-off-by: Andrew Morton --- include/linux/fs.h | 2 ++ include/linux/mm_inline.h | 3 +++ mm/fadvise.c | 5 ++++- 3 files changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index c1769a2c5d70..d353c262d669 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -166,6 +166,8 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, /* File supports DIRECT IO */ #define FMODE_CAN_ODIRECT ((__force fmode_t)0x400000) +#define FMODE_NOREUSE ((__force fmode_t)0x800000) + /* File was opened by fanotify and shouldn't generate fanotify events */ #define FMODE_NONOTIFY ((__force fmode_t)0x4000000) diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index 4abebf2615a3..26dcbda07e92 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -599,6 +599,9 @@ static inline bool vma_has_recency(struct vm_area_struct *vma) if (vma->vm_flags & (VM_SEQ_READ | VM_RAND_READ)) return false; + if (vma->vm_file && (vma->vm_file->f_mode & FMODE_NOREUSE)) + return false; + return true; } diff --git a/mm/fadvise.c b/mm/fadvise.c index bf04fec87f35..fb7c5f43fd2a 100644 --- a/mm/fadvise.c +++ b/mm/fadvise.c @@ -80,7 +80,7 @@ int generic_fadvise(struct file *file, loff_t offset, loff_t len, int advice) case POSIX_FADV_NORMAL: file->f_ra.ra_pages = bdi->ra_pages; spin_lock(&file->f_lock); - file->f_mode &= ~FMODE_RANDOM; + file->f_mode &= ~(FMODE_RANDOM | FMODE_NOREUSE); spin_unlock(&file->f_lock); break; case POSIX_FADV_RANDOM: @@ -107,6 +107,9 @@ int generic_fadvise(struct file *file, loff_t offset, loff_t len, int advice) force_page_cache_readahead(mapping, file, start_index, nrpages); break; case POSIX_FADV_NOREUSE: + spin_lock(&file->f_lock); + file->f_mode |= FMODE_NOREUSE; + spin_unlock(&file->f_lock); break; case POSIX_FADV_DONTNEED: __filemap_fdatawrite_range(mapping, offset, endbyte, -- cgit v1.2.3 From 02d65d6fb1aae151570c8bfd1bd77a8153d2e607 Mon Sep 17 00:00:00 2001 From: Sidhartha Kumar Date: Fri, 6 Jan 2023 15:52:51 -0600 Subject: mm: introduce folio_is_pfmemalloc Add a folio equivalent for page_is_pfmemalloc. This removes two instances of page_is_pfmemalloc(folio_page(folio, 0)) so the folio can be used directly. Link: https://lkml.kernel.org/r/20230106215251.599222-1-sidhartha.kumar@oracle.com Suggested-by: Matthew Wilcox Signed-off-by: Sidhartha Kumar Reviewed-by: Matthew Wilcox (Oracle) Reviewed-by: SeongJae Park Acked-by: Vlastimil Babka Signed-off-by: Andrew Morton --- include/linux/mm.h | 15 +++++++++++++++ mm/slab.c | 2 +- mm/slub.c | 2 +- 3 files changed, 17 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 8a8563359946..76c97cb8ee9a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1926,6 +1926,21 @@ static inline bool page_is_pfmemalloc(const struct page *page) return (uintptr_t)page->lru.next & BIT(1); } +/* + * Return true only if the folio has been allocated with + * ALLOC_NO_WATERMARKS and the low watermark was not + * met implying that the system is under some pressure. + */ +static inline bool folio_is_pfmemalloc(const struct folio *folio) +{ + /* + * lru.next has bit 1 set if the page is allocated from the + * pfmemalloc reserves. Callers may simply overwrite it if + * they do not need to preserve that information. + */ + return (uintptr_t)folio->lru.next & BIT(1); +} + /* * Only to be called by the page allocator on a freshly allocated * page. diff --git a/mm/slab.c b/mm/slab.c index 7a269db050ee..b77be9c6d6b1 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -1373,7 +1373,7 @@ static struct slab *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, /* Make the flag visible before any changes to folio->mapping */ smp_wmb(); /* Record if ALLOC_NO_WATERMARKS was set when allocating the slab */ - if (sk_memalloc_socks() && page_is_pfmemalloc(folio_page(folio, 0))) + if (sk_memalloc_socks() && folio_is_pfmemalloc(folio)) slab_set_pfmemalloc(slab); return slab; diff --git a/mm/slub.c b/mm/slub.c index 13459c69095a..67020074ecb4 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1859,7 +1859,7 @@ static inline struct slab *alloc_slab_page(gfp_t flags, int node, __folio_set_slab(folio); /* Make the flag visible before any changes to folio->mapping */ smp_wmb(); - if (page_is_pfmemalloc(folio_page(folio, 0))) + if (folio_is_pfmemalloc(folio)) slab_set_pfmemalloc(slab); return slab; -- cgit v1.2.3 From 2c3e674465e73e2f7eb52c39dc5c5e97e78e68ea Mon Sep 17 00:00:00 2001 From: Cristian Marussi Date: Thu, 22 Dec 2022 18:50:47 +0000 Subject: firmware: arm_scmi: Refactor device create/destroy helpers Refactor SCMI device create/destroy helpers: it is now possible to ask for the creation of all the currently requested devices for a whole protocol, not only for the creation of a single well-defined device. While at that, re-instate uniqueness checks on the creation of SCMI SystemPower devices. Signed-off-by: Cristian Marussi Link: https://lore.kernel.org/r/20221222185049.737625-8-cristian.marussi@arm.com Signed-off-by: Sudeep Holla --- drivers/firmware/arm_scmi/bus.c | 141 ++++++++++++++++++++++++++++++++++--- drivers/firmware/arm_scmi/common.h | 8 ++- drivers/firmware/arm_scmi/driver.c | 9 ++- include/linux/scmi_protocol.h | 5 -- 4 files changed, 141 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/drivers/firmware/arm_scmi/bus.c b/drivers/firmware/arm_scmi/bus.c index 61113def5a9a..190999a658b2 100644 --- a/drivers/firmware/arm_scmi/bus.c +++ b/drivers/firmware/arm_scmi/bus.c @@ -7,6 +7,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include #include #include #include @@ -30,6 +31,9 @@ struct scmi_requested_dev { struct list_head node; }; +/* Track globally the creation of SCMI SystemPower related devices */ +static atomic_t scmi_syspower_registered = ATOMIC_INIT(0); + /** * scmi_protocol_device_request - Helper to request a device * @@ -213,11 +217,11 @@ static int scmi_match_by_id_table(struct device *dev, void *data) struct scmi_device_id *id_table = data; return sdev->protocol_id == id_table->protocol_id && - !strcmp(sdev->name, id_table->name); + (id_table->name && !strcmp(sdev->name, id_table->name)); } -struct scmi_device *scmi_child_dev_find(struct device *parent, - int prot_id, const char *name) +static struct scmi_device *scmi_child_dev_find(struct device *parent, + int prot_id, const char *name) { struct scmi_device_id id_table; struct device *dev; @@ -297,13 +301,53 @@ static void scmi_device_release(struct device *dev) kfree(to_scmi_dev(dev)); } -struct scmi_device * -scmi_device_create(struct device_node *np, struct device *parent, int protocol, - const char *name) +static void __scmi_device_destroy(struct scmi_device *scmi_dev) +{ + pr_debug("(%s) Destroying SCMI device '%s' for protocol 0x%x (%s)\n", + of_node_full_name(scmi_dev->dev.parent->of_node), + dev_name(&scmi_dev->dev), scmi_dev->protocol_id, + scmi_dev->name); + + if (scmi_dev->protocol_id == SCMI_PROTOCOL_SYSTEM) + atomic_set(&scmi_syspower_registered, 0); + + kfree_const(scmi_dev->name); + ida_free(&scmi_bus_id, scmi_dev->id); + device_unregister(&scmi_dev->dev); +} + +static struct scmi_device * +__scmi_device_create(struct device_node *np, struct device *parent, + int protocol, const char *name) { int id, retval; struct scmi_device *scmi_dev; + /* + * If the same protocol/name device already exist under the same parent + * (i.e. SCMI instance) just return the existent device. + * This avoids any race between the SCMI driver, creating devices for + * each DT defined protocol at probe time, and the concurrent + * registration of SCMI drivers. + */ + scmi_dev = scmi_child_dev_find(parent, protocol, name); + if (scmi_dev) + return scmi_dev; + + /* + * Ignore any possible subsequent failures while creating the device + * since we are doomed anyway at that point; not using a mutex which + * spans across this whole function to keep things simple and to avoid + * to serialize all the __scmi_device_create calls across possibly + * different SCMI server instances (parent) + */ + if (protocol == SCMI_PROTOCOL_SYSTEM && + atomic_cmpxchg(&scmi_syspower_registered, 0, 1)) { + dev_warn(parent, + "SCMI SystemPower protocol device must be unique !\n"); + return NULL; + } + scmi_dev = kzalloc(sizeof(*scmi_dev), GFP_KERNEL); if (!scmi_dev) return NULL; @@ -333,6 +377,10 @@ scmi_device_create(struct device_node *np, struct device *parent, int protocol, if (retval) goto put_dev; + pr_debug("(%s) Created SCMI device '%s' for protocol 0x%x (%s)\n", + of_node_full_name(parent->of_node), + dev_name(&scmi_dev->dev), protocol, name); + return scmi_dev; put_dev: kfree_const(scmi_dev->name); @@ -341,18 +389,85 @@ put_dev: return NULL; } -void scmi_device_destroy(struct scmi_device *scmi_dev) +/** + * scmi_device_create - A method to create one or more SCMI devices + * + * @np: A reference to the device node to use for the new device(s) + * @parent: The parent device to use identifying a specific SCMI instance + * @protocol: The SCMI protocol to be associated with this device + * @name: The requested-name of the device to be created; this is optional + * and if no @name is provided, all the devices currently known to + * be requested on the SCMI bus for @protocol will be created. + * + * This method can be invoked to create a single well-defined device (like + * a transport device or a device requested by an SCMI driver loaded after + * the core SCMI stack has been probed), or to create all the devices currently + * known to have been requested by the loaded SCMI drivers for a specific + * protocol (typically during SCMI core protocol enumeration at probe time). + * + * Return: The created device (or one of them if @name was NOT provided and + * multiple devices were created) or NULL if no device was created; + * note that NULL indicates an error ONLY in case a specific @name + * was provided: when @name param was not provided, a number of devices + * could have been potentially created for a whole protocol, unless no + * device was found to have been requested for that specific protocol. + */ +struct scmi_device *scmi_device_create(struct device_node *np, + struct device *parent, int protocol, + const char *name) { - kfree_const(scmi_dev->name); - ida_free(&scmi_bus_id, scmi_dev->id); - device_unregister(&scmi_dev->dev); + struct list_head *phead; + struct scmi_requested_dev *rdev; + struct scmi_device *scmi_dev = NULL; + + if (name) + return __scmi_device_create(np, parent, protocol, name); + + mutex_lock(&scmi_requested_devices_mtx); + phead = idr_find(&scmi_requested_devices, protocol); + /* Nothing to do. */ + if (!phead) { + mutex_unlock(&scmi_requested_devices_mtx); + return scmi_dev; + } + + /* Walk the list of requested devices for protocol and create them */ + list_for_each_entry(rdev, phead, node) { + struct scmi_device *sdev; + + sdev = __scmi_device_create(np, parent, + rdev->id_table->protocol_id, + rdev->id_table->name); + /* Report errors and carry on... */ + if (sdev) + scmi_dev = sdev; + else + pr_err("(%s) Failed to create device for protocol 0x%x (%s)\n", + of_node_full_name(parent->of_node), + rdev->id_table->protocol_id, + rdev->id_table->name); + } + mutex_unlock(&scmi_requested_devices_mtx); + + return scmi_dev; } +EXPORT_SYMBOL_GPL(scmi_device_create); + +void scmi_device_destroy(struct device *parent, int protocol, const char *name) +{ + struct scmi_device *scmi_dev; + + scmi_dev = scmi_child_dev_find(parent, protocol, name); + if (scmi_dev) + __scmi_device_destroy(scmi_dev); +} +EXPORT_SYMBOL_GPL(scmi_device_destroy); static int __scmi_devices_unregister(struct device *dev, void *data) { struct scmi_device *scmi_dev = to_scmi_dev(dev); - scmi_device_destroy(scmi_dev); + __scmi_device_destroy(scmi_dev); return 0; } @@ -374,6 +489,10 @@ int __init scmi_bus_init(void) void __exit scmi_bus_exit(void) { + /* + * Destroy all remaining devices: just in case the drivers were + * manually unbound and at first and then the modules unloaded. + */ scmi_devices_unregister(); bus_unregister(&scmi_bus_type); ida_destroy(&scmi_bus_id); diff --git a/drivers/firmware/arm_scmi/common.h b/drivers/firmware/arm_scmi/common.h index 07d34954c060..19726a037991 100644 --- a/drivers/firmware/arm_scmi/common.h +++ b/drivers/firmware/arm_scmi/common.h @@ -107,6 +107,11 @@ extern struct bus_type scmi_bus_type; #define SCMI_BUS_NOTIFY_DEVICE_UNREQUEST 1 extern struct blocking_notifier_head scmi_requested_devices_nh; +struct scmi_device *scmi_device_create(struct device_node *np, + struct device *parent, int protocol, + const char *name); +void scmi_device_destroy(struct device *parent, int protocol, const char *name); + int scmi_protocol_acquire(const struct scmi_handle *handle, u8 protocol_id); void scmi_protocol_release(const struct scmi_handle *handle, u8 protocol_id); @@ -168,9 +173,6 @@ struct scmi_transport_ops { bool (*poll_done)(struct scmi_chan_info *cinfo, struct scmi_xfer *xfer); }; -struct scmi_device *scmi_child_dev_find(struct device *parent, - int prot_id, const char *name); - /** * struct scmi_desc - Description of SoC integration * diff --git a/drivers/firmware/arm_scmi/driver.c b/drivers/firmware/arm_scmi/driver.c index 8591b2c740c6..83a43a5f7bb4 100644 --- a/drivers/firmware/arm_scmi/driver.c +++ b/drivers/firmware/arm_scmi/driver.c @@ -2091,6 +2091,8 @@ static int scmi_chan_setup(struct scmi_info *info, struct device_node *of_node, /* Create a uniquely named, dedicated transport device for this chan */ tdev = scmi_device_create(of_node, info->dev, prot_id, name); if (!tdev) { + dev_err(info->dev, + "failed to create transport device (%s)\n", name); devm_kfree(info->dev, cinfo); return -EINVAL; } @@ -2100,7 +2102,7 @@ static int scmi_chan_setup(struct scmi_info *info, struct device_node *of_node, ret = info->desc->ops->chan_setup(cinfo, info->dev, tx); if (ret) { of_node_put(of_node); - scmi_device_destroy(tdev); + scmi_device_destroy(info->dev, prot_id, name); devm_kfree(info->dev, cinfo); return ret; } @@ -2123,7 +2125,7 @@ idr_alloc: /* Destroy channel and device only if created by this call. */ if (tdev) { of_node_put(of_node); - scmi_device_destroy(tdev); + scmi_device_destroy(info->dev, prot_id, name); devm_kfree(info->dev, cinfo); } return ret; @@ -2202,10 +2204,11 @@ static int scmi_chan_destroy(int id, void *p, void *idr) struct scmi_chan_info *cinfo = p; if (cinfo->dev) { + struct scmi_info *info = handle_to_scmi_info(cinfo->handle); struct scmi_device *sdev = to_scmi_dev(cinfo->dev); of_node_put(cinfo->dev->of_node); - scmi_device_destroy(sdev); + scmi_device_destroy(info->dev, id, sdev->name); cinfo->dev = NULL; } diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h index 4f765bc788ff..0ce5746a4470 100644 --- a/include/linux/scmi_protocol.h +++ b/include/linux/scmi_protocol.h @@ -804,11 +804,6 @@ struct scmi_device { #define to_scmi_dev(d) container_of(d, struct scmi_device, dev) -struct scmi_device * -scmi_device_create(struct device_node *np, struct device *parent, int protocol, - const char *name); -void scmi_device_destroy(struct scmi_device *scmi_dev); - struct scmi_device_id { u8 protocol_id; const char *name; -- cgit v1.2.3 From 338a588e9db3c5ea7a35bb332cb3bdb532fd1f08 Mon Sep 17 00:00:00 2001 From: Mike Leach Date: Mon, 16 Jan 2023 12:49:14 +0000 Subject: coresight: trace-id: Add API to dynamically assign Trace ID values The existing mechanism to assign Trace ID values to sources is limited and does not scale for larger multicore / multi trace source systems. The API introduces functions that reserve IDs based on availabilty represented by a coresight_trace_id_map structure. This records the used and free IDs in a bitmap. CPU bound sources such as ETMs use the coresight_trace_id_get_cpu_id coresight_trace_id_put_cpu_id pair of functions. The API will record the ID associated with the CPU. This ensures that the same ID will be re-used while perf events are active on the CPU. The put_cpu_id function will pend release of the ID until all perf cs_etm sessions are complete. For backward compatibility the functions will attempt to use the same CPU IDs as the legacy system would have used if these are still available. Non-cpu sources, such as the STM can use coresight_trace_id_get_system_id / coresight_trace_id_put_system_id. Signed-off-by: Mike Leach [ Fix checkpatch warning in drivers/hwtracing/coresight/coresight-trace-id.c ] Signed-off-by: Suzuki K Poulose Link: https://lore.kernel.org/r/20230116124928.5440-2-mike.leach@linaro.org --- drivers/hwtracing/coresight/Makefile | 2 +- drivers/hwtracing/coresight/coresight-trace-id.c | 264 +++++++++++++++++++++++ drivers/hwtracing/coresight/coresight-trace-id.h | 156 ++++++++++++++ include/linux/coresight-pmu.h | 10 + 4 files changed, 431 insertions(+), 1 deletion(-) create mode 100644 drivers/hwtracing/coresight/coresight-trace-id.c create mode 100644 drivers/hwtracing/coresight/coresight-trace-id.h (limited to 'include/linux') diff --git a/drivers/hwtracing/coresight/Makefile b/drivers/hwtracing/coresight/Makefile index 344dba8d6ff8..80f99d915bc9 100644 --- a/drivers/hwtracing/coresight/Makefile +++ b/drivers/hwtracing/coresight/Makefile @@ -6,7 +6,7 @@ obj-$(CONFIG_CORESIGHT) += coresight.o coresight-y := coresight-core.o coresight-etm-perf.o coresight-platform.o \ coresight-sysfs.o coresight-syscfg.o coresight-config.o \ coresight-cfg-preload.o coresight-cfg-afdo.o \ - coresight-syscfg-configfs.o + coresight-syscfg-configfs.o coresight-trace-id.o obj-$(CONFIG_CORESIGHT_LINK_AND_SINK_TMC) += coresight-tmc.o coresight-tmc-y := coresight-tmc-core.o coresight-tmc-etf.o \ coresight-tmc-etr.o diff --git a/drivers/hwtracing/coresight/coresight-trace-id.c b/drivers/hwtracing/coresight/coresight-trace-id.c new file mode 100644 index 000000000000..23df04747084 --- /dev/null +++ b/drivers/hwtracing/coresight/coresight-trace-id.c @@ -0,0 +1,264 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2022, Linaro Limited, All rights reserved. + * Author: Mike Leach + */ +#include +#include +#include +#include +#include + +#include "coresight-trace-id.h" + +/* Default trace ID map. Used on systems that don't require per sink mappings */ +static struct coresight_trace_id_map id_map_default; + +/* maintain a record of the mapping of IDs and pending releases per cpu */ +static DEFINE_PER_CPU(atomic_t, cpu_id) = ATOMIC_INIT(0); +static cpumask_t cpu_id_release_pending; + +/* perf session active counter */ +static atomic_t perf_cs_etm_session_active = ATOMIC_INIT(0); + +/* lock to protect id_map and cpu data */ +static DEFINE_SPINLOCK(id_map_lock); + +/* unlocked read of current trace ID value for given CPU */ +static int _coresight_trace_id_read_cpu_id(int cpu) +{ + return atomic_read(&per_cpu(cpu_id, cpu)); +} + +/* look for next available odd ID, return 0 if none found */ +static int coresight_trace_id_find_odd_id(struct coresight_trace_id_map *id_map) +{ + int found_id = 0, bit = 1, next_id; + + while ((bit < CORESIGHT_TRACE_ID_RES_TOP) && !found_id) { + /* + * bitmap length of CORESIGHT_TRACE_ID_RES_TOP, + * search from offset `bit`. + */ + next_id = find_next_zero_bit(id_map->used_ids, + CORESIGHT_TRACE_ID_RES_TOP, bit); + if ((next_id < CORESIGHT_TRACE_ID_RES_TOP) && (next_id & 0x1)) + found_id = next_id; + else + bit = next_id + 1; + } + return found_id; +} + +/* + * Allocate new ID and set in use + * + * if @preferred_id is a valid id then try to use that value if available. + * if @preferred_id is not valid and @prefer_odd_id is true, try for odd id. + * + * Otherwise allocate next available ID. + */ +static int coresight_trace_id_alloc_new_id(struct coresight_trace_id_map *id_map, + int preferred_id, bool prefer_odd_id) +{ + int id = 0; + + /* for backwards compatibility, cpu IDs may use preferred value */ + if (IS_VALID_CS_TRACE_ID(preferred_id) && + !test_bit(preferred_id, id_map->used_ids)) { + id = preferred_id; + goto trace_id_allocated; + } else if (prefer_odd_id) { + /* may use odd ids to avoid preferred legacy cpu IDs */ + id = coresight_trace_id_find_odd_id(id_map); + if (id) + goto trace_id_allocated; + } + + /* + * skip reserved bit 0, look at bitmap length of + * CORESIGHT_TRACE_ID_RES_TOP from offset of bit 1. + */ + id = find_next_zero_bit(id_map->used_ids, CORESIGHT_TRACE_ID_RES_TOP, 1); + if (id >= CORESIGHT_TRACE_ID_RES_TOP) + return -EINVAL; + + /* mark as used */ +trace_id_allocated: + set_bit(id, id_map->used_ids); + return id; +} + +static void coresight_trace_id_free(int id, struct coresight_trace_id_map *id_map) +{ + if (WARN(!IS_VALID_CS_TRACE_ID(id), "Invalid Trace ID %d\n", id)) + return; + if (WARN(!test_bit(id, id_map->used_ids), "Freeing unused ID %d\n", id)) + return; + clear_bit(id, id_map->used_ids); +} + +static void coresight_trace_id_set_pend_rel(int id, struct coresight_trace_id_map *id_map) +{ + if (WARN(!IS_VALID_CS_TRACE_ID(id), "Invalid Trace ID %d\n", id)) + return; + set_bit(id, id_map->pend_rel_ids); +} + +/* + * release all pending IDs for all current maps & clear CPU associations + * + * This currently operates on the default id map, but may be extended to + * operate on all registered id maps if per sink id maps are used. + */ +static void coresight_trace_id_release_all_pending(void) +{ + struct coresight_trace_id_map *id_map = &id_map_default; + unsigned long flags; + int cpu, bit; + + spin_lock_irqsave(&id_map_lock, flags); + for_each_set_bit(bit, id_map->pend_rel_ids, CORESIGHT_TRACE_ID_RES_TOP) { + clear_bit(bit, id_map->used_ids); + clear_bit(bit, id_map->pend_rel_ids); + } + for_each_cpu(cpu, &cpu_id_release_pending) { + atomic_set(&per_cpu(cpu_id, cpu), 0); + cpumask_clear_cpu(cpu, &cpu_id_release_pending); + } + spin_unlock_irqrestore(&id_map_lock, flags); +} + +static int coresight_trace_id_map_get_cpu_id(int cpu, struct coresight_trace_id_map *id_map) +{ + unsigned long flags; + int id; + + spin_lock_irqsave(&id_map_lock, flags); + + /* check for existing allocation for this CPU */ + id = _coresight_trace_id_read_cpu_id(cpu); + if (id) + goto get_cpu_id_clr_pend; + + /* + * Find a new ID. + * + * Use legacy values where possible in the dynamic trace ID allocator to + * allow older tools to continue working if they are not upgraded at the + * same time as the kernel drivers. + * + * If the generated legacy ID is invalid, or not available then the next + * available dynamic ID will be used. + */ + id = coresight_trace_id_alloc_new_id(id_map, + CORESIGHT_LEGACY_CPU_TRACE_ID(cpu), + false); + if (!IS_VALID_CS_TRACE_ID(id)) + goto get_cpu_id_out_unlock; + + /* allocate the new id to the cpu */ + atomic_set(&per_cpu(cpu_id, cpu), id); + +get_cpu_id_clr_pend: + /* we are (re)using this ID - so ensure it is not marked for release */ + cpumask_clear_cpu(cpu, &cpu_id_release_pending); + clear_bit(id, id_map->pend_rel_ids); + +get_cpu_id_out_unlock: + spin_unlock_irqrestore(&id_map_lock, flags); + + return id; +} + +static void coresight_trace_id_map_put_cpu_id(int cpu, struct coresight_trace_id_map *id_map) +{ + unsigned long flags; + int id; + + /* check for existing allocation for this CPU */ + id = _coresight_trace_id_read_cpu_id(cpu); + if (!id) + return; + + spin_lock_irqsave(&id_map_lock, flags); + + if (atomic_read(&perf_cs_etm_session_active)) { + /* set release at pending if perf still active */ + coresight_trace_id_set_pend_rel(id, id_map); + cpumask_set_cpu(cpu, &cpu_id_release_pending); + } else { + /* otherwise clear id */ + coresight_trace_id_free(id, id_map); + atomic_set(&per_cpu(cpu_id, cpu), 0); + } + + spin_unlock_irqrestore(&id_map_lock, flags); +} + +static int coresight_trace_id_map_get_system_id(struct coresight_trace_id_map *id_map) +{ + unsigned long flags; + int id; + + spin_lock_irqsave(&id_map_lock, flags); + /* prefer odd IDs for system components to avoid legacy CPU IDS */ + id = coresight_trace_id_alloc_new_id(id_map, 0, true); + spin_unlock_irqrestore(&id_map_lock, flags); + + return id; +} + +static void coresight_trace_id_map_put_system_id(struct coresight_trace_id_map *id_map, int id) +{ + unsigned long flags; + + spin_lock_irqsave(&id_map_lock, flags); + coresight_trace_id_free(id, id_map); + spin_unlock_irqrestore(&id_map_lock, flags); +} + +/* API functions */ + +int coresight_trace_id_get_cpu_id(int cpu) +{ + return coresight_trace_id_map_get_cpu_id(cpu, &id_map_default); +} +EXPORT_SYMBOL_GPL(coresight_trace_id_get_cpu_id); + +void coresight_trace_id_put_cpu_id(int cpu) +{ + coresight_trace_id_map_put_cpu_id(cpu, &id_map_default); +} +EXPORT_SYMBOL_GPL(coresight_trace_id_put_cpu_id); + +int coresight_trace_id_read_cpu_id(int cpu) +{ + return _coresight_trace_id_read_cpu_id(cpu); +} +EXPORT_SYMBOL_GPL(coresight_trace_id_read_cpu_id); + +int coresight_trace_id_get_system_id(void) +{ + return coresight_trace_id_map_get_system_id(&id_map_default); +} +EXPORT_SYMBOL_GPL(coresight_trace_id_get_system_id); + +void coresight_trace_id_put_system_id(int id) +{ + coresight_trace_id_map_put_system_id(&id_map_default, id); +} +EXPORT_SYMBOL_GPL(coresight_trace_id_put_system_id); + +void coresight_trace_id_perf_start(void) +{ + atomic_inc(&perf_cs_etm_session_active); +} +EXPORT_SYMBOL_GPL(coresight_trace_id_perf_start); + +void coresight_trace_id_perf_stop(void) +{ + if (!atomic_dec_return(&perf_cs_etm_session_active)) + coresight_trace_id_release_all_pending(); +} +EXPORT_SYMBOL_GPL(coresight_trace_id_perf_stop); diff --git a/drivers/hwtracing/coresight/coresight-trace-id.h b/drivers/hwtracing/coresight/coresight-trace-id.h new file mode 100644 index 000000000000..3797777d367e --- /dev/null +++ b/drivers/hwtracing/coresight/coresight-trace-id.h @@ -0,0 +1,156 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright(C) 2022 Linaro Limited. All rights reserved. + * Author: Mike Leach + */ + +#ifndef _CORESIGHT_TRACE_ID_H +#define _CORESIGHT_TRACE_ID_H + +/* + * Coresight trace ID allocation API + * + * With multi cpu systems, and more additional trace sources a scalable + * trace ID reservation system is required. + * + * The system will allocate Ids on a demand basis, and allow them to be + * released when done. + * + * In order to ensure that a consistent cpu / ID matching is maintained + * throughout a perf cs_etm event session - a session in progress flag will + * be maintained, and released IDs not cleared until the perf session is + * complete. This allows the same CPU to be re-allocated its prior ID. + * + * + * Trace ID maps will be created and initialised to prevent architecturally + * reserved IDs from being allocated. + * + * API permits multiple maps to be maintained - for large systems where + * different sets of cpus trace into different independent sinks. + */ + +#include +#include + + +/* architecturally we have 128 IDs some of which are reserved */ +#define CORESIGHT_TRACE_IDS_MAX 128 + +/* ID 0 is reserved */ +#define CORESIGHT_TRACE_ID_RES_0 0 + +/* ID 0x70 onwards are reserved */ +#define CORESIGHT_TRACE_ID_RES_TOP 0x70 + +/* check an ID is in the valid range */ +#define IS_VALID_CS_TRACE_ID(id) \ + ((id > CORESIGHT_TRACE_ID_RES_0) && (id < CORESIGHT_TRACE_ID_RES_TOP)) + +/** + * Trace ID map. + * + * @used_ids: Bitmap to register available (bit = 0) and in use (bit = 1) IDs. + * Initialised so that the reserved IDs are permanently marked as + * in use. + * @pend_rel_ids: CPU IDs that have been released by the trace source but not + * yet marked as available, to allow re-allocation to the same + * CPU during a perf session. + */ +struct coresight_trace_id_map { + DECLARE_BITMAP(used_ids, CORESIGHT_TRACE_IDS_MAX); + DECLARE_BITMAP(pend_rel_ids, CORESIGHT_TRACE_IDS_MAX); +}; + +/* Allocate and release IDs for a single default trace ID map */ + +/** + * Read and optionally allocate a CoreSight trace ID and associate with a CPU. + * + * Function will read the current trace ID for the associated CPU, + * allocating an new ID if one is not currently allocated. + * + * Numeric ID values allocated use legacy allocation algorithm if possible, + * otherwise any available ID is used. + * + * @cpu: The CPU index to allocate for. + * + * return: CoreSight trace ID or -EINVAL if allocation impossible. + */ +int coresight_trace_id_get_cpu_id(int cpu); + +/** + * Release an allocated trace ID associated with the CPU. + * + * This will release the CoreSight trace ID associated with the CPU, + * unless a perf session is in operation. + * + * If a perf session is in operation then the ID will be marked as pending + * release. + * + * @cpu: The CPU index to release the associated trace ID. + */ +void coresight_trace_id_put_cpu_id(int cpu); + +/** + * Read the current allocated CoreSight Trace ID value for the CPU. + * + * Fast read of the current value that does not allocate if no ID allocated + * for the CPU. + * + * Used in perf context where it is known that the value for the CPU will not + * be changing, when perf starts and event on a core and outputs the Trace ID + * for the CPU as a packet in the data file. IDs cannot change during a perf + * session. + * + * This function does not take the lock protecting the ID lists, avoiding + * locking dependency issues with perf locks. + * + * @cpu: The CPU index to read. + * + * return: current value, will be 0 if unallocated. + */ +int coresight_trace_id_read_cpu_id(int cpu); + +/** + * Allocate a CoreSight trace ID for a system component. + * + * Unconditionally allocates a Trace ID, without associating the ID with a CPU. + * + * Used to allocate IDs for system trace sources such as STM. + * + * return: Trace ID or -EINVAL if allocation is impossible. + */ +int coresight_trace_id_get_system_id(void); + +/** + * Release an allocated system trace ID. + * + * Unconditionally release a trace ID allocated to a system component. + * + * @id: value of trace ID allocated. + */ +void coresight_trace_id_put_system_id(int id); + +/* notifiers for perf session start and stop */ + +/** + * Notify the Trace ID allocator that a perf session is starting. + * + * Increase the perf session reference count - called by perf when setting up + * a trace event. + * + * This reference count is used by the ID allocator to ensure that trace IDs + * associated with a CPU cannot change or be released during a perf session. + */ +void coresight_trace_id_perf_start(void); + +/** + * Notify the ID allocator that a perf session is stopping. + * + * Decrease the perf session reference count. + * if this causes the count to go to zero, then all Trace IDs marked as pending + * release, will be released. + */ +void coresight_trace_id_perf_stop(void); + +#endif /* _CORESIGHT_TRACE_ID_H */ diff --git a/include/linux/coresight-pmu.h b/include/linux/coresight-pmu.h index 6c2fd6cc5a98..ffff4e6277e5 100644 --- a/include/linux/coresight-pmu.h +++ b/include/linux/coresight-pmu.h @@ -10,6 +10,16 @@ #define CORESIGHT_ETM_PMU_NAME "cs_etm" #define CORESIGHT_ETM_PMU_SEED 0x10 +/* + * The legacy Trace ID system based on fixed calculation from the cpu + * number. This has been replaced by drivers using a dynamic allocation + * system - but need to retain the legacy algorithm for backward comparibility + * in certain situations:- + * a) new perf running on older systems that generate the legacy mapping + * b) older tools that may not update at the same time as the kernel. + */ +#define CORESIGHT_LEGACY_CPU_TRACE_ID(cpu) (0x10 + (cpu * 2)) + /* * Below are the definition of bit offsets for perf option, and works as * arbitrary values for all ETM versions. -- cgit v1.2.3 From 42708bac18cf7f09c058058cd4564f879c53b900 Mon Sep 17 00:00:00 2001 From: Mike Leach Date: Mon, 16 Jan 2023 12:49:20 +0000 Subject: coresight: etmX.X: stm: Remove trace_id() callback CoreSight sources provide a callback (.trace_id) in the standard source ops which returns the ID to the core code. This was used to check that sources all had a unique Trace ID. Uniqueness is now gauranteed by the Trace ID allocation system, and the check code has been removed from the core. This patch removes the unneeded and unused .trace_id source ops from the ops structure and implementations in etm3x, etm4x and stm. Signed-off-by: Mike Leach Reviewed-by: Suzuki K Poulose Signed-off-by: Suzuki K Poulose Link: https://lore.kernel.org/r/20230116124928.5440-8-mike.leach@linaro.org --- drivers/hwtracing/coresight/coresight-etm.h | 1 - drivers/hwtracing/coresight/coresight-etm3x-core.c | 37 ---------------------- drivers/hwtracing/coresight/coresight-etm4x-core.c | 8 ----- drivers/hwtracing/coresight/coresight-stm.c | 8 ----- include/linux/coresight.h | 3 -- 5 files changed, 57 deletions(-) (limited to 'include/linux') diff --git a/drivers/hwtracing/coresight/coresight-etm.h b/drivers/hwtracing/coresight/coresight-etm.h index 3667428d38b6..9a0d08b092ae 100644 --- a/drivers/hwtracing/coresight/coresight-etm.h +++ b/drivers/hwtracing/coresight/coresight-etm.h @@ -283,7 +283,6 @@ static inline unsigned int etm_readl(struct etm_drvdata *drvdata, u32 off) } extern const struct attribute_group *coresight_etm_groups[]; -int etm_get_trace_id(struct etm_drvdata *drvdata); void etm_set_default(struct etm_config *config); void etm_config_trace_mode(struct etm_config *config); struct etm_config *get_etm_config(struct etm_drvdata *drvdata); diff --git a/drivers/hwtracing/coresight/coresight-etm3x-core.c b/drivers/hwtracing/coresight/coresight-etm3x-core.c index 090b6fbf6305..afc57195ee52 100644 --- a/drivers/hwtracing/coresight/coresight-etm3x-core.c +++ b/drivers/hwtracing/coresight/coresight-etm3x-core.c @@ -455,42 +455,6 @@ static int etm_cpu_id(struct coresight_device *csdev) return drvdata->cpu; } -int etm_get_trace_id(struct etm_drvdata *drvdata) -{ - unsigned long flags; - int trace_id = -1; - struct device *etm_dev; - - if (!drvdata) - goto out; - - etm_dev = drvdata->csdev->dev.parent; - if (!local_read(&drvdata->mode)) - return drvdata->traceid; - - pm_runtime_get_sync(etm_dev); - - spin_lock_irqsave(&drvdata->spinlock, flags); - - CS_UNLOCK(drvdata->base); - trace_id = (etm_readl(drvdata, ETMTRACEIDR) & ETM_TRACEID_MASK); - CS_LOCK(drvdata->base); - - spin_unlock_irqrestore(&drvdata->spinlock, flags); - pm_runtime_put(etm_dev); - -out: - return trace_id; - -} - -static int etm_trace_id(struct coresight_device *csdev) -{ - struct etm_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); - - return etm_get_trace_id(drvdata); -} - int etm_read_alloc_trace_id(struct etm_drvdata *drvdata) { int trace_id; @@ -737,7 +701,6 @@ static void etm_disable(struct coresight_device *csdev, static const struct coresight_ops_source etm_source_ops = { .cpu_id = etm_cpu_id, - .trace_id = etm_trace_id, .enable = etm_enable, .disable = etm_disable, }; diff --git a/drivers/hwtracing/coresight/coresight-etm4x-core.c b/drivers/hwtracing/coresight/coresight-etm4x-core.c index 346c0c37c177..1ea8f173cca0 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x-core.c +++ b/drivers/hwtracing/coresight/coresight-etm4x-core.c @@ -231,13 +231,6 @@ static int etm4_cpu_id(struct coresight_device *csdev) return drvdata->cpu; } -static int etm4_trace_id(struct coresight_device *csdev) -{ - struct etmv4_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); - - return drvdata->trcid; -} - int etm4_read_alloc_trace_id(struct etmv4_drvdata *drvdata) { int trace_id; @@ -1023,7 +1016,6 @@ static void etm4_disable(struct coresight_device *csdev, static const struct coresight_ops_source etm4_source_ops = { .cpu_id = etm4_cpu_id, - .trace_id = etm4_trace_id, .enable = etm4_enable, .disable = etm4_disable, }; diff --git a/drivers/hwtracing/coresight/coresight-stm.c b/drivers/hwtracing/coresight/coresight-stm.c index 6af1b996af6f..66a614c5492c 100644 --- a/drivers/hwtracing/coresight/coresight-stm.c +++ b/drivers/hwtracing/coresight/coresight-stm.c @@ -281,15 +281,7 @@ static void stm_disable(struct coresight_device *csdev, } } -static int stm_trace_id(struct coresight_device *csdev) -{ - struct stm_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); - - return drvdata->traceid; -} - static const struct coresight_ops_source stm_source_ops = { - .trace_id = stm_trace_id, .enable = stm_enable, .disable = stm_disable, }; diff --git a/include/linux/coresight.h b/include/linux/coresight.h index 1554021231f9..e241eb88dfb9 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -314,14 +314,11 @@ struct coresight_ops_link { * Operations available for sources. * @cpu_id: returns the value of the CPU number this component * is associated to. - * @trace_id: returns the value of the component's trace ID as known - * to the HW. * @enable: enables tracing for a source. * @disable: disables tracing for a source. */ struct coresight_ops_source { int (*cpu_id)(struct coresight_device *csdev); - int (*trace_id)(struct coresight_device *csdev); int (*enable)(struct coresight_device *csdev, struct perf_event *event, u32 mode); void (*disable)(struct coresight_device *csdev, -- cgit v1.2.3 From 206bb3858949b6509de75f7d3697303a073cbaa1 Mon Sep 17 00:00:00 2001 From: Mike Leach Date: Mon, 16 Jan 2023 12:49:21 +0000 Subject: coresight: trace id: Remove legacy get trace ID function. Removes legacy coresight_get_trace_id() function now its use has been removed from the ETM code. Signed-off-by: Mike Leach Reviewed-by: Suzuki K Poulose Signed-off-by: Suzuki K Poulose Link: https://lore.kernel.org/r/20230116124928.5440-9-mike.leach@linaro.org --- include/linux/coresight-pmu.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/coresight-pmu.h b/include/linux/coresight-pmu.h index ffff4e6277e5..624f4843453e 100644 --- a/include/linux/coresight-pmu.h +++ b/include/linux/coresight-pmu.h @@ -8,7 +8,6 @@ #define _LINUX_CORESIGHT_PMU_H #define CORESIGHT_ETM_PMU_NAME "cs_etm" -#define CORESIGHT_ETM_PMU_SEED 0x10 /* * The legacy Trace ID system based on fixed calculation from the cpu @@ -44,15 +43,4 @@ #define ETM4_CFG_BIT_RETSTK 12 #define ETM4_CFG_BIT_VMID_OPT 15 -static inline int coresight_get_trace_id(int cpu) -{ - /* - * A trace ID of value 0 is invalid, so let's start at some - * random value that fits in 7 bits and go from there. Since - * the common convention is to have data trace IDs be I(N) + 1, - * set instruction trace IDs as a function of the CPU number. - */ - return (CORESIGHT_ETM_PMU_SEED + (cpu * 2)); -} - #endif -- cgit v1.2.3 From aa19bb4c35834dd574b36d482cc44c78816e6fcd Mon Sep 17 00:00:00 2001 From: Mike Leach Date: Mon, 16 Jan 2023 12:49:26 +0000 Subject: coresight: events: PERF_RECORD_AUX_OUTPUT_HW_ID used for Trace ID Use the perf_report_aux_output_id() call to output the CoreSight trace ID and associated CPU as a PERF_RECORD_AUX_OUTPUT_HW_ID record in the perf.data file. Signed-off-by: Mike Leach Reviewed-by: Suzuki K Poulose Signed-off-by: Suzuki K Poulose Link: https://lore.kernel.org/r/20230116124928.5440-14-mike.leach@linaro.org --- drivers/hwtracing/coresight/coresight-etm-perf.c | 7 +++++++ include/linux/coresight-pmu.h | 14 ++++++++++++++ 2 files changed, 21 insertions(+) (limited to 'include/linux') diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.c b/drivers/hwtracing/coresight/coresight-etm-perf.c index bdb9ab86173a..12fff661456e 100644 --- a/drivers/hwtracing/coresight/coresight-etm-perf.c +++ b/drivers/hwtracing/coresight/coresight-etm-perf.c @@ -4,6 +4,7 @@ * Author: Mathieu Poirier */ +#include #include #include #include @@ -448,6 +449,7 @@ static void etm_event_start(struct perf_event *event, int flags) struct perf_output_handle *handle = &ctxt->handle; struct coresight_device *sink, *csdev = per_cpu(csdev_src, cpu); struct list_head *path; + u64 hw_id; if (!csdev) goto fail; @@ -493,6 +495,11 @@ static void etm_event_start(struct perf_event *event, int flags) if (source_ops(csdev)->enable(csdev, event, CS_MODE_PERF)) goto fail_disable_path; + /* output cpu / trace ID in perf record */ + hw_id = FIELD_PREP(CS_AUX_HW_ID_VERSION_MASK, CS_AUX_HW_ID_CURR_VERSION); + hw_id |= FIELD_PREP(CS_AUX_HW_ID_TRACE_ID_MASK, coresight_trace_id_read_cpu_id(cpu)); + perf_report_aux_output_id(event, hw_id); + out: /* Tell the perf core the event is alive */ event->hw.state = 0; diff --git a/include/linux/coresight-pmu.h b/include/linux/coresight-pmu.h index 624f4843453e..51ac441a37c3 100644 --- a/include/linux/coresight-pmu.h +++ b/include/linux/coresight-pmu.h @@ -7,6 +7,8 @@ #ifndef _LINUX_CORESIGHT_PMU_H #define _LINUX_CORESIGHT_PMU_H +#include + #define CORESIGHT_ETM_PMU_NAME "cs_etm" /* @@ -43,4 +45,16 @@ #define ETM4_CFG_BIT_RETSTK 12 #define ETM4_CFG_BIT_VMID_OPT 15 +/* + * Interpretation of the PERF_RECORD_AUX_OUTPUT_HW_ID payload. + * Used to associate a CPU with the CoreSight Trace ID. + * [07:00] - Trace ID - uses 8 bits to make value easy to read in file. + * [59:08] - Unused (SBZ) + * [63:60] - Version + */ +#define CS_AUX_HW_ID_TRACE_ID_MASK GENMASK_ULL(7, 0) +#define CS_AUX_HW_ID_VERSION_MASK GENMASK_ULL(63, 60) + +#define CS_AUX_HW_ID_CURR_VERSION 0 + #endif -- cgit v1.2.3 From 93c473948c588978cd55d9a3adad8b3e8057aa21 Mon Sep 17 00:00:00 2001 From: Jó Ágila Bitsch Date: Fri, 13 Jan 2023 01:53:19 +0100 Subject: usb: gadget: add WebUSB landing page support There is a custom (non-USB IF) extension to the USB standard: https://wicg.github.io/webusb/ This specification is published under the W3C Community Contributor Agreement, which in particular allows to implement the specification without any royalties. The specification allows USB gadgets to announce an URL to landing page and describes a Javascript interface for websites to interact with the USB gadget, if the user allows it. It is currently supported by Chromium-based browsers, such as Chrome, Edge and Opera on all major operating systems including Linux. This patch adds optional support for Linux-based USB gadgets wishing to expose such a landing page. During device enumeration, a host recognizes that the announced USB version is at least 2.01, which means, that there are BOS descriptors available. The device than announces WebUSB support using a platform device capability. This includes a vendor code under which the landing page URL can be retrieved using a vendor-specific request. Previously, the BOS descriptors would unconditionally include an LPM related descriptor, as BOS descriptors were only ever sent when the device was LPM capable. As this is no longer the case, this patch puts this descriptor behind a lpm_capable condition. Usage is modeled after os_desc descriptors: echo 1 > webusb/use echo "https://www.kernel.org" > webusb/landingPage lsusb will report the device with the following lines: Platform Device Capability: bLength 24 bDescriptorType 16 bDevCapabilityType 5 bReserved 0 PlatformCapabilityUUID {3408b638-09a9-47a0-8bfd-a0768815b665} WebUSB: bcdVersion 1.00 bVendorCode 0 iLandingPage 1 https://www.kernel.org Signed-off-by: Jó Ágila Bitsch Link: https://lore.kernel.org/r/Y8Crf8P2qAWuuk/F@jo-einhundert Signed-off-by: Greg Kroah-Hartman --- Documentation/ABI/testing/configfs-usb-gadget | 13 ++ drivers/usb/gadget/composite.c | 102 ++++++++++++++-- drivers/usb/gadget/configfs.c | 166 ++++++++++++++++++++++++++ include/linux/usb/composite.h | 7 ++ include/linux/usb/webusb.h | 83 +++++++++++++ include/uapi/linux/usb/ch9.h | 16 +++ 6 files changed, 377 insertions(+), 10 deletions(-) create mode 100644 include/linux/usb/webusb.h (limited to 'include/linux') diff --git a/Documentation/ABI/testing/configfs-usb-gadget b/Documentation/ABI/testing/configfs-usb-gadget index b7943aa7e997..a8bb896def54 100644 --- a/Documentation/ABI/testing/configfs-usb-gadget +++ b/Documentation/ABI/testing/configfs-usb-gadget @@ -143,3 +143,16 @@ Description: qw_sign an identifier to be reported as "OS String" proper ============= =============================================== + +What: /config/usb-gadget/gadget/webusb +Date: Dec 2022 +KernelVersion: 6.3 +Description: + This group contains "WebUSB" extension handling attributes. + + ============= =============================================== + use flag turning "WebUSB" support on/off + bcdVersion bcd WebUSB specification version number + bVendorCode one-byte value used for custom per-device + landingPage UTF-8 encoded URL of the device's landing page + ============= =============================================== diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c index 403563c06477..8e2603688016 100644 --- a/drivers/usb/gadget/composite.c +++ b/drivers/usb/gadget/composite.c @@ -14,9 +14,11 @@ #include #include #include +#include #include #include +#include #include #include "u_os_desc.h" @@ -713,14 +715,16 @@ static int bos_desc(struct usb_composite_dev *cdev) * A SuperSpeed device shall include the USB2.0 extension descriptor * and shall support LPM when operating in USB2.0 HS mode. */ - usb_ext = cdev->req->buf + le16_to_cpu(bos->wTotalLength); - bos->bNumDeviceCaps++; - le16_add_cpu(&bos->wTotalLength, USB_DT_USB_EXT_CAP_SIZE); - usb_ext->bLength = USB_DT_USB_EXT_CAP_SIZE; - usb_ext->bDescriptorType = USB_DT_DEVICE_CAPABILITY; - usb_ext->bDevCapabilityType = USB_CAP_TYPE_EXT; - usb_ext->bmAttributes = cpu_to_le32(USB_LPM_SUPPORT | - USB_BESL_SUPPORT | besl); + if (cdev->gadget->lpm_capable) { + usb_ext = cdev->req->buf + le16_to_cpu(bos->wTotalLength); + bos->bNumDeviceCaps++; + le16_add_cpu(&bos->wTotalLength, USB_DT_USB_EXT_CAP_SIZE); + usb_ext->bLength = USB_DT_USB_EXT_CAP_SIZE; + usb_ext->bDescriptorType = USB_DT_DEVICE_CAPABILITY; + usb_ext->bDevCapabilityType = USB_CAP_TYPE_EXT; + usb_ext->bmAttributes = cpu_to_le32(USB_LPM_SUPPORT | + USB_BESL_SUPPORT | besl); + } /* * The Superspeed USB Capability descriptor shall be implemented by all @@ -821,6 +825,37 @@ static int bos_desc(struct usb_composite_dev *cdev) } } + /* The WebUSB Platform Capability descriptor */ + if (cdev->use_webusb) { + struct usb_plat_dev_cap_descriptor *webusb_cap; + struct usb_webusb_cap_data *webusb_cap_data; + uuid_t webusb_uuid = WEBUSB_UUID; + + webusb_cap = cdev->req->buf + le16_to_cpu(bos->wTotalLength); + webusb_cap_data = (struct usb_webusb_cap_data *) webusb_cap->CapabilityData; + bos->bNumDeviceCaps++; + le16_add_cpu(&bos->wTotalLength, + USB_DT_USB_PLAT_DEV_CAP_SIZE(USB_WEBUSB_CAP_DATA_SIZE)); + + webusb_cap->bLength = USB_DT_USB_PLAT_DEV_CAP_SIZE(USB_WEBUSB_CAP_DATA_SIZE); + webusb_cap->bDescriptorType = USB_DT_DEVICE_CAPABILITY; + webusb_cap->bDevCapabilityType = USB_PLAT_DEV_CAP_TYPE; + webusb_cap->bReserved = 0; + export_uuid(webusb_cap->UUID, &webusb_uuid); + + if (cdev->bcd_webusb_version != 0) + webusb_cap_data->bcdVersion = cpu_to_le16(cdev->bcd_webusb_version); + else + webusb_cap_data->bcdVersion = WEBUSB_VERSION_1_00; + + webusb_cap_data->bVendorCode = cdev->b_webusb_vendor_code; + + if (strnlen(cdev->landing_page, sizeof(cdev->landing_page)) > 0) + webusb_cap_data->iLandingPage = WEBUSB_LANDING_PAGE_PRESENT; + else + webusb_cap_data->iLandingPage = WEBUSB_LANDING_PAGE_NOT_PRESENT; + } + return le16_to_cpu(bos->wTotalLength); } @@ -1744,7 +1779,7 @@ composite_setup(struct usb_gadget *gadget, const struct usb_ctrlrequest *ctrl) cdev->desc.bcdUSB = cpu_to_le16(0x0210); } } else { - if (gadget->lpm_capable) + if (gadget->lpm_capable || cdev->use_webusb) cdev->desc.bcdUSB = cpu_to_le16(0x0201); else cdev->desc.bcdUSB = cpu_to_le16(0x0200); @@ -1779,7 +1814,7 @@ composite_setup(struct usb_gadget *gadget, const struct usb_ctrlrequest *ctrl) break; case USB_DT_BOS: if (gadget_is_superspeed(gadget) || - gadget->lpm_capable) { + gadget->lpm_capable || cdev->use_webusb) { value = bos_desc(cdev); value = min(w_length, (u16) value); } @@ -2013,6 +2048,53 @@ unknown: goto check_value; } + /* + * WebUSB URL descriptor handling, following: + * https://wicg.github.io/webusb/#device-requests + */ + if (cdev->use_webusb && + ctrl->bRequestType == (USB_DIR_IN | USB_TYPE_VENDOR) && + w_index == WEBUSB_GET_URL && + w_value == WEBUSB_LANDING_PAGE_PRESENT && + ctrl->bRequest == cdev->b_webusb_vendor_code) { + unsigned int landing_page_length; + unsigned int landing_page_offset; + struct webusb_url_descriptor *url_descriptor = + (struct webusb_url_descriptor *)cdev->req->buf; + + url_descriptor->bDescriptorType = WEBUSB_URL_DESCRIPTOR_TYPE; + + if (strncasecmp(cdev->landing_page, "https://", 8) == 0) { + landing_page_offset = 8; + url_descriptor->bScheme = WEBUSB_URL_SCHEME_HTTPS; + } else if (strncasecmp(cdev->landing_page, "http://", 7) == 0) { + landing_page_offset = 7; + url_descriptor->bScheme = WEBUSB_URL_SCHEME_HTTP; + } else { + landing_page_offset = 0; + url_descriptor->bScheme = WEBUSB_URL_SCHEME_NONE; + } + + landing_page_length = strnlen(cdev->landing_page, + sizeof(url_descriptor->URL) + - WEBUSB_URL_DESCRIPTOR_HEADER_LENGTH + landing_page_offset); + + if (ctrl->wLength < WEBUSB_URL_DESCRIPTOR_HEADER_LENGTH + + landing_page_length) + landing_page_length = ctrl->wLength + - WEBUSB_URL_DESCRIPTOR_HEADER_LENGTH + landing_page_offset; + + memcpy(url_descriptor->URL, + cdev->landing_page + landing_page_offset, + landing_page_length - landing_page_offset); + url_descriptor->bLength = landing_page_length + - landing_page_offset + WEBUSB_URL_DESCRIPTOR_HEADER_LENGTH; + + value = url_descriptor->bLength; + + goto check_value; + } + VDBG(cdev, "non-core control req%02x.%02x v%04x i%04x l%d\n", ctrl->bRequestType, ctrl->bRequest, diff --git a/drivers/usb/gadget/configfs.c b/drivers/usb/gadget/configfs.c index 96121d1c8df4..4a1236063c19 100644 --- a/drivers/usb/gadget/configfs.c +++ b/drivers/usb/gadget/configfs.c @@ -7,6 +7,7 @@ #include #include #include +#include #include "configfs.h" #include "u_f.h" #include "u_os_desc.h" @@ -39,6 +40,7 @@ struct gadget_info { struct config_group configs_group; struct config_group strings_group; struct config_group os_desc_group; + struct config_group webusb_group; struct mutex lock; struct usb_gadget_strings *gstrings[MAX_USB_STRING_LANGS + 1]; @@ -50,6 +52,11 @@ struct gadget_info { bool use_os_desc; char b_vendor_code; char qw_sign[OS_STRING_QW_SIGN_LEN]; + bool use_webusb; + u16 bcd_webusb_version; + u8 b_webusb_vendor_code; + char landing_page[WEBUSB_URL_RAW_MAX_LENGTH]; + spinlock_t spinlock; bool unbind; }; @@ -780,6 +787,154 @@ static void gadget_strings_attr_release(struct config_item *item) USB_CONFIG_STRING_RW_OPS(gadget_strings); USB_CONFIG_STRINGS_LANG(gadget_strings, gadget_info); +static inline struct gadget_info *webusb_item_to_gadget_info( + struct config_item *item) +{ + return container_of(to_config_group(item), + struct gadget_info, webusb_group); +} + +static ssize_t webusb_use_show(struct config_item *item, char *page) +{ + return sysfs_emit(page, "%d\n", + webusb_item_to_gadget_info(item)->use_webusb); +} + +static ssize_t webusb_use_store(struct config_item *item, const char *page, + size_t len) +{ + struct gadget_info *gi = webusb_item_to_gadget_info(item); + int ret; + bool use; + + mutex_lock(&gi->lock); + ret = kstrtobool(page, &use); + if (!ret) { + gi->use_webusb = use; + ret = len; + } + mutex_unlock(&gi->lock); + + return ret; +} + +static ssize_t webusb_bcdVersion_show(struct config_item *item, char *page) +{ + return sysfs_emit(page, "0x%04x\n", + webusb_item_to_gadget_info(item)->bcd_webusb_version); +} + +static ssize_t webusb_bcdVersion_store(struct config_item *item, + const char *page, size_t len) +{ + struct gadget_info *gi = webusb_item_to_gadget_info(item); + u16 bcdVersion; + int ret; + + mutex_lock(&gi->lock); + ret = kstrtou16(page, 0, &bcdVersion); + if (ret) + goto out; + ret = is_valid_bcd(bcdVersion); + if (ret) + goto out; + + gi->bcd_webusb_version = bcdVersion; + ret = len; + +out: + mutex_unlock(&gi->lock); + + return ret; +} + +static ssize_t webusb_bVendorCode_show(struct config_item *item, char *page) +{ + return sysfs_emit(page, "0x%02x\n", + webusb_item_to_gadget_info(item)->b_webusb_vendor_code); +} + +static ssize_t webusb_bVendorCode_store(struct config_item *item, + const char *page, size_t len) +{ + struct gadget_info *gi = webusb_item_to_gadget_info(item); + int ret; + u8 b_vendor_code; + + mutex_lock(&gi->lock); + ret = kstrtou8(page, 0, &b_vendor_code); + if (!ret) { + gi->b_webusb_vendor_code = b_vendor_code; + ret = len; + } + mutex_unlock(&gi->lock); + + return ret; +} + +static ssize_t webusb_landingPage_show(struct config_item *item, char *page) +{ + return sysfs_emit(page, "%s\n", webusb_item_to_gadget_info(item)->landing_page); +} + +static ssize_t webusb_landingPage_store(struct config_item *item, const char *page, + size_t len) +{ + struct gadget_info *gi = webusb_item_to_gadget_info(item); + unsigned int bytes_to_strip = 0; + int l = len; + + if (page[l - 1] == '\n') { + --l; + ++bytes_to_strip; + } + + if (l > sizeof(gi->landing_page)) { + pr_err("webusb: landingPage URL too long\n"); + return -EINVAL; + } + + // validation + if (strncasecmp(page, "https://", 8) == 0) + bytes_to_strip = 8; + else if (strncasecmp(page, "http://", 7) == 0) + bytes_to_strip = 7; + else + bytes_to_strip = 0; + + if (l > U8_MAX - WEBUSB_URL_DESCRIPTOR_HEADER_LENGTH + bytes_to_strip) { + pr_err("webusb: landingPage URL %d bytes too long for given URL scheme\n", + l - U8_MAX + WEBUSB_URL_DESCRIPTOR_HEADER_LENGTH - bytes_to_strip); + return -EINVAL; + } + + mutex_lock(&gi->lock); + // ensure 0 bytes are set, in case the new landing page is shorter then the old one. + memset(gi->landing_page, 0, sizeof(gi->landing_page)); + memcpy(gi->landing_page, page, l); + mutex_unlock(&gi->lock); + + return len; +} + +CONFIGFS_ATTR(webusb_, use); +CONFIGFS_ATTR(webusb_, bVendorCode); +CONFIGFS_ATTR(webusb_, bcdVersion); +CONFIGFS_ATTR(webusb_, landingPage); + +static struct configfs_attribute *webusb_attrs[] = { + &webusb_attr_use, + &webusb_attr_bcdVersion, + &webusb_attr_bVendorCode, + &webusb_attr_landingPage, + NULL, +}; + +static struct config_item_type webusb_type = { + .ct_attrs = webusb_attrs, + .ct_owner = THIS_MODULE, +}; + static inline struct gadget_info *os_desc_item_to_gadget_info( struct config_item *item) { @@ -1341,6 +1496,13 @@ static int configfs_composite_bind(struct usb_gadget *gadget, gi->cdev.desc.iSerialNumber = s[USB_GADGET_SERIAL_IDX].id; } + if (gi->use_webusb) { + cdev->use_webusb = true; + cdev->bcd_webusb_version = gi->bcd_webusb_version; + cdev->b_webusb_vendor_code = gi->b_webusb_vendor_code; + memcpy(cdev->landing_page, gi->landing_page, WEBUSB_URL_RAW_MAX_LENGTH); + } + if (gi->use_os_desc) { cdev->use_os_string = true; cdev->b_vendor_code = gi->b_vendor_code; @@ -1605,6 +1767,10 @@ static struct config_group *gadgets_make( &os_desc_type); configfs_add_default_group(&gi->os_desc_group, &gi->group); + config_group_init_type_name(&gi->webusb_group, "webusb", + &webusb_type); + configfs_add_default_group(&gi->webusb_group, &gi->group); + gi->composite.bind = configfs_do_nothing; gi->composite.unbind = configfs_do_nothing; gi->composite.suspend = NULL; diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h index 43ac3fa760db..91d22c3ed458 100644 --- a/include/linux/usb/composite.h +++ b/include/linux/usb/composite.h @@ -25,6 +25,7 @@ #include #include #include +#include #include #include @@ -474,6 +475,12 @@ struct usb_composite_dev { struct usb_configuration *os_desc_config; unsigned int use_os_string:1; + /* WebUSB */ + u16 bcd_webusb_version; + u8 b_webusb_vendor_code; + char landing_page[WEBUSB_URL_RAW_MAX_LENGTH]; + unsigned int use_webusb:1; + /* private: */ /* internals */ unsigned int suspended:1; diff --git a/include/linux/usb/webusb.h b/include/linux/usb/webusb.h new file mode 100644 index 000000000000..b430d84357f3 --- /dev/null +++ b/include/linux/usb/webusb.h @@ -0,0 +1,83 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * WebUSB descriptors and constants + * + * Copyright (C) 2023 Jó Ágila Bitsch + */ + +#ifndef __LINUX_USB_WEBUSB_H +#define __LINUX_USB_WEBUSB_H + +#include "uapi/linux/usb/ch9.h" + +/* + * little endian PlatformCapablityUUID for WebUSB + * 3408b638-09a9-47a0-8bfd-a0768815b665 + * to identify Platform Device Capability descriptors as referring to WebUSB + * + * the UUID above MUST be sent over the wire as the byte sequence: + * {0x38, 0xB6, 0x08, 0x34, 0xA9, 0x09, 0xA0, 0x47, 0x8B, 0xFD, 0xA0, 0x76, 0x88, 0x15, 0xB6, 0x65}. + */ +#define WEBUSB_UUID \ + UUID_INIT(0x38b60834, 0xa909, 0xa047, 0x8b, 0xfd, 0xa0, 0x76, 0x88, 0x15, 0xb6, 0x65) + +/* + * WebUSB Platform Capability data + * + * A device announces support for the + * WebUSB command set by including the following Platform Descriptor Data in its + * Binary Object Store associated with the WebUSB_UUID above. + * See: https://wicg.github.io/webusb/#webusb-platform-capability-descriptor + */ +struct usb_webusb_cap_data { + __le16 bcdVersion; +#define WEBUSB_VERSION_1_00 cpu_to_le16(0x0100) /* currently only version 1.00 is defined */ + u8 bVendorCode; + u8 iLandingPage; +#define WEBUSB_LANDING_PAGE_NOT_PRESENT 0 +#define WEBUSB_LANDING_PAGE_PRESENT 1 /* we chose the fixed index 1 for the URL descriptor */ +} __packed; + +#define USB_WEBUSB_CAP_DATA_SIZE 4 + +/* + * Get URL Request + * + * The request to fetch an URL is defined in https://wicg.github.io/webusb/#get-url as: + * bmRequestType: (USB_DIR_IN | USB_TYPE_VENDOR) = 11000000B + * bRequest: bVendorCode + * wValue: iLandingPage + * wIndex: GET_URL = 2 + * wLength: Descriptor Length (typically U8_MAX = 255) + * Data: URL Descriptor + */ +#define WEBUSB_GET_URL 2 + +/* + * This descriptor contains a single URL and is returned by the Get URL request. + * + * See: https://wicg.github.io/webusb/#url-descriptor + */ +struct webusb_url_descriptor { + u8 bLength; +#define WEBUSB_URL_DESCRIPTOR_HEADER_LENGTH 3 + u8 bDescriptorType; +#define WEBUSB_URL_DESCRIPTOR_TYPE 3 + u8 bScheme; +#define WEBUSB_URL_SCHEME_HTTP 0 +#define WEBUSB_URL_SCHEME_HTTPS 1 +#define WEBUSB_URL_SCHEME_NONE 255 + u8 URL[U8_MAX - WEBUSB_URL_DESCRIPTOR_HEADER_LENGTH]; +} __packed; + +/* + * Buffer size to hold the longest URL that can be in an URL descriptor + * + * The descriptor can be U8_MAX bytes long. + * WEBUSB_URL_DESCRIPTOR_HEADER_LENGTH bytes are used for a header. + * Since the longest prefix that might be stripped is "https://", we may accommodate an additional + * 8 bytes. + */ +#define WEBUSB_URL_RAW_MAX_LENGTH (U8_MAX - WEBUSB_URL_DESCRIPTOR_HEADER_LENGTH + 8) + +#endif /* __LINUX_USB_USBNET_H */ diff --git a/include/uapi/linux/usb/ch9.h b/include/uapi/linux/usb/ch9.h index 31fcfa084e63..b17e3a21b15f 100644 --- a/include/uapi/linux/usb/ch9.h +++ b/include/uapi/linux/usb/ch9.h @@ -947,6 +947,22 @@ struct usb_ss_container_id_descriptor { #define USB_DT_USB_SS_CONTN_ID_SIZE 20 +/* + * Platform Device Capability descriptor: Defines platform specific device + * capabilities + */ +#define USB_PLAT_DEV_CAP_TYPE 5 +struct usb_plat_dev_cap_descriptor { + __u8 bLength; + __u8 bDescriptorType; + __u8 bDevCapabilityType; + __u8 bReserved; + __u8 UUID[16]; + __u8 CapabilityData[]; +} __attribute__((packed)); + +#define USB_DT_USB_PLAT_DEV_CAP_SIZE(capability_data_size) (20 + capability_data_size) + /* * SuperSpeed Plus USB Capability descriptor: Defines the set of * SuperSpeed Plus USB specific device level capabilities -- cgit v1.2.3 From 52af7863508e94f3e05e43a3f2f3943a71dcffab Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 17 Jan 2023 17:21:20 +0200 Subject: device property: Make fwnode_graph_for_each_endpoint() consistent Make fwnode_graph_for_each_endpoint() consistent with the rest of for_each_*() definitions in the file, i.e. use the form of for (iter = func(NULL); iter; \ iter = func(iter)) as it's done in all the rest of the similar macro definitions. Signed-off-by: Andy Shevchenko Acked-by: Rafael J. Wysocki Acked-by: Sakari Ailus Acked-by: Heikki Krogerus Link: https://lore.kernel.org/r/20230117152120.42531-1-andriy.shevchenko@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/property.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/property.h b/include/linux/property.h index 1ffd4f9bb67b..0a29db15ff34 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -436,9 +436,9 @@ fwnode_graph_get_endpoint_by_id(const struct fwnode_handle *fwnode, unsigned int fwnode_graph_get_endpoint_count(struct fwnode_handle *fwnode, unsigned long flags); -#define fwnode_graph_for_each_endpoint(fwnode, child) \ - for (child = NULL; \ - (child = fwnode_graph_get_next_endpoint(fwnode, child)); ) +#define fwnode_graph_for_each_endpoint(fwnode, child) \ + for (child = fwnode_graph_get_next_endpoint(fwnode, NULL); child; \ + child = fwnode_graph_get_next_endpoint(fwnode, child)) int fwnode_graph_parse_endpoint(const struct fwnode_handle *fwnode, struct fwnode_endpoint *endpoint); -- cgit v1.2.3 From 41000b03af9e15075061cdbeea461cfa5e12a8eb Mon Sep 17 00:00:00 2001 From: Ricardo Ribalda Date: Thu, 24 Nov 2022 13:39:08 +0100 Subject: earlycon: Increase options size Now that the clock frequency is also part of the options, 16 bytes is too little. Without this patch dmesg does not show the whole options, Eg: earlycon: uart0 at MMIO32 0x00000000fedc9000 (options '115200n8,480000') instead of: '115200n8,48000000' Signed-off-by: Ricardo Ribalda Reviewed-by: Jiri Slaby Link: https://lore.kernel.org/r/20221123-serial-clk-v3-2-49c516980ae0@chromium.org Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_core.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index fd59f600094a..026294c6ccb8 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -781,7 +781,7 @@ static inline int uart_poll_timeout(struct uart_port *port) struct earlycon_device { struct console *con; struct uart_port port; - char options[16]; /* e.g., 115200n8 */ + char options[32]; /* e.g., 115200n8 */ unsigned int baud; }; -- cgit v1.2.3 From ef460db2a7c1df5eda2ea6011e7586e54e23b8c4 Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Fri, 25 Nov 2022 15:05:04 +0200 Subject: serial: 8250: Use defined IER bits Instead of literal 0x0f, add a define for enabling all IER bits the 8250 driver is interested in. Don't make the define for combined flags part of UAPI. Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20221125130509.8482-2-ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250_port.c | 10 +++++----- include/linux/serial.h | 5 +++++ 2 files changed, 10 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index beba8f38b3dc..8676f8b7f2e3 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -1236,14 +1236,14 @@ static void autoconfig(struct uart_8250_port *up) * Mask out IER[7:4] bits for test as some UARTs (e.g. TL * 16C754B) allow only to modify them if an EFR bit is set. */ - scratch2 = serial_in(up, UART_IER) & 0x0f; - serial_out(up, UART_IER, 0x0F); + scratch2 = serial_in(up, UART_IER) & UART_IER_ALL_INTR; + serial_out(up, UART_IER, UART_IER_ALL_INTR); #ifdef __i386__ outb(0, 0x080); #endif - scratch3 = serial_in(up, UART_IER) & 0x0f; + scratch3 = serial_in(up, UART_IER) & UART_IER_ALL_INTR; serial_out(up, UART_IER, scratch); - if (scratch2 != 0 || scratch3 != 0x0F) { + if (scratch2 != 0 || scratch3 != UART_IER_ALL_INTR) { /* * We failed; there's nothing here */ @@ -1394,7 +1394,7 @@ static void autoconfig_irq(struct uart_8250_port *up) serial8250_out_MCR(up, UART_MCR_DTR | UART_MCR_RTS | UART_MCR_OUT2); } - serial_out(up, UART_IER, 0x0f); /* enable all intrs */ + serial_out(up, UART_IER, UART_IER_ALL_INTR); serial_in(up, UART_LSR); serial_in(up, UART_RX); serial_in(up, UART_IIR); diff --git a/include/linux/serial.h b/include/linux/serial.h index 3d6fe3ef92cf..ad6e1c37e2d5 100644 --- a/include/linux/serial.h +++ b/include/linux/serial.h @@ -12,6 +12,11 @@ #include #include +#define UART_IER_ALL_INTR (UART_IER_MSI | \ + UART_IER_RLSI | \ + UART_IER_THRI | \ + UART_IER_RDI) + /* Helper for dealing with UART_LCR_WLEN* defines */ #define UART_LCR_WLEN(x) ((x) - 5) -- cgit v1.2.3 From d9c1d3cbdeec94f077679b73ed5ce3a4fe4bf4b8 Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Fri, 25 Nov 2022 15:05:05 +0200 Subject: serial: 8250: Name MSR literals Add UART_MSR_STATUS_BITS for CD, RI, DSR & CTS. Use names for the literal. Don't make the define for combined flags part of UAPI. Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20221125130509.8482-3-ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250_port.c | 4 ++-- include/linux/serial.h | 5 +++++ 2 files changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index 8676f8b7f2e3..c870ee8e80b6 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -1268,9 +1268,9 @@ static void autoconfig(struct uart_8250_port *up) */ if (!(port->flags & UPF_SKIP_TEST)) { serial8250_out_MCR(up, UART_MCR_LOOP | 0x0A); - status1 = serial_in(up, UART_MSR) & 0xF0; + status1 = serial_in(up, UART_MSR) & UART_MSR_STATUS_BITS; serial8250_out_MCR(up, save_mcr); - if (status1 != 0x90) { + if (status1 != (UART_MSR_DCD | UART_MSR_CTS)) { spin_unlock_irqrestore(&port->lock, flags); DEBUG_AUTOCONF("LOOP test failed (%02x) ", status1); diff --git a/include/linux/serial.h b/include/linux/serial.h index ad6e1c37e2d5..bfda927dde15 100644 --- a/include/linux/serial.h +++ b/include/linux/serial.h @@ -28,6 +28,11 @@ static inline bool uart_lsr_tx_empty(u16 lsr) return (lsr & UART_LSR_BOTH_EMPTY) == UART_LSR_BOTH_EMPTY; } +#define UART_MSR_STATUS_BITS (UART_MSR_DCD | \ + UART_MSR_RI | \ + UART_MSR_DSR | \ + UART_MSR_CTS) + /* * Counters of the input lines (CTS, DSR, RI, CD) interrupts */ -- cgit v1.2.3 From feb36abbedea2644bf31693aa287a33a3a9fbd7c Mon Sep 17 00:00:00 2001 From: Jiri Slaby (SUSE) Date: Thu, 12 Jan 2023 09:01:31 +0100 Subject: tty: vt: remove struct uni_screen It contains only lines with pointers to characters (u32s). So use simple clear 'u32 **lines' all over the code. This avoids zero-length arrays. It also makes the allocation less error-prone (size of the struct wasn't taken into account at all). Signed-off-by: Jiri Slaby (SUSE) Reviewed-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20230112080136.4929-6-jirislaby@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/tty/vt/vt.c | 117 ++++++++++++++++++++--------------------- include/linux/console_struct.h | 3 +- 2 files changed, 59 insertions(+), 61 deletions(-) (limited to 'include/linux') diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index 4a0ea4cf7752..0487d7d20f73 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -320,58 +320,55 @@ void schedule_console_callback(void) * Our screen buffer is preceded by an array of line pointers so that * scrolling only implies some pointer shuffling. */ -struct uni_screen { - u32 *lines[0]; -}; -static struct uni_screen *vc_uniscr_alloc(unsigned int cols, unsigned int rows) +static u32 **vc_uniscr_alloc(unsigned int cols, unsigned int rows) { - struct uni_screen *uniscr; + u32 **uni_lines; void *p; - unsigned int memsize, i, col_size = cols * sizeof(**uniscr->lines); + unsigned int memsize, i, col_size = cols * sizeof(**uni_lines); /* allocate everything in one go */ memsize = col_size * rows; - memsize += rows * sizeof(*uniscr->lines); - p = vzalloc(memsize); - if (!p) + memsize += rows * sizeof(*uni_lines); + uni_lines = vzalloc(memsize); + if (!uni_lines) return NULL; /* initial line pointers */ - uniscr = p; - p = uniscr->lines + rows; + p = uni_lines + rows; for (i = 0; i < rows; i++) { - uniscr->lines[i] = p; + uni_lines[i] = p; p += col_size; } - return uniscr; + + return uni_lines; } -static void vc_uniscr_free(struct uni_screen *uniscr) +static void vc_uniscr_free(u32 **uni_lines) { - vfree(uniscr); + vfree(uni_lines); } -static void vc_uniscr_set(struct vc_data *vc, struct uni_screen *new_uniscr) +static void vc_uniscr_set(struct vc_data *vc, u32 **new_uni_lines) { - vc_uniscr_free(vc->vc_uni_screen); - vc->vc_uni_screen = new_uniscr; + vc_uniscr_free(vc->vc_uni_lines); + vc->vc_uni_lines = new_uni_lines; } static void vc_uniscr_putc(struct vc_data *vc, u32 uc) { - struct uni_screen *uniscr = vc->vc_uni_screen; + u32 **uni_lines = vc->vc_uni_lines; - if (uniscr) - uniscr->lines[vc->state.y][vc->state.x] = uc; + if (uni_lines) + uni_lines[vc->state.y][vc->state.x] = uc; } static void vc_uniscr_insert(struct vc_data *vc, unsigned int nr) { - struct uni_screen *uniscr = vc->vc_uni_screen; + u32 **uni_lines = vc->vc_uni_lines; - if (uniscr) { - u32 *ln = uniscr->lines[vc->state.y]; + if (uni_lines) { + u32 *ln = uni_lines[vc->state.y]; unsigned int x = vc->state.x, cols = vc->vc_cols; memmove(&ln[x + nr], &ln[x], (cols - x - nr) * sizeof(*ln)); @@ -381,10 +378,10 @@ static void vc_uniscr_insert(struct vc_data *vc, unsigned int nr) static void vc_uniscr_delete(struct vc_data *vc, unsigned int nr) { - struct uni_screen *uniscr = vc->vc_uni_screen; + u32 **uni_lines = vc->vc_uni_lines; - if (uniscr) { - u32 *ln = uniscr->lines[vc->state.y]; + if (uni_lines) { + u32 *ln = uni_lines[vc->state.y]; unsigned int x = vc->state.x, cols = vc->vc_cols; memcpy(&ln[x], &ln[x + nr], (cols - x - nr) * sizeof(*ln)); @@ -395,10 +392,10 @@ static void vc_uniscr_delete(struct vc_data *vc, unsigned int nr) static void vc_uniscr_clear_line(struct vc_data *vc, unsigned int x, unsigned int nr) { - struct uni_screen *uniscr = vc->vc_uni_screen; + u32 **uni_lines = vc->vc_uni_lines; - if (uniscr) { - u32 *ln = uniscr->lines[vc->state.y]; + if (uni_lines) { + u32 *ln = uni_lines[vc->state.y]; memset32(&ln[x], ' ', nr); } @@ -407,22 +404,22 @@ static void vc_uniscr_clear_line(struct vc_data *vc, unsigned int x, static void vc_uniscr_clear_lines(struct vc_data *vc, unsigned int y, unsigned int nr) { - struct uni_screen *uniscr = vc->vc_uni_screen; + u32 **uni_lines = vc->vc_uni_lines; - if (uniscr) { + if (uni_lines) { unsigned int cols = vc->vc_cols; while (nr--) - memset32(uniscr->lines[y++], ' ', cols); + memset32(uni_lines[y++], ' ', cols); } } static void vc_uniscr_scroll(struct vc_data *vc, unsigned int t, unsigned int b, enum con_scroll dir, unsigned int nr) { - struct uni_screen *uniscr = vc->vc_uni_screen; + u32 **uni_lines = vc->vc_uni_lines; - if (uniscr) { + if (uni_lines) { unsigned int i, j, k, sz, d, clear; sz = b - t; @@ -433,7 +430,7 @@ static void vc_uniscr_scroll(struct vc_data *vc, unsigned int t, unsigned int b, d = sz - nr; } for (i = 0; i < gcd(d, sz); i++) { - u32 *tmp = uniscr->lines[t + i]; + u32 *tmp = uni_lines[t + i]; j = i; while (1) { k = j + d; @@ -441,31 +438,31 @@ static void vc_uniscr_scroll(struct vc_data *vc, unsigned int t, unsigned int b, k -= sz; if (k == i) break; - uniscr->lines[t + j] = uniscr->lines[t + k]; + uni_lines[t + j] = uni_lines[t + k]; j = k; } - uniscr->lines[t + j] = tmp; + uni_lines[t + j] = tmp; } vc_uniscr_clear_lines(vc, clear, nr); } } -static void vc_uniscr_copy_area(struct uni_screen *dst, +static void vc_uniscr_copy_area(u32 **dst_lines, unsigned int dst_cols, unsigned int dst_rows, - struct uni_screen *src, + u32 **src_lines, unsigned int src_cols, unsigned int src_top_row, unsigned int src_bot_row) { unsigned int dst_row = 0; - if (!dst) + if (!dst_lines) return; while (src_top_row < src_bot_row) { - u32 *src_line = src->lines[src_top_row]; - u32 *dst_line = dst->lines[dst_row]; + u32 *src_line = src_lines[src_top_row]; + u32 *dst_line = dst_lines[dst_row]; memcpy(dst_line, src_line, src_cols * sizeof(*src_line)); if (dst_cols - src_cols) @@ -474,7 +471,7 @@ static void vc_uniscr_copy_area(struct uni_screen *dst, dst_row++; } while (dst_row < dst_rows) { - u32 *dst_line = dst->lines[dst_row]; + u32 *dst_line = dst_lines[dst_row]; memset32(dst_line, ' ', dst_cols); dst_row++; @@ -489,7 +486,7 @@ static void vc_uniscr_copy_area(struct uni_screen *dst, */ int vc_uniscr_check(struct vc_data *vc) { - struct uni_screen *uniscr; + u32 **uni_lines; unsigned short *p; int x, y, mask; @@ -498,11 +495,11 @@ int vc_uniscr_check(struct vc_data *vc) if (!vc->vc_utf) return -ENODATA; - if (vc->vc_uni_screen) + if (vc->vc_uni_lines) return 0; - uniscr = vc_uniscr_alloc(vc->vc_cols, vc->vc_rows); - if (!uniscr) + uni_lines = vc_uniscr_alloc(vc->vc_cols, vc->vc_rows); + if (!uni_lines) return -ENOMEM; /* @@ -514,14 +511,15 @@ int vc_uniscr_check(struct vc_data *vc) p = (unsigned short *)vc->vc_origin; mask = vc->vc_hi_font_mask | 0xff; for (y = 0; y < vc->vc_rows; y++) { - u32 *line = uniscr->lines[y]; + u32 *line = uni_lines[y]; for (x = 0; x < vc->vc_cols; x++) { u16 glyph = scr_readw(p++) & mask; line[x] = inverse_translate(vc, glyph, true); } } - vc->vc_uni_screen = uniscr; + vc->vc_uni_lines = uni_lines; + return 0; } @@ -533,11 +531,11 @@ int vc_uniscr_check(struct vc_data *vc) void vc_uniscr_copy_line(const struct vc_data *vc, void *dest, bool viewed, unsigned int row, unsigned int col, unsigned int nr) { - struct uni_screen *uniscr = vc->vc_uni_screen; + u32 **uni_lines = vc->vc_uni_lines; int offset = row * vc->vc_size_row + col * 2; unsigned long pos; - BUG_ON(!uniscr); + BUG_ON(!uni_lines); pos = (unsigned long)screenpos(vc, offset, viewed); if (pos >= vc->vc_origin && pos < vc->vc_scr_end) { @@ -548,7 +546,7 @@ void vc_uniscr_copy_line(const struct vc_data *vc, void *dest, bool viewed, */ row = (pos - vc->vc_origin) / vc->vc_size_row; col = ((pos - vc->vc_origin) % vc->vc_size_row) / 2; - memcpy(dest, &uniscr->lines[row][col], nr * sizeof(u32)); + memcpy(dest, &uni_lines[row][col], nr * sizeof(u32)); } else { /* * Scrollback is active. For now let's simply backtranslate @@ -1150,7 +1148,7 @@ static int vc_do_resize(struct tty_struct *tty, struct vc_data *vc, unsigned int new_cols, new_rows, new_row_size, new_screen_size; unsigned int user; unsigned short *oldscreen, *newscreen; - struct uni_screen *new_uniscr = NULL; + u32 **new_uniscr = NULL; WARN_CONSOLE_UNLOCKED(); @@ -1194,7 +1192,7 @@ static int vc_do_resize(struct tty_struct *tty, struct vc_data *vc, if (!newscreen) return -ENOMEM; - if (vc->vc_uni_screen) { + if (vc->vc_uni_lines) { new_uniscr = vc_uniscr_alloc(new_cols, new_rows); if (!new_uniscr) { kfree(newscreen); @@ -1246,7 +1244,7 @@ static int vc_do_resize(struct tty_struct *tty, struct vc_data *vc, end = old_origin + old_row_size * min(old_rows, new_rows); vc_uniscr_copy_area(new_uniscr, new_cols, new_rows, - vc->vc_uni_screen, rlth/2, first_copied_row, + vc->vc_uni_lines, rlth/2, first_copied_row, min(old_rows, new_rows)); vc_uniscr_set(vc, new_uniscr); @@ -4694,10 +4692,11 @@ EXPORT_SYMBOL_GPL(screen_glyph); u32 screen_glyph_unicode(const struct vc_data *vc, int n) { - struct uni_screen *uniscr = vc->vc_uni_screen; + u32 **uni_lines = vc->vc_uni_lines; + + if (uni_lines) + return uni_lines[n / vc->vc_cols][n % vc->vc_cols]; - if (uniscr) - return uniscr->lines[n / vc->vc_cols][n % vc->vc_cols]; return inverse_translate(vc, screen_glyph(vc, n * 2), true); } EXPORT_SYMBOL_GPL(screen_glyph_unicode); diff --git a/include/linux/console_struct.h b/include/linux/console_struct.h index 1518568aaf0f..539f1cd45309 100644 --- a/include/linux/console_struct.h +++ b/include/linux/console_struct.h @@ -18,7 +18,6 @@ #include struct uni_pagedict; -struct uni_screen; #define NPAR 16 #define VC_TABSTOPS_COUNT 256U @@ -159,7 +158,7 @@ struct vc_data { struct vc_data **vc_display_fg; /* [!] Ptr to var holding fg console for this display */ struct uni_pagedict *uni_pagedict; struct uni_pagedict **uni_pagedict_loc; /* [!] Location of uni_pagedict variable for this console */ - struct uni_screen *vc_uni_screen; /* unicode screen content */ + u32 **vc_uni_lines; /* unicode screen content */ /* additional information is in vt_kern.h */ }; -- cgit v1.2.3 From 7de06d8455211d2d875bb174e361ccb6faa5ae3f Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Thu, 29 Dec 2022 16:50:29 +0100 Subject: soc: qcom-geni-se: add more symbol definitions The following symbols will be used when adding support for SE DMA in the qcom geni serial driver. Signed-off-by: Bartosz Golaszewski Reviewed-by: Konrad Dybcio Link: https://lore.kernel.org/r/20221229155030.418800-14-brgl@bgdev.pl Signed-off-by: Greg Kroah-Hartman --- include/linux/qcom-geni-se.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/qcom-geni-se.h b/include/linux/qcom-geni-se.h index f5672785c0c4..400213daa461 100644 --- a/include/linux/qcom-geni-se.h +++ b/include/linux/qcom-geni-se.h @@ -103,6 +103,7 @@ struct geni_se { #define SE_DMA_TX_FSM_RST 0xc58 #define SE_DMA_RX_IRQ_STAT 0xd40 #define SE_DMA_RX_IRQ_CLR 0xd44 +#define SE_DMA_RX_LEN_IN 0xd54 #define SE_DMA_RX_FSM_RST 0xd58 #define SE_HW_PARAM_0 0xe24 #define SE_HW_PARAM_1 0xe28 @@ -235,6 +236,8 @@ struct geni_se { #define RX_SBE BIT(2) #define RX_RESET_DONE BIT(3) #define RX_FLUSH_DONE BIT(4) +#define RX_DMA_PARITY_ERR BIT(5) +#define RX_DMA_BREAK GENMASK(8, 7) #define RX_GENI_GP_IRQ GENMASK(10, 5) #define RX_GENI_CANCEL_IRQ BIT(11) #define RX_GENI_GP_IRQ_EXT GENMASK(13, 12) -- cgit v1.2.3 From 163f080eb717d237f02d9a8c179b07ed31fdd6ad Mon Sep 17 00:00:00 2001 From: Christoph Niedermaier Date: Fri, 2 Dec 2022 11:41:25 +0100 Subject: serial: core: Add option to output RS485 RX_DURING_TX state via GPIO This patch provides a generic GPIO variable for outputting the state of RS485 RX_DURING_TX. The GPIO is defined by the devicetree property "rs485-rx-during-tx-gpios". To use it in a low level serial driver, the evaluation of this variable must be implemented there accordingly. Signed-off-by: Christoph Niedermaier Link: https://lore.kernel.org/r/20221202104127.122761-2-cniedermaier@dh-electronics.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/serial_core.c | 12 ++++++++++++ include/linux/serial_core.h | 1 + 2 files changed, 13 insertions(+) (limited to 'include/linux') diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index b9fbbee598b8..867f2675caca 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -3410,6 +3410,7 @@ int uart_get_rs485_mode(struct uart_port *port) struct device *dev = port->dev; u32 rs485_delay[2]; int ret; + int rx_during_tx_gpio_flag; ret = device_property_read_u32_array(dev, "rs485-rts-delay", rs485_delay, 2); @@ -3458,6 +3459,17 @@ int uart_get_rs485_mode(struct uart_port *port) if (port->rs485_term_gpio) port->rs485_supported.flags |= SER_RS485_TERMINATE_BUS; + rx_during_tx_gpio_flag = (rs485conf->flags & SER_RS485_RX_DURING_TX) ? + GPIOD_OUT_HIGH : GPIOD_OUT_LOW; + port->rs485_rx_during_tx_gpio = devm_gpiod_get_optional(dev, + "rs485-rx-during-tx", + rx_during_tx_gpio_flag); + if (IS_ERR(port->rs485_rx_during_tx_gpio)) { + ret = PTR_ERR(port->rs485_rx_during_tx_gpio); + port->rs485_rx_during_tx_gpio = NULL; + return dev_err_probe(dev, ret, "Cannot get rs485-rx-during-tx-gpios\n"); + } + return 0; } EXPORT_SYMBOL_GPL(uart_get_rs485_mode); diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 026294c6ccb8..0b37a86bedc5 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -579,6 +579,7 @@ struct uart_port { struct serial_rs485 rs485; struct serial_rs485 rs485_supported; /* Supported mask for serial_rs485 */ struct gpio_desc *rs485_term_gpio; /* enable RS485 bus termination */ + struct gpio_desc *rs485_rx_during_tx_gpio; /* Output GPIO that sets the state of RS485 RX during TX */ struct serial_iso7816 iso7816; void *private_data; /* generic platform data pointer */ }; -- cgit v1.2.3 From b300fb26c59a749bf49559932fa8a85eb916b5a7 Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Tue, 17 Jan 2023 11:03:52 +0200 Subject: tty: Convert ->carrier_raised() and callchains to bool Return boolean from ->carrier_raised() instead of 0 and 1. Make the return type change also to tty_port_carrier_raised() that makes the ->carrier_raised() call (+ cd variable in moxa into which its return value is stored). Also cleans up a few unnecessary constructs related to this change: return xx ? 1 : 0; -> return xx; if (xx) return 1; return 0; -> return xx; Reviewed-by: Jiri Slaby Acked-by: Ulf Hansson # For MMC Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20230117090358.4796-7-ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/char/pcmcia/synclink_cs.c | 8 +++----- drivers/mmc/core/sdio_uart.c | 7 +++---- drivers/tty/amiserial.c | 2 +- drivers/tty/moxa.c | 4 ++-- drivers/tty/mxser.c | 5 +++-- drivers/tty/n_gsm.c | 8 ++++---- drivers/tty/serial/serial_core.c | 9 ++++----- drivers/tty/synclink_gt.c | 7 ++++--- drivers/tty/tty_port.c | 4 ++-- drivers/usb/serial/usb-serial.c | 4 ++-- include/linux/tty_port.h | 6 +++--- net/bluetooth/rfcomm/tty.c | 2 +- 12 files changed, 32 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/drivers/char/pcmcia/synclink_cs.c b/drivers/char/pcmcia/synclink_cs.c index baa46e8a094b..4391138e1b8a 100644 --- a/drivers/char/pcmcia/synclink_cs.c +++ b/drivers/char/pcmcia/synclink_cs.c @@ -377,7 +377,7 @@ static void async_mode(MGSLPC_INFO *info); static void tx_timeout(struct timer_list *t); -static int carrier_raised(struct tty_port *port); +static bool carrier_raised(struct tty_port *port); static void dtr_rts(struct tty_port *port, int onoff); #if SYNCLINK_GENERIC_HDLC @@ -2430,7 +2430,7 @@ static void mgslpc_hangup(struct tty_struct *tty) tty_port_hangup(&info->port); } -static int carrier_raised(struct tty_port *port) +static bool carrier_raised(struct tty_port *port) { MGSLPC_INFO *info = container_of(port, MGSLPC_INFO, port); unsigned long flags; @@ -2439,9 +2439,7 @@ static int carrier_raised(struct tty_port *port) get_signals(info); spin_unlock_irqrestore(&info->lock, flags); - if (info->serial_signals & SerialSignal_DCD) - return 1; - return 0; + return info->serial_signals & SerialSignal_DCD; } static void dtr_rts(struct tty_port *port, int onoff) diff --git a/drivers/mmc/core/sdio_uart.c b/drivers/mmc/core/sdio_uart.c index ae7ef2e038be..47f58258d8ff 100644 --- a/drivers/mmc/core/sdio_uart.c +++ b/drivers/mmc/core/sdio_uart.c @@ -526,7 +526,7 @@ static void sdio_uart_irq(struct sdio_func *func) port->in_sdio_uart_irq = NULL; } -static int uart_carrier_raised(struct tty_port *tport) +static bool uart_carrier_raised(struct tty_port *tport) { struct sdio_uart_port *port = container_of(tport, struct sdio_uart_port, port); @@ -535,9 +535,8 @@ static int uart_carrier_raised(struct tty_port *tport) return 1; ret = sdio_uart_get_mctrl(port); sdio_uart_release_func(port); - if (ret & TIOCM_CAR) - return 1; - return 0; + + return ret & TIOCM_CAR; } /** diff --git a/drivers/tty/amiserial.c b/drivers/tty/amiserial.c index 460d33a1e70b..01c4fd3ce7c8 100644 --- a/drivers/tty/amiserial.c +++ b/drivers/tty/amiserial.c @@ -1454,7 +1454,7 @@ static const struct tty_operations serial_ops = { .proc_show = rs_proc_show, }; -static int amiga_carrier_raised(struct tty_port *port) +static bool amiga_carrier_raised(struct tty_port *port) { return !(ciab.pra & SER_DCD); } diff --git a/drivers/tty/moxa.c b/drivers/tty/moxa.c index 2d9635e14ded..6a1e78e33a2c 100644 --- a/drivers/tty/moxa.c +++ b/drivers/tty/moxa.c @@ -501,7 +501,7 @@ static int moxa_tiocmset(struct tty_struct *tty, static void moxa_poll(struct timer_list *); static void moxa_set_tty_param(struct tty_struct *, const struct ktermios *); static void moxa_shutdown(struct tty_port *); -static int moxa_carrier_raised(struct tty_port *); +static bool moxa_carrier_raised(struct tty_port *); static void moxa_dtr_rts(struct tty_port *, int); /* * moxa board interface functions: @@ -1432,7 +1432,7 @@ static void moxa_shutdown(struct tty_port *port) MoxaPortFlushData(ch, 2); } -static int moxa_carrier_raised(struct tty_port *port) +static bool moxa_carrier_raised(struct tty_port *port) { struct moxa_port *ch = container_of(port, struct moxa_port, port); int dcd; diff --git a/drivers/tty/mxser.c b/drivers/tty/mxser.c index 2926a831727d..96c72e691cd7 100644 --- a/drivers/tty/mxser.c +++ b/drivers/tty/mxser.c @@ -458,10 +458,11 @@ static void __mxser_stop_tx(struct mxser_port *info) outb(info->IER, info->ioaddr + UART_IER); } -static int mxser_carrier_raised(struct tty_port *port) +static bool mxser_carrier_raised(struct tty_port *port) { struct mxser_port *mp = container_of(port, struct mxser_port, port); - return (inb(mp->ioaddr + UART_MSR) & UART_MSR_DCD)?1:0; + + return inb(mp->ioaddr + UART_MSR) & UART_MSR_DCD; } static void mxser_dtr_rts(struct tty_port *port, int on) diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c index ced0e6dc179d..64abc5fbf2c1 100644 --- a/drivers/tty/n_gsm.c +++ b/drivers/tty/n_gsm.c @@ -3770,16 +3770,16 @@ static int gsm_modem_update(struct gsm_dlci *dlci, u8 brk) return -EPROTONOSUPPORT; } -static int gsm_carrier_raised(struct tty_port *port) +static bool gsm_carrier_raised(struct tty_port *port) { struct gsm_dlci *dlci = container_of(port, struct gsm_dlci, port); struct gsm_mux *gsm = dlci->gsm; /* Not yet open so no carrier info */ if (dlci->state != DLCI_OPEN) - return 0; + return false; if (debug & DBG_CD_ON) - return 1; + return true; /* * Basic mode with control channel in ADM mode may not respond @@ -3787,7 +3787,7 @@ static int gsm_carrier_raised(struct tty_port *port) */ if (gsm->encoding == GSM_BASIC_OPT && gsm->dlci[0]->mode == DLCI_MODE_ADM && !dlci->modem_rx) - return 1; + return true; return dlci->modem_rx & TIOCM_CD; } diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index 84a53f6761be..ddf14c4f4bf5 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -1861,7 +1861,7 @@ static void uart_port_shutdown(struct tty_port *port) } } -static int uart_carrier_raised(struct tty_port *port) +static bool uart_carrier_raised(struct tty_port *port) { struct uart_state *state = container_of(port, struct uart_state, port); struct uart_port *uport; @@ -1875,15 +1875,14 @@ static int uart_carrier_raised(struct tty_port *port) * continue and not sleep */ if (WARN_ON(!uport)) - return 1; + return true; spin_lock_irq(&uport->lock); uart_enable_ms(uport); mctrl = uport->ops->get_mctrl(uport); spin_unlock_irq(&uport->lock); uart_port_deref(uport); - if (mctrl & TIOCM_CAR) - return 1; - return 0; + + return mctrl & TIOCM_CAR; } static void uart_dtr_rts(struct tty_port *port, int raise) diff --git a/drivers/tty/synclink_gt.c b/drivers/tty/synclink_gt.c index 81c94906f06e..4ba71ec764f7 100644 --- a/drivers/tty/synclink_gt.c +++ b/drivers/tty/synclink_gt.c @@ -3126,7 +3126,7 @@ static int tiocmset(struct tty_struct *tty, return 0; } -static int carrier_raised(struct tty_port *port) +static bool carrier_raised(struct tty_port *port) { unsigned long flags; struct slgt_info *info = container_of(port, struct slgt_info, port); @@ -3134,7 +3134,8 @@ static int carrier_raised(struct tty_port *port) spin_lock_irqsave(&info->lock,flags); get_gtsignals(info); spin_unlock_irqrestore(&info->lock,flags); - return (info->signals & SerialSignal_DCD) ? 1 : 0; + + return info->signals & SerialSignal_DCD; } static void dtr_rts(struct tty_port *port, int on) @@ -3162,7 +3163,7 @@ static int block_til_ready(struct tty_struct *tty, struct file *filp, int retval; bool do_clocal = false; unsigned long flags; - int cd; + bool cd; struct tty_port *port = &info->port; DBGINFO(("%s block_til_ready\n", tty->driver->name)); diff --git a/drivers/tty/tty_port.c b/drivers/tty/tty_port.c index 469de3c010b8..a573c500f95b 100644 --- a/drivers/tty/tty_port.c +++ b/drivers/tty/tty_port.c @@ -444,10 +444,10 @@ EXPORT_SYMBOL_GPL(tty_port_tty_wakeup); * to hide some internal details. This will eventually become entirely * internal to the tty port. */ -int tty_port_carrier_raised(struct tty_port *port) +bool tty_port_carrier_raised(struct tty_port *port) { if (port->ops->carrier_raised == NULL) - return 1; + return true; return port->ops->carrier_raised(port); } EXPORT_SYMBOL(tty_port_carrier_raised); diff --git a/drivers/usb/serial/usb-serial.c b/drivers/usb/serial/usb-serial.c index 164521ee10c6..019720a63fac 100644 --- a/drivers/usb/serial/usb-serial.c +++ b/drivers/usb/serial/usb-serial.c @@ -754,7 +754,7 @@ static struct usb_serial_driver *search_serial_device( return NULL; } -static int serial_port_carrier_raised(struct tty_port *port) +static bool serial_port_carrier_raised(struct tty_port *port) { struct usb_serial_port *p = container_of(port, struct usb_serial_port, port); struct usb_serial_driver *drv = p->serial->type; @@ -762,7 +762,7 @@ static int serial_port_carrier_raised(struct tty_port *port) if (drv->carrier_raised) return drv->carrier_raised(p); /* No carrier control - don't block */ - return 1; + return true; } static void serial_port_dtr_rts(struct tty_port *port, int on) diff --git a/include/linux/tty_port.h b/include/linux/tty_port.h index fa3c3bdaa234..cf098459cb01 100644 --- a/include/linux/tty_port.h +++ b/include/linux/tty_port.h @@ -15,7 +15,7 @@ struct tty_struct; /** * struct tty_port_operations -- operations on tty_port - * @carrier_raised: return 1 if the carrier is raised on @port + * @carrier_raised: return true if the carrier is raised on @port * @dtr_rts: raise the DTR line if @raise is nonzero, otherwise lower DTR * @shutdown: called when the last close completes or a hangup finishes IFF the * port was initialized. Do not use to free resources. Turn off the device @@ -31,7 +31,7 @@ struct tty_struct; * the port itself. */ struct tty_port_operations { - int (*carrier_raised)(struct tty_port *port); + bool (*carrier_raised)(struct tty_port *port); void (*dtr_rts)(struct tty_port *port, int raise); void (*shutdown)(struct tty_port *port); int (*activate)(struct tty_port *port, struct tty_struct *tty); @@ -230,7 +230,7 @@ static inline void tty_port_set_kopened(struct tty_port *port, bool val) struct tty_struct *tty_port_tty_get(struct tty_port *port); void tty_port_tty_set(struct tty_port *port, struct tty_struct *tty); -int tty_port_carrier_raised(struct tty_port *port); +bool tty_port_carrier_raised(struct tty_port *port); void tty_port_raise_dtr_rts(struct tty_port *port); void tty_port_lower_dtr_rts(struct tty_port *port); void tty_port_hangup(struct tty_port *port); diff --git a/net/bluetooth/rfcomm/tty.c b/net/bluetooth/rfcomm/tty.c index 8009e0e93216..5697df9d4394 100644 --- a/net/bluetooth/rfcomm/tty.c +++ b/net/bluetooth/rfcomm/tty.c @@ -119,7 +119,7 @@ static int rfcomm_dev_activate(struct tty_port *port, struct tty_struct *tty) } /* we block the open until the dlc->state becomes BT_CONNECTED */ -static int rfcomm_dev_carrier_raised(struct tty_port *port) +static bool rfcomm_dev_carrier_raised(struct tty_port *port) { struct rfcomm_dev *dev = container_of(port, struct rfcomm_dev, port); -- cgit v1.2.3 From 5d420399073770134d2b03e004b2c0201c7fa26f Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Tue, 17 Jan 2023 11:03:53 +0200 Subject: tty: Convert ->dtr_rts() to take bool argument Convert the raise/on parameter in ->dtr_rts() to bool through the callchain. The parameter is used like bool. In USB serial, there remains a few implicit bool -> larger type conversions because some devices use u8 in their control messages. In moxa_tiocmget(), dtr variable was reused for line status which requires int so use a separate variable for status. Reviewed-by: Jiri Slaby Acked-by: Ulf Hansson # For MMC Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20230117090358.4796-8-ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/char/pcmcia/synclink_cs.c | 4 +-- drivers/mmc/core/sdio_uart.c | 4 +-- drivers/staging/greybus/uart.c | 2 +- drivers/tty/amiserial.c | 2 +- drivers/tty/hvc/hvc_console.c | 4 +-- drivers/tty/hvc/hvc_console.h | 2 +- drivers/tty/hvc/hvc_iucv.c | 4 +-- drivers/tty/moxa.c | 54 ++++++++++++++++++++------------------- drivers/tty/mxser.c | 2 +- drivers/tty/n_gsm.c | 2 +- drivers/tty/serial/serial_core.c | 8 +++--- drivers/tty/synclink_gt.c | 2 +- drivers/tty/tty_port.c | 4 +-- drivers/usb/class/cdc-acm.c | 2 +- drivers/usb/serial/usb-serial.c | 2 +- include/linux/tty_port.h | 4 +-- 16 files changed, 52 insertions(+), 50 deletions(-) (limited to 'include/linux') diff --git a/drivers/char/pcmcia/synclink_cs.c b/drivers/char/pcmcia/synclink_cs.c index 4391138e1b8a..46a0b586d234 100644 --- a/drivers/char/pcmcia/synclink_cs.c +++ b/drivers/char/pcmcia/synclink_cs.c @@ -378,7 +378,7 @@ static void async_mode(MGSLPC_INFO *info); static void tx_timeout(struct timer_list *t); static bool carrier_raised(struct tty_port *port); -static void dtr_rts(struct tty_port *port, int onoff); +static void dtr_rts(struct tty_port *port, bool onoff); #if SYNCLINK_GENERIC_HDLC #define dev_to_port(D) (dev_to_hdlc(D)->priv) @@ -2442,7 +2442,7 @@ static bool carrier_raised(struct tty_port *port) return info->serial_signals & SerialSignal_DCD; } -static void dtr_rts(struct tty_port *port, int onoff) +static void dtr_rts(struct tty_port *port, bool onoff) { MGSLPC_INFO *info = container_of(port, MGSLPC_INFO, port); unsigned long flags; diff --git a/drivers/mmc/core/sdio_uart.c b/drivers/mmc/core/sdio_uart.c index 47f58258d8ff..c6b4b2b2a4b2 100644 --- a/drivers/mmc/core/sdio_uart.c +++ b/drivers/mmc/core/sdio_uart.c @@ -548,14 +548,14 @@ static bool uart_carrier_raised(struct tty_port *tport) * adjusted during an open, close and hangup. */ -static void uart_dtr_rts(struct tty_port *tport, int onoff) +static void uart_dtr_rts(struct tty_port *tport, bool onoff) { struct sdio_uart_port *port = container_of(tport, struct sdio_uart_port, port); int ret = sdio_uart_claim_func(port); if (ret) return; - if (onoff == 0) + if (!onoff) sdio_uart_clear_mctrl(port, TIOCM_DTR | TIOCM_RTS); else sdio_uart_set_mctrl(port, TIOCM_DTR | TIOCM_RTS); diff --git a/drivers/staging/greybus/uart.c b/drivers/staging/greybus/uart.c index 90ff07f2cbf7..92d49740d5a4 100644 --- a/drivers/staging/greybus/uart.c +++ b/drivers/staging/greybus/uart.c @@ -701,7 +701,7 @@ static int gb_tty_ioctl(struct tty_struct *tty, unsigned int cmd, return -ENOIOCTLCMD; } -static void gb_tty_dtr_rts(struct tty_port *port, int on) +static void gb_tty_dtr_rts(struct tty_port *port, bool on) { struct gb_tty *gb_tty; u8 newctrl; diff --git a/drivers/tty/amiserial.c b/drivers/tty/amiserial.c index 01c4fd3ce7c8..29d4c554f6b8 100644 --- a/drivers/tty/amiserial.c +++ b/drivers/tty/amiserial.c @@ -1459,7 +1459,7 @@ static bool amiga_carrier_raised(struct tty_port *port) return !(ciab.pra & SER_DCD); } -static void amiga_dtr_rts(struct tty_port *port, int raise) +static void amiga_dtr_rts(struct tty_port *port, bool raise) { struct serial_state *info = container_of(port, struct serial_state, tport); diff --git a/drivers/tty/hvc/hvc_console.c b/drivers/tty/hvc/hvc_console.c index a683e21df19c..10c10cfdf92a 100644 --- a/drivers/tty/hvc/hvc_console.c +++ b/drivers/tty/hvc/hvc_console.c @@ -376,7 +376,7 @@ static int hvc_open(struct tty_struct *tty, struct file * filp) /* We are ready... raise DTR/RTS */ if (C_BAUD(tty)) if (hp->ops->dtr_rts) - hp->ops->dtr_rts(hp, 1); + hp->ops->dtr_rts(hp, true); tty_port_set_initialized(&hp->port, true); } @@ -406,7 +406,7 @@ static void hvc_close(struct tty_struct *tty, struct file * filp) if (C_HUPCL(tty)) if (hp->ops->dtr_rts) - hp->ops->dtr_rts(hp, 0); + hp->ops->dtr_rts(hp, false); if (hp->ops->notifier_del) hp->ops->notifier_del(hp, hp->data); diff --git a/drivers/tty/hvc/hvc_console.h b/drivers/tty/hvc/hvc_console.h index 18d005814e4b..6d3428bf868f 100644 --- a/drivers/tty/hvc/hvc_console.h +++ b/drivers/tty/hvc/hvc_console.h @@ -66,7 +66,7 @@ struct hv_ops { int (*tiocmset)(struct hvc_struct *hp, unsigned int set, unsigned int clear); /* Callbacks to handle tty ports */ - void (*dtr_rts)(struct hvc_struct *hp, int raise); + void (*dtr_rts)(struct hvc_struct *hp, bool raise); }; /* Register a vterm and a slot index for use as a console (console_init) */ diff --git a/drivers/tty/hvc/hvc_iucv.c b/drivers/tty/hvc/hvc_iucv.c index 7d49a872de48..fe862a6882d6 100644 --- a/drivers/tty/hvc/hvc_iucv.c +++ b/drivers/tty/hvc/hvc_iucv.c @@ -658,13 +658,13 @@ static void hvc_iucv_notifier_hangup(struct hvc_struct *hp, int id) /** * hvc_iucv_dtr_rts() - HVC notifier for handling DTR/RTS * @hp: Pointer the HVC device (struct hvc_struct) - * @raise: Non-zero to raise or zero to lower DTR/RTS lines + * @raise: True to raise or false to lower DTR/RTS lines * * This routine notifies the HVC back-end to raise or lower DTR/RTS * lines. Raising DTR/RTS is ignored. Lowering DTR/RTS indicates to * drop the IUCV connection (similar to hang up the modem). */ -static void hvc_iucv_dtr_rts(struct hvc_struct *hp, int raise) +static void hvc_iucv_dtr_rts(struct hvc_struct *hp, bool raise) { struct hvc_iucv_private *priv; struct iucv_path *path; diff --git a/drivers/tty/moxa.c b/drivers/tty/moxa.c index 6a1e78e33a2c..9be3d585d5a9 100644 --- a/drivers/tty/moxa.c +++ b/drivers/tty/moxa.c @@ -502,15 +502,15 @@ static void moxa_poll(struct timer_list *); static void moxa_set_tty_param(struct tty_struct *, const struct ktermios *); static void moxa_shutdown(struct tty_port *); static bool moxa_carrier_raised(struct tty_port *); -static void moxa_dtr_rts(struct tty_port *, int); +static void moxa_dtr_rts(struct tty_port *, bool); /* * moxa board interface functions: */ static void MoxaPortEnable(struct moxa_port *); static void MoxaPortDisable(struct moxa_port *); static int MoxaPortSetTermio(struct moxa_port *, struct ktermios *, speed_t); -static int MoxaPortGetLineOut(struct moxa_port *, int *, int *); -static void MoxaPortLineCtrl(struct moxa_port *, int, int); +static int MoxaPortGetLineOut(struct moxa_port *, bool *, bool *); +static void MoxaPortLineCtrl(struct moxa_port *, bool, bool); static void MoxaPortFlowCtrl(struct moxa_port *, int, int, int, int, int); static int MoxaPortLineStatus(struct moxa_port *); static void MoxaPortFlushData(struct moxa_port *, int); @@ -1443,7 +1443,7 @@ static bool moxa_carrier_raised(struct tty_port *port) return dcd; } -static void moxa_dtr_rts(struct tty_port *port, int onoff) +static void moxa_dtr_rts(struct tty_port *port, bool onoff) { struct moxa_port *ch = container_of(port, struct moxa_port, port); MoxaPortLineCtrl(ch, onoff, onoff); @@ -1481,7 +1481,7 @@ static int moxa_open(struct tty_struct *tty, struct file *filp) if (!tty_port_initialized(&ch->port)) { ch->statusflags = 0; moxa_set_tty_param(tty, &tty->termios); - MoxaPortLineCtrl(ch, 1, 1); + MoxaPortLineCtrl(ch, true, true); MoxaPortEnable(ch); MoxaSetFifo(ch, ch->type == PORT_16550A); tty_port_set_initialized(&ch->port, true); @@ -1557,19 +1557,21 @@ static unsigned int moxa_chars_in_buffer(struct tty_struct *tty) static int moxa_tiocmget(struct tty_struct *tty) { struct moxa_port *ch = tty->driver_data; - int flag = 0, dtr, rts; + bool dtr, rts; + int flag = 0; + int status; MoxaPortGetLineOut(ch, &dtr, &rts); if (dtr) flag |= TIOCM_DTR; if (rts) flag |= TIOCM_RTS; - dtr = MoxaPortLineStatus(ch); - if (dtr & 1) + status = MoxaPortLineStatus(ch); + if (status & 1) flag |= TIOCM_CTS; - if (dtr & 2) + if (status & 2) flag |= TIOCM_DSR; - if (dtr & 4) + if (status & 4) flag |= TIOCM_CD; return flag; } @@ -1578,7 +1580,7 @@ static int moxa_tiocmset(struct tty_struct *tty, unsigned int set, unsigned int clear) { struct moxa_port *ch; - int dtr, rts; + bool dtr, rts; mutex_lock(&moxa_openlock); ch = tty->driver_data; @@ -1589,13 +1591,13 @@ static int moxa_tiocmset(struct tty_struct *tty, MoxaPortGetLineOut(ch, &dtr, &rts); if (set & TIOCM_RTS) - rts = 1; + rts = true; if (set & TIOCM_DTR) - dtr = 1; + dtr = true; if (clear & TIOCM_RTS) - rts = 0; + rts = false; if (clear & TIOCM_DTR) - dtr = 0; + dtr = false; MoxaPortLineCtrl(ch, dtr, rts); mutex_unlock(&moxa_openlock); return 0; @@ -1877,12 +1879,12 @@ static void MoxaPortFlushData(struct moxa_port *port, int mode) * * Function 13: Get the DTR/RTS state of this port. * Syntax: - * int MoxaPortGetLineOut(int port, int *dtrState, int *rtsState); + * int MoxaPortGetLineOut(int port, bool *dtrState, bool *rtsState); * int port : port number (0 - 127) - * int * dtrState : pointer to INT to receive the current DTR + * bool * dtrState : pointer to bool to receive the current DTR * state. (if NULL, this function will not * write to this address) - * int * rtsState : pointer to INT to receive the current RTS + * bool * rtsState : pointer to bool to receive the current RTS * state. (if NULL, this function will not * write to this address) * @@ -1892,10 +1894,10 @@ static void MoxaPortFlushData(struct moxa_port *port, int mode) * * Function 14: Setting the DTR/RTS output state of this port. * Syntax: - * void MoxaPortLineCtrl(int port, int dtrState, int rtsState); + * void MoxaPortLineCtrl(int port, bool dtrState, bool rtsState); * int port : port number (0 - 127) - * int dtrState : DTR output state (0: off, 1: on) - * int rtsState : RTS output state (0: off, 1: on) + * bool dtrState : DTR output state + * bool rtsState : RTS output state * * * Function 15: Setting the flow control of this port. @@ -2103,18 +2105,18 @@ static int MoxaPortSetTermio(struct moxa_port *port, struct ktermios *termio, return baud; } -static int MoxaPortGetLineOut(struct moxa_port *port, int *dtrState, - int *rtsState) +static int MoxaPortGetLineOut(struct moxa_port *port, bool *dtrState, + bool *rtsState) { if (dtrState) - *dtrState = !!(port->lineCtrl & DTR_ON); + *dtrState = port->lineCtrl & DTR_ON; if (rtsState) - *rtsState = !!(port->lineCtrl & RTS_ON); + *rtsState = port->lineCtrl & RTS_ON; return 0; } -static void MoxaPortLineCtrl(struct moxa_port *port, int dtr, int rts) +static void MoxaPortLineCtrl(struct moxa_port *port, bool dtr, bool rts) { u8 mode = 0; diff --git a/drivers/tty/mxser.c b/drivers/tty/mxser.c index 96c72e691cd7..d4fb11e39bb1 100644 --- a/drivers/tty/mxser.c +++ b/drivers/tty/mxser.c @@ -465,7 +465,7 @@ static bool mxser_carrier_raised(struct tty_port *port) return inb(mp->ioaddr + UART_MSR) & UART_MSR_DCD; } -static void mxser_dtr_rts(struct tty_port *port, int on) +static void mxser_dtr_rts(struct tty_port *port, bool on) { struct mxser_port *mp = container_of(port, struct mxser_port, port); unsigned long flags; diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c index 64abc5fbf2c1..12b734b1b556 100644 --- a/drivers/tty/n_gsm.c +++ b/drivers/tty/n_gsm.c @@ -3792,7 +3792,7 @@ static bool gsm_carrier_raised(struct tty_port *port) return dlci->modem_rx & TIOCM_CD; } -static void gsm_dtr_rts(struct tty_port *port, int onoff) +static void gsm_dtr_rts(struct tty_port *port, bool onoff) { struct gsm_dlci *dlci = container_of(port, struct gsm_dlci, port); unsigned int modem_tx = dlci->modem_tx; diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index ddf14c4f4bf5..c09c17cf6af6 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -169,7 +169,7 @@ uart_update_mctrl(struct uart_port *port, unsigned int set, unsigned int clear) #define uart_set_mctrl(port, set) uart_update_mctrl(port, set, 0) #define uart_clear_mctrl(port, clear) uart_update_mctrl(port, 0, clear) -static void uart_port_dtr_rts(struct uart_port *uport, int raise) +static void uart_port_dtr_rts(struct uart_port *uport, bool raise) { if (raise) uart_set_mctrl(uport, TIOCM_DTR | TIOCM_RTS); @@ -239,7 +239,7 @@ static int uart_port_startup(struct tty_struct *tty, struct uart_state *state, * port is open and ready to respond. */ if (init_hw && C_BAUD(tty)) - uart_port_dtr_rts(uport, 1); + uart_port_dtr_rts(uport, true); } /* @@ -302,7 +302,7 @@ static void uart_shutdown(struct tty_struct *tty, struct uart_state *state) } if (!tty || C_HUPCL(tty)) - uart_port_dtr_rts(uport, 0); + uart_port_dtr_rts(uport, false); uart_port_shutdown(port); } @@ -1885,7 +1885,7 @@ static bool uart_carrier_raised(struct tty_port *port) return mctrl & TIOCM_CAR; } -static void uart_dtr_rts(struct tty_port *port, int raise) +static void uart_dtr_rts(struct tty_port *port, bool raise) { struct uart_state *state = container_of(port, struct uart_state, port); struct uart_port *uport; diff --git a/drivers/tty/synclink_gt.c b/drivers/tty/synclink_gt.c index 4ba71ec764f7..2b786265ce7b 100644 --- a/drivers/tty/synclink_gt.c +++ b/drivers/tty/synclink_gt.c @@ -3138,7 +3138,7 @@ static bool carrier_raised(struct tty_port *port) return info->signals & SerialSignal_DCD; } -static void dtr_rts(struct tty_port *port, int on) +static void dtr_rts(struct tty_port *port, bool on) { unsigned long flags; struct slgt_info *info = container_of(port, struct slgt_info, port); diff --git a/drivers/tty/tty_port.c b/drivers/tty/tty_port.c index a573c500f95b..a788a6bf487d 100644 --- a/drivers/tty/tty_port.c +++ b/drivers/tty/tty_port.c @@ -463,7 +463,7 @@ EXPORT_SYMBOL(tty_port_carrier_raised); void tty_port_raise_dtr_rts(struct tty_port *port) { if (port->ops->dtr_rts) - port->ops->dtr_rts(port, 1); + port->ops->dtr_rts(port, true); } EXPORT_SYMBOL(tty_port_raise_dtr_rts); @@ -478,7 +478,7 @@ EXPORT_SYMBOL(tty_port_raise_dtr_rts); void tty_port_lower_dtr_rts(struct tty_port *port) { if (port->ops->dtr_rts) - port->ops->dtr_rts(port, 0); + port->ops->dtr_rts(port, false); } EXPORT_SYMBOL(tty_port_lower_dtr_rts); diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index 36bf051b345b..d4f9220b8162 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -651,7 +651,7 @@ static int acm_tty_open(struct tty_struct *tty, struct file *filp) return tty_port_open(&acm->port, tty, filp); } -static void acm_port_dtr_rts(struct tty_port *port, int raise) +static void acm_port_dtr_rts(struct tty_port *port, bool raise) { struct acm *acm = container_of(port, struct acm, port); int val; diff --git a/drivers/usb/serial/usb-serial.c b/drivers/usb/serial/usb-serial.c index 019720a63fac..f8404073558b 100644 --- a/drivers/usb/serial/usb-serial.c +++ b/drivers/usb/serial/usb-serial.c @@ -765,7 +765,7 @@ static bool serial_port_carrier_raised(struct tty_port *port) return true; } -static void serial_port_dtr_rts(struct tty_port *port, int on) +static void serial_port_dtr_rts(struct tty_port *port, bool on) { struct usb_serial_port *p = container_of(port, struct usb_serial_port, port); struct usb_serial_driver *drv = p->serial->type; diff --git a/include/linux/tty_port.h b/include/linux/tty_port.h index cf098459cb01..c44e489de0ff 100644 --- a/include/linux/tty_port.h +++ b/include/linux/tty_port.h @@ -16,7 +16,7 @@ struct tty_struct; /** * struct tty_port_operations -- operations on tty_port * @carrier_raised: return true if the carrier is raised on @port - * @dtr_rts: raise the DTR line if @raise is nonzero, otherwise lower DTR + * @dtr_rts: raise the DTR line if @raise is true, otherwise lower DTR * @shutdown: called when the last close completes or a hangup finishes IFF the * port was initialized. Do not use to free resources. Turn off the device * only. Called under the port mutex to serialize against @activate and @@ -32,7 +32,7 @@ struct tty_struct; */ struct tty_port_operations { bool (*carrier_raised)(struct tty_port *port); - void (*dtr_rts)(struct tty_port *port, int raise); + void (*dtr_rts)(struct tty_port *port, bool raise); void (*shutdown)(struct tty_port *port); int (*activate)(struct tty_port *port, struct tty_struct *tty); void (*destruct)(struct tty_port *port); -- cgit v1.2.3 From 0388a152fc5544be82e736343496f99c4eef8d62 Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Tue, 17 Jan 2023 11:03:54 +0200 Subject: tty/serial: Make ->dcd_change()+uart_handle_dcd_change() status bool active Convert status parameter for ->dcd_change() and uart_handle_dcd_change() to bool which matches to how the parameter is used. Rename status to active to better describe what the parameter means. Acked-by: Rodolfo Giometti Reviewed-by: Jiri Slaby Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20230117090358.4796-9-ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/pps/clients/pps-ldisc.c | 6 +++--- drivers/tty/serial/serial_core.c | 8 ++++---- drivers/tty/serial/sunhv.c | 8 ++++---- include/linux/serial_core.h | 3 +-- include/linux/tty_ldisc.h | 4 ++-- 5 files changed, 14 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/drivers/pps/clients/pps-ldisc.c b/drivers/pps/clients/pps-ldisc.c index d73c4c2ed4e1..443d6bae19d1 100644 --- a/drivers/pps/clients/pps-ldisc.c +++ b/drivers/pps/clients/pps-ldisc.c @@ -13,7 +13,7 @@ #include #include -static void pps_tty_dcd_change(struct tty_struct *tty, unsigned int status) +static void pps_tty_dcd_change(struct tty_struct *tty, bool active) { struct pps_device *pps; struct pps_event_time ts; @@ -29,11 +29,11 @@ static void pps_tty_dcd_change(struct tty_struct *tty, unsigned int status) return; /* Now do the PPS event report */ - pps_event(pps, &ts, status ? PPS_CAPTUREASSERT : + pps_event(pps, &ts, active ? PPS_CAPTUREASSERT : PPS_CAPTURECLEAR, NULL); dev_dbg(pps->dev, "PPS %s at %lu\n", - status ? "assert" : "clear", jiffies); + active ? "assert" : "clear", jiffies); } static int (*alias_n_tty_open)(struct tty_struct *tty); diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index c09c17cf6af6..7319a6f55013 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -3252,11 +3252,11 @@ EXPORT_SYMBOL(uart_match_port); /** * uart_handle_dcd_change - handle a change of carrier detect state * @uport: uart_port structure for the open port - * @status: new carrier detect status, nonzero if active + * @active: new carrier detect status * * Caller must hold uport->lock. */ -void uart_handle_dcd_change(struct uart_port *uport, unsigned int status) +void uart_handle_dcd_change(struct uart_port *uport, bool active) { struct tty_port *port = &uport->state->port; struct tty_struct *tty = port->tty; @@ -3268,7 +3268,7 @@ void uart_handle_dcd_change(struct uart_port *uport, unsigned int status) ld = tty_ldisc_ref(tty); if (ld) { if (ld->ops->dcd_change) - ld->ops->dcd_change(tty, status); + ld->ops->dcd_change(tty, active); tty_ldisc_deref(ld); } } @@ -3276,7 +3276,7 @@ void uart_handle_dcd_change(struct uart_port *uport, unsigned int status) uport->icount.dcd++; if (uart_dcd_enabled(uport)) { - if (status) + if (active) wake_up_interruptible(&port->open_wait); else if (tty) tty_hangup(tty); diff --git a/drivers/tty/serial/sunhv.c b/drivers/tty/serial/sunhv.c index 16c746a63258..7d38c33ef506 100644 --- a/drivers/tty/serial/sunhv.c +++ b/drivers/tty/serial/sunhv.c @@ -87,10 +87,10 @@ static int receive_chars_getchar(struct uart_port *port) if (c == CON_HUP) { hung_up = 1; - uart_handle_dcd_change(port, 0); + uart_handle_dcd_change(port, false); } else if (hung_up) { hung_up = 0; - uart_handle_dcd_change(port, 1); + uart_handle_dcd_change(port, true); } if (port->state == NULL) { @@ -133,7 +133,7 @@ static int receive_chars_read(struct uart_port *port) bytes_read = 1; } else if (stat == CON_HUP) { hung_up = 1; - uart_handle_dcd_change(port, 0); + uart_handle_dcd_change(port, false); continue; } else { /* HV_EWOULDBLOCK, etc. */ @@ -143,7 +143,7 @@ static int receive_chars_read(struct uart_port *port) if (hung_up) { hung_up = 0; - uart_handle_dcd_change(port, 1); + uart_handle_dcd_change(port, true); } if (port->sysrq != 0 && *con_read_page) { diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 0b37a86bedc5..8c4187c4884a 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -897,8 +897,7 @@ static inline bool uart_softcts_mode(struct uart_port *uport) * The following are helper functions for the low level drivers. */ -extern void uart_handle_dcd_change(struct uart_port *uport, - unsigned int status); +extern void uart_handle_dcd_change(struct uart_port *uport, bool active); extern void uart_handle_cts_change(struct uart_port *uport, unsigned int status); diff --git a/include/linux/tty_ldisc.h b/include/linux/tty_ldisc.h index dcb61ec11424..49dc172dedc7 100644 --- a/include/linux/tty_ldisc.h +++ b/include/linux/tty_ldisc.h @@ -170,7 +170,7 @@ int ldsem_down_write_nested(struct ld_semaphore *sem, int subclass, * send, please arise a tasklet or workqueue to do the real data transfer. * Do not send data in this hook, it may lead to a deadlock. * - * @dcd_change: [DRV] ``void ()(struct tty_struct *tty, unsigned int status)`` + * @dcd_change: [DRV] ``void ()(struct tty_struct *tty, bool active)`` * * Tells the discipline that the DCD pin has changed its status. Used * exclusively by the %N_PPS (Pulse-Per-Second) line discipline. @@ -238,7 +238,7 @@ struct tty_ldisc_ops { void (*receive_buf)(struct tty_struct *tty, const unsigned char *cp, const char *fp, int count); void (*write_wakeup)(struct tty_struct *tty); - void (*dcd_change)(struct tty_struct *tty, unsigned int status); + void (*dcd_change)(struct tty_struct *tty, bool active); int (*receive_buf2)(struct tty_struct *tty, const unsigned char *cp, const char *fp, int count); void (*lookahead_buf)(struct tty_struct *tty, const unsigned char *cp, -- cgit v1.2.3 From 968d64578ec92968e8c79d766eb966efd1f68d7e Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Tue, 17 Jan 2023 11:03:55 +0200 Subject: serial: Make uart_handle_cts_change() status param bool active Convert uart_handle_cts_change() to bool which is more appropriate than unsigned int. Rename status to active to better describe what the parameter means. While at it, make the comment about the active parameter easier to parse. Cleanup callsites from operations that are not necessary with bool. Reviewed-by: Jiri Slaby Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20230117090358.4796-10-ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/imx.c | 2 +- drivers/tty/serial/max3100.c | 2 +- drivers/tty/serial/max310x.c | 3 +-- drivers/tty/serial/serial_core.c | 8 ++++---- include/linux/serial_core.h | 3 +-- 5 files changed, 8 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c index f2b43fb497ff..ae75135dccb8 100644 --- a/drivers/tty/serial/imx.c +++ b/drivers/tty/serial/imx.c @@ -773,7 +773,7 @@ static irqreturn_t __imx_uart_rtsint(int irq, void *dev_id) imx_uart_writel(sport, USR1_RTSD, USR1); usr1 = imx_uart_readl(sport, USR1) & USR1_RTSS; - uart_handle_cts_change(&sport->port, !!usr1); + uart_handle_cts_change(&sport->port, usr1); wake_up_interruptible(&sport->port.state->port.delta_msr_wait); return IRQ_HANDLED; diff --git a/drivers/tty/serial/max3100.c b/drivers/tty/serial/max3100.c index bb74f23251fe..86dcbff8faa3 100644 --- a/drivers/tty/serial/max3100.c +++ b/drivers/tty/serial/max3100.c @@ -247,7 +247,7 @@ static int max3100_handlerx(struct max3100_port *s, u16 rx) cts = (rx & MAX3100_CTS) > 0; if (s->cts != cts) { s->cts = cts; - uart_handle_cts_change(&s->port, cts ? TIOCM_CTS : 0); + uart_handle_cts_change(&s->port, cts); } return ret; diff --git a/drivers/tty/serial/max310x.c b/drivers/tty/serial/max310x.c index 4eb24e3407f8..e9cacfe7e032 100644 --- a/drivers/tty/serial/max310x.c +++ b/drivers/tty/serial/max310x.c @@ -819,8 +819,7 @@ static irqreturn_t max310x_port_irq(struct max310x_port *s, int portno) if (ists & MAX310X_IRQ_CTS_BIT) { lsr = max310x_port_read(port, MAX310X_LSR_IRQSTS_REG); - uart_handle_cts_change(port, - !!(lsr & MAX310X_LSR_CTS_BIT)); + uart_handle_cts_change(port, lsr & MAX310X_LSR_CTS_BIT); } if (rxlen) max310x_handle_rx(port, rxlen); diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index 7319a6f55013..371440faa14c 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -3287,11 +3287,11 @@ EXPORT_SYMBOL_GPL(uart_handle_dcd_change); /** * uart_handle_cts_change - handle a change of clear-to-send state * @uport: uart_port structure for the open port - * @status: new clear to send status, nonzero if active + * @active: new clear-to-send status * * Caller must hold uport->lock. */ -void uart_handle_cts_change(struct uart_port *uport, unsigned int status) +void uart_handle_cts_change(struct uart_port *uport, bool active) { lockdep_assert_held_once(&uport->lock); @@ -3299,13 +3299,13 @@ void uart_handle_cts_change(struct uart_port *uport, unsigned int status) if (uart_softcts_mode(uport)) { if (uport->hw_stopped) { - if (status) { + if (active) { uport->hw_stopped = 0; uport->ops->start_tx(uport); uart_write_wakeup(uport); } } else { - if (!status) { + if (!active) { uport->hw_stopped = 1; uport->ops->stop_tx(uport); } diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 8c4187c4884a..9e3e5e0d11b2 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -898,8 +898,7 @@ static inline bool uart_softcts_mode(struct uart_port *uport) */ extern void uart_handle_dcd_change(struct uart_port *uport, bool active); -extern void uart_handle_cts_change(struct uart_port *uport, - unsigned int status); +extern void uart_handle_cts_change(struct uart_port *uport, bool active); extern void uart_insert_char(struct uart_port *port, unsigned int status, unsigned int overrun, unsigned int ch, unsigned int flag); -- cgit v1.2.3 From 87f22db4c251ff92d588c2cc710031a59d5e4ec0 Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Tue, 17 Jan 2023 11:03:56 +0200 Subject: tty: Return bool from tty_termios_hw_change() Change tty_termios_hw_change() to return bool. Reviewed-by: Jiri Slaby Reviewed-by: Johan Hovold Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20230117090358.4796-11-ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/tty_ioctl.c | 8 ++++---- include/linux/tty.h | 2 +- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/tty/tty_ioctl.c b/drivers/tty/tty_ioctl.c index ce511557b98b..12983ce4e43e 100644 --- a/drivers/tty/tty_ioctl.c +++ b/drivers/tty/tty_ioctl.c @@ -270,13 +270,13 @@ EXPORT_SYMBOL(tty_termios_copy_hw); * between the two termios structures, or a speed change is needed. */ -int tty_termios_hw_change(const struct ktermios *a, const struct ktermios *b) +bool tty_termios_hw_change(const struct ktermios *a, const struct ktermios *b) { if (a->c_ispeed != b->c_ispeed || a->c_ospeed != b->c_ospeed) - return 1; + return true; if ((a->c_cflag ^ b->c_cflag) & ~(HUPCL | CREAD | CLOCAL)) - return 1; - return 0; + return true; + return false; } EXPORT_SYMBOL(tty_termios_hw_change); diff --git a/include/linux/tty.h b/include/linux/tty.h index 730c3301d710..093935e97f42 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -453,7 +453,7 @@ unsigned char tty_get_char_size(unsigned int cflag); unsigned char tty_get_frame_size(unsigned int cflag); void tty_termios_copy_hw(struct ktermios *new, const struct ktermios *old); -int tty_termios_hw_change(const struct ktermios *a, const struct ktermios *b); +bool tty_termios_hw_change(const struct ktermios *a, const struct ktermios *b); int tty_set_termios(struct tty_struct *tty, struct ktermios *kt); void tty_wakeup(struct tty_struct *tty); -- cgit v1.2.3 From 5701cb8bf50e1c723553344b3f731b308da8ea21 Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Tue, 17 Jan 2023 11:03:57 +0200 Subject: tty: Call ->dtr_rts() parameter active consistently Convert various parameter names for ->dtr_rts() and related functions from onoff, on, and raise to active. Reviewed-by: Jiri Slaby Acked-by: Ulf Hansson # For MMC Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20230117090358.4796-12-ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/char/pcmcia/synclink_cs.c | 6 +++--- drivers/mmc/core/sdio_uart.c | 6 +++--- drivers/staging/greybus/uart.c | 4 ++-- drivers/tty/amiserial.c | 4 ++-- drivers/tty/hvc/hvc_console.h | 2 +- drivers/tty/hvc/hvc_iucv.c | 6 +++--- drivers/tty/mxser.c | 4 ++-- drivers/tty/n_gsm.c | 4 ++-- drivers/tty/serial/serial_core.c | 8 ++++---- drivers/tty/synclink_gt.c | 4 ++-- drivers/usb/class/cdc-acm.c | 4 ++-- include/linux/tty_port.h | 4 ++-- 12 files changed, 28 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/drivers/char/pcmcia/synclink_cs.c b/drivers/char/pcmcia/synclink_cs.c index 46a0b586d234..1577eba6fe0e 100644 --- a/drivers/char/pcmcia/synclink_cs.c +++ b/drivers/char/pcmcia/synclink_cs.c @@ -378,7 +378,7 @@ static void async_mode(MGSLPC_INFO *info); static void tx_timeout(struct timer_list *t); static bool carrier_raised(struct tty_port *port); -static void dtr_rts(struct tty_port *port, bool onoff); +static void dtr_rts(struct tty_port *port, bool active); #if SYNCLINK_GENERIC_HDLC #define dev_to_port(D) (dev_to_hdlc(D)->priv) @@ -2442,13 +2442,13 @@ static bool carrier_raised(struct tty_port *port) return info->serial_signals & SerialSignal_DCD; } -static void dtr_rts(struct tty_port *port, bool onoff) +static void dtr_rts(struct tty_port *port, bool active) { MGSLPC_INFO *info = container_of(port, MGSLPC_INFO, port); unsigned long flags; spin_lock_irqsave(&info->lock, flags); - if (onoff) + if (active) info->serial_signals |= SerialSignal_RTS | SerialSignal_DTR; else info->serial_signals &= ~(SerialSignal_RTS | SerialSignal_DTR); diff --git a/drivers/mmc/core/sdio_uart.c b/drivers/mmc/core/sdio_uart.c index c6b4b2b2a4b2..50536fe59f1a 100644 --- a/drivers/mmc/core/sdio_uart.c +++ b/drivers/mmc/core/sdio_uart.c @@ -542,20 +542,20 @@ static bool uart_carrier_raised(struct tty_port *tport) /** * uart_dtr_rts - port helper to set uart signals * @tport: tty port to be updated - * @onoff: set to turn on DTR/RTS + * @active: set to turn on DTR/RTS * * Called by the tty port helpers when the modem signals need to be * adjusted during an open, close and hangup. */ -static void uart_dtr_rts(struct tty_port *tport, bool onoff) +static void uart_dtr_rts(struct tty_port *tport, bool active) { struct sdio_uart_port *port = container_of(tport, struct sdio_uart_port, port); int ret = sdio_uart_claim_func(port); if (ret) return; - if (!onoff) + if (!active) sdio_uart_clear_mctrl(port, TIOCM_DTR | TIOCM_RTS); else sdio_uart_set_mctrl(port, TIOCM_DTR | TIOCM_RTS); diff --git a/drivers/staging/greybus/uart.c b/drivers/staging/greybus/uart.c index 92d49740d5a4..20a34599859f 100644 --- a/drivers/staging/greybus/uart.c +++ b/drivers/staging/greybus/uart.c @@ -701,7 +701,7 @@ static int gb_tty_ioctl(struct tty_struct *tty, unsigned int cmd, return -ENOIOCTLCMD; } -static void gb_tty_dtr_rts(struct tty_port *port, bool on) +static void gb_tty_dtr_rts(struct tty_port *port, bool active) { struct gb_tty *gb_tty; u8 newctrl; @@ -709,7 +709,7 @@ static void gb_tty_dtr_rts(struct tty_port *port, bool on) gb_tty = container_of(port, struct gb_tty, port); newctrl = gb_tty->ctrlout; - if (on) + if (active) newctrl |= (GB_UART_CTRL_DTR | GB_UART_CTRL_RTS); else newctrl &= ~(GB_UART_CTRL_DTR | GB_UART_CTRL_RTS); diff --git a/drivers/tty/amiserial.c b/drivers/tty/amiserial.c index 29d4c554f6b8..d7515d61659e 100644 --- a/drivers/tty/amiserial.c +++ b/drivers/tty/amiserial.c @@ -1459,13 +1459,13 @@ static bool amiga_carrier_raised(struct tty_port *port) return !(ciab.pra & SER_DCD); } -static void amiga_dtr_rts(struct tty_port *port, bool raise) +static void amiga_dtr_rts(struct tty_port *port, bool active) { struct serial_state *info = container_of(port, struct serial_state, tport); unsigned long flags; - if (raise) + if (active) info->MCR |= SER_DTR|SER_RTS; else info->MCR &= ~(SER_DTR|SER_RTS); diff --git a/drivers/tty/hvc/hvc_console.h b/drivers/tty/hvc/hvc_console.h index 6d3428bf868f..9668f821db01 100644 --- a/drivers/tty/hvc/hvc_console.h +++ b/drivers/tty/hvc/hvc_console.h @@ -66,7 +66,7 @@ struct hv_ops { int (*tiocmset)(struct hvc_struct *hp, unsigned int set, unsigned int clear); /* Callbacks to handle tty ports */ - void (*dtr_rts)(struct hvc_struct *hp, bool raise); + void (*dtr_rts)(struct hvc_struct *hp, bool active); }; /* Register a vterm and a slot index for use as a console (console_init) */ diff --git a/drivers/tty/hvc/hvc_iucv.c b/drivers/tty/hvc/hvc_iucv.c index fe862a6882d6..543f35ddf523 100644 --- a/drivers/tty/hvc/hvc_iucv.c +++ b/drivers/tty/hvc/hvc_iucv.c @@ -658,13 +658,13 @@ static void hvc_iucv_notifier_hangup(struct hvc_struct *hp, int id) /** * hvc_iucv_dtr_rts() - HVC notifier for handling DTR/RTS * @hp: Pointer the HVC device (struct hvc_struct) - * @raise: True to raise or false to lower DTR/RTS lines + * @active: True to raise or false to lower DTR/RTS lines * * This routine notifies the HVC back-end to raise or lower DTR/RTS * lines. Raising DTR/RTS is ignored. Lowering DTR/RTS indicates to * drop the IUCV connection (similar to hang up the modem). */ -static void hvc_iucv_dtr_rts(struct hvc_struct *hp, bool raise) +static void hvc_iucv_dtr_rts(struct hvc_struct *hp, bool active) { struct hvc_iucv_private *priv; struct iucv_path *path; @@ -672,7 +672,7 @@ static void hvc_iucv_dtr_rts(struct hvc_struct *hp, bool raise) /* Raising the DTR/RTS is ignored as IUCV connections can be * established at any times. */ - if (raise) + if (active) return; priv = hvc_iucv_get_private(hp->vtermno); diff --git a/drivers/tty/mxser.c b/drivers/tty/mxser.c index d4fb11e39bb1..ef3116e87975 100644 --- a/drivers/tty/mxser.c +++ b/drivers/tty/mxser.c @@ -465,7 +465,7 @@ static bool mxser_carrier_raised(struct tty_port *port) return inb(mp->ioaddr + UART_MSR) & UART_MSR_DCD; } -static void mxser_dtr_rts(struct tty_port *port, bool on) +static void mxser_dtr_rts(struct tty_port *port, bool active) { struct mxser_port *mp = container_of(port, struct mxser_port, port); unsigned long flags; @@ -473,7 +473,7 @@ static void mxser_dtr_rts(struct tty_port *port, bool on) spin_lock_irqsave(&mp->slock, flags); mcr = inb(mp->ioaddr + UART_MCR); - if (on) + if (active) mcr |= UART_MCR_DTR | UART_MCR_RTS; else mcr &= ~(UART_MCR_DTR | UART_MCR_RTS); diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c index 12b734b1b556..5783801d6524 100644 --- a/drivers/tty/n_gsm.c +++ b/drivers/tty/n_gsm.c @@ -3792,11 +3792,11 @@ static bool gsm_carrier_raised(struct tty_port *port) return dlci->modem_rx & TIOCM_CD; } -static void gsm_dtr_rts(struct tty_port *port, bool onoff) +static void gsm_dtr_rts(struct tty_port *port, bool active) { struct gsm_dlci *dlci = container_of(port, struct gsm_dlci, port); unsigned int modem_tx = dlci->modem_tx; - if (onoff) + if (active) modem_tx |= TIOCM_DTR | TIOCM_RTS; else modem_tx &= ~(TIOCM_DTR | TIOCM_RTS); diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index 371440faa14c..8633252339f4 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -169,9 +169,9 @@ uart_update_mctrl(struct uart_port *port, unsigned int set, unsigned int clear) #define uart_set_mctrl(port, set) uart_update_mctrl(port, set, 0) #define uart_clear_mctrl(port, clear) uart_update_mctrl(port, 0, clear) -static void uart_port_dtr_rts(struct uart_port *uport, bool raise) +static void uart_port_dtr_rts(struct uart_port *uport, bool active) { - if (raise) + if (active) uart_set_mctrl(uport, TIOCM_DTR | TIOCM_RTS); else uart_clear_mctrl(uport, TIOCM_DTR | TIOCM_RTS); @@ -1885,7 +1885,7 @@ static bool uart_carrier_raised(struct tty_port *port) return mctrl & TIOCM_CAR; } -static void uart_dtr_rts(struct tty_port *port, bool raise) +static void uart_dtr_rts(struct tty_port *port, bool active) { struct uart_state *state = container_of(port, struct uart_state, port); struct uart_port *uport; @@ -1893,7 +1893,7 @@ static void uart_dtr_rts(struct tty_port *port, bool raise) uport = uart_port_ref(state); if (!uport) return; - uart_port_dtr_rts(uport, raise); + uart_port_dtr_rts(uport, active); uart_port_deref(uport); } diff --git a/drivers/tty/synclink_gt.c b/drivers/tty/synclink_gt.c index 2b786265ce7b..33f258d6fef9 100644 --- a/drivers/tty/synclink_gt.c +++ b/drivers/tty/synclink_gt.c @@ -3138,13 +3138,13 @@ static bool carrier_raised(struct tty_port *port) return info->signals & SerialSignal_DCD; } -static void dtr_rts(struct tty_port *port, bool on) +static void dtr_rts(struct tty_port *port, bool active) { unsigned long flags; struct slgt_info *info = container_of(port, struct slgt_info, port); spin_lock_irqsave(&info->lock,flags); - if (on) + if (active) info->signals |= SerialSignal_RTS | SerialSignal_DTR; else info->signals &= ~(SerialSignal_RTS | SerialSignal_DTR); diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index d4f9220b8162..11da5fb284d0 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -651,13 +651,13 @@ static int acm_tty_open(struct tty_struct *tty, struct file *filp) return tty_port_open(&acm->port, tty, filp); } -static void acm_port_dtr_rts(struct tty_port *port, bool raise) +static void acm_port_dtr_rts(struct tty_port *port, bool active) { struct acm *acm = container_of(port, struct acm, port); int val; int res; - if (raise) + if (active) val = USB_CDC_CTRL_DTR | USB_CDC_CTRL_RTS; else val = 0; diff --git a/include/linux/tty_port.h b/include/linux/tty_port.h index c44e489de0ff..edf685a24f7c 100644 --- a/include/linux/tty_port.h +++ b/include/linux/tty_port.h @@ -16,7 +16,7 @@ struct tty_struct; /** * struct tty_port_operations -- operations on tty_port * @carrier_raised: return true if the carrier is raised on @port - * @dtr_rts: raise the DTR line if @raise is true, otherwise lower DTR + * @dtr_rts: raise the DTR line if @active is true, otherwise lower DTR * @shutdown: called when the last close completes or a hangup finishes IFF the * port was initialized. Do not use to free resources. Turn off the device * only. Called under the port mutex to serialize against @activate and @@ -32,7 +32,7 @@ struct tty_struct; */ struct tty_port_operations { bool (*carrier_raised)(struct tty_port *port); - void (*dtr_rts)(struct tty_port *port, bool raise); + void (*dtr_rts)(struct tty_port *port, bool active); void (*shutdown)(struct tty_port *port); int (*activate)(struct tty_port *port, struct tty_struct *tty); void (*destruct)(struct tty_port *port); -- cgit v1.2.3 From 4747ab89b4a652f835494fcf8342aaa0efb9b0fd Mon Sep 17 00:00:00 2001 From: Matthew Gerlach Date: Sun, 15 Jan 2023 07:14:46 -0800 Subject: fpga: dfl: add basic support for DFHv1 Version 1 of the Device Feature Header (DFH) definition adds functionality to the Device Feature List (DFL) bus. A DFHv1 header may have one or more parameter blocks that further describes the HW to SW. Add support to the DFL bus to parse the MSI-X parameter. The location of a feature's register set is explicitly described in DFHv1 and can be relative to the base of the DFHv1 or an absolute address. Parse the location and pass the information to DFL driver. Signed-off-by: Matthew Gerlach Reviewed-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20230115151447.1353428-4-matthew.gerlach@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/fpga/dfl.c | 245 +++++++++++++++++++++++++++++++++++++++++----------- drivers/fpga/dfl.h | 11 +++ include/linux/dfl.h | 8 ++ 3 files changed, 213 insertions(+), 51 deletions(-) (limited to 'include/linux') diff --git a/drivers/fpga/dfl.c b/drivers/fpga/dfl.c index b9aae85ba930..0a4227bc9462 100644 --- a/drivers/fpga/dfl.c +++ b/drivers/fpga/dfl.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include "dfl.h" @@ -342,6 +343,8 @@ static void release_dfl_dev(struct device *dev) if (ddev->mmio_res.parent) release_resource(&ddev->mmio_res); + kfree(ddev->params); + ida_free(&dfl_device_ida, ddev->id); kfree(ddev->irqs); kfree(ddev); @@ -380,7 +383,16 @@ dfl_dev_add(struct dfl_feature_platform_data *pdata, ddev->type = feature_dev_id_type(pdev); ddev->feature_id = feature->id; ddev->revision = feature->revision; + ddev->dfh_version = feature->dfh_version; ddev->cdev = pdata->dfl_cdev; + if (feature->param_size) { + ddev->params = kmemdup(feature->params, feature->param_size, GFP_KERNEL); + if (!ddev->params) { + ret = -ENOMEM; + goto put_dev; + } + ddev->param_size = feature->param_size; + } /* add mmio resource */ parent_res = &pdev->resource[feature->resource_index]; @@ -708,20 +720,27 @@ struct build_feature_devs_info { * struct dfl_feature_info - sub feature info collected during feature dev build * * @fid: id of this sub feature. + * @revision: revision of this sub feature + * @dfh_version: version of Device Feature Header (DFH) * @mmio_res: mmio resource of this sub feature. * @ioaddr: mapped base address of mmio resource. * @node: node in sub_features linked list. * @irq_base: start of irq index in this sub feature. * @nr_irqs: number of irqs of this sub feature. + * @param_size: size DFH parameters. + * @params: DFH parameter data. */ struct dfl_feature_info { u16 fid; u8 revision; + u8 dfh_version; struct resource mmio_res; void __iomem *ioaddr; struct list_head node; unsigned int irq_base; unsigned int nr_irqs; + unsigned int param_size; + u64 params[]; }; static void dfl_fpga_cdev_add_port_dev(struct dfl_fpga_cdev *cdev, @@ -797,7 +816,17 @@ static int build_info_commit_dev(struct build_feature_devs_info *binfo) feature->dev = fdev; feature->id = finfo->fid; feature->revision = finfo->revision; + feature->dfh_version = finfo->dfh_version; + if (finfo->param_size) { + feature->params = devm_kmemdup(binfo->dev, + finfo->params, finfo->param_size, + GFP_KERNEL); + if (!feature->params) + return -ENOMEM; + + feature->param_size = finfo->param_size; + } /* * the FIU header feature has some fundamental functions (sriov * set, port enable/disable) needed for the dfl bus device and @@ -934,56 +963,115 @@ static u16 feature_id(u64 value) return 0; } +static u64 *find_param(u64 *params, resource_size_t max, int param_id) +{ + u64 *end = params + max / sizeof(u64); + u64 v, next; + + while (params < end) { + v = *params; + if (param_id == FIELD_GET(DFHv1_PARAM_HDR_ID, v)) + return params; + + if (FIELD_GET(DFHv1_PARAM_HDR_NEXT_EOP, v)) + break; + + next = FIELD_GET(DFHv1_PARAM_HDR_NEXT_OFFSET, v); + params += next; + } + + return NULL; +} + +/** + * dfh_find_param() - find parameter block for the given parameter id + * @dfl_dev: dfl device + * @param_id: id of dfl parameter + * @psize: destination to store size of parameter data in bytes + * + * Return: pointer to start of parameter data, PTR_ERR otherwise. + */ +void *dfh_find_param(struct dfl_device *dfl_dev, int param_id, size_t *psize) +{ + u64 *phdr = find_param(dfl_dev->params, dfl_dev->param_size, param_id); + + if (!phdr) + return ERR_PTR(-ENOENT); + + if (psize) + *psize = (FIELD_GET(DFHv1_PARAM_HDR_NEXT_OFFSET, *phdr) - 1) * sizeof(u64); + + return phdr + 1; +} +EXPORT_SYMBOL_GPL(dfh_find_param); + static int parse_feature_irqs(struct build_feature_devs_info *binfo, - resource_size_t ofst, u16 fid, - unsigned int *irq_base, unsigned int *nr_irqs) + resource_size_t ofst, struct dfl_feature_info *finfo) { void __iomem *base = binfo->ioaddr + ofst; unsigned int i, ibase, inr = 0; + void *params = finfo->params; enum dfl_id_type type; + u16 fid = finfo->fid; int virq; + u64 *p; u64 v; - type = feature_dev_id_type(binfo->feature_dev); + switch (finfo->dfh_version) { + case 0: + /* + * DFHv0 only provides MMIO resource information for each feature + * in the DFL header. There is no generic interrupt information. + * Instead, features with interrupt functionality provide + * the information in feature specific registers. + */ + type = feature_dev_id_type(binfo->feature_dev); + if (type == PORT_ID) { + switch (fid) { + case PORT_FEATURE_ID_UINT: + v = readq(base + PORT_UINT_CAP); + ibase = FIELD_GET(PORT_UINT_CAP_FST_VECT, v); + inr = FIELD_GET(PORT_UINT_CAP_INT_NUM, v); + break; + case PORT_FEATURE_ID_ERROR: + v = readq(base + PORT_ERROR_CAP); + ibase = FIELD_GET(PORT_ERROR_CAP_INT_VECT, v); + inr = FIELD_GET(PORT_ERROR_CAP_SUPP_INT, v); + break; + } + } else if (type == FME_ID) { + switch (fid) { + case FME_FEATURE_ID_GLOBAL_ERR: + v = readq(base + FME_ERROR_CAP); + ibase = FIELD_GET(FME_ERROR_CAP_INT_VECT, v); + inr = FIELD_GET(FME_ERROR_CAP_SUPP_INT, v); + break; + } + } + break; - /* - * Ideally DFL framework should only read info from DFL header, but - * current version DFL only provides mmio resources information for - * each feature in DFL Header, no field for interrupt resources. - * Interrupt resource information is provided by specific mmio - * registers of each private feature which supports interrupt. So in - * order to parse and assign irq resources, DFL framework has to look - * into specific capability registers of these private features. - * - * Once future DFL version supports generic interrupt resource - * information in common DFL headers, the generic interrupt parsing - * code will be added. But in order to be compatible to old version - * DFL, the driver may still fall back to these quirks. - */ - if (type == PORT_ID) { - switch (fid) { - case PORT_FEATURE_ID_UINT: - v = readq(base + PORT_UINT_CAP); - ibase = FIELD_GET(PORT_UINT_CAP_FST_VECT, v); - inr = FIELD_GET(PORT_UINT_CAP_INT_NUM, v); - break; - case PORT_FEATURE_ID_ERROR: - v = readq(base + PORT_ERROR_CAP); - ibase = FIELD_GET(PORT_ERROR_CAP_INT_VECT, v); - inr = FIELD_GET(PORT_ERROR_CAP_SUPP_INT, v); + case 1: + /* + * DFHv1 provides interrupt resource information in DFHv1 + * parameter blocks. + */ + p = find_param(params, finfo->param_size, DFHv1_PARAM_ID_MSI_X); + if (!p) break; - } - } else if (type == FME_ID) { - if (fid == FME_FEATURE_ID_GLOBAL_ERR) { - v = readq(base + FME_ERROR_CAP); - ibase = FIELD_GET(FME_ERROR_CAP_INT_VECT, v); - inr = FIELD_GET(FME_ERROR_CAP_SUPP_INT, v); - } + + p++; + ibase = FIELD_GET(DFHv1_PARAM_MSI_X_STARTV, *p); + inr = FIELD_GET(DFHv1_PARAM_MSI_X_NUMV, *p); + break; + + default: + dev_warn(binfo->dev, "unexpected DFH version %d\n", finfo->dfh_version); + break; } if (!inr) { - *irq_base = 0; - *nr_irqs = 0; + finfo->irq_base = 0; + finfo->nr_irqs = 0; return 0; } @@ -1006,12 +1094,37 @@ static int parse_feature_irqs(struct build_feature_devs_info *binfo, } } - *irq_base = ibase; - *nr_irqs = inr; + finfo->irq_base = ibase; + finfo->nr_irqs = inr; return 0; } +static int dfh_get_param_size(void __iomem *dfh_base, resource_size_t max) +{ + int size = 0; + u64 v, next; + + if (!FIELD_GET(DFHv1_CSR_SIZE_GRP_HAS_PARAMS, + readq(dfh_base + DFHv1_CSR_SIZE_GRP))) + return 0; + + while (size + DFHv1_PARAM_HDR < max) { + v = readq(dfh_base + DFHv1_PARAM_HDR + size); + + next = FIELD_GET(DFHv1_PARAM_HDR_NEXT_OFFSET, v); + if (!next) + return -EINVAL; + + size += next * sizeof(u64); + + if (FIELD_GET(DFHv1_PARAM_HDR_NEXT_EOP, v)) + return size; + } + + return -ENOENT; +} + /* * when create sub feature instances, for private features, it doesn't need * to provide resource size and feature id as they could be read from DFH @@ -1023,39 +1136,69 @@ static int create_feature_instance(struct build_feature_devs_info *binfo, resource_size_t ofst, resource_size_t size, u16 fid) { - unsigned int irq_base, nr_irqs; struct dfl_feature_info *finfo; + resource_size_t start, end; + int dfh_psize = 0; u8 revision = 0; + u64 v, addr_off; + u8 dfh_ver = 0; int ret; - u64 v; if (fid != FEATURE_ID_AFU) { v = readq(binfo->ioaddr + ofst); revision = FIELD_GET(DFH_REVISION, v); - + dfh_ver = FIELD_GET(DFH_VERSION, v); /* read feature size and id if inputs are invalid */ size = size ? size : feature_size(v); fid = fid ? fid : feature_id(v); + if (dfh_ver == 1) { + dfh_psize = dfh_get_param_size(binfo->ioaddr + ofst, size); + if (dfh_psize < 0) { + dev_err(binfo->dev, + "failed to read size of DFHv1 parameters %d\n", + dfh_psize); + return dfh_psize; + } + dev_dbg(binfo->dev, "dfhv1_psize %d\n", dfh_psize); + } } if (binfo->len - ofst < size) return -EINVAL; - ret = parse_feature_irqs(binfo, ofst, fid, &irq_base, &nr_irqs); - if (ret) - return ret; - - finfo = kzalloc(sizeof(*finfo), GFP_KERNEL); + finfo = kzalloc(struct_size(finfo, params, dfh_psize / sizeof(u64)), GFP_KERNEL); if (!finfo) return -ENOMEM; + memcpy_fromio(finfo->params, binfo->ioaddr + ofst + DFHv1_PARAM_HDR, dfh_psize); + finfo->param_size = dfh_psize; + finfo->fid = fid; finfo->revision = revision; - finfo->mmio_res.start = binfo->start + ofst; - finfo->mmio_res.end = finfo->mmio_res.start + size - 1; + finfo->dfh_version = dfh_ver; + if (dfh_ver == 1) { + v = readq(binfo->ioaddr + ofst + DFHv1_CSR_ADDR); + addr_off = FIELD_GET(DFHv1_CSR_ADDR_MASK, v); + if (FIELD_GET(DFHv1_CSR_ADDR_REL, v)) + start = addr_off << 1; + else + start = binfo->start + ofst + addr_off; + + v = readq(binfo->ioaddr + ofst + DFHv1_CSR_SIZE_GRP); + end = start + FIELD_GET(DFHv1_CSR_SIZE_GRP_SIZE, v) - 1; + } else { + start = binfo->start + ofst; + end = start + size - 1; + } finfo->mmio_res.flags = IORESOURCE_MEM; - finfo->irq_base = irq_base; - finfo->nr_irqs = nr_irqs; + finfo->mmio_res.start = start; + finfo->mmio_res.end = end; + + ret = parse_feature_irqs(binfo, ofst, finfo); + if (ret) { + kfree(finfo); + return ret; + } list_add_tail(&finfo->node, &binfo->sub_features); binfo->feature_num++; diff --git a/drivers/fpga/dfl.h b/drivers/fpga/dfl.h index fc59f33367ee..20eaddce6988 100644 --- a/drivers/fpga/dfl.h +++ b/drivers/fpga/dfl.h @@ -111,6 +111,10 @@ #define DFHv1_PARAM_HDR_NEXT_EOP BIT_ULL(32) #define DFHv1_PARAM_DATA 0x08 /* Offset of Param data from Param header */ +#define DFHv1_PARAM_ID_MSI_X 0x1 +#define DFHv1_PARAM_MSI_X_NUMV GENMASK_ULL(63, 32) +#define DFHv1_PARAM_MSI_X_STARTV GENMASK_ULL(31, 0) + /* Next AFU Register Bitfield */ #define NEXT_AFU_NEXT_DFH_OFST GENMASK_ULL(23, 0) /* Offset to next AFU */ @@ -263,6 +267,7 @@ struct dfl_feature_irq_ctx { * * @dev: ptr to pdev of the feature device which has the sub feature. * @id: sub feature id. + * @revision: revisition of the instance of a feature. * @resource_index: each sub feature has one mmio resource for its registers. * this index is used to find its mmio resource from the * feature dev (platform device)'s resources. @@ -272,6 +277,9 @@ struct dfl_feature_irq_ctx { * @ops: ops of this sub feature. * @ddev: ptr to the dfl device of this sub feature. * @priv: priv data of this feature. + * @dfh_version: version of the DFH + * @param_size: size of dfh parameters + * @params: point to memory copy of dfh parameters */ struct dfl_feature { struct platform_device *dev; @@ -284,6 +292,9 @@ struct dfl_feature { const struct dfl_feature_ops *ops; struct dfl_device *ddev; void *priv; + u8 dfh_version; + unsigned int param_size; + void *params; }; #define FEATURE_DEV_ID_UNUSED (-1) diff --git a/include/linux/dfl.h b/include/linux/dfl.h index 431636a0dc78..0a7a00a0ee7f 100644 --- a/include/linux/dfl.h +++ b/include/linux/dfl.h @@ -27,11 +27,15 @@ enum dfl_id_type { * @id: id of the dfl device. * @type: type of DFL FIU of the device. See enum dfl_id_type. * @feature_id: feature identifier local to its DFL FIU type. + * @revision: revision of this dfl device feature. * @mmio_res: mmio resource of this dfl device. * @irqs: list of Linux IRQ numbers of this dfl device. * @num_irqs: number of IRQs supported by this dfl device. * @cdev: pointer to DFL FPGA container device this dfl device belongs to. * @id_entry: matched id entry in dfl driver's id table. + * @dfh_version: version of DFH for the device + * @param_size: size of the block parameters in bytes + * @params: pointer to block of parameters copied memory */ struct dfl_device { struct device dev; @@ -44,6 +48,9 @@ struct dfl_device { unsigned int num_irqs; struct dfl_fpga_cdev *cdev; const struct dfl_device_id *id_entry; + u8 dfh_version; + unsigned int param_size; + void *params; }; /** @@ -84,4 +91,5 @@ void dfl_driver_unregister(struct dfl_driver *dfl_drv); module_driver(__dfl_driver, dfl_driver_register, \ dfl_driver_unregister) +void *dfh_find_param(struct dfl_device *dfl_dev, int param_id, size_t *pcount); #endif /* __LINUX_DFL_H */ -- cgit v1.2.3 From ffc1e089725e3f8a15ddfdce283db42f7d0fa147 Mon Sep 17 00:00:00 2001 From: Samuel Thibault Date: Thu, 19 Jan 2023 16:19:15 +0100 Subject: VT: Add height parameter to con_font_get/set consw operations The current con_font_get/set API currently hardcodes a 32-pixel-tall limitation, which only dates from the old VGA hardware which could not handle taller fonts than that. This change just adds a vpitch parameter to release this constraint. Drivers which do not support vpitch != 32 can just return EINVAL when it is not 32, font loading tools will revert to trying 32 and succeed. This change makes the fbcon driver consider vpitch appropriately, thus making it able to load large fonts. Signed-off-by: Samuel Thibault Link: https://lore.kernel.org/r/20230119151934.932642243@ens-lyon.org Signed-off-by: Greg Kroah-Hartman --- drivers/tty/vt/vt.c | 4 ++-- drivers/video/console/newport_con.c | 9 +++++---- drivers/video/console/sticon.c | 9 +++++---- drivers/video/console/vgacon.c | 8 ++++---- drivers/video/fbdev/core/fbcon.c | 33 +++++++++++++-------------------- include/linux/console.h | 5 +++-- 6 files changed, 32 insertions(+), 36 deletions(-) (limited to 'include/linux') diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index 71f182416835..268d0f57fdd4 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -4552,7 +4552,7 @@ static int con_font_get(struct vc_data *vc, struct console_font_op *op) if (vc->vc_mode != KD_TEXT) rc = -EINVAL; else if (vc->vc_sw->con_font_get) - rc = vc->vc_sw->con_font_get(vc, &font); + rc = vc->vc_sw->con_font_get(vc, &font, 32); else rc = -ENOSYS; console_unlock(); @@ -4613,7 +4613,7 @@ static int con_font_set(struct vc_data *vc, struct console_font_op *op) else if (vc->vc_sw->con_font_set) { if (vc_is_sel(vc)) clear_selection(); - rc = vc->vc_sw->con_font_set(vc, &font, op->flags); + rc = vc->vc_sw->con_font_set(vc, &font, 32, op->flags); } else rc = -ENOSYS; console_unlock(); diff --git a/drivers/video/console/newport_con.c b/drivers/video/console/newport_con.c index d9c682ae0392..e8e4f82cd4a1 100644 --- a/drivers/video/console/newport_con.c +++ b/drivers/video/console/newport_con.c @@ -497,7 +497,7 @@ static int newport_blank(struct vc_data *c, int blank, int mode_switch) return 1; } -static int newport_set_font(int unit, struct console_font *op) +static int newport_set_font(int unit, struct console_font *op, unsigned int vpitch) { int w = op->width; int h = op->height; @@ -507,7 +507,7 @@ static int newport_set_font(int unit, struct console_font *op) /* ladis: when I grow up, there will be a day... and more sizes will * be supported ;-) */ - if ((w != 8) || (h != 16) + if ((w != 8) || (h != 16) || (vpitch != 32) || (op->charcount != 256 && op->charcount != 512)) return -EINVAL; @@ -569,9 +569,10 @@ static int newport_font_default(struct vc_data *vc, struct console_font *op, cha return newport_set_def_font(vc->vc_num, op); } -static int newport_font_set(struct vc_data *vc, struct console_font *font, unsigned flags) +static int newport_font_set(struct vc_data *vc, struct console_font *font, + unsigned int vpitch, unsigned int flags) { - return newport_set_font(vc->vc_num, font); + return newport_set_font(vc->vc_num, font, vpitch); } static bool newport_scroll(struct vc_data *vc, unsigned int t, unsigned int b, diff --git a/drivers/video/console/sticon.c b/drivers/video/console/sticon.c index f304163e87e9..2cea69418a83 100644 --- a/drivers/video/console/sticon.c +++ b/drivers/video/console/sticon.c @@ -169,7 +169,8 @@ static int sticon_set_def_font(int unit, struct console_font *op) return 0; } -static int sticon_set_font(struct vc_data *vc, struct console_font *op) +static int sticon_set_font(struct vc_data *vc, struct console_font *op, + unsigned int vpitch) { struct sti_struct *sti = sticon_sti; int vc_cols, vc_rows, vc_old_cols, vc_old_rows; @@ -181,7 +182,7 @@ static int sticon_set_font(struct vc_data *vc, struct console_font *op) struct sti_cooked_font *cooked_font; unsigned char *data = op->data, *p; - if ((w < 6) || (h < 6) || (w > 32) || (h > 32) + if ((w < 6) || (h < 6) || (w > 32) || (h > 32) || (vpitch != 32) || (op->charcount != 256 && op->charcount != 512)) return -EINVAL; pitch = ALIGN(w, 8) / 8; @@ -267,9 +268,9 @@ static int sticon_font_default(struct vc_data *vc, struct console_font *op, char } static int sticon_font_set(struct vc_data *vc, struct console_font *font, - unsigned int flags) + unsigned int vpitch, unsigned int flags) { - return sticon_set_font(vc, font); + return sticon_set_font(vc, font, vpitch); } static void sticon_init(struct vc_data *c, int init) diff --git a/drivers/video/console/vgacon.c b/drivers/video/console/vgacon.c index fcdf017e2665..03c2cce71c0c 100644 --- a/drivers/video/console/vgacon.c +++ b/drivers/video/console/vgacon.c @@ -1029,7 +1029,7 @@ static int vgacon_adjust_height(struct vc_data *vc, unsigned fontheight) } static int vgacon_font_set(struct vc_data *c, struct console_font *font, - unsigned int flags) + unsigned int vpitch, unsigned int flags) { unsigned charcount = font->charcount; int rc; @@ -1037,7 +1037,7 @@ static int vgacon_font_set(struct vc_data *c, struct console_font *font, if (vga_video_type < VIDEO_TYPE_EGAM) return -EINVAL; - if (font->width != VGA_FONTWIDTH || + if (font->width != VGA_FONTWIDTH || vpitch != 32 || (charcount != 256 && charcount != 512)) return -EINVAL; @@ -1050,9 +1050,9 @@ static int vgacon_font_set(struct vc_data *c, struct console_font *font, return rc; } -static int vgacon_font_get(struct vc_data *c, struct console_font *font) +static int vgacon_font_get(struct vc_data *c, struct console_font *font, unsigned int vpitch) { - if (vga_video_type < VIDEO_TYPE_EGAM) + if (vga_video_type < VIDEO_TYPE_EGAM || vpitch != 32) return -EINVAL; font->width = VGA_FONTWIDTH; diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c index 14a7d404062c..7cd7346bbc9a 100644 --- a/drivers/video/fbdev/core/fbcon.c +++ b/drivers/video/fbdev/core/fbcon.c @@ -2271,7 +2271,7 @@ static int fbcon_debug_leave(struct vc_data *vc) return 0; } -static int fbcon_get_font(struct vc_data *vc, struct console_font *font) +static int fbcon_get_font(struct vc_data *vc, struct console_font *font, unsigned int vpitch) { u8 *fontdata = vc->vc_font.data; u8 *data = font->data; @@ -2290,8 +2290,8 @@ static int fbcon_get_font(struct vc_data *vc, struct console_font *font) for (i = 0; i < font->charcount; i++) { memcpy(data, fontdata, j); - memset(data + j, 0, 32 - j); - data += 32; + memset(data + j, 0, vpitch - j); + data += vpitch; fontdata += j; } } else if (font->width <= 16) { @@ -2301,8 +2301,8 @@ static int fbcon_get_font(struct vc_data *vc, struct console_font *font) for (i = 0; i < font->charcount; i++) { memcpy(data, fontdata, j); - memset(data + j, 0, 64 - j); - data += 64; + memset(data + j, 0, 2*vpitch - j); + data += 2*vpitch; fontdata += j; } } else if (font->width <= 24) { @@ -2316,8 +2316,8 @@ static int fbcon_get_font(struct vc_data *vc, struct console_font *font) *data++ = fontdata[2]; fontdata += sizeof(u32); } - memset(data, 0, 3 * (32 - j)); - data += 3 * (32 - j); + memset(data, 0, 3 * (vpitch - j)); + data += 3 * (vpitch - j); } } else { j = vc->vc_font.height * 4; @@ -2326,8 +2326,8 @@ static int fbcon_get_font(struct vc_data *vc, struct console_font *font) for (i = 0; i < font->charcount; i++) { memcpy(data, fontdata, j); - memset(data + j, 0, 128 - j); - data += 128; + memset(data + j, 0, 4 * vpitch - j); + data += 4 * vpitch; fontdata += j; } } @@ -2462,19 +2462,12 @@ err_out: } /* - * User asked to set font; we are guaranteed that - * a) width and height are in range 1..32 - * b) charcount does not exceed 512 - * but lets not assume that, since someone might someday want to use larger - * fonts. And charcount of 512 is small for unicode support. - * - * However, user space gives the font in 32 rows , regardless of - * actual font height. So a new API is needed if support for larger fonts - * is ever implemented. + * User asked to set font; we are guaranteed that charcount does not exceed 512 + * but lets not assume that, since charcount of 512 is small for unicode support. */ static int fbcon_set_font(struct vc_data *vc, struct console_font *font, - unsigned int flags) + unsigned int vpitch, unsigned int flags) { struct fb_info *info = fbcon_info_from_console(vc->vc_num); unsigned charcount = font->charcount; @@ -2517,7 +2510,7 @@ static int fbcon_set_font(struct vc_data *vc, struct console_font *font, FNTSIZE(new_data) = size; REFCOUNT(new_data) = 0; /* usage counter */ for (i=0; i< charcount; i++) { - memcpy(new_data + i*h*pitch, data + i*32*pitch, h*pitch); + memcpy(new_data + i*h*pitch, data + i*vpitch*pitch, h*pitch); } /* Since linux has a nice crc32 function use it for counting font diff --git a/include/linux/console.h b/include/linux/console.h index 9cea254b34b8..9e52de94a583 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -59,8 +59,9 @@ struct consw { int (*con_switch)(struct vc_data *vc); int (*con_blank)(struct vc_data *vc, int blank, int mode_switch); int (*con_font_set)(struct vc_data *vc, struct console_font *font, - unsigned int flags); - int (*con_font_get)(struct vc_data *vc, struct console_font *font); + unsigned int vpitch, unsigned int flags); + int (*con_font_get)(struct vc_data *vc, struct console_font *font, + unsigned int vpitch); int (*con_font_default)(struct vc_data *vc, struct console_font *font, char *name); int (*con_resize)(struct vc_data *vc, unsigned int width, -- cgit v1.2.3 From e610e81464e4e52645a0f5d259b8a9e3632db6ff Mon Sep 17 00:00:00 2001 From: Garmin.Chang Date: Fri, 23 Dec 2022 16:05:53 +0800 Subject: soc: mediatek: pm-domains: Add support for mt8188 Add domain control data including bus protection data size change due to more protection steps in mt8188. Signed-off-by: Garmin.Chang Reviewed-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20221223080553.9397-3-Garmin.Chang@mediatek.com Signed-off-by: Matthias Brugger --- drivers/soc/mediatek/mt8188-pm-domains.h | 623 +++++++++++++++++++++++++++++++ drivers/soc/mediatek/mtk-pm-domains.c | 5 + include/linux/soc/mediatek/infracfg.h | 121 ++++++ 3 files changed, 749 insertions(+) create mode 100644 drivers/soc/mediatek/mt8188-pm-domains.h (limited to 'include/linux') diff --git a/drivers/soc/mediatek/mt8188-pm-domains.h b/drivers/soc/mediatek/mt8188-pm-domains.h new file mode 100644 index 000000000000..0692cb444ed0 --- /dev/null +++ b/drivers/soc/mediatek/mt8188-pm-domains.h @@ -0,0 +1,623 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2022 MediaTek Inc. + * Author: Garmin Chang + */ + +#ifndef __SOC_MEDIATEK_MT8188_PM_DOMAINS_H +#define __SOC_MEDIATEK_MT8188_PM_DOMAINS_H + +#include "mtk-pm-domains.h" +#include + +/* + * MT8188 power domain support + */ + +static const struct scpsys_domain_data scpsys_domain_data_mt8188[] = { + [MT8188_POWER_DOMAIN_MFG0] = { + .name = "mfg0", + .sta_mask = BIT(1), + .ctl_offs = 0x300, + .pwr_sta_offs = 0x174, + .pwr_sta2nd_offs = 0x178, + .sram_pdn_bits = BIT(8), + .sram_pdn_ack_bits = BIT(12), + .caps = MTK_SCPD_KEEP_DEFAULT_OFF | MTK_SCPD_DOMAIN_SUPPLY, + }, + [MT8188_POWER_DOMAIN_MFG1] = { + .name = "mfg1", + .sta_mask = BIT(2), + .ctl_offs = 0x304, + .pwr_sta_offs = 0x174, + .pwr_sta2nd_offs = 0x178, + .sram_pdn_bits = BIT(8), + .sram_pdn_ack_bits = BIT(12), + .bp_infracfg = { + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_MFG1_STEP1, + MT8188_TOP_AXI_PROT_EN_SET, + MT8188_TOP_AXI_PROT_EN_CLR, + MT8188_TOP_AXI_PROT_EN_STA), + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_2_MFG1_STEP2, + MT8188_TOP_AXI_PROT_EN_2_SET, + MT8188_TOP_AXI_PROT_EN_2_CLR, + MT8188_TOP_AXI_PROT_EN_2_STA), + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_1_MFG1_STEP3, + MT8188_TOP_AXI_PROT_EN_1_SET, + MT8188_TOP_AXI_PROT_EN_1_CLR, + MT8188_TOP_AXI_PROT_EN_1_STA), + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_2_MFG1_STEP4, + MT8188_TOP_AXI_PROT_EN_2_SET, + MT8188_TOP_AXI_PROT_EN_2_CLR, + MT8188_TOP_AXI_PROT_EN_2_STA), + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_MFG1_STEP5, + MT8188_TOP_AXI_PROT_EN_SET, + MT8188_TOP_AXI_PROT_EN_CLR, + MT8188_TOP_AXI_PROT_EN_STA), + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_SUB_INFRA_VDNR_MFG1_STEP6, + MT8188_TOP_AXI_PROT_EN_SUB_INFRA_VDNR_SET, + MT8188_TOP_AXI_PROT_EN_SUB_INFRA_VDNR_CLR, + MT8188_TOP_AXI_PROT_EN_SUB_INFRA_VDNR_STA), + }, + .caps = MTK_SCPD_KEEP_DEFAULT_OFF | MTK_SCPD_DOMAIN_SUPPLY, + }, + [MT8188_POWER_DOMAIN_MFG2] = { + .name = "mfg2", + .sta_mask = BIT(3), + .ctl_offs = 0x308, + .pwr_sta_offs = 0x174, + .pwr_sta2nd_offs = 0x178, + .sram_pdn_bits = BIT(8), + .sram_pdn_ack_bits = BIT(12), + .caps = MTK_SCPD_KEEP_DEFAULT_OFF, + }, + [MT8188_POWER_DOMAIN_MFG3] = { + .name = "mfg3", + .sta_mask = BIT(4), + .ctl_offs = 0x30C, + .pwr_sta_offs = 0x174, + .pwr_sta2nd_offs = 0x178, + .sram_pdn_bits = BIT(8), + .sram_pdn_ack_bits = BIT(12), + .caps = MTK_SCPD_KEEP_DEFAULT_OFF, + }, + [MT8188_POWER_DOMAIN_MFG4] = { + .name = "mfg4", + .sta_mask = BIT(5), + .ctl_offs = 0x310, + .pwr_sta_offs = 0x174, + .pwr_sta2nd_offs = 0x178, + .sram_pdn_bits = BIT(8), + .sram_pdn_ack_bits = BIT(12), + .caps = MTK_SCPD_KEEP_DEFAULT_OFF, + }, + [MT8188_POWER_DOMAIN_PEXTP_MAC_P0] = { + .name = "pextp_mac_p0", + .sta_mask = BIT(10), + .ctl_offs = 0x324, + .pwr_sta_offs = 0x174, + .pwr_sta2nd_offs = 0x178, + .sram_pdn_bits = BIT(8), + .sram_pdn_ack_bits = BIT(12), + .bp_infracfg = { + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_PEXTP_MAC_P0_STEP1, + MT8188_TOP_AXI_PROT_EN_SET, + MT8188_TOP_AXI_PROT_EN_CLR, + MT8188_TOP_AXI_PROT_EN_STA), + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_INFRA_VDNR_PEXTP_MAC_P0_STEP2, + MT8188_TOP_AXI_PROT_EN_INFRA_VDNR_SET, + MT8188_TOP_AXI_PROT_EN_INFRA_VDNR_CLR, + MT8188_TOP_AXI_PROT_EN_INFRA_VDNR_STA), + }, + .caps = MTK_SCPD_KEEP_DEFAULT_OFF, + }, + [MT8188_POWER_DOMAIN_PEXTP_PHY_TOP] = { + .name = "pextp_phy_top", + .sta_mask = BIT(12), + .ctl_offs = 0x328, + .pwr_sta_offs = 0x174, + .pwr_sta2nd_offs = 0x178, + .caps = MTK_SCPD_KEEP_DEFAULT_OFF, + }, + [MT8188_POWER_DOMAIN_CSIRX_TOP] = { + .name = "pextp_csirx_top", + .sta_mask = BIT(17), + .ctl_offs = 0x3C4, + .pwr_sta_offs = 0x174, + .pwr_sta2nd_offs = 0x178, + .caps = MTK_SCPD_KEEP_DEFAULT_OFF, + }, + [MT8188_POWER_DOMAIN_ETHER] = { + .name = "ether", + .sta_mask = BIT(1), + .ctl_offs = 0x338, + .pwr_sta_offs = 0x16C, + .pwr_sta2nd_offs = 0x170, + .sram_pdn_bits = BIT(8), + .sram_pdn_ack_bits = BIT(12), + .bp_infracfg = { + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_INFRA_VDNR_ETHER_STEP1, + MT8188_TOP_AXI_PROT_EN_INFRA_VDNR_SET, + MT8188_TOP_AXI_PROT_EN_INFRA_VDNR_CLR, + MT8188_TOP_AXI_PROT_EN_INFRA_VDNR_STA), + }, + .caps = MTK_SCPD_KEEP_DEFAULT_OFF | MTK_SCPD_ACTIVE_WAKEUP, + }, + [MT8188_POWER_DOMAIN_HDMI_TX] = { + .name = "hdmi_tx", + .sta_mask = BIT(18), + .ctl_offs = 0x37C, + .pwr_sta_offs = 0x16C, + .pwr_sta2nd_offs = 0x170, + .sram_pdn_bits = BIT(8), + .sram_pdn_ack_bits = BIT(12), + .bp_infracfg = { + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_INFRA_VDNR_HDMI_TX_STEP1, + MT8188_TOP_AXI_PROT_EN_INFRA_VDNR_SET, + MT8188_TOP_AXI_PROT_EN_INFRA_VDNR_CLR, + MT8188_TOP_AXI_PROT_EN_INFRA_VDNR_STA), + }, + .caps = MTK_SCPD_KEEP_DEFAULT_OFF | MTK_SCPD_ACTIVE_WAKEUP, + }, + [MT8188_POWER_DOMAIN_ADSP_AO] = { + .name = "adsp_ao", + .sta_mask = BIT(10), + .ctl_offs = 0x35C, + .pwr_sta_offs = 0x16C, + .pwr_sta2nd_offs = 0x170, + .bp_infracfg = { + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_2_ADSP_AO_STEP1, + MT8188_TOP_AXI_PROT_EN_2_SET, + MT8188_TOP_AXI_PROT_EN_2_CLR, + MT8188_TOP_AXI_PROT_EN_2_STA), + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_2_ADSP_AO_STEP2, + MT8188_TOP_AXI_PROT_EN_2_SET, + MT8188_TOP_AXI_PROT_EN_2_CLR, + MT8188_TOP_AXI_PROT_EN_2_STA), + }, + .caps = MTK_SCPD_ALWAYS_ON, + }, + [MT8188_POWER_DOMAIN_ADSP_INFRA] = { + .name = "adsp_infra", + .sta_mask = BIT(9), + .ctl_offs = 0x358, + .pwr_sta_offs = 0x16C, + .pwr_sta2nd_offs = 0x170, + .sram_pdn_bits = BIT(8), + .sram_pdn_ack_bits = BIT(12), + .bp_infracfg = { + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_2_ADSP_INFRA_STEP1, + MT8188_TOP_AXI_PROT_EN_2_SET, + MT8188_TOP_AXI_PROT_EN_2_CLR, + MT8188_TOP_AXI_PROT_EN_2_STA), + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_2_ADSP_INFRA_STEP2, + MT8188_TOP_AXI_PROT_EN_2_SET, + MT8188_TOP_AXI_PROT_EN_2_CLR, + MT8188_TOP_AXI_PROT_EN_2_STA), + }, + .caps = MTK_SCPD_SRAM_ISO | MTK_SCPD_ALWAYS_ON, + }, + [MT8188_POWER_DOMAIN_ADSP] = { + .name = "adsp", + .sta_mask = BIT(8), + .ctl_offs = 0x354, + .pwr_sta_offs = 0x16C, + .pwr_sta2nd_offs = 0x170, + .sram_pdn_bits = BIT(8), + .sram_pdn_ack_bits = BIT(12), + .bp_infracfg = { + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_2_ADSP_STEP1, + MT8188_TOP_AXI_PROT_EN_2_SET, + MT8188_TOP_AXI_PROT_EN_2_CLR, + MT8188_TOP_AXI_PROT_EN_2_STA), + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_2_ADSP_STEP2, + MT8188_TOP_AXI_PROT_EN_2_SET, + MT8188_TOP_AXI_PROT_EN_2_CLR, + MT8188_TOP_AXI_PROT_EN_2_STA), + }, + .caps = MTK_SCPD_KEEP_DEFAULT_OFF | MTK_SCPD_SRAM_ISO | MTK_SCPD_ACTIVE_WAKEUP, + }, + [MT8188_POWER_DOMAIN_AUDIO] = { + .name = "audio", + .sta_mask = BIT(6), + .ctl_offs = 0x34C, + .pwr_sta_offs = 0x16C, + .pwr_sta2nd_offs = 0x170, + .sram_pdn_bits = BIT(8), + .sram_pdn_ack_bits = BIT(12), + .bp_infracfg = { + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_2_AUDIO_STEP1, + MT8188_TOP_AXI_PROT_EN_2_SET, + MT8188_TOP_AXI_PROT_EN_2_CLR, + MT8188_TOP_AXI_PROT_EN_2_STA), + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_2_AUDIO_STEP2, + MT8188_TOP_AXI_PROT_EN_2_SET, + MT8188_TOP_AXI_PROT_EN_2_CLR, + MT8188_TOP_AXI_PROT_EN_2_STA), + }, + .caps = MTK_SCPD_KEEP_DEFAULT_OFF | MTK_SCPD_ACTIVE_WAKEUP, + }, + [MT8188_POWER_DOMAIN_AUDIO_ASRC] = { + .name = "audio_asrc", + .sta_mask = BIT(7), + .ctl_offs = 0x350, + .pwr_sta_offs = 0x16C, + .pwr_sta2nd_offs = 0x170, + .sram_pdn_bits = BIT(8), + .sram_pdn_ack_bits = BIT(12), + .bp_infracfg = { + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_2_AUDIO_ASRC_STEP1, + MT8188_TOP_AXI_PROT_EN_2_SET, + MT8188_TOP_AXI_PROT_EN_2_CLR, + MT8188_TOP_AXI_PROT_EN_2_STA), + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_2_AUDIO_ASRC_STEP2, + MT8188_TOP_AXI_PROT_EN_2_SET, + MT8188_TOP_AXI_PROT_EN_2_CLR, + MT8188_TOP_AXI_PROT_EN_2_STA), + }, + .caps = MTK_SCPD_KEEP_DEFAULT_OFF, + }, + [MT8188_POWER_DOMAIN_VPPSYS0] = { + .name = "vppsys0", + .sta_mask = BIT(11), + .ctl_offs = 0x360, + .pwr_sta_offs = 0x16C, + .pwr_sta2nd_offs = 0x170, + .sram_pdn_bits = BIT(8), + .sram_pdn_ack_bits = BIT(12), + .bp_infracfg = { + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_VPPSYS0_STEP1, + MT8188_TOP_AXI_PROT_EN_SET, + MT8188_TOP_AXI_PROT_EN_CLR, + MT8188_TOP_AXI_PROT_EN_STA), + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_MM_2_VPPSYS0_STEP2, + MT8188_TOP_AXI_PROT_EN_MM_2_SET, + MT8188_TOP_AXI_PROT_EN_MM_2_CLR, + MT8188_TOP_AXI_PROT_EN_MM_2_STA), + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_VPPSYS0_STEP3, + MT8188_TOP_AXI_PROT_EN_SET, + MT8188_TOP_AXI_PROT_EN_CLR, + MT8188_TOP_AXI_PROT_EN_STA), + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_MM_2_VPPSYS0_STEP4, + MT8188_TOP_AXI_PROT_EN_MM_2_SET, + MT8188_TOP_AXI_PROT_EN_MM_2_CLR, + MT8188_TOP_AXI_PROT_EN_MM_2_STA), + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_SUB_INFRA_VDNR_VPPSYS0_STEP5, + MT8188_TOP_AXI_PROT_EN_SUB_INFRA_VDNR_SET, + MT8188_TOP_AXI_PROT_EN_SUB_INFRA_VDNR_CLR, + MT8188_TOP_AXI_PROT_EN_SUB_INFRA_VDNR_STA), + }, + }, + [MT8188_POWER_DOMAIN_VDOSYS0] = { + .name = "vdosys0", + .sta_mask = BIT(13), + .ctl_offs = 0x368, + .pwr_sta_offs = 0x16C, + .pwr_sta2nd_offs = 0x170, + .sram_pdn_bits = BIT(8), + .sram_pdn_ack_bits = BIT(12), + .bp_infracfg = { + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_MM_VDOSYS0_STEP1, + MT8188_TOP_AXI_PROT_EN_MM_SET, + MT8188_TOP_AXI_PROT_EN_MM_CLR, + MT8188_TOP_AXI_PROT_EN_MM_STA), + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_VDOSYS0_STEP2, + MT8188_TOP_AXI_PROT_EN_SET, + MT8188_TOP_AXI_PROT_EN_CLR, + MT8188_TOP_AXI_PROT_EN_STA), + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_SUB_INFRA_VDNR_VDOSYS0_STEP3, + MT8188_TOP_AXI_PROT_EN_SUB_INFRA_VDNR_SET, + MT8188_TOP_AXI_PROT_EN_SUB_INFRA_VDNR_CLR, + MT8188_TOP_AXI_PROT_EN_SUB_INFRA_VDNR_STA), + }, + }, + [MT8188_POWER_DOMAIN_VDOSYS1] = { + .name = "vdosys1", + .sta_mask = BIT(14), + .ctl_offs = 0x36C, + .pwr_sta_offs = 0x16C, + .pwr_sta2nd_offs = 0x170, + .sram_pdn_bits = BIT(8), + .sram_pdn_ack_bits = BIT(12), + .bp_infracfg = { + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_MM_VDOSYS1_STEP1, + MT8188_TOP_AXI_PROT_EN_MM_SET, + MT8188_TOP_AXI_PROT_EN_MM_CLR, + MT8188_TOP_AXI_PROT_EN_MM_STA), + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_MM_VDOSYS1_STEP2, + MT8188_TOP_AXI_PROT_EN_MM_SET, + MT8188_TOP_AXI_PROT_EN_MM_CLR, + MT8188_TOP_AXI_PROT_EN_MM_STA), + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_MM_2_VDOSYS1_STEP3, + MT8188_TOP_AXI_PROT_EN_MM_2_SET, + MT8188_TOP_AXI_PROT_EN_MM_2_CLR, + MT8188_TOP_AXI_PROT_EN_MM_2_STA), + }, + }, + [MT8188_POWER_DOMAIN_DP_TX] = { + .name = "dp_tx", + .sta_mask = BIT(16), + .ctl_offs = 0x374, + .pwr_sta_offs = 0x16C, + .pwr_sta2nd_offs = 0x170, + .sram_pdn_bits = BIT(8), + .sram_pdn_ack_bits = BIT(12), + .bp_infracfg = { + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_INFRA_VDNR_DP_TX_STEP1, + MT8188_TOP_AXI_PROT_EN_INFRA_VDNR_SET, + MT8188_TOP_AXI_PROT_EN_INFRA_VDNR_CLR, + MT8188_TOP_AXI_PROT_EN_INFRA_VDNR_STA), + }, + .caps = MTK_SCPD_KEEP_DEFAULT_OFF, + }, + [MT8188_POWER_DOMAIN_EDP_TX] = { + .name = "edp_tx", + .sta_mask = BIT(17), + .ctl_offs = 0x378, + .pwr_sta_offs = 0x16C, + .pwr_sta2nd_offs = 0x170, + .sram_pdn_bits = BIT(8), + .sram_pdn_ack_bits = BIT(12), + .bp_infracfg = { + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_INFRA_VDNR_EDP_TX_STEP1, + MT8188_TOP_AXI_PROT_EN_INFRA_VDNR_SET, + MT8188_TOP_AXI_PROT_EN_INFRA_VDNR_CLR, + MT8188_TOP_AXI_PROT_EN_INFRA_VDNR_STA), + }, + .caps = MTK_SCPD_KEEP_DEFAULT_OFF, + }, + [MT8188_POWER_DOMAIN_VPPSYS1] = { + .name = "vppsys1", + .sta_mask = BIT(12), + .ctl_offs = 0x364, + .pwr_sta_offs = 0x16C, + .pwr_sta2nd_offs = 0x170, + .sram_pdn_bits = BIT(8), + .sram_pdn_ack_bits = BIT(12), + .bp_infracfg = { + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_MM_VPPSYS1_STEP1, + MT8188_TOP_AXI_PROT_EN_MM_SET, + MT8188_TOP_AXI_PROT_EN_MM_CLR, + MT8188_TOP_AXI_PROT_EN_MM_STA), + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_MM_VPPSYS1_STEP2, + MT8188_TOP_AXI_PROT_EN_MM_SET, + MT8188_TOP_AXI_PROT_EN_MM_CLR, + MT8188_TOP_AXI_PROT_EN_MM_STA), + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_MM_2_VPPSYS1_STEP3, + MT8188_TOP_AXI_PROT_EN_MM_2_SET, + MT8188_TOP_AXI_PROT_EN_MM_2_CLR, + MT8188_TOP_AXI_PROT_EN_MM_2_STA), + }, + }, + [MT8188_POWER_DOMAIN_WPE] = { + .name = "wpe", + .sta_mask = BIT(15), + .ctl_offs = 0x370, + .pwr_sta_offs = 0x16C, + .pwr_sta2nd_offs = 0x170, + .sram_pdn_bits = BIT(8), + .sram_pdn_ack_bits = BIT(12), + .bp_infracfg = { + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_MM_2_WPE_STEP1, + MT8188_TOP_AXI_PROT_EN_MM_2_SET, + MT8188_TOP_AXI_PROT_EN_MM_2_CLR, + MT8188_TOP_AXI_PROT_EN_MM_2_STA), + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_MM_2_WPE_STEP2, + MT8188_TOP_AXI_PROT_EN_MM_2_SET, + MT8188_TOP_AXI_PROT_EN_MM_2_CLR, + MT8188_TOP_AXI_PROT_EN_MM_2_STA), + }, + .caps = MTK_SCPD_KEEP_DEFAULT_OFF, + }, + [MT8188_POWER_DOMAIN_VDEC0] = { + .name = "vdec0", + .sta_mask = BIT(19), + .ctl_offs = 0x380, + .pwr_sta_offs = 0x16C, + .pwr_sta2nd_offs = 0x170, + .sram_pdn_bits = BIT(8), + .sram_pdn_ack_bits = BIT(12), + .bp_infracfg = { + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_MM_VDEC0_STEP1, + MT8188_TOP_AXI_PROT_EN_MM_SET, + MT8188_TOP_AXI_PROT_EN_MM_CLR, + MT8188_TOP_AXI_PROT_EN_MM_STA), + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_MM_2_VDEC0_STEP2, + MT8188_TOP_AXI_PROT_EN_MM_2_SET, + MT8188_TOP_AXI_PROT_EN_MM_2_CLR, + MT8188_TOP_AXI_PROT_EN_MM_2_STA), + }, + .caps = MTK_SCPD_KEEP_DEFAULT_OFF, + }, + [MT8188_POWER_DOMAIN_VDEC1] = { + .name = "vdec1", + .sta_mask = BIT(20), + .ctl_offs = 0x384, + .pwr_sta_offs = 0x16C, + .pwr_sta2nd_offs = 0x170, + .sram_pdn_bits = BIT(8), + .sram_pdn_ack_bits = BIT(12), + .bp_infracfg = { + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_MM_VDEC1_STEP1, + MT8188_TOP_AXI_PROT_EN_MM_SET, + MT8188_TOP_AXI_PROT_EN_MM_CLR, + MT8188_TOP_AXI_PROT_EN_MM_STA), + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_MM_VDEC1_STEP2, + MT8188_TOP_AXI_PROT_EN_MM_SET, + MT8188_TOP_AXI_PROT_EN_MM_CLR, + MT8188_TOP_AXI_PROT_EN_MM_STA), + }, + .caps = MTK_SCPD_KEEP_DEFAULT_OFF, + }, + [MT8188_POWER_DOMAIN_VENC] = { + .name = "venc", + .sta_mask = BIT(22), + .ctl_offs = 0x38C, + .pwr_sta_offs = 0x16C, + .pwr_sta2nd_offs = 0x170, + .sram_pdn_bits = BIT(8), + .sram_pdn_ack_bits = BIT(12), + .bp_infracfg = { + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_MM_VENC_STEP1, + MT8188_TOP_AXI_PROT_EN_MM_SET, + MT8188_TOP_AXI_PROT_EN_MM_CLR, + MT8188_TOP_AXI_PROT_EN_MM_STA), + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_MM_VENC_STEP2, + MT8188_TOP_AXI_PROT_EN_MM_SET, + MT8188_TOP_AXI_PROT_EN_MM_CLR, + MT8188_TOP_AXI_PROT_EN_MM_STA), + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_MM_2_VENC_STEP3, + MT8188_TOP_AXI_PROT_EN_MM_2_SET, + MT8188_TOP_AXI_PROT_EN_MM_2_CLR, + MT8188_TOP_AXI_PROT_EN_MM_2_STA), + }, + .caps = MTK_SCPD_KEEP_DEFAULT_OFF, + }, + [MT8188_POWER_DOMAIN_IMG_VCORE] = { + .name = "vcore", + .sta_mask = BIT(28), + .ctl_offs = 0x3A4, + .pwr_sta_offs = 0x16C, + .pwr_sta2nd_offs = 0x170, + .bp_infracfg = { + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_MM_IMG_VCORE_STEP1, + MT8188_TOP_AXI_PROT_EN_MM_SET, + MT8188_TOP_AXI_PROT_EN_MM_CLR, + MT8188_TOP_AXI_PROT_EN_MM_STA), + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_MM_IMG_VCORE_STEP2, + MT8188_TOP_AXI_PROT_EN_MM_SET, + MT8188_TOP_AXI_PROT_EN_MM_CLR, + MT8188_TOP_AXI_PROT_EN_MM_STA), + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_MM_2_IMG_VCORE_STEP3, + MT8188_TOP_AXI_PROT_EN_MM_2_SET, + MT8188_TOP_AXI_PROT_EN_MM_2_CLR, + MT8188_TOP_AXI_PROT_EN_MM_2_STA), + }, + .caps = MTK_SCPD_KEEP_DEFAULT_OFF | MTK_SCPD_DOMAIN_SUPPLY, + }, + [MT8188_POWER_DOMAIN_IMG_MAIN] = { + .name = "img_main", + .sta_mask = BIT(29), + .ctl_offs = 0x3A8, + .pwr_sta_offs = 0x16C, + .pwr_sta2nd_offs = 0x170, + .sram_pdn_bits = BIT(8), + .sram_pdn_ack_bits = BIT(12), + .bp_infracfg = { + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_MM_2_IMG_MAIN_STEP1, + MT8188_TOP_AXI_PROT_EN_MM_2_SET, + MT8188_TOP_AXI_PROT_EN_MM_2_CLR, + MT8188_TOP_AXI_PROT_EN_MM_2_STA), + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_MM_2_IMG_MAIN_STEP2, + MT8188_TOP_AXI_PROT_EN_MM_2_SET, + MT8188_TOP_AXI_PROT_EN_MM_2_CLR, + MT8188_TOP_AXI_PROT_EN_MM_2_STA), + }, + .caps = MTK_SCPD_KEEP_DEFAULT_OFF, + }, + [MT8188_POWER_DOMAIN_DIP] = { + .name = "dip", + .sta_mask = BIT(30), + .ctl_offs = 0x3AC, + .pwr_sta_offs = 0x16C, + .pwr_sta2nd_offs = 0x170, + .sram_pdn_bits = BIT(8), + .sram_pdn_ack_bits = BIT(12), + .caps = MTK_SCPD_KEEP_DEFAULT_OFF, + }, + [MT8188_POWER_DOMAIN_IPE] = { + .name = "ipe", + .sta_mask = BIT(31), + .ctl_offs = 0x3B0, + .pwr_sta_offs = 0x16C, + .pwr_sta2nd_offs = 0x170, + .sram_pdn_bits = BIT(8), + .sram_pdn_ack_bits = BIT(12), + .caps = MTK_SCPD_KEEP_DEFAULT_OFF, + }, + [MT8188_POWER_DOMAIN_CAM_VCORE] = { + .name = "cam_vcore", + .sta_mask = BIT(27), + .ctl_offs = 0x3A0, + .pwr_sta_offs = 0x16C, + .pwr_sta2nd_offs = 0x170, + .bp_infracfg = { + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_MM_CAM_VCORE_STEP1, + MT8188_TOP_AXI_PROT_EN_MM_SET, + MT8188_TOP_AXI_PROT_EN_MM_CLR, + MT8188_TOP_AXI_PROT_EN_MM_STA), + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_2_CAM_VCORE_STEP2, + MT8188_TOP_AXI_PROT_EN_2_SET, + MT8188_TOP_AXI_PROT_EN_2_CLR, + MT8188_TOP_AXI_PROT_EN_2_STA), + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_1_CAM_VCORE_STEP3, + MT8188_TOP_AXI_PROT_EN_1_SET, + MT8188_TOP_AXI_PROT_EN_1_CLR, + MT8188_TOP_AXI_PROT_EN_1_STA), + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_MM_CAM_VCORE_STEP4, + MT8188_TOP_AXI_PROT_EN_MM_SET, + MT8188_TOP_AXI_PROT_EN_MM_CLR, + MT8188_TOP_AXI_PROT_EN_MM_STA), + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_MM_2_CAM_VCORE_STEP5, + MT8188_TOP_AXI_PROT_EN_MM_2_SET, + MT8188_TOP_AXI_PROT_EN_MM_2_CLR, + MT8188_TOP_AXI_PROT_EN_MM_2_STA), + }, + .caps = MTK_SCPD_KEEP_DEFAULT_OFF | MTK_SCPD_DOMAIN_SUPPLY, + }, + [MT8188_POWER_DOMAIN_CAM_MAIN] = { + .name = "cam_main", + .sta_mask = BIT(24), + .ctl_offs = 0x394, + .pwr_sta_offs = 0x16C, + .pwr_sta2nd_offs = 0x170, + .sram_pdn_bits = BIT(8), + .sram_pdn_ack_bits = BIT(12), + .bp_infracfg = { + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_MM_2_CAM_MAIN_STEP1, + MT8188_TOP_AXI_PROT_EN_MM_2_SET, + MT8188_TOP_AXI_PROT_EN_MM_2_CLR, + MT8188_TOP_AXI_PROT_EN_MM_2_STA), + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_2_CAM_MAIN_STEP2, + MT8188_TOP_AXI_PROT_EN_2_SET, + MT8188_TOP_AXI_PROT_EN_2_CLR, + MT8188_TOP_AXI_PROT_EN_2_STA), + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_MM_2_CAM_MAIN_STEP3, + MT8188_TOP_AXI_PROT_EN_MM_2_SET, + MT8188_TOP_AXI_PROT_EN_MM_2_CLR, + MT8188_TOP_AXI_PROT_EN_MM_2_STA), + BUS_PROT_WR(MT8188_TOP_AXI_PROT_EN_2_CAM_MAIN_STEP4, + MT8188_TOP_AXI_PROT_EN_2_SET, + MT8188_TOP_AXI_PROT_EN_2_CLR, + MT8188_TOP_AXI_PROT_EN_2_STA), + }, + .caps = MTK_SCPD_KEEP_DEFAULT_OFF, + }, + [MT8188_POWER_DOMAIN_CAM_SUBA] = { + .name = "cam_suba", + .sta_mask = BIT(25), + .ctl_offs = 0x398, + .pwr_sta_offs = 0x16C, + .pwr_sta2nd_offs = 0x170, + .sram_pdn_bits = BIT(8), + .sram_pdn_ack_bits = BIT(12), + .caps = MTK_SCPD_KEEP_DEFAULT_OFF, + }, + [MT8188_POWER_DOMAIN_CAM_SUBB] = { + .name = "cam_subb", + .sta_mask = BIT(26), + .ctl_offs = 0x39C, + .pwr_sta_offs = 0x16C, + .pwr_sta2nd_offs = 0x170, + .sram_pdn_bits = BIT(8), + .sram_pdn_ack_bits = BIT(12), + .caps = MTK_SCPD_KEEP_DEFAULT_OFF, + }, +}; + +static const struct scpsys_soc_data mt8188_scpsys_data = { + .domains_data = scpsys_domain_data_mt8188, + .num_domains = ARRAY_SIZE(scpsys_domain_data_mt8188), +}; + +#endif /* __SOC_MEDIATEK_MT8188_PM_DOMAINS_H */ diff --git a/drivers/soc/mediatek/mtk-pm-domains.c b/drivers/soc/mediatek/mtk-pm-domains.c index 474b272f9b02..ea3878bf4387 100644 --- a/drivers/soc/mediatek/mtk-pm-domains.c +++ b/drivers/soc/mediatek/mtk-pm-domains.c @@ -21,6 +21,7 @@ #include "mt8173-pm-domains.h" #include "mt8183-pm-domains.h" #include "mt8186-pm-domains.h" +#include "mt8188-pm-domains.h" #include "mt8192-pm-domains.h" #include "mt8195-pm-domains.h" @@ -579,6 +580,10 @@ static const struct of_device_id scpsys_of_match[] = { .compatible = "mediatek,mt8186-power-controller", .data = &mt8186_scpsys_data, }, + { + .compatible = "mediatek,mt8188-power-controller", + .data = &mt8188_scpsys_data, + }, { .compatible = "mediatek,mt8192-power-controller", .data = &mt8192_scpsys_data, diff --git a/include/linux/soc/mediatek/infracfg.h b/include/linux/soc/mediatek/infracfg.h index 50804ac748bd..07f67b3d8e97 100644 --- a/include/linux/soc/mediatek/infracfg.h +++ b/include/linux/soc/mediatek/infracfg.h @@ -140,6 +140,127 @@ #define MT8192_TOP_AXI_PROT_EN_MM_2_MDP_2ND BIT(13) #define MT8192_TOP_AXI_PROT_EN_VDNR_CAM BIT(21) +#define MT8188_TOP_AXI_PROT_EN_SET 0x2A0 +#define MT8188_TOP_AXI_PROT_EN_CLR 0x2A4 +#define MT8188_TOP_AXI_PROT_EN_STA 0x228 +#define MT8188_TOP_AXI_PROT_EN_1_SET 0x2A8 +#define MT8188_TOP_AXI_PROT_EN_1_CLR 0x2AC +#define MT8188_TOP_AXI_PROT_EN_1_STA 0x258 +#define MT8188_TOP_AXI_PROT_EN_2_SET 0x714 +#define MT8188_TOP_AXI_PROT_EN_2_CLR 0x718 +#define MT8188_TOP_AXI_PROT_EN_2_STA 0x724 + +#define MT8188_TOP_AXI_PROT_EN_MM_SET 0x2D4 +#define MT8188_TOP_AXI_PROT_EN_MM_CLR 0x2D8 +#define MT8188_TOP_AXI_PROT_EN_MM_STA 0x2EC +#define MT8188_TOP_AXI_PROT_EN_MM_2_SET 0xDCC +#define MT8188_TOP_AXI_PROT_EN_MM_2_CLR 0xDD0 +#define MT8188_TOP_AXI_PROT_EN_MM_2_STA 0xDD8 + +#define MT8188_TOP_AXI_PROT_EN_INFRA_VDNR_SET 0xB84 +#define MT8188_TOP_AXI_PROT_EN_INFRA_VDNR_CLR 0xB88 +#define MT8188_TOP_AXI_PROT_EN_INFRA_VDNR_STA 0xB90 +#define MT8188_TOP_AXI_PROT_EN_SUB_INFRA_VDNR_SET 0xBCC +#define MT8188_TOP_AXI_PROT_EN_SUB_INFRA_VDNR_CLR 0xBD0 +#define MT8188_TOP_AXI_PROT_EN_SUB_INFRA_VDNR_STA 0xBD8 + +#define MT8188_TOP_AXI_PROT_EN_MFG1_STEP1 BIT(11) +#define MT8188_TOP_AXI_PROT_EN_2_MFG1_STEP2 BIT(7) +#define MT8188_TOP_AXI_PROT_EN_1_MFG1_STEP3 BIT(19) +#define MT8188_TOP_AXI_PROT_EN_2_MFG1_STEP4 BIT(5) +#define MT8188_TOP_AXI_PROT_EN_MFG1_STEP5 GENMASK(22, 21) +#define MT8188_TOP_AXI_PROT_EN_SUB_INFRA_VDNR_MFG1_STEP6 BIT(17) + +#define MT8188_TOP_AXI_PROT_EN_PEXTP_MAC_P0_STEP1 BIT(2) +#define MT8188_TOP_AXI_PROT_EN_INFRA_VDNR_PEXTP_MAC_P0_STEP2 (BIT(8) | BIT(18) | BIT(30)) +#define MT8188_TOP_AXI_PROT_EN_INFRA_VDNR_ETHER_STEP1 BIT(24) +#define MT8188_TOP_AXI_PROT_EN_INFRA_VDNR_HDMI_TX_STEP1 BIT(20) +#define MT8188_TOP_AXI_PROT_EN_2_ADSP_AO_STEP1 GENMASK(31, 29) +#define MT8188_TOP_AXI_PROT_EN_2_ADSP_AO_STEP2 (GENMASK(4, 3) | BIT(28)) +#define MT8188_TOP_AXI_PROT_EN_2_ADSP_INFRA_STEP1 (GENMASK(16, 14) | BIT(23) | \ + BIT(27)) +#define MT8188_TOP_AXI_PROT_EN_2_ADSP_INFRA_STEP2 (GENMASK(19, 17) | GENMASK(26, 25)) +#define MT8188_TOP_AXI_PROT_EN_2_ADSP_STEP1 GENMASK(11, 8) +#define MT8188_TOP_AXI_PROT_EN_2_ADSP_STEP2 GENMASK(22, 21) +#define MT8188_TOP_AXI_PROT_EN_2_AUDIO_STEP1 BIT(20) +#define MT8188_TOP_AXI_PROT_EN_2_AUDIO_STEP2 BIT(12) +#define MT8188_TOP_AXI_PROT_EN_2_AUDIO_ASRC_STEP1 BIT(24) +#define MT8188_TOP_AXI_PROT_EN_2_AUDIO_ASRC_STEP2 BIT(13) + +#define MT8188_TOP_AXI_PROT_EN_VPPSYS0_STEP1 BIT(10) +#define MT8188_TOP_AXI_PROT_EN_MM_2_VPPSYS0_STEP2 GENMASK(9, 8) +#define MT8188_TOP_AXI_PROT_EN_VPPSYS0_STEP3 BIT(23) +#define MT8188_TOP_AXI_PROT_EN_MM_2_VPPSYS0_STEP4 (BIT(1) | BIT(4) | BIT(11)) +#define MT8188_TOP_AXI_PROT_EN_SUB_INFRA_VDNR_VPPSYS0_STEP5 (BIT(20)) +#define MT8188_TOP_AXI_PROT_EN_MM_VDOSYS0_STEP1 (GENMASK(18, 17) | GENMASK(21, 20)) +#define MT8188_TOP_AXI_PROT_EN_VDOSYS0_STEP2 BIT(6) +#define MT8188_TOP_AXI_PROT_EN_SUB_INFRA_VDNR_VDOSYS0_STEP3 BIT(21) +#define MT8188_TOP_AXI_PROT_EN_MM_VDOSYS1_STEP1 GENMASK(31, 30) +#define MT8188_TOP_AXI_PROT_EN_MM_VDOSYS1_STEP2 BIT(22) +#define MT8188_TOP_AXI_PROT_EN_MM_2_VDOSYS1_STEP3 BIT(10) +#define MT8188_TOP_AXI_PROT_EN_INFRA_VDNR_DP_TX_STEP1 BIT(23) +#define MT8188_TOP_AXI_PROT_EN_INFRA_VDNR_EDP_TX_STEP1 BIT(22) + +#define MT8188_TOP_AXI_PROT_EN_MM_VPPSYS1_STEP1 GENMASK(6, 5) +#define MT8188_TOP_AXI_PROT_EN_MM_VPPSYS1_STEP2 BIT(23) +#define MT8188_TOP_AXI_PROT_EN_MM_2_VPPSYS1_STEP3 BIT(18) +#define MT8188_TOP_AXI_PROT_EN_MM_2_WPE_STEP1 BIT(23) +#define MT8188_TOP_AXI_PROT_EN_MM_2_WPE_STEP2 BIT(21) +#define MT8188_TOP_AXI_PROT_EN_MM_VDEC0_STEP1 BIT(13) +#define MT8188_TOP_AXI_PROT_EN_MM_2_VDEC0_STEP2 BIT(13) +#define MT8188_TOP_AXI_PROT_EN_MM_VDEC1_STEP1 BIT(14) +#define MT8188_TOP_AXI_PROT_EN_MM_VDEC1_STEP2 BIT(29) +#define MT8188_TOP_AXI_PROT_EN_MM_VENC_STEP1 (BIT(9) | BIT(11)) +#define MT8188_TOP_AXI_PROT_EN_MM_VENC_STEP2 BIT(26) +#define MT8188_TOP_AXI_PROT_EN_MM_2_VENC_STEP3 BIT(2) +#define MT8188_TOP_AXI_PROT_EN_MM_IMG_VCORE_STEP1 (BIT(1) | BIT(3)) +#define MT8188_TOP_AXI_PROT_EN_MM_IMG_VCORE_STEP2 BIT(25) +#define MT8188_TOP_AXI_PROT_EN_MM_2_IMG_VCORE_STEP3 BIT(16) +#define MT8188_TOP_AXI_PROT_EN_MM_2_IMG_MAIN_STEP1 GENMASK(27, 26) +#define MT8188_TOP_AXI_PROT_EN_MM_2_IMG_MAIN_STEP2 GENMASK(25, 24) +#define MT8188_TOP_AXI_PROT_EN_MM_CAM_VCORE_STEP1 (BIT(2) | BIT(4)) +#define MT8188_TOP_AXI_PROT_EN_2_CAM_VCORE_STEP2 BIT(0) +#define MT8188_TOP_AXI_PROT_EN_1_CAM_VCORE_STEP3 BIT(22) +#define MT8188_TOP_AXI_PROT_EN_MM_CAM_VCORE_STEP4 BIT(24) +#define MT8188_TOP_AXI_PROT_EN_MM_2_CAM_VCORE_STEP5 BIT(17) +#define MT8188_TOP_AXI_PROT_EN_MM_2_CAM_MAIN_STEP1 GENMASK(31, 30) +#define MT8188_TOP_AXI_PROT_EN_2_CAM_MAIN_STEP2 BIT(2) +#define MT8188_TOP_AXI_PROT_EN_MM_2_CAM_MAIN_STEP3 GENMASK(29, 28) +#define MT8188_TOP_AXI_PROT_EN_2_CAM_MAIN_STEP4 BIT(1) + +#define MT8188_SMI_COMMON_CLAMP_EN_STA 0x3C0 +#define MT8188_SMI_COMMON_CLAMP_EN_SET 0x3C4 +#define MT8188_SMI_COMMON_CLAMP_EN_CLR 0x3C8 + +#define MT8188_SMI_COMMON_SMI_CLAMP_DIP_TO_VDO0 GENMASK(3, 1) +#define MT8188_SMI_COMMON_SMI_CLAMP_DIP_TO_VPP1 GENMASK(2, 1) +#define MT8188_SMI_COMMON_SMI_CLAMP_IPE_TO_VPP1 BIT(0) + +#define MT8188_SMI_COMMON_SMI_CLAMP_CAM_SUBA_TO_VPP0 GENMASK(3, 2) +#define MT8188_SMI_COMMON_SMI_CLAMP_CAM_SUBB_TO_VDO0 GENMASK(3, 2) + +#define MT8188_SMI_LARB10_RESET_ADDR 0xC +#define MT8188_SMI_LARB11A_RESET_ADDR 0xC +#define MT8188_SMI_LARB11C_RESET_ADDR 0xC +#define MT8188_SMI_LARB12_RESET_ADDR 0xC +#define MT8188_SMI_LARB11B_RESET_ADDR 0xC +#define MT8188_SMI_LARB15_RESET_ADDR 0xC +#define MT8188_SMI_LARB16B_RESET_ADDR 0xA0 +#define MT8188_SMI_LARB17B_RESET_ADDR 0xA0 +#define MT8188_SMI_LARB16A_RESET_ADDR 0xA0 +#define MT8188_SMI_LARB17A_RESET_ADDR 0xA0 + +#define MT8188_SMI_LARB10_RESET BIT(0) +#define MT8188_SMI_LARB11A_RESET BIT(0) +#define MT8188_SMI_LARB11C_RESET BIT(0) +#define MT8188_SMI_LARB12_RESET BIT(8) +#define MT8188_SMI_LARB11B_RESET BIT(0) +#define MT8188_SMI_LARB15_RESET BIT(0) +#define MT8188_SMI_LARB16B_RESET BIT(4) +#define MT8188_SMI_LARB17B_RESET BIT(4) +#define MT8188_SMI_LARB16A_RESET BIT(4) +#define MT8188_SMI_LARB17A_RESET BIT(4) + #define MT8186_TOP_AXI_PROT_EN_SET (0x2A0) #define MT8186_TOP_AXI_PROT_EN_CLR (0x2A4) #define MT8186_TOP_AXI_PROT_EN_STA (0x228) -- cgit v1.2.3 From cecafc0a830f7ea89bc11c644e2841f603fcc4e6 Mon Sep 17 00:00:00 2001 From: Yu Zhang Date: Thu, 5 Jan 2023 21:01:27 +0800 Subject: KVM: MMU: Make the definition of 'INVALID_GPA' common KVM already has a 'GPA_INVALID' defined as (~(gpa_t)0) in kvm_types.h, and it is used by ARM code. We do not need another definition of 'INVALID_GPA' for X86 specifically. Instead of using the common 'GPA_INVALID' for X86, replace it with 'INVALID_GPA', and change the users of 'GPA_INVALID' so that the diff can be smaller. Also because the name 'INVALID_GPA' tells the user we are using an invalid GPA, while the name 'GPA_INVALID' is emphasizing the GPA is an invalid one. No functional change intended. Signed-off-by: Yu Zhang Reviewed-by: Paul Durrant Reviewed-by: Sean Christopherson Link: https://lore.kernel.org/r/20230105130127.866171-1-yu.c.zhang@linux.intel.com Signed-off-by: Oliver Upton --- arch/arm64/include/asm/kvm_host.h | 4 ++-- arch/arm64/kvm/hypercalls.c | 2 +- arch/arm64/kvm/pvtime.c | 8 ++++---- arch/x86/include/asm/kvm_host.h | 2 -- include/linux/kvm_types.h | 2 +- 5 files changed, 8 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 35a159d131b5..37766e57c8f2 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -916,12 +916,12 @@ void kvm_arm_vmid_clear_active(void); static inline void kvm_arm_pvtime_vcpu_init(struct kvm_vcpu_arch *vcpu_arch) { - vcpu_arch->steal.base = GPA_INVALID; + vcpu_arch->steal.base = INVALID_GPA; } static inline bool kvm_arm_is_pvtime_enabled(struct kvm_vcpu_arch *vcpu_arch) { - return (vcpu_arch->steal.base != GPA_INVALID); + return (vcpu_arch->steal.base != INVALID_GPA); } void kvm_set_sei_esr(struct kvm_vcpu *vcpu, u64 syndrome); diff --git a/arch/arm64/kvm/hypercalls.c b/arch/arm64/kvm/hypercalls.c index c9f401fa01a9..64c086c02c60 100644 --- a/arch/arm64/kvm/hypercalls.c +++ b/arch/arm64/kvm/hypercalls.c @@ -198,7 +198,7 @@ int kvm_hvc_call_handler(struct kvm_vcpu *vcpu) break; case ARM_SMCCC_HV_PV_TIME_ST: gpa = kvm_init_stolen_time(vcpu); - if (gpa != GPA_INVALID) + if (gpa != INVALID_GPA) val[0] = gpa; break; case ARM_SMCCC_VENDOR_HYP_CALL_UID_FUNC_ID: diff --git a/arch/arm64/kvm/pvtime.c b/arch/arm64/kvm/pvtime.c index 78a09f7a6637..4ceabaa4c30b 100644 --- a/arch/arm64/kvm/pvtime.c +++ b/arch/arm64/kvm/pvtime.c @@ -19,7 +19,7 @@ void kvm_update_stolen_time(struct kvm_vcpu *vcpu) u64 steal = 0; int idx; - if (base == GPA_INVALID) + if (base == INVALID_GPA) return; idx = srcu_read_lock(&kvm->srcu); @@ -40,7 +40,7 @@ long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu) switch (feature) { case ARM_SMCCC_HV_PV_TIME_FEATURES: case ARM_SMCCC_HV_PV_TIME_ST: - if (vcpu->arch.steal.base != GPA_INVALID) + if (vcpu->arch.steal.base != INVALID_GPA) val = SMCCC_RET_SUCCESS; break; } @@ -54,7 +54,7 @@ gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu) struct kvm *kvm = vcpu->kvm; u64 base = vcpu->arch.steal.base; - if (base == GPA_INVALID) + if (base == INVALID_GPA) return base; /* @@ -89,7 +89,7 @@ int kvm_arm_pvtime_set_attr(struct kvm_vcpu *vcpu, return -EFAULT; if (!IS_ALIGNED(ipa, 64)) return -EINVAL; - if (vcpu->arch.steal.base != GPA_INVALID) + if (vcpu->arch.steal.base != INVALID_GPA) return -EEXIST; /* Check the address is in a valid memslot */ diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index f35f1ff4427b..46e50cb6c9ca 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -134,8 +134,6 @@ #define INVALID_PAGE (~(hpa_t)0) #define VALID_PAGE(x) ((x) != INVALID_PAGE) -#define INVALID_GPA (~(gpa_t)0) - /* KVM Hugepage definitions for x86 */ #define KVM_MAX_HUGEPAGE_LEVEL PG_LEVEL_1G #define KVM_NR_PAGE_SIZES (KVM_MAX_HUGEPAGE_LEVEL - PG_LEVEL_4K + 1) diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h index 76de36e56cdf..2728d49bbdf6 100644 --- a/include/linux/kvm_types.h +++ b/include/linux/kvm_types.h @@ -40,7 +40,7 @@ typedef unsigned long gva_t; typedef u64 gpa_t; typedef u64 gfn_t; -#define GPA_INVALID (~(gpa_t)0) +#define INVALID_GPA (~(gpa_t)0) typedef unsigned long hva_t; typedef u64 hpa_t; -- cgit v1.2.3 From 344da544f177f919cf6919e5abcd388f27aa53db Mon Sep 17 00:00:00 2001 From: Paul E. McKenney Date: Fri, 16 Dec 2022 16:52:01 -0800 Subject: x86/nmi: Print reasons why backtrace NMIs are ignored Instrument nmi_trigger_cpumask_backtrace() to dump out diagnostics based on evidence accumulated by exc_nmi(). These diagnostics are dumped for CPUs that ignored an NMI backtrace request for more than 10 seconds. [ paulmck: Apply Ingo Molnar feedback. ] Signed-off-by: Paul E. McKenney Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: Dave Hansen Cc: "H. Peter Anvin" Cc: Reviewed-by: Ingo Molnar --- arch/x86/kernel/nmi.c | 73 +++++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/nmi.h | 8 ++++++ lib/nmi_backtrace.c | 2 ++ 3 files changed, 83 insertions(+) (limited to 'include/linux') diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index 701ff27a77ec..c315b18ec7c8 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -570,6 +570,79 @@ DEFINE_IDTENTRY_RAW(exc_nmi_noist) EXPORT_SYMBOL_GPL(asm_exc_nmi_noist); #endif +#ifdef CONFIG_NMI_CHECK_CPU + +static char *nmi_check_stall_msg[] = { +/* */ +/* +--------- nsp->idt_seq_snap & 0x1: CPU is in NMI handler. */ +/* | +------ cpu_is_offline(cpu) */ +/* | | +--- nsp->idt_calls_snap != atomic_long_read(&nsp->idt_calls): */ +/* | | | NMI handler has been invoked. */ +/* | | | */ +/* V V V */ +/* 0 0 0 */ "NMIs are not reaching exc_nmi() handler", +/* 0 0 1 */ "exc_nmi() handler is ignoring NMIs", +/* 0 1 0 */ "CPU is offline and NMIs are not reaching exc_nmi() handler", +/* 0 1 1 */ "CPU is offline and exc_nmi() handler is legitimately ignoring NMIs", +/* 1 0 0 */ "CPU is in exc_nmi() handler and no further NMIs are reaching handler", +/* 1 0 1 */ "CPU is in exc_nmi() handler which is legitimately ignoring NMIs", +/* 1 1 0 */ "CPU is offline in exc_nmi() handler and no more NMIs are reaching exc_nmi() handler", +/* 1 1 1 */ "CPU is offline in exc_nmi() handler which is legitimately ignoring NMIs", +}; + +void nmi_backtrace_stall_snap(const struct cpumask *btp) +{ + int cpu; + struct nmi_stats *nsp; + + for_each_cpu(cpu, btp) { + nsp = per_cpu_ptr(&nmi_stats, cpu); + nsp->idt_seq_snap = READ_ONCE(nsp->idt_seq); + nsp->idt_nmi_seq_snap = READ_ONCE(nsp->idt_nmi_seq); + nsp->idt_ignored_snap = READ_ONCE(nsp->idt_ignored); + nsp->idt_calls_snap = atomic_long_read(&nsp->idt_calls); + } +} + +void nmi_backtrace_stall_check(const struct cpumask *btp) +{ + int cpu; + int idx; + unsigned long nmi_seq; + unsigned long j = jiffies; + char *modp; + char *msgp; + char *msghp; + struct nmi_stats *nsp; + + for_each_cpu(cpu, btp) { + nsp = per_cpu_ptr(&nmi_stats, cpu); + modp = ""; + msghp = ""; + nmi_seq = READ_ONCE(nsp->idt_nmi_seq); + if (nsp->idt_nmi_seq_snap + 1 == nmi_seq && (nmi_seq & 0x1)) { + msgp = "CPU entered NMI handler function, but has not exited"; + } else if ((nsp->idt_nmi_seq_snap & 0x1) != (nmi_seq & 0x1)) { + msgp = "CPU is handling NMIs"; + } else { + idx = ((nsp->idt_seq_snap & 0x1) << 2) | + (cpu_is_offline(cpu) << 1) | + (nsp->idt_calls_snap != atomic_long_read(&nsp->idt_calls)); + msgp = nmi_check_stall_msg[idx]; + if (nsp->idt_ignored_snap != READ_ONCE(nsp->idt_ignored) && (idx & 0x1)) + modp = ", but OK because ignore_nmis was set"; + if (nmi_seq & ~0x1) + msghp = " (CPU currently in NMI handler function)"; + else if (nsp->idt_nmi_seq_snap + 1 == nmi_seq) + msghp = " (CPU exited one NMI handler function)"; + } + pr_alert("%s: CPU %d: %s%s%s, last activity: %lu jiffies ago.\n", + __func__, cpu, msgp, modp, msghp, j - READ_ONCE(nsp->recv_jiffies)); + } +} + +#endif + void stop_nmi(void) { ignore_nmis++; diff --git a/include/linux/nmi.h b/include/linux/nmi.h index f700ff2df074..048c0b9aa623 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -214,4 +214,12 @@ int proc_watchdog_cpumask(struct ctl_table *, int, void *, size_t *, loff_t *); #include #endif +#ifdef CONFIG_NMI_CHECK_CPU +void nmi_backtrace_stall_snap(const struct cpumask *btp); +void nmi_backtrace_stall_check(const struct cpumask *btp); +#else +static inline void nmi_backtrace_stall_snap(const struct cpumask *btp) {} +static inline void nmi_backtrace_stall_check(const struct cpumask *btp) {} +#endif + #endif diff --git a/lib/nmi_backtrace.c b/lib/nmi_backtrace.c index d01aec6ae15c..5274bbb026d7 100644 --- a/lib/nmi_backtrace.c +++ b/lib/nmi_backtrace.c @@ -64,6 +64,7 @@ void nmi_trigger_cpumask_backtrace(const cpumask_t *mask, if (!cpumask_empty(to_cpumask(backtrace_mask))) { pr_info("Sending NMI from CPU %d to CPUs %*pbl:\n", this_cpu, nr_cpumask_bits, to_cpumask(backtrace_mask)); + nmi_backtrace_stall_snap(to_cpumask(backtrace_mask)); raise(to_cpumask(backtrace_mask)); } @@ -74,6 +75,7 @@ void nmi_trigger_cpumask_backtrace(const cpumask_t *mask, mdelay(1); touch_softlockup_watchdog(); } + nmi_backtrace_stall_check(to_cpumask(backtrace_mask)); /* * Force flush any remote buffers that might be stuck in IRQ context -- cgit v1.2.3 From 13e80244ca7e51d5eb7803f05e0579b11fc89048 Mon Sep 17 00:00:00 2001 From: Hanna Hawa Date: Wed, 28 Dec 2022 16:48:12 +0000 Subject: pinctrl: Add an API to get the pinctrl pins if initialized Add an API to get the pinctrl pins if it was initialized before driver probed. This API will be used in I2C core to get the device pinctrl information for recovery state change. Signed-off-by: Hanna Hawa Reviewed-by: Andy Shevchenko Reviewed-by: Linus Walleij Signed-off-by: Wolfram Sang --- include/linux/pinctrl/devinfo.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pinctrl/devinfo.h b/include/linux/pinctrl/devinfo.h index 9e8b559e1253..bb6653af4f92 100644 --- a/include/linux/pinctrl/devinfo.h +++ b/include/linux/pinctrl/devinfo.h @@ -18,6 +18,8 @@ struct device; #ifdef CONFIG_PINCTRL +#include + /* The device core acts as a consumer toward pinctrl */ #include @@ -44,6 +46,14 @@ struct dev_pin_info { extern int pinctrl_bind_pins(struct device *dev); extern int pinctrl_init_done(struct device *dev); +static inline struct pinctrl *dev_pinctrl(struct device *dev) +{ + if (!dev->pins) + return NULL; + + return dev->pins->p; +} + #else /* Stubs if we're not using pinctrl */ @@ -58,5 +68,10 @@ static inline int pinctrl_init_done(struct device *dev) return 0; } +static inline struct pinctrl *dev_pinctrl(struct device *dev) +{ + return NULL; +} + #endif /* CONFIG_PINCTRL */ #endif /* PINCTRL_DEVINFO_H */ -- cgit v1.2.3 From e3e289fbc0b520cf469469e8cdba84a50424eb65 Mon Sep 17 00:00:00 2001 From: Kai Ye Date: Sat, 19 Nov 2022 07:48:15 +0000 Subject: uacce: supports device isolation feature UACCE adds the hardware error isolation feature. To improve service reliability, some uacce devices that frequently encounter hardware errors are isolated. Therefore, this feature is added. Users can configure the hardware error threshold by 'isolate_strategy' sysfs node. The user space can get the device isolated state by 'isolate' sysfs node. If the number of device errors exceeds the configured error threshold, the device will be isolated. It means the uacce device is unavailable. Signed-off-by: Kai Ye Link: https://lore.kernel.org/r/20221119074817.12063-2-yekai13@huawei.com Signed-off-by: Greg Kroah-Hartman --- drivers/misc/uacce/uacce.c | 50 ++++++++++++++++++++++++++++++++++++++++++++++ include/linux/uacce.h | 12 +++++++++++ 2 files changed, 62 insertions(+) (limited to 'include/linux') diff --git a/drivers/misc/uacce/uacce.c b/drivers/misc/uacce/uacce.c index 905eff1f840e..d3a217929a24 100644 --- a/drivers/misc/uacce/uacce.c +++ b/drivers/misc/uacce/uacce.c @@ -363,12 +363,52 @@ static ssize_t region_dus_size_show(struct device *dev, uacce->qf_pg_num[UACCE_QFRT_DUS] << PAGE_SHIFT); } +static ssize_t isolate_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct uacce_device *uacce = to_uacce_device(dev); + + return sysfs_emit(buf, "%d\n", uacce->ops->get_isolate_state(uacce)); +} + +static ssize_t isolate_strategy_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct uacce_device *uacce = to_uacce_device(dev); + u32 val; + + val = uacce->ops->isolate_err_threshold_read(uacce); + + return sysfs_emit(buf, "%u\n", val); +} + +static ssize_t isolate_strategy_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + struct uacce_device *uacce = to_uacce_device(dev); + unsigned long val; + int ret; + + if (kstrtoul(buf, 0, &val) < 0) + return -EINVAL; + + if (val > UACCE_MAX_ERR_THRESHOLD) + return -EINVAL; + + ret = uacce->ops->isolate_err_threshold_write(uacce, val); + if (ret) + return ret; + + return count; +} + static DEVICE_ATTR_RO(api); static DEVICE_ATTR_RO(flags); static DEVICE_ATTR_RO(available_instances); static DEVICE_ATTR_RO(algorithms); static DEVICE_ATTR_RO(region_mmio_size); static DEVICE_ATTR_RO(region_dus_size); +static DEVICE_ATTR_RO(isolate); +static DEVICE_ATTR_RW(isolate_strategy); static struct attribute *uacce_dev_attrs[] = { &dev_attr_api.attr, @@ -377,6 +417,8 @@ static struct attribute *uacce_dev_attrs[] = { &dev_attr_algorithms.attr, &dev_attr_region_mmio_size.attr, &dev_attr_region_dus_size.attr, + &dev_attr_isolate.attr, + &dev_attr_isolate_strategy.attr, NULL, }; @@ -392,6 +434,14 @@ static umode_t uacce_dev_is_visible(struct kobject *kobj, (!uacce->qf_pg_num[UACCE_QFRT_DUS]))) return 0; + if (attr == &dev_attr_isolate_strategy.attr && + (!uacce->ops->isolate_err_threshold_read && + !uacce->ops->isolate_err_threshold_write)) + return 0; + + if (attr == &dev_attr_isolate.attr && !uacce->ops->get_isolate_state) + return 0; + return attr->mode; } diff --git a/include/linux/uacce.h b/include/linux/uacce.h index 9ce88c28b0a8..0a81c3dfd26c 100644 --- a/include/linux/uacce.h +++ b/include/linux/uacce.h @@ -8,6 +8,7 @@ #define UACCE_NAME "uacce" #define UACCE_MAX_REGION 2 #define UACCE_MAX_NAME_SIZE 64 +#define UACCE_MAX_ERR_THRESHOLD 65535 struct uacce_queue; struct uacce_device; @@ -30,6 +31,9 @@ struct uacce_qfile_region { * @is_q_updated: check whether the task is finished * @mmap: mmap addresses of queue to user space * @ioctl: ioctl for user space users of the queue + * @get_isolate_state: get the device state after set the isolate strategy + * @isolate_err_threshold_write: stored the isolate error threshold to the device + * @isolate_err_threshold_read: read the isolate error threshold value from the device */ struct uacce_ops { int (*get_available_instances)(struct uacce_device *uacce); @@ -43,6 +47,9 @@ struct uacce_ops { struct uacce_qfile_region *qfr); long (*ioctl)(struct uacce_queue *q, unsigned int cmd, unsigned long arg); + enum uacce_dev_state (*get_isolate_state)(struct uacce_device *uacce); + int (*isolate_err_threshold_write)(struct uacce_device *uacce, u32 num); + u32 (*isolate_err_threshold_read)(struct uacce_device *uacce); }; /** @@ -57,6 +64,11 @@ struct uacce_interface { const struct uacce_ops *ops; }; +enum uacce_dev_state { + UACCE_DEV_NORMAL, + UACCE_DEV_ISOLATE, +}; + enum uacce_q_state { UACCE_Q_ZOMBIE = 0, UACCE_Q_INIT, -- cgit v1.2.3 From cd0ac51c5760d4eed4981be5de9cad0255976512 Mon Sep 17 00:00:00 2001 From: Kai Ye Date: Sat, 19 Nov 2022 07:48:17 +0000 Subject: crypto: hisilicon/qm - define the device isolation strategy Define the device isolation strategy by the device driver. The user configures a hardware error threshold value by uacce interface. If the number of hardware errors exceeds the value of setting error threshold in one hour. The device will not be available in user space. The VF device use the PF device isolation strategy. All the hardware errors are processed by PF driver. Signed-off-by: Kai Ye Acked-by: Herbert Xu Link: https://lore.kernel.org/r/20221119074817.12063-4-yekai13@huawei.com Signed-off-by: Greg Kroah-Hartman --- drivers/crypto/hisilicon/qm.c | 169 ++++++++++++++++++++++++++++++++++++++---- include/linux/hisi_acc_qm.h | 15 ++++ 2 files changed, 169 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/drivers/crypto/hisilicon/qm.c b/drivers/crypto/hisilicon/qm.c index 007ac7a69ce7..58d023f6fba3 100644 --- a/drivers/crypto/hisilicon/qm.c +++ b/drivers/crypto/hisilicon/qm.c @@ -367,6 +367,16 @@ struct hisi_qm_resource { struct list_head list; }; +/** + * struct qm_hw_err - Structure describing the device errors + * @list: hardware error list + * @timestamp: timestamp when the error occurred + */ +struct qm_hw_err { + struct list_head list; + unsigned long long timestamp; +}; + struct hisi_qm_hw_ops { int (*get_vft)(struct hisi_qm *qm, u32 *base, u32 *number); void (*qm_db)(struct hisi_qm *qm, u16 qn, @@ -2469,6 +2479,113 @@ static long hisi_qm_uacce_ioctl(struct uacce_queue *q, unsigned int cmd, return -EINVAL; } +/** + * qm_hw_err_isolate() - Try to set the isolation status of the uacce device + * according to user's configuration of error threshold. + * @qm: the uacce device + */ +static int qm_hw_err_isolate(struct hisi_qm *qm) +{ + struct qm_hw_err *err, *tmp, *hw_err; + struct qm_err_isolate *isolate; + u32 count = 0; + + isolate = &qm->isolate_data; + +#define SECONDS_PER_HOUR 3600 + + /* All the hw errs are processed by PF driver */ + if (qm->uacce->is_vf || isolate->is_isolate || !isolate->err_threshold) + return 0; + + hw_err = kzalloc(sizeof(*hw_err), GFP_KERNEL); + if (!hw_err) + return -ENOMEM; + + /* + * Time-stamp every slot AER error. Then check the AER error log when the + * next device AER error occurred. if the device slot AER error count exceeds + * the setting error threshold in one hour, the isolated state will be set + * to true. And the AER error logs that exceed one hour will be cleared. + */ + mutex_lock(&isolate->isolate_lock); + hw_err->timestamp = jiffies; + list_for_each_entry_safe(err, tmp, &isolate->qm_hw_errs, list) { + if ((hw_err->timestamp - err->timestamp) / HZ > + SECONDS_PER_HOUR) { + list_del(&err->list); + kfree(err); + } else { + count++; + } + } + list_add(&hw_err->list, &isolate->qm_hw_errs); + mutex_unlock(&isolate->isolate_lock); + + if (count >= isolate->err_threshold) + isolate->is_isolate = true; + + return 0; +} + +static void qm_hw_err_destroy(struct hisi_qm *qm) +{ + struct qm_hw_err *err, *tmp; + + mutex_lock(&qm->isolate_data.isolate_lock); + list_for_each_entry_safe(err, tmp, &qm->isolate_data.qm_hw_errs, list) { + list_del(&err->list); + kfree(err); + } + mutex_unlock(&qm->isolate_data.isolate_lock); +} + +static enum uacce_dev_state hisi_qm_get_isolate_state(struct uacce_device *uacce) +{ + struct hisi_qm *qm = uacce->priv; + struct hisi_qm *pf_qm; + + if (uacce->is_vf) + pf_qm = pci_get_drvdata(pci_physfn(qm->pdev)); + else + pf_qm = qm; + + return pf_qm->isolate_data.is_isolate ? + UACCE_DEV_ISOLATE : UACCE_DEV_NORMAL; +} + +static int hisi_qm_isolate_threshold_write(struct uacce_device *uacce, u32 num) +{ + struct hisi_qm *qm = uacce->priv; + + /* Must be set by PF */ + if (uacce->is_vf) + return -EPERM; + + if (qm->isolate_data.is_isolate) + return -EPERM; + + qm->isolate_data.err_threshold = num; + + /* After the policy is updated, need to reset the hardware err list */ + qm_hw_err_destroy(qm); + + return 0; +} + +static u32 hisi_qm_isolate_threshold_read(struct uacce_device *uacce) +{ + struct hisi_qm *qm = uacce->priv; + struct hisi_qm *pf_qm; + + if (uacce->is_vf) { + pf_qm = pci_get_drvdata(pci_physfn(qm->pdev)); + return pf_qm->isolate_data.err_threshold; + } + + return qm->isolate_data.err_threshold; +} + static const struct uacce_ops uacce_qm_ops = { .get_available_instances = hisi_qm_get_available_instances, .get_queue = hisi_qm_uacce_get_queue, @@ -2478,8 +2595,22 @@ static const struct uacce_ops uacce_qm_ops = { .mmap = hisi_qm_uacce_mmap, .ioctl = hisi_qm_uacce_ioctl, .is_q_updated = hisi_qm_is_q_updated, + .get_isolate_state = hisi_qm_get_isolate_state, + .isolate_err_threshold_write = hisi_qm_isolate_threshold_write, + .isolate_err_threshold_read = hisi_qm_isolate_threshold_read, }; +static void qm_remove_uacce(struct hisi_qm *qm) +{ + struct uacce_device *uacce = qm->uacce; + + if (qm->use_sva) { + qm_hw_err_destroy(qm); + uacce_remove(uacce); + qm->uacce = NULL; + } +} + static int qm_alloc_uacce(struct hisi_qm *qm) { struct pci_dev *pdev = qm->pdev; @@ -2506,8 +2637,7 @@ static int qm_alloc_uacce(struct hisi_qm *qm) qm->use_sva = true; } else { /* only consider sva case */ - uacce_remove(uacce); - qm->uacce = NULL; + qm_remove_uacce(qm); return -EINVAL; } @@ -2540,6 +2670,8 @@ static int qm_alloc_uacce(struct hisi_qm *qm) uacce->qf_pg_num[UACCE_QFRT_DUS] = dus_page_nr; qm->uacce = uacce; + INIT_LIST_HEAD(&qm->isolate_data.qm_hw_errs); + mutex_init(&qm->isolate_data.isolate_lock); return 0; } @@ -4029,6 +4161,12 @@ static int qm_controller_reset_prepare(struct hisi_qm *qm) return ret; } + if (qm->use_sva) { + ret = qm_hw_err_isolate(qm); + if (ret) + pci_err(pdev, "failed to isolate hw err!\n"); + } + ret = qm_wait_vf_prepare_finish(qm); if (ret) pci_err(pdev, "failed to stop by vfs in soft reset!\n"); @@ -4336,21 +4474,25 @@ static int qm_controller_reset(struct hisi_qm *qm) qm->err_ini->show_last_dfx_regs(qm); ret = qm_soft_reset(qm); - if (ret) { - pci_err(pdev, "Controller reset failed (%d)\n", ret); - qm_reset_bit_clear(qm); - return ret; - } + if (ret) + goto err_reset; ret = qm_controller_reset_done(qm); - if (ret) { - qm_reset_bit_clear(qm); - return ret; - } + if (ret) + goto err_reset; pci_info(pdev, "Controller reset complete\n"); return 0; + +err_reset: + pci_err(pdev, "Controller reset failed (%d)\n", ret); + qm_reset_bit_clear(qm); + + /* if resetting fails, isolate the device */ + if (qm->use_sva) + qm->isolate_data.is_isolate = true; + return ret; } /** @@ -5271,10 +5413,7 @@ int hisi_qm_init(struct hisi_qm *qm) err_free_qm_memory: hisi_qm_memory_uninit(qm); err_alloc_uacce: - if (qm->use_sva) { - uacce_remove(qm->uacce); - qm->uacce = NULL; - } + qm_remove_uacce(qm); err_irq_register: qm_irqs_unregister(qm); err_pci_init: diff --git a/include/linux/hisi_acc_qm.h b/include/linux/hisi_acc_qm.h index be3aedaa96dc..d08bff0f87f9 100644 --- a/include/linux/hisi_acc_qm.h +++ b/include/linux/hisi_acc_qm.h @@ -272,6 +272,20 @@ struct hisi_qm_poll_data { u16 *qp_finish_id; }; +/** + * struct qm_err_isolate + * @isolate_lock: protects device error log + * @err_threshold: user config error threshold which triggers isolation + * @is_isolate: device isolation state + * @uacce_hw_errs: index into qm device error list + */ +struct qm_err_isolate { + struct mutex isolate_lock; + u32 err_threshold; + bool is_isolate; + struct list_head qm_hw_errs; +}; + struct hisi_qm { enum qm_hw_ver ver; enum qm_fun_type fun_type; @@ -341,6 +355,7 @@ struct hisi_qm { struct qm_shaper_factor *factor; u32 mb_qos; u32 type_rate; + struct qm_err_isolate isolate_data; }; struct hisi_qp_status { -- cgit v1.2.3 From b3c71626a9333b0b29f9921a39cef30b5961766f Mon Sep 17 00:00:00 2001 From: Mao Jinlong Date: Tue, 17 Jan 2023 06:57:01 -0800 Subject: Coresight: Add coresight TPDM source driver Add driver to support Coresight device TPDM (Trace, Profiling and Diagnostics Monitor). TPDM is a monitor to collect data from different datasets. This change is to add probe/enable/disable functions for tpdm source. Signed-off-by: Tao Zhang Signed-off-by: Mao Jinlong Signed-off-by: Suzuki K Poulose Link: https://lore.kernel.org/r/20230120095301.30792-1-quic_jinlmao@quicinc.com --- drivers/hwtracing/coresight/Kconfig | 12 +++ drivers/hwtracing/coresight/Makefile | 1 + drivers/hwtracing/coresight/coresight-core.c | 5 +- drivers/hwtracing/coresight/coresight-tpdm.c | 149 +++++++++++++++++++++++++++ drivers/hwtracing/coresight/coresight-tpdm.h | 26 +++++ include/linux/coresight.h | 1 + 6 files changed, 193 insertions(+), 1 deletion(-) create mode 100644 drivers/hwtracing/coresight/coresight-tpdm.c create mode 100644 drivers/hwtracing/coresight/coresight-tpdm.h (limited to 'include/linux') diff --git a/drivers/hwtracing/coresight/Kconfig b/drivers/hwtracing/coresight/Kconfig index ba035d7894e0..e2debad59608 100644 --- a/drivers/hwtracing/coresight/Kconfig +++ b/drivers/hwtracing/coresight/Kconfig @@ -213,4 +213,16 @@ config ULTRASOC_SMB To compile this driver as a module, choose M here: the module will be called ultrasoc-smb. + +config CORESIGHT_TPDM + tristate "CoreSight Trace, Profiling & Diagnostics Monitor driver" + select CORESIGHT_LINKS_AND_SINKS + help + This driver provides support for configuring monitor. Monitors are + primarily responsible for data set collection and support the + ability to collect any permutation of data set types. + + To compile this driver as a module, choose M here: the module will be + called coresight-tpdm. + endif diff --git a/drivers/hwtracing/coresight/Makefile b/drivers/hwtracing/coresight/Makefile index 80f99d915bc9..c637376e0efd 100644 --- a/drivers/hwtracing/coresight/Makefile +++ b/drivers/hwtracing/coresight/Makefile @@ -25,6 +25,7 @@ obj-$(CONFIG_CORESIGHT_CPU_DEBUG) += coresight-cpu-debug.o obj-$(CONFIG_CORESIGHT_CATU) += coresight-catu.o obj-$(CONFIG_CORESIGHT_CTI) += coresight-cti.o obj-$(CONFIG_CORESIGHT_TRBE) += coresight-trbe.o +obj-$(CONFIG_CORESIGHT_TPDM) += coresight-tpdm.o coresight-cti-y := coresight-cti-core.o coresight-cti-platform.o \ coresight-cti-sysfs.o obj-$(CONFIG_ULTRASOC_SMB) += ultrasoc-smb.o diff --git a/drivers/hwtracing/coresight/coresight-core.c b/drivers/hwtracing/coresight/coresight-core.c index 5eb013f49a0d..a798008ac56e 100644 --- a/drivers/hwtracing/coresight/coresight-core.c +++ b/drivers/hwtracing/coresight/coresight-core.c @@ -1061,7 +1061,8 @@ static int coresight_validate_source(struct coresight_device *csdev, } if (subtype != CORESIGHT_DEV_SUBTYPE_SOURCE_PROC && - subtype != CORESIGHT_DEV_SUBTYPE_SOURCE_SOFTWARE) { + subtype != CORESIGHT_DEV_SUBTYPE_SOURCE_SOFTWARE && + subtype != CORESIGHT_DEV_SUBTYPE_SOURCE_OTHERS) { dev_err(&csdev->dev, "wrong device subtype in %s\n", function); return -EINVAL; } @@ -1130,6 +1131,7 @@ int coresight_enable(struct coresight_device *csdev) per_cpu(tracer_path, cpu) = path; break; case CORESIGHT_DEV_SUBTYPE_SOURCE_SOFTWARE: + case CORESIGHT_DEV_SUBTYPE_SOURCE_OTHERS: /* * Use the hash of source's device name as ID * and map the ID to the pointer of the path. @@ -1179,6 +1181,7 @@ void coresight_disable(struct coresight_device *csdev) per_cpu(tracer_path, cpu) = NULL; break; case CORESIGHT_DEV_SUBTYPE_SOURCE_SOFTWARE: + case CORESIGHT_DEV_SUBTYPE_SOURCE_OTHERS: hash = hashlen_hash(hashlen_string(NULL, dev_name(&csdev->dev))); /* Find the path by the hash. */ path = idr_find(&path_idr, hash); diff --git a/drivers/hwtracing/coresight/coresight-tpdm.c b/drivers/hwtracing/coresight/coresight-tpdm.c new file mode 100644 index 000000000000..baeabc2ab168 --- /dev/null +++ b/drivers/hwtracing/coresight/coresight-tpdm.c @@ -0,0 +1,149 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2023 Qualcomm Innovation Center, Inc. All rights reserved. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "coresight-priv.h" +#include "coresight-tpdm.h" + +DEFINE_CORESIGHT_DEVLIST(tpdm_devs, "tpdm"); + +/* TPDM enable operations */ +static int tpdm_enable(struct coresight_device *csdev, + struct perf_event *event, u32 mode) +{ + struct tpdm_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + + spin_lock(&drvdata->spinlock); + if (drvdata->enable) { + spin_unlock(&drvdata->spinlock); + return -EBUSY; + } + + drvdata->enable = true; + spin_unlock(&drvdata->spinlock); + + dev_dbg(drvdata->dev, "TPDM tracing enabled\n"); + return 0; +} + +/* TPDM disable operations */ +static void tpdm_disable(struct coresight_device *csdev, + struct perf_event *event) +{ + struct tpdm_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + + spin_lock(&drvdata->spinlock); + if (!drvdata->enable) { + spin_unlock(&drvdata->spinlock); + return; + } + + drvdata->enable = false; + spin_unlock(&drvdata->spinlock); + + dev_dbg(drvdata->dev, "TPDM tracing disabled\n"); +} + +static const struct coresight_ops_source tpdm_source_ops = { + .enable = tpdm_enable, + .disable = tpdm_disable, +}; + +static const struct coresight_ops tpdm_cs_ops = { + .source_ops = &tpdm_source_ops, +}; + +static int tpdm_probe(struct amba_device *adev, const struct amba_id *id) +{ + void __iomem *base; + struct device *dev = &adev->dev; + struct coresight_platform_data *pdata; + struct tpdm_drvdata *drvdata; + struct coresight_desc desc = { 0 }; + + pdata = coresight_get_platform_data(dev); + if (IS_ERR(pdata)) + return PTR_ERR(pdata); + adev->dev.platform_data = pdata; + + /* driver data*/ + drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL); + if (!drvdata) + return -ENOMEM; + drvdata->dev = &adev->dev; + dev_set_drvdata(dev, drvdata); + + base = devm_ioremap_resource(dev, &adev->res); + if (IS_ERR(base)) + return PTR_ERR(base); + + drvdata->base = base; + + /* Set up coresight component description */ + desc.name = coresight_alloc_device_name(&tpdm_devs, dev); + if (!desc.name) + return -ENOMEM; + desc.type = CORESIGHT_DEV_TYPE_SOURCE; + desc.subtype.source_subtype = CORESIGHT_DEV_SUBTYPE_SOURCE_OTHERS; + desc.ops = &tpdm_cs_ops; + desc.pdata = adev->dev.platform_data; + desc.dev = &adev->dev; + desc.access = CSDEV_ACCESS_IOMEM(base); + drvdata->csdev = coresight_register(&desc); + if (IS_ERR(drvdata->csdev)) + return PTR_ERR(drvdata->csdev); + + spin_lock_init(&drvdata->spinlock); + /* Decrease pm refcount when probe is done.*/ + pm_runtime_put(&adev->dev); + + return 0; +} + +static void __exit tpdm_remove(struct amba_device *adev) +{ + struct tpdm_drvdata *drvdata = dev_get_drvdata(&adev->dev); + + coresight_unregister(drvdata->csdev); +} + +/* + * Different TPDM has different periph id. + * The difference is 0-7 bits' value. So ignore 0-7 bits. + */ +static struct amba_id tpdm_ids[] = { + { + .id = 0x000f0e00, + .mask = 0x000fff00, + }, + { 0, 0}, +}; + +static struct amba_driver tpdm_driver = { + .drv = { + .name = "coresight-tpdm", + .owner = THIS_MODULE, + .suppress_bind_attrs = true, + }, + .probe = tpdm_probe, + .id_table = tpdm_ids, + .remove = tpdm_remove, +}; + +module_amba_driver(tpdm_driver); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Trace, Profiling & Diagnostic Monitor driver"); diff --git a/drivers/hwtracing/coresight/coresight-tpdm.h b/drivers/hwtracing/coresight/coresight-tpdm.h new file mode 100644 index 000000000000..2ec8a6810771 --- /dev/null +++ b/drivers/hwtracing/coresight/coresight-tpdm.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2023 Qualcomm Innovation Center, Inc. All rights reserved. + */ + +#ifndef _CORESIGHT_CORESIGHT_TPDM_H +#define _CORESIGHT_CORESIGHT_TPDM_H + +/** + * struct tpdm_drvdata - specifics associated to an TPDM component + * @base: memory mapped base address for this component. + * @dev: The device entity associated to this component. + * @csdev: component vitals needed by the framework. + * @spinlock: lock for the drvdata value. + * @enable: enable status of the component. + */ + +struct tpdm_drvdata { + void __iomem *base; + struct device *dev; + struct coresight_device *csdev; + spinlock_t spinlock; + bool enable; +}; + +#endif /* _CORESIGHT_CORESIGHT_TPDM_H */ diff --git a/include/linux/coresight.h b/include/linux/coresight.h index e241eb88dfb9..f19a47b9bb5a 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -61,6 +61,7 @@ enum coresight_dev_subtype_source { CORESIGHT_DEV_SUBTYPE_SOURCE_PROC, CORESIGHT_DEV_SUBTYPE_SOURCE_BUS, CORESIGHT_DEV_SUBTYPE_SOURCE_SOFTWARE, + CORESIGHT_DEV_SUBTYPE_SOURCE_OTHERS, }; enum coresight_dev_subtype_helper { -- cgit v1.2.3 From 6640727fc55b7f0b561e927bc9c5b9d4c459fd8e Mon Sep 17 00:00:00 2001 From: Maciej W. Rozycki Date: Sun, 8 Jan 2023 21:56:52 +0000 Subject: parport_pc: Let chipset drivers mask ECR bits on writes Provide an `ecr_writable' parameter to `__parport_pc_probe_port' so that callers can specify a mask of bits to modify on ECR writes. To avoid the need for separate bit set and bit clear masks always set bit 0 whenever a non-zero mask has been set, as all the currently known cases where a mask is required, that is Oxford Semiconductor devices, do require this bit to be set. If further cases are discovered where the bit is required to be clear, we can update code accordingly, but chances are very low as the bit is supposed to be read-only[1]. Skip ECR probing, which can be problematic as the Oxford Semiconductor OX12PCI840 part has been reported to lock up on setting bit 2, whenever a non-zero mask has been requested by a port subdriver, assuming that the ECR must be there if the subdriver has requested a specific way to access it. References: [1] "Extended Capabilities Port Protocol and ISA Interface Standard", Microsoft Corporation, Revision: 1.14, July 14, 1993, Table 14 "Extended Control Register" Signed-off-by: Maciej W. Rozycki Signed-off-by: Sudip Mukherjee Link: https://lore.kernel.org/r/20230108215656.6433-3-sudipm.mukherjee@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/parport/parport_pc.c | 46 ++++++++++++++++++++++++++++---------------- include/linux/parport_pc.h | 3 +++ 2 files changed, 32 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/drivers/parport/parport_pc.c b/drivers/parport/parport_pc.c index 9daaaaa305e6..ad49fd356c7b 100644 --- a/drivers/parport/parport_pc.c +++ b/drivers/parport/parport_pc.c @@ -106,15 +106,22 @@ static int pnp_registered_parport; static void frob_econtrol(struct parport *pb, unsigned char m, unsigned char v) { + const struct parport_pc_private *priv = pb->physport->private_data; + unsigned char ecr_writable = priv->ecr_writable; unsigned char ectr = 0; + unsigned char new; if (m != 0xff) ectr = inb(ECONTROL(pb)); - pr_debug("frob_econtrol(%02x,%02x): %02x -> %02x\n", - m, v, ectr, (ectr & ~m) ^ v); + new = (ectr & ~m) ^ v; + if (ecr_writable) + /* All known users of the ECR mask require bit 0 to be set. */ + new = (new & ecr_writable) | 1; - outb((ectr & ~m) ^ v, ECONTROL(pb)); + pr_debug("frob_econtrol(%02x,%02x): %02x -> %02x\n", m, v, ectr, new); + + outb(new, ECONTROL(pb)); } static inline void frob_set_mode(struct parport *p, int mode) @@ -1479,21 +1486,24 @@ static int parport_ECR_present(struct parport *pb) struct parport_pc_private *priv = pb->private_data; unsigned char r = 0xc; - outb(r, CONTROL(pb)); - if ((inb(ECONTROL(pb)) & 0x3) == (r & 0x3)) { - outb(r ^ 0x2, CONTROL(pb)); /* Toggle bit 1 */ + if (!priv->ecr_writable) { + outb(r, CONTROL(pb)); + if ((inb(ECONTROL(pb)) & 0x3) == (r & 0x3)) { + outb(r ^ 0x2, CONTROL(pb)); /* Toggle bit 1 */ - r = inb(CONTROL(pb)); - if ((inb(ECONTROL(pb)) & 0x2) == (r & 0x2)) - goto no_reg; /* Sure that no ECR register exists */ - } + r = inb(CONTROL(pb)); + if ((inb(ECONTROL(pb)) & 0x2) == (r & 0x2)) + /* Sure that no ECR register exists */ + goto no_reg; + } - if ((inb(ECONTROL(pb)) & 0x3) != 0x1) - goto no_reg; + if ((inb(ECONTROL(pb)) & 0x3) != 0x1) + goto no_reg; - ECR_WRITE(pb, 0x34); - if (inb(ECONTROL(pb)) != 0x35) - goto no_reg; + ECR_WRITE(pb, 0x34); + if (inb(ECONTROL(pb)) != 0x35) + goto no_reg; + } priv->ecr = 1; outb(0xc, CONTROL(pb)); @@ -2005,7 +2015,8 @@ static struct parport *__parport_pc_probe_port(unsigned long int base, int irq, int dma, struct device *dev, int irqflags, - unsigned int mode_mask) + unsigned int mode_mask, + unsigned char ecr_writable) { struct parport_pc_private *priv; struct parport_operations *ops; @@ -2054,6 +2065,7 @@ static struct parport *__parport_pc_probe_port(unsigned long int base, priv->ctr = 0xc; priv->ctr_writable = ~0x10; priv->ecr = 0; + priv->ecr_writable = ecr_writable; priv->fifo_depth = 0; priv->dma_buf = NULL; priv->dma_handle = 0; @@ -2256,7 +2268,7 @@ struct parport *parport_pc_probe_port(unsigned long int base, int irqflags) { return __parport_pc_probe_port(base, base_hi, irq, dma, - dev, irqflags, 0); + dev, irqflags, 0, 0); } EXPORT_SYMBOL(parport_pc_probe_port); diff --git a/include/linux/parport_pc.h b/include/linux/parport_pc.h index 3d6fc576d6a1..f1ec5c10c3b3 100644 --- a/include/linux/parport_pc.h +++ b/include/linux/parport_pc.h @@ -26,6 +26,9 @@ struct parport_pc_private { /* Whether or not there's an ECR. */ int ecr; + /* Bitmask of writable ECR bits. */ + unsigned char ecr_writable; + /* Number of PWords that FIFO will hold. */ int fifo_depth; -- cgit v1.2.3 From a86367803838b369fe5486ac18771d14723c258c Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Thu, 10 Nov 2022 18:23:07 +0800 Subject: drivers: base: transport_class: fix possible memory leak Current some drivers(like iscsi) call transport_register_device() failed, they don't call transport_destroy_device() to release the memory allocated in transport_setup_device(), because they don't know what was done, it should be internal thing to release the resource in register function. So fix this leak by calling destroy function inside register function. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Yang Yingliang Link: https://lore.kernel.org/r/20221110102307.3492557-1-yangyingliang@huawei.com Signed-off-by: Greg Kroah-Hartman --- include/linux/transport_class.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/transport_class.h b/include/linux/transport_class.h index 63076fb835e3..2efc271a96fa 100644 --- a/include/linux/transport_class.h +++ b/include/linux/transport_class.h @@ -70,8 +70,14 @@ void transport_destroy_device(struct device *); static inline int transport_register_device(struct device *dev) { + int ret; + transport_setup_device(dev); - return transport_add_device(dev); + ret = transport_add_device(dev); + if (ret) + transport_destroy_device(dev); + + return ret; } static inline void -- cgit v1.2.3 From 8aaec1177521eed07240ec5ac2bc55b2a1c35b42 Mon Sep 17 00:00:00 2001 From: joewu (吳仲振) Date: Fri, 20 Jan 2023 09:17:02 -0800 Subject: Input: cros_ec_keyb - add 3 buttons for monitor function Add 3 extra buttons: 'brightness up', 'brightness down' and 'screen lock' to support monitor manipulating function. Signed-off-by: Joe Wu Link: https://lore.kernel.org/r/e23628e2cb464d238eb1c33a9e1e516b@msi.com Signed-off-by: Dmitry Torokhov --- drivers/input/keyboard/cros_ec_keyb.c | 15 +++++++++++++++ include/linux/platform_data/cros_ec_commands.h | 3 +++ 2 files changed, 18 insertions(+) (limited to 'include/linux') diff --git a/drivers/input/keyboard/cros_ec_keyb.c b/drivers/input/keyboard/cros_ec_keyb.c index 6f435125ec03..e7ecfca838df 100644 --- a/drivers/input/keyboard/cros_ec_keyb.c +++ b/drivers/input/keyboard/cros_ec_keyb.c @@ -100,6 +100,21 @@ static const struct cros_ec_bs_map cros_ec_keyb_bs[] = { .code = KEY_VOLUMEDOWN, .bit = EC_MKBP_VOL_DOWN, }, + { + .ev_type = EV_KEY, + .code = KEY_BRIGHTNESSUP, + .bit = EC_MKBP_BRI_UP, + }, + { + .ev_type = EV_KEY, + .code = KEY_BRIGHTNESSDOWN, + .bit = EC_MKBP_BRI_DOWN, + }, + { + .ev_type = EV_KEY, + .code = KEY_SCREENLOCK, + .bit = EC_MKBP_SCREEN_LOCK, + }, /* Switches */ { diff --git a/include/linux/platform_data/cros_ec_commands.h b/include/linux/platform_data/cros_ec_commands.h index 5744a2d746aa..a2073ed43972 100644 --- a/include/linux/platform_data/cros_ec_commands.h +++ b/include/linux/platform_data/cros_ec_commands.h @@ -3471,6 +3471,9 @@ struct ec_response_get_next_event_v1 { #define EC_MKBP_VOL_UP 1 #define EC_MKBP_VOL_DOWN 2 #define EC_MKBP_RECOVERY 3 +#define EC_MKBP_BRI_UP 4 +#define EC_MKBP_BRI_DOWN 5 +#define EC_MKBP_SCREEN_LOCK 6 /* Switches */ #define EC_MKBP_LID_OPEN 0 -- cgit v1.2.3 From aca1d27ac38a61d7db4b56418386992cb96b63f0 Mon Sep 17 00:00:00 2001 From: Demi Marie Obenour Date: Thu, 19 Jan 2023 14:03:57 -0500 Subject: efi: xen: Implement memory descriptor lookup based on hypercall Xen on x86 boots dom0 in EFI mode but without providing a memory map. This means that some consistency checks we would like to perform on configuration tables or other data structures in memory are not currently possible. Xen does, however, expose EFI memory descriptor info via a Xen hypercall, so let's wire that up instead. It turns out that the returned information is not identical to what Linux's efi_mem_desc_lookup would return: the address returned is the address passed to the hypercall, and the size returned is the number of bytes remaining in the configuration table. However, none of the callers of efi_mem_desc_lookup() currently care about this. In the future, Xen may gain a hypercall that returns the actual start address, which can be used instead. Co-developed-by: Ard Biesheuvel Signed-off-by: Ard Biesheuvel Signed-off-by: Demi Marie Obenour Tested-by: Marek Marczykowski-Górecki Signed-off-by: Ard Biesheuvel --- drivers/firmware/efi/efi.c | 5 ++++- drivers/xen/efi.c | 36 ++++++++++++++++++++++++++++++++++++ include/linux/efi.h | 1 + 3 files changed, 41 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index d295be116039..90142f6e588d 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -478,7 +478,7 @@ void __init efi_find_mirror(void) * and if so, populate the supplied memory descriptor with the appropriate * data. */ -int efi_mem_desc_lookup(u64 phys_addr, efi_memory_desc_t *out_md) +int __efi_mem_desc_lookup(u64 phys_addr, efi_memory_desc_t *out_md) { efi_memory_desc_t *md; @@ -512,6 +512,9 @@ int efi_mem_desc_lookup(u64 phys_addr, efi_memory_desc_t *out_md) return -ENOENT; } +extern int efi_mem_desc_lookup(u64 phys_addr, efi_memory_desc_t *out_md) + __weak __alias(__efi_mem_desc_lookup); + /* * Calculate the highest address of an efi memory descriptor. */ diff --git a/drivers/xen/efi.c b/drivers/xen/efi.c index d1ff2186ebb4..3c792353b730 100644 --- a/drivers/xen/efi.c +++ b/drivers/xen/efi.c @@ -26,6 +26,7 @@ #include #include +#include #include #include @@ -292,3 +293,38 @@ void __init xen_efi_runtime_setup(void) efi.get_next_high_mono_count = xen_efi_get_next_high_mono_count; efi.reset_system = xen_efi_reset_system; } + +int efi_mem_desc_lookup(u64 phys_addr, efi_memory_desc_t *out_md) +{ + static_assert(XEN_PAGE_SHIFT == EFI_PAGE_SHIFT, + "Mismatch between EFI_PAGE_SHIFT and XEN_PAGE_SHIFT"); + struct xen_platform_op op; + union xenpf_efi_info *info = &op.u.firmware_info.u.efi_info; + int rc; + + if (!efi_enabled(EFI_PARAVIRT) || efi_enabled(EFI_MEMMAP)) + return __efi_mem_desc_lookup(phys_addr, out_md); + phys_addr &= ~(u64)(EFI_PAGE_SIZE - 1); + op = (struct xen_platform_op) { + .cmd = XENPF_firmware_info, + .u.firmware_info = { + .type = XEN_FW_EFI_INFO, + .index = XEN_FW_EFI_MEM_INFO, + .u.efi_info.mem.addr = phys_addr, + .u.efi_info.mem.size = U64_MAX - phys_addr, + }, + }; + + rc = HYPERVISOR_platform_op(&op); + if (rc) { + pr_warn("Failed to lookup header 0x%llx in Xen memory map: error %d\n", + phys_addr, rc); + } + + out_md->phys_addr = info->mem.addr; + out_md->num_pages = info->mem.size >> EFI_PAGE_SHIFT; + out_md->type = info->mem.type; + out_md->attribute = info->mem.attr; + + return 0; +} diff --git a/include/linux/efi.h b/include/linux/efi.h index f6b107da1cbc..4d7a44f60990 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -731,6 +731,7 @@ extern u64 efi_mem_attribute (unsigned long phys_addr, unsigned long size); extern int __init efi_uart_console_only (void); extern u64 efi_mem_desc_end(efi_memory_desc_t *md); extern int efi_mem_desc_lookup(u64 phys_addr, efi_memory_desc_t *out_md); +extern int __efi_mem_desc_lookup(u64 phys_addr, efi_memory_desc_t *out_md); extern void efi_mem_reserve(phys_addr_t addr, u64 size); extern int efi_mem_reserve_persistent(phys_addr_t addr, u64 size); extern void efi_initialize_iomem_resources(struct resource *code_resource, -- cgit v1.2.3 From c0fecaa44dc341d86e4ce96efcda9ea8b4c106af Mon Sep 17 00:00:00 2001 From: Demi Marie Obenour Date: Thu, 19 Jan 2023 14:03:58 -0500 Subject: efi: Apply allowlist to EFI configuration tables when running under Xen As it turns out, Xen does not guarantee that EFI boot services data regions in memory are preserved, which means that EFI configuration tables pointing into such memory regions may be corrupted before the dom0 OS has had a chance to inspect them. This is causing problems for Qubes OS when it attempts to perform system firmware updates, which requires that the contents of the EFI System Resource Table are valid when the fwupd userspace program runs. However, other configuration tables such as the memory attributes table or the runtime properties table are equally affected, and so we need a comprehensive workaround that works for any table type. So when running under Xen, check the EFI memory descriptor covering the start of the table, and disregard the table if it does not reside in memory that is preserved by Xen. Co-developed-by: Ard Biesheuvel Signed-off-by: Ard Biesheuvel Signed-off-by: Demi Marie Obenour Tested-by: Marek Marczykowski-Górecki Signed-off-by: Ard Biesheuvel --- drivers/firmware/efi/efi.c | 13 ++++++++++--- drivers/xen/efi.c | 25 +++++++++++++++++++++++++ include/linux/efi.h | 10 ++++++++++ 3 files changed, 45 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index 90142f6e588d..19c1191e6210 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -589,13 +589,20 @@ static __init int match_config_table(const efi_guid_t *guid, int i; for (i = 0; efi_guidcmp(table_types[i].guid, NULL_GUID); i++) { - if (!efi_guidcmp(*guid, table_types[i].guid)) { - *(table_types[i].ptr) = table; + if (efi_guidcmp(*guid, table_types[i].guid)) + continue; + + if (!efi_config_table_is_usable(guid, table)) { if (table_types[i].name[0]) - pr_cont("%s=0x%lx ", + pr_cont("(%s=0x%lx unusable) ", table_types[i].name, table); return 1; } + + *(table_types[i].ptr) = table; + if (table_types[i].name[0]) + pr_cont("%s=0x%lx ", table_types[i].name, table); + return 1; } return 0; diff --git a/drivers/xen/efi.c b/drivers/xen/efi.c index 3c792353b730..fb321cd6415a 100644 --- a/drivers/xen/efi.c +++ b/drivers/xen/efi.c @@ -328,3 +328,28 @@ int efi_mem_desc_lookup(u64 phys_addr, efi_memory_desc_t *out_md) return 0; } + +bool __init xen_efi_config_table_is_usable(const efi_guid_t *guid, + unsigned long table) +{ + efi_memory_desc_t md; + int rc; + + if (!efi_enabled(EFI_PARAVIRT)) + return true; + + rc = efi_mem_desc_lookup(table, &md); + if (rc) + return false; + + switch (md.type) { + case EFI_RUNTIME_SERVICES_CODE: + case EFI_RUNTIME_SERVICES_DATA: + case EFI_ACPI_RECLAIM_MEMORY: + case EFI_ACPI_MEMORY_NVS: + case EFI_RESERVED_TYPE: + return true; + default: + return false; + } +} diff --git a/include/linux/efi.h b/include/linux/efi.h index 4d7a44f60990..1a1adc8d3ba3 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1322,4 +1322,14 @@ struct linux_efi_initrd { /* Header of a populated EFI secret area */ #define EFI_SECRET_TABLE_HEADER_GUID EFI_GUID(0x1e74f542, 0x71dd, 0x4d66, 0x96, 0x3e, 0xef, 0x42, 0x87, 0xff, 0x17, 0x3b) +bool xen_efi_config_table_is_usable(const efi_guid_t *guid, unsigned long table); + +static inline +bool efi_config_table_is_usable(const efi_guid_t *guid, unsigned long table) +{ + if (!IS_ENABLED(CONFIG_XEN_EFI)) + return true; + return xen_efi_config_table_is_usable(guid, table); +} + #endif /* _LINUX_EFI_H */ -- cgit v1.2.3 From 43651e60aa167974955b23f73a25eb79886ab6d0 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Mon, 16 Jan 2023 10:47:35 +0100 Subject: mtd: rawnand: Fix nand_chip kdoc Describe the continuous read nand_chip fields to avoid the following htmldocs warning: include/linux/mtd/rawnand.h:1325: warning: Function parameter or member 'cont_read' not described in 'nand_chip' Reported-by: Stephen Rothwell Fixes: 003fe4b9545b ("mtd: rawnand: Support for sequential cache reads") Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20230116094735.11483-1-miquel.raynal@bootlin.com --- include/linux/mtd/rawnand.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 1b0936fe3c6e..f8d4be9c587a 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1260,6 +1260,10 @@ struct nand_secure_region { * @read_retries: The number of read retry modes supported * @secure_regions: Structure containing the secure regions info * @nr_secure_regions: Number of secure regions + * @cont_read: Sequential page read internals + * @cont_read.ongoing: Whether a continuous read is ongoing or not + * @cont_read.first_page: Start of the continuous read operation + * @cont_read.last_page: End of the continuous read operation * @controller: The hardware controller structure which is shared among multiple * independent devices * @ecc: The ECC controller structure -- cgit v1.2.3 From 8681e3663411ee6b64dd0714b23f5c86f64f7533 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Fri, 20 Jan 2023 18:31:02 +0100 Subject: drm/simpledrm: Support the XB24/AB24 format Add XB24 and AB24 to the list of supported formats. The format helpers support conversion to these formats and they are documented in the simple-framebuffer device tree bindings. Reviewed-by: Thomas Zimmermann Signed-off-by: Thierry Reding Link: https://patchwork.freedesktop.org/patch/msgid/20230120173103.4002342-8-thierry.reding@gmail.com --- include/linux/platform_data/simplefb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/simplefb.h b/include/linux/platform_data/simplefb.h index 27ea99af6e1d..4f94d52ac99f 100644 --- a/include/linux/platform_data/simplefb.h +++ b/include/linux/platform_data/simplefb.h @@ -22,6 +22,7 @@ { "r8g8b8", 24, {16, 8}, {8, 8}, {0, 8}, {0, 0}, DRM_FORMAT_RGB888 }, \ { "x8r8g8b8", 32, {16, 8}, {8, 8}, {0, 8}, {0, 0}, DRM_FORMAT_XRGB8888 }, \ { "a8r8g8b8", 32, {16, 8}, {8, 8}, {0, 8}, {24, 8}, DRM_FORMAT_ARGB8888 }, \ + { "x8b8g8r8", 32, {0, 8}, {8, 8}, {16, 8}, {0, 0}, DRM_FORMAT_XBGR8888 }, \ { "a8b8g8r8", 32, {0, 8}, {8, 8}, {16, 8}, {24, 8}, DRM_FORMAT_ABGR8888 }, \ { "x2r10g10b10", 32, {20, 10}, {10, 10}, {0, 10}, {0, 0}, DRM_FORMAT_XRGB2101010 }, \ { "a2r10g10b10", 32, {20, 10}, {10, 10}, {0, 10}, {30, 2}, DRM_FORMAT_ARGB2101010 }, \ -- cgit v1.2.3 From 8786b095df02c1b881643146869a7d6f80411e6a Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Wed, 18 Jan 2023 22:55:12 +0100 Subject: i2c: gpio: support write-only sda/scl w/o pull-up There are slave devices that understand I2C but have read-only SDA and SCL. Examples are FD650 7-segment LED controller and its derivatives. Typical board designs don't even have a pull-up for both pins. Handle the new attributes for write-only SDA and missing pull-up on SDA/SCL. For either pin the open-drain and has-no-pullup properties are mutually-exclusive, what is documented in the DT property documentation. We don't add an extra warning here because the open-drain properties are marked deprecated anyway. Signed-off-by: Heiner Kallweit [wsa: switched to device properties] Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-gpio.c | 13 ++++++++++--- include/linux/platform_data/i2c-gpio.h | 9 +++++++++ 2 files changed, 19 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/i2c/busses/i2c-gpio.c b/drivers/i2c/busses/i2c-gpio.c index e4a59840c4fc..1794c0399f22 100644 --- a/drivers/i2c/busses/i2c-gpio.c +++ b/drivers/i2c/busses/i2c-gpio.c @@ -317,6 +317,12 @@ static void i2c_gpio_get_properties(struct device *dev, device_property_read_bool(dev, "i2c-gpio,scl-open-drain"); pdata->scl_is_output_only = device_property_read_bool(dev, "i2c-gpio,scl-output-only"); + pdata->sda_is_output_only = + device_property_read_bool(dev, "i2c-gpio,sda-output-only"); + pdata->sda_has_no_pullup = + device_property_read_bool(dev, "i2c-gpio,sda-has-no-pullup"); + pdata->scl_has_no_pullup = + device_property_read_bool(dev, "i2c-gpio,scl-has-no-pullup"); } static struct gpio_desc *i2c_gpio_get_desc(struct device *dev, @@ -393,7 +399,7 @@ static int i2c_gpio_probe(struct platform_device *pdev) * handle them as we handle any other output. Else we enforce open * drain as this is required for an I2C bus. */ - if (pdata->sda_is_open_drain) + if (pdata->sda_is_open_drain || pdata->sda_has_no_pullup) gflags = GPIOD_OUT_HIGH; else gflags = GPIOD_OUT_HIGH_OPEN_DRAIN; @@ -401,7 +407,7 @@ static int i2c_gpio_probe(struct platform_device *pdev) if (IS_ERR(priv->sda)) return PTR_ERR(priv->sda); - if (pdata->scl_is_open_drain) + if (pdata->scl_is_open_drain || pdata->scl_has_no_pullup) gflags = GPIOD_OUT_HIGH; else gflags = GPIOD_OUT_HIGH_OPEN_DRAIN; @@ -419,7 +425,8 @@ static int i2c_gpio_probe(struct platform_device *pdev) if (!pdata->scl_is_output_only) bit_data->getscl = i2c_gpio_getscl; - bit_data->getsda = i2c_gpio_getsda; + if (!pdata->sda_is_output_only) + bit_data->getsda = i2c_gpio_getsda; if (pdata->udelay) bit_data->udelay = pdata->udelay; diff --git a/include/linux/platform_data/i2c-gpio.h b/include/linux/platform_data/i2c-gpio.h index a907774fd177..545639bcca72 100644 --- a/include/linux/platform_data/i2c-gpio.h +++ b/include/linux/platform_data/i2c-gpio.h @@ -16,16 +16,25 @@ * isn't actively driven high when setting the output value high. * gpio_get_value() must return the actual pin state even if the * pin is configured as an output. + * @sda_is_output_only: SDA output drivers can't be turned off. + * This is for clients that can only read SDA/SCL. + * @sda_has_no_pullup: SDA is used in a non-compliant way and has no pull-up. + * Therefore disable open-drain. * @scl_is_open_drain: SCL is set up as open drain. Same requirements * as for sda_is_open_drain apply. * @scl_is_output_only: SCL output drivers cannot be turned off. + * @scl_has_no_pullup: SCL is used in a non-compliant way and has no pull-up. + * Therefore disable open-drain. */ struct i2c_gpio_platform_data { int udelay; int timeout; unsigned int sda_is_open_drain:1; + unsigned int sda_is_output_only:1; + unsigned int sda_has_no_pullup:1; unsigned int scl_is_open_drain:1; unsigned int scl_is_output_only:1; + unsigned int scl_has_no_pullup:1; }; #endif /* _LINUX_I2C_GPIO_H */ -- cgit v1.2.3 From 998101f2a78cf506022f2094461105cb3d00e19f Mon Sep 17 00:00:00 2001 From: Javier Martinez Canillas Date: Sat, 21 Jan 2023 20:24:16 +0100 Subject: fbdev: Remove unused struct fb_deferred_io .first_io field This optional callback was added in the commit 1f45f9dbb392 ("fb_defio: add first_io callback") but it was never used by a driver. Let's remove it since it's unlikely that will be used after a decade that was added. Signed-off-by: Javier Martinez Canillas Reviewed-by: Thomas Zimmermann Link: https://patchwork.freedesktop.org/patch/msgid/20230121192418.2814955-2-javierm@redhat.com --- drivers/video/fbdev/core/fb_defio.c | 4 ---- include/linux/fb.h | 1 - 2 files changed, 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/video/fbdev/core/fb_defio.c b/drivers/video/fbdev/core/fb_defio.c index c730253ab85c..1b680742b7f3 100644 --- a/drivers/video/fbdev/core/fb_defio.c +++ b/drivers/video/fbdev/core/fb_defio.c @@ -157,10 +157,6 @@ static vm_fault_t fb_deferred_io_track_page(struct fb_info *info, unsigned long /* protect against the workqueue changing the page list */ mutex_lock(&fbdefio->lock); - /* first write in this cycle, notify the driver */ - if (fbdefio->first_io && list_empty(&fbdefio->pagereflist)) - fbdefio->first_io(info); - pageref = fb_deferred_io_pageref_get(info, offset, page); if (WARN_ON_ONCE(!pageref)) { ret = VM_FAULT_OOM; diff --git a/include/linux/fb.h b/include/linux/fb.h index 30183fd259ae..daf336385613 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -215,7 +215,6 @@ struct fb_deferred_io { struct mutex lock; /* mutex that protects the pageref list */ struct list_head pagereflist; /* list of pagerefs for touched pages */ /* callback */ - void (*first_io)(struct fb_info *info); void (*deferred_io)(struct fb_info *info, struct list_head *pagelist); }; #endif -- cgit v1.2.3 From b1cd16330c8c6bc73e769b7b63e46cec2e292d6c Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Thu, 17 Nov 2022 23:34:19 +0300 Subject: KVM: account allocation in generic version of kvm_arch_alloc_vm() Account the allocation of VMs in the generic version of kvm_arch_alloc_vm(), the VM is tied to the current task/process. Note, x86 already accounts its allocation. Signed-off-by: Alexey Dobriyan Reviewed-by: Sean Christopherson Link: https://lore.kernel.org/r/Y3aay2u2KQgiR0un@p183 [sean: reworded changelog] Signed-off-by: Sean Christopherson --- include/linux/kvm_host.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 109b18e2789c..c2bd15204c3f 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1461,7 +1461,7 @@ int kvm_arch_create_vm_debugfs(struct kvm *kvm); */ static inline struct kvm *kvm_arch_alloc_vm(void) { - return kzalloc(sizeof(struct kvm), GFP_KERNEL); + return kzalloc(sizeof(struct kvm), GFP_KERNEL_ACCOUNT); } #endif -- cgit v1.2.3 From b9926482ab91cd6dc19e28ae4f0ae98c6c1217d7 Mon Sep 17 00:00:00 2001 From: Wang Liang Date: Tue, 20 Sep 2022 14:02:10 +0800 Subject: kvm_host.h: fix spelling typo in function declaration Make parameters in function declaration consistent with those in function definition for better cscope-ability Signed-off-by: Wang Liang Reviewed-by: Sean Christopherson Link: https://lore.kernel.org/r/20220920060210.4842-1-wangliangzz@126.com Signed-off-by: Sean Christopherson --- include/linux/kvm_host.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index c2bd15204c3f..a7d6a6111f5e 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1353,7 +1353,7 @@ void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu); bool kvm_vcpu_wake_up(struct kvm_vcpu *vcpu); void kvm_vcpu_kick(struct kvm_vcpu *vcpu); int kvm_vcpu_yield_to(struct kvm_vcpu *target); -void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu, bool usermode_vcpu_not_eligible); +void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu, bool yield_to_kernel_mode); void kvm_flush_remote_tlbs(struct kvm *kvm); -- cgit v1.2.3 From e251c21372c07694f547afe3c9828f7f6ef01267 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Fri, 20 Jan 2023 18:42:48 +0100 Subject: of: Introduce of_translate_dma_region() This function is similar to of_translate_dma_address() but also reads a length in addition to an address from a device tree property. Reviewed-by: Rob Herring Signed-off-by: Thierry Reding Link: https://lore.kernel.org/r/20230120174251.4004100-2-thierry.reding@gmail.com Signed-off-by: Joerg Roedel --- drivers/of/address.c | 41 +++++++++++++++++++++++++++++++++++++++++ include/linux/of_address.h | 2 ++ 2 files changed, 43 insertions(+) (limited to 'include/linux') diff --git a/drivers/of/address.c b/drivers/of/address.c index c34ac33b7338..14f137a21b0c 100644 --- a/drivers/of/address.c +++ b/drivers/of/address.c @@ -626,6 +626,47 @@ u64 of_translate_dma_address(struct device_node *dev, const __be32 *in_addr) } EXPORT_SYMBOL(of_translate_dma_address); +/** + * of_translate_dma_region - Translate device tree address and size tuple + * @dev: device tree node for which to translate + * @prop: pointer into array of cells + * @start: return value for the start of the DMA range + * @length: return value for the length of the DMA range + * + * Returns a pointer to the cell immediately following the translated DMA region. + */ +const __be32 *of_translate_dma_region(struct device_node *dev, const __be32 *prop, + phys_addr_t *start, size_t *length) +{ + struct device_node *parent; + u64 address, size; + int na, ns; + + parent = __of_get_dma_parent(dev); + if (!parent) + return NULL; + + na = of_bus_n_addr_cells(parent); + ns = of_bus_n_size_cells(parent); + + of_node_put(parent); + + address = of_translate_dma_address(dev, prop); + if (address == OF_BAD_ADDR) + return NULL; + + size = of_read_number(prop + na, ns); + + if (start) + *start = address; + + if (length) + *length = size; + + return prop + na + ns; +} +EXPORT_SYMBOL(of_translate_dma_region); + const __be32 *__of_get_address(struct device_node *dev, int index, int bar_no, u64 *size, unsigned int *flags) { diff --git a/include/linux/of_address.h b/include/linux/of_address.h index 265f26eeaf6b..376671594746 100644 --- a/include/linux/of_address.h +++ b/include/linux/of_address.h @@ -38,6 +38,8 @@ struct of_pci_range { /* Translate a DMA address from device space to CPU space */ extern u64 of_translate_dma_address(struct device_node *dev, const __be32 *in_addr); +extern const __be32 *of_translate_dma_region(struct device_node *dev, const __be32 *addr, + phys_addr_t *start, size_t *length); #ifdef CONFIG_OF_ADDRESS extern u64 of_translate_address(struct device_node *np, const __be32 *addr); -- cgit v1.2.3 From a5bf3cfce8cb77d9d24613ab52d520896f83dd48 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Fri, 20 Jan 2023 18:42:50 +0100 Subject: iommu: Implement of_iommu_get_resv_regions() This is an implementation that IOMMU drivers can use to obtain reserved memory regions from a device tree node. It uses the reserved-memory DT bindings to find the regions associated with a given device. If these regions are marked accordingly, identity mappings will be created for them in the IOMMU domain that the devices will be attached to. Cc: Frank Rowand Cc: devicetree@vger.kernel.org Reviewed-by: Rob Herring Acked-by: Robin Murphy Signed-off-by: Thierry Reding Link: https://lore.kernel.org/r/20230120174251.4004100-4-thierry.reding@gmail.com Signed-off-by: Joerg Roedel --- drivers/iommu/of_iommu.c | 94 ++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/of_iommu.h | 8 +++++ 2 files changed, 102 insertions(+) (limited to 'include/linux') diff --git a/drivers/iommu/of_iommu.c b/drivers/iommu/of_iommu.c index 00d98f08732f..3c2e2a13cf9c 100644 --- a/drivers/iommu/of_iommu.c +++ b/drivers/iommu/of_iommu.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -171,3 +172,96 @@ const struct iommu_ops *of_iommu_configure(struct device *dev, return ops; } + +static enum iommu_resv_type iommu_resv_region_get_type(struct device *dev, struct resource *phys, + phys_addr_t start, size_t length) +{ + phys_addr_t end = start + length - 1; + + /* + * IOMMU regions without an associated physical region cannot be + * mapped and are simply reservations. + */ + if (phys->start >= phys->end) + return IOMMU_RESV_RESERVED; + + /* may be IOMMU_RESV_DIRECT_RELAXABLE for certain cases */ + if (start == phys->start && end == phys->end) + return IOMMU_RESV_DIRECT; + + dev_warn(dev, "treating non-direct mapping [%pr] -> [%pap-%pap] as reservation\n", &phys, + &start, &end); + return IOMMU_RESV_RESERVED; +} + +/** + * of_iommu_get_resv_regions - reserved region driver helper for device tree + * @dev: device for which to get reserved regions + * @list: reserved region list + * + * IOMMU drivers can use this to implement their .get_resv_regions() callback + * for memory regions attached to a device tree node. See the reserved-memory + * device tree bindings on how to use these: + * + * Documentation/devicetree/bindings/reserved-memory/reserved-memory.txt + */ +void of_iommu_get_resv_regions(struct device *dev, struct list_head *list) +{ +#if IS_ENABLED(CONFIG_OF_ADDRESS) + struct of_phandle_iterator it; + int err; + + of_for_each_phandle(&it, err, dev->of_node, "memory-region", NULL, 0) { + const __be32 *maps, *end; + struct resource phys; + int size; + + memset(&phys, 0, sizeof(phys)); + + /* + * The "reg" property is optional and can be omitted by reserved-memory regions + * that represent reservations in the IOVA space, which are regions that should + * not be mapped. + */ + if (of_find_property(it.node, "reg", NULL)) { + err = of_address_to_resource(it.node, 0, &phys); + if (err < 0) { + dev_err(dev, "failed to parse memory region %pOF: %d\n", + it.node, err); + continue; + } + } + + maps = of_get_property(it.node, "iommu-addresses", &size); + if (!maps) + continue; + + end = maps + size / sizeof(__be32); + + while (maps < end) { + struct device_node *np; + u32 phandle; + + phandle = be32_to_cpup(maps++); + np = of_find_node_by_phandle(phandle); + + if (np == dev->of_node) { + int prot = IOMMU_READ | IOMMU_WRITE; + struct iommu_resv_region *region; + enum iommu_resv_type type; + phys_addr_t iova; + size_t length; + + maps = of_translate_dma_region(np, maps, &iova, &length); + type = iommu_resv_region_get_type(dev, &phys, iova, length); + + region = iommu_alloc_resv_region(iova, length, prot, type, + GFP_KERNEL); + if (region) + list_add_tail(®ion->list, list); + } + } + } +#endif +} +EXPORT_SYMBOL(of_iommu_get_resv_regions); diff --git a/include/linux/of_iommu.h b/include/linux/of_iommu.h index 55c1eb300a86..9a5e6b410dd2 100644 --- a/include/linux/of_iommu.h +++ b/include/linux/of_iommu.h @@ -12,6 +12,9 @@ extern const struct iommu_ops *of_iommu_configure(struct device *dev, struct device_node *master_np, const u32 *id); +extern void of_iommu_get_resv_regions(struct device *dev, + struct list_head *list); + #else static inline const struct iommu_ops *of_iommu_configure(struct device *dev, @@ -21,6 +24,11 @@ static inline const struct iommu_ops *of_iommu_configure(struct device *dev, return NULL; } +static inline void of_iommu_get_resv_regions(struct device *dev, + struct list_head *list) +{ +} + #endif /* CONFIG_OF_IOMMU */ #endif /* __OF_IOMMU_H */ -- cgit v1.2.3 From 1369459b2e219a6f4c861404c4f195cd81dcbb40 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Mon, 23 Jan 2023 16:35:54 -0400 Subject: iommu: Add a gfp parameter to iommu_map() The internal mechanisms support this, but instead of exposting the gfp to the caller it wrappers it into iommu_map() and iommu_map_atomic() Fix this instead of adding more variants for GFP_KERNEL_ACCOUNT. Reviewed-by: Kevin Tian Signed-off-by: Jason Gunthorpe Reviewed-by: Mathieu Poirier Link: https://lore.kernel.org/r/1-v3-76b587fe28df+6e3-iommu_map_gfp_jgg@nvidia.com Signed-off-by: Joerg Roedel --- arch/arm/mm/dma-mapping.c | 11 +++++++---- .../gpu/drm/nouveau/nvkm/subdev/instmem/gk20a.c | 3 ++- drivers/gpu/drm/tegra/drm.c | 2 +- drivers/gpu/host1x/cdma.c | 2 +- drivers/infiniband/hw/usnic/usnic_uiom.c | 4 ++-- drivers/iommu/dma-iommu.c | 2 +- drivers/iommu/iommu.c | 22 +++++++++++----------- drivers/iommu/iommufd/pages.c | 6 ++++-- drivers/media/platform/qcom/venus/firmware.c | 2 +- drivers/net/ipa/ipa_mem.c | 6 ++++-- drivers/net/wireless/ath/ath10k/snoc.c | 2 +- drivers/net/wireless/ath/ath11k/ahb.c | 4 ++-- drivers/remoteproc/remoteproc_core.c | 5 +++-- drivers/vfio/vfio_iommu_type1.c | 9 +++++---- drivers/vhost/vdpa.c | 2 +- include/linux/iommu.h | 4 ++-- 16 files changed, 48 insertions(+), 38 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index c135f6e37a00..8bc01071474a 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -984,7 +984,8 @@ __iommu_create_mapping(struct device *dev, struct page **pages, size_t size, len = (j - i) << PAGE_SHIFT; ret = iommu_map(mapping->domain, iova, phys, len, - __dma_info_to_prot(DMA_BIDIRECTIONAL, attrs)); + __dma_info_to_prot(DMA_BIDIRECTIONAL, attrs), + GFP_KERNEL); if (ret < 0) goto fail; iova += len; @@ -1207,7 +1208,8 @@ static int __map_sg_chunk(struct device *dev, struct scatterlist *sg, prot = __dma_info_to_prot(dir, attrs); - ret = iommu_map(mapping->domain, iova, phys, len, prot); + ret = iommu_map(mapping->domain, iova, phys, len, prot, + GFP_KERNEL); if (ret < 0) goto fail; count += len >> PAGE_SHIFT; @@ -1379,7 +1381,8 @@ static dma_addr_t arm_iommu_map_page(struct device *dev, struct page *page, prot = __dma_info_to_prot(dir, attrs); - ret = iommu_map(mapping->domain, dma_addr, page_to_phys(page), len, prot); + ret = iommu_map(mapping->domain, dma_addr, page_to_phys(page), len, + prot, GFP_KERNEL); if (ret < 0) goto fail; @@ -1443,7 +1446,7 @@ static dma_addr_t arm_iommu_map_resource(struct device *dev, prot = __dma_info_to_prot(dir, attrs) | IOMMU_MMIO; - ret = iommu_map(mapping->domain, dma_addr, addr, len, prot); + ret = iommu_map(mapping->domain, dma_addr, addr, len, prot, GFP_KERNEL); if (ret < 0) goto fail; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/gk20a.c b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/gk20a.c index 648ecf5a8fbc..a4ac94a2ab57 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/gk20a.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/gk20a.c @@ -475,7 +475,8 @@ gk20a_instobj_ctor_iommu(struct gk20a_instmem *imem, u32 npages, u32 align, u32 offset = (r->offset + i) << imem->iommu_pgshift; ret = iommu_map(imem->domain, offset, node->dma_addrs[i], - PAGE_SIZE, IOMMU_READ | IOMMU_WRITE); + PAGE_SIZE, IOMMU_READ | IOMMU_WRITE, + GFP_KERNEL); if (ret < 0) { nvkm_error(subdev, "IOMMU mapping failure: %d\n", ret); diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c index 7bd2e65c2a16..6ca9f396e55b 100644 --- a/drivers/gpu/drm/tegra/drm.c +++ b/drivers/gpu/drm/tegra/drm.c @@ -1057,7 +1057,7 @@ void *tegra_drm_alloc(struct tegra_drm *tegra, size_t size, dma_addr_t *dma) *dma = iova_dma_addr(&tegra->carveout.domain, alloc); err = iommu_map(tegra->domain, *dma, virt_to_phys(virt), - size, IOMMU_READ | IOMMU_WRITE); + size, IOMMU_READ | IOMMU_WRITE, GFP_KERNEL); if (err < 0) goto free_iova; diff --git a/drivers/gpu/host1x/cdma.c b/drivers/gpu/host1x/cdma.c index 103fda055394..4ddfcd2138c9 100644 --- a/drivers/gpu/host1x/cdma.c +++ b/drivers/gpu/host1x/cdma.c @@ -105,7 +105,7 @@ static int host1x_pushbuffer_init(struct push_buffer *pb) pb->dma = iova_dma_addr(&host1x->iova, alloc); err = iommu_map(host1x->domain, pb->dma, pb->phys, size, - IOMMU_READ); + IOMMU_READ, GFP_KERNEL); if (err) goto iommu_free_iova; } else { diff --git a/drivers/infiniband/hw/usnic/usnic_uiom.c b/drivers/infiniband/hw/usnic/usnic_uiom.c index c301b3be9f30..aeeaca65ace9 100644 --- a/drivers/infiniband/hw/usnic/usnic_uiom.c +++ b/drivers/infiniband/hw/usnic/usnic_uiom.c @@ -277,7 +277,7 @@ iter_chunk: usnic_dbg("va 0x%lx pa %pa size 0x%zx flags 0x%x", va_start, &pa_start, size, flags); err = iommu_map(pd->domain, va_start, pa_start, - size, flags); + size, flags, GFP_KERNEL); if (err) { usnic_err("Failed to map va 0x%lx pa %pa size 0x%zx with err %d\n", va_start, &pa_start, size, err); @@ -294,7 +294,7 @@ iter_chunk: usnic_dbg("va 0x%lx pa %pa size 0x%zx flags 0x%x\n", va_start, &pa_start, size, flags); err = iommu_map(pd->domain, va_start, pa_start, - size, flags); + size, flags, GFP_KERNEL); if (err) { usnic_err("Failed to map va 0x%lx pa %pa size 0x%zx with err %d\n", va_start, &pa_start, size, err); diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index f798c44e0903..8bdb65e7686f 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -1615,7 +1615,7 @@ static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev, if (!iova) goto out_free_page; - if (iommu_map(domain, iova, msi_addr, size, prot)) + if (iommu_map(domain, iova, msi_addr, size, prot, GFP_KERNEL)) goto out_free_iova; INIT_LIST_HEAD(&msi_page->list); diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index de91dd88705b..4d596b8b89e8 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -930,7 +930,7 @@ map_end: if (map_size) { ret = iommu_map(domain, addr - map_size, addr - map_size, map_size, - entry->prot); + entry->prot, GFP_KERNEL); if (ret) goto out; map_size = 0; @@ -2360,31 +2360,31 @@ static int __iommu_map(struct iommu_domain *domain, unsigned long iova, return ret; } -static int _iommu_map(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot, gfp_t gfp) +int iommu_map(struct iommu_domain *domain, unsigned long iova, + phys_addr_t paddr, size_t size, int prot, gfp_t gfp) { const struct iommu_domain_ops *ops = domain->ops; int ret; + might_sleep_if(gfpflags_allow_blocking(gfp)); + + /* Discourage passing strange GFP flags */ + if (WARN_ON_ONCE(gfp & (__GFP_COMP | __GFP_DMA | __GFP_DMA32 | + __GFP_HIGHMEM))) + return -EINVAL; + ret = __iommu_map(domain, iova, paddr, size, prot, gfp); if (ret == 0 && ops->iotlb_sync_map) ops->iotlb_sync_map(domain, iova, size); return ret; } - -int iommu_map(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot) -{ - might_sleep(); - return _iommu_map(domain, iova, paddr, size, prot, GFP_KERNEL); -} EXPORT_SYMBOL_GPL(iommu_map); int iommu_map_atomic(struct iommu_domain *domain, unsigned long iova, phys_addr_t paddr, size_t size, int prot) { - return _iommu_map(domain, iova, paddr, size, prot, GFP_ATOMIC); + return iommu_map(domain, iova, paddr, size, prot, GFP_ATOMIC); } EXPORT_SYMBOL_GPL(iommu_map_atomic); diff --git a/drivers/iommu/iommufd/pages.c b/drivers/iommu/iommufd/pages.c index 1e1d3509efae..22cc3bb0c6c5 100644 --- a/drivers/iommu/iommufd/pages.c +++ b/drivers/iommu/iommufd/pages.c @@ -456,7 +456,8 @@ static int batch_iommu_map_small(struct iommu_domain *domain, size % PAGE_SIZE); while (size) { - rc = iommu_map(domain, iova, paddr, PAGE_SIZE, prot); + rc = iommu_map(domain, iova, paddr, PAGE_SIZE, prot, + GFP_KERNEL); if (rc) goto err_unmap; iova += PAGE_SIZE; @@ -500,7 +501,8 @@ static int batch_to_domain(struct pfn_batch *batch, struct iommu_domain *domain, else rc = iommu_map(domain, iova, PFN_PHYS(batch->pfns[cur]) + page_offset, - next_iova - iova, area->iommu_prot); + next_iova - iova, area->iommu_prot, + GFP_KERNEL); if (rc) goto err_unmap; iova = next_iova; diff --git a/drivers/media/platform/qcom/venus/firmware.c b/drivers/media/platform/qcom/venus/firmware.c index 142d4c74017c..07d4dceb5e72 100644 --- a/drivers/media/platform/qcom/venus/firmware.c +++ b/drivers/media/platform/qcom/venus/firmware.c @@ -158,7 +158,7 @@ static int venus_boot_no_tz(struct venus_core *core, phys_addr_t mem_phys, core->fw.mapped_mem_size = mem_size; ret = iommu_map(iommu, VENUS_FW_START_ADDR, mem_phys, mem_size, - IOMMU_READ | IOMMU_WRITE | IOMMU_PRIV); + IOMMU_READ | IOMMU_WRITE | IOMMU_PRIV, GFP_KERNEL); if (ret) { dev_err(dev, "could not map video firmware region\n"); return ret; diff --git a/drivers/net/ipa/ipa_mem.c b/drivers/net/ipa/ipa_mem.c index 9ec5af323f73..991a7d39f066 100644 --- a/drivers/net/ipa/ipa_mem.c +++ b/drivers/net/ipa/ipa_mem.c @@ -466,7 +466,8 @@ static int ipa_imem_init(struct ipa *ipa, unsigned long addr, size_t size) size = PAGE_ALIGN(size + addr - phys); iova = phys; /* We just want a direct mapping */ - ret = iommu_map(domain, iova, phys, size, IOMMU_READ | IOMMU_WRITE); + ret = iommu_map(domain, iova, phys, size, IOMMU_READ | IOMMU_WRITE, + GFP_KERNEL); if (ret) return ret; @@ -574,7 +575,8 @@ static int ipa_smem_init(struct ipa *ipa, u32 item, size_t size) size = PAGE_ALIGN(size + addr - phys); iova = phys; /* We just want a direct mapping */ - ret = iommu_map(domain, iova, phys, size, IOMMU_READ | IOMMU_WRITE); + ret = iommu_map(domain, iova, phys, size, IOMMU_READ | IOMMU_WRITE, + GFP_KERNEL); if (ret) return ret; diff --git a/drivers/net/wireless/ath/ath10k/snoc.c b/drivers/net/wireless/ath/ath10k/snoc.c index cfcb759a87de..9a82f0336d95 100644 --- a/drivers/net/wireless/ath/ath10k/snoc.c +++ b/drivers/net/wireless/ath/ath10k/snoc.c @@ -1639,7 +1639,7 @@ static int ath10k_fw_init(struct ath10k *ar) ret = iommu_map(iommu_dom, ar_snoc->fw.fw_start_addr, ar->msa.paddr, ar->msa.mem_size, - IOMMU_READ | IOMMU_WRITE); + IOMMU_READ | IOMMU_WRITE, GFP_KERNEL); if (ret) { ath10k_err(ar, "failed to map firmware region: %d\n", ret); goto err_iommu_detach; diff --git a/drivers/net/wireless/ath/ath11k/ahb.c b/drivers/net/wireless/ath/ath11k/ahb.c index d34a4d6325b2..df8fdc7067f9 100644 --- a/drivers/net/wireless/ath/ath11k/ahb.c +++ b/drivers/net/wireless/ath/ath11k/ahb.c @@ -1021,7 +1021,7 @@ static int ath11k_ahb_fw_resources_init(struct ath11k_base *ab) ret = iommu_map(iommu_dom, ab_ahb->fw.msa_paddr, ab_ahb->fw.msa_paddr, ab_ahb->fw.msa_size, - IOMMU_READ | IOMMU_WRITE); + IOMMU_READ | IOMMU_WRITE, GFP_KERNEL); if (ret) { ath11k_err(ab, "failed to map firmware region: %d\n", ret); goto err_iommu_detach; @@ -1029,7 +1029,7 @@ static int ath11k_ahb_fw_resources_init(struct ath11k_base *ab) ret = iommu_map(iommu_dom, ab_ahb->fw.ce_paddr, ab_ahb->fw.ce_paddr, ab_ahb->fw.ce_size, - IOMMU_READ | IOMMU_WRITE); + IOMMU_READ | IOMMU_WRITE, GFP_KERNEL); if (ret) { ath11k_err(ab, "failed to map firmware CE region: %d\n", ret); goto err_iommu_unmap; diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c index 1cd4815a6dd1..80072b6b6283 100644 --- a/drivers/remoteproc/remoteproc_core.c +++ b/drivers/remoteproc/remoteproc_core.c @@ -643,7 +643,8 @@ static int rproc_handle_devmem(struct rproc *rproc, void *ptr, if (!mapping) return -ENOMEM; - ret = iommu_map(rproc->domain, rsc->da, rsc->pa, rsc->len, rsc->flags); + ret = iommu_map(rproc->domain, rsc->da, rsc->pa, rsc->len, rsc->flags, + GFP_KERNEL); if (ret) { dev_err(dev, "failed to map devmem: %d\n", ret); goto out; @@ -737,7 +738,7 @@ static int rproc_alloc_carveout(struct rproc *rproc, } ret = iommu_map(rproc->domain, mem->da, dma, mem->len, - mem->flags); + mem->flags, GFP_KERNEL); if (ret) { dev_err(dev, "iommu_map failed: %d\n", ret); goto free_mapping; diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index 23c24fe98c00..e14f86a8ef52 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -1480,7 +1480,8 @@ static int vfio_iommu_map(struct vfio_iommu *iommu, dma_addr_t iova, list_for_each_entry(d, &iommu->domain_list, next) { ret = iommu_map(d->domain, iova, (phys_addr_t)pfn << PAGE_SHIFT, - npage << PAGE_SHIFT, prot | IOMMU_CACHE); + npage << PAGE_SHIFT, prot | IOMMU_CACHE, + GFP_KERNEL); if (ret) goto unwind; @@ -1777,8 +1778,8 @@ static int vfio_iommu_replay(struct vfio_iommu *iommu, size = npage << PAGE_SHIFT; } - ret = iommu_map(domain->domain, iova, phys, - size, dma->prot | IOMMU_CACHE); + ret = iommu_map(domain->domain, iova, phys, size, + dma->prot | IOMMU_CACHE, GFP_KERNEL); if (ret) { if (!dma->iommu_mapped) { vfio_unpin_pages_remote(dma, iova, @@ -1866,7 +1867,7 @@ static void vfio_test_domain_fgsp(struct vfio_domain *domain) return; ret = iommu_map(domain->domain, 0, page_to_phys(pages), PAGE_SIZE * 2, - IOMMU_READ | IOMMU_WRITE | IOMMU_CACHE); + IOMMU_READ | IOMMU_WRITE | IOMMU_CACHE, GFP_KERNEL); if (!ret) { size_t unmapped = iommu_unmap(domain->domain, 0, PAGE_SIZE); diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index ec32f785dfde..fd1536de5b1d 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -792,7 +792,7 @@ static int vhost_vdpa_map(struct vhost_vdpa *v, struct vhost_iotlb *iotlb, r = ops->set_map(vdpa, asid, iotlb); } else { r = iommu_map(v->domain, iova, pa, size, - perm_to_iommu_flags(perm)); + perm_to_iommu_flags(perm), GFP_KERNEL); } if (r) { vhost_iotlb_del_range(iotlb, iova, iova + size - 1); diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 46e1347bfa22..d2020994f292 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -467,7 +467,7 @@ extern int iommu_sva_unbind_gpasid(struct iommu_domain *domain, extern struct iommu_domain *iommu_get_domain_for_dev(struct device *dev); extern struct iommu_domain *iommu_get_dma_domain(struct device *dev); extern int iommu_map(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot); + phys_addr_t paddr, size_t size, int prot, gfp_t gfp); extern int iommu_map_atomic(struct iommu_domain *domain, unsigned long iova, phys_addr_t paddr, size_t size, int prot); extern size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova, @@ -773,7 +773,7 @@ static inline struct iommu_domain *iommu_get_domain_for_dev(struct device *dev) } static inline int iommu_map(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot) + phys_addr_t paddr, size_t size, int prot, gfp_t gfp) { return -ENODEV; } -- cgit v1.2.3 From 4dc6376af596d9b2a46fa9baf94c9f2fa5a3d246 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Mon, 23 Jan 2023 16:35:55 -0400 Subject: iommu: Remove iommu_map_atomic() There is only one call site and it can now just pass the GFP_ATOMIC to the normal iommu_map(). Reviewed-by: Kevin Tian Signed-off-by: Jason Gunthorpe Link: https://lore.kernel.org/r/2-v3-76b587fe28df+6e3-iommu_map_gfp_jgg@nvidia.com Signed-off-by: Joerg Roedel --- drivers/iommu/dma-iommu.c | 2 +- drivers/iommu/iommu.c | 7 ------- include/linux/iommu.h | 9 --------- 3 files changed, 1 insertion(+), 17 deletions(-) (limited to 'include/linux') diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index 8bdb65e7686f..7016db569f81 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -713,7 +713,7 @@ static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys, if (!iova) return DMA_MAPPING_ERROR; - if (iommu_map_atomic(domain, iova, phys - iova_off, size, prot)) { + if (iommu_map(domain, iova, phys - iova_off, size, prot, GFP_ATOMIC)) { iommu_dma_free_iova(cookie, iova, size, NULL); return DMA_MAPPING_ERROR; } diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 4d596b8b89e8..19b1c3315a2c 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -2381,13 +2381,6 @@ int iommu_map(struct iommu_domain *domain, unsigned long iova, } EXPORT_SYMBOL_GPL(iommu_map); -int iommu_map_atomic(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot) -{ - return iommu_map(domain, iova, paddr, size, prot, GFP_ATOMIC); -} -EXPORT_SYMBOL_GPL(iommu_map_atomic); - static size_t __iommu_unmap_pages(struct iommu_domain *domain, unsigned long iova, size_t size, struct iommu_iotlb_gather *iotlb_gather) diff --git a/include/linux/iommu.h b/include/linux/iommu.h index d2020994f292..521cd79700f4 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -468,8 +468,6 @@ extern struct iommu_domain *iommu_get_domain_for_dev(struct device *dev); extern struct iommu_domain *iommu_get_dma_domain(struct device *dev); extern int iommu_map(struct iommu_domain *domain, unsigned long iova, phys_addr_t paddr, size_t size, int prot, gfp_t gfp); -extern int iommu_map_atomic(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot); extern size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size); extern size_t iommu_unmap_fast(struct iommu_domain *domain, @@ -778,13 +776,6 @@ static inline int iommu_map(struct iommu_domain *domain, unsigned long iova, return -ENODEV; } -static inline int iommu_map_atomic(struct iommu_domain *domain, - unsigned long iova, phys_addr_t paddr, - size_t size, int prot) -{ - return -ENODEV; -} - static inline size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size) { -- cgit v1.2.3 From f2b2c051be6262edc3c6fce50d3d4f01b59ba228 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Mon, 23 Jan 2023 16:35:56 -0400 Subject: iommu: Add a gfp parameter to iommu_map_sg() Follow the pattern for iommu_map() and remove iommu_map_sg_atomic(). This allows __iommu_dma_alloc_noncontiguous() to use a GFP_KERNEL allocation here, based on the provided gfp flags. Reviewed-by: Kevin Tian Signed-off-by: Jason Gunthorpe Link: https://lore.kernel.org/r/3-v3-76b587fe28df+6e3-iommu_map_gfp_jgg@nvidia.com Signed-off-by: Joerg Roedel --- drivers/iommu/dma-iommu.c | 5 +++-- drivers/iommu/iommu.c | 26 ++++++++++---------------- include/linux/iommu.h | 18 +++++------------- 3 files changed, 18 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index 7016db569f81..72cfa24503b8 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -833,7 +833,8 @@ static struct page **__iommu_dma_alloc_noncontiguous(struct device *dev, arch_dma_prep_coherent(sg_page(sg), sg->length); } - ret = iommu_map_sg_atomic(domain, iova, sgt->sgl, sgt->orig_nents, ioprot); + ret = iommu_map_sg(domain, iova, sgt->sgl, sgt->orig_nents, ioprot, + GFP_ATOMIC); if (ret < 0 || ret < size) goto out_free_sg; @@ -1281,7 +1282,7 @@ static int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg, * We'll leave any physical concatenation to the IOMMU driver's * implementation - it knows better than we do. */ - ret = iommu_map_sg_atomic(domain, iova, sg, nents, prot); + ret = iommu_map_sg(domain, iova, sg, nents, prot, GFP_ATOMIC); if (ret < 0 || ret < iova_len) goto out_free_iova; diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 19b1c3315a2c..1b7d0698b045 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -2470,9 +2470,9 @@ size_t iommu_unmap_fast(struct iommu_domain *domain, } EXPORT_SYMBOL_GPL(iommu_unmap_fast); -static ssize_t __iommu_map_sg(struct iommu_domain *domain, unsigned long iova, - struct scatterlist *sg, unsigned int nents, int prot, - gfp_t gfp) +ssize_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova, + struct scatterlist *sg, unsigned int nents, int prot, + gfp_t gfp) { const struct iommu_domain_ops *ops = domain->ops; size_t len = 0, mapped = 0; @@ -2480,6 +2480,13 @@ static ssize_t __iommu_map_sg(struct iommu_domain *domain, unsigned long iova, unsigned int i = 0; int ret; + might_sleep_if(gfpflags_allow_blocking(gfp)); + + /* Discourage passing strange GFP flags */ + if (WARN_ON_ONCE(gfp & (__GFP_COMP | __GFP_DMA | __GFP_DMA32 | + __GFP_HIGHMEM))) + return -EINVAL; + while (i <= nents) { phys_addr_t s_phys = sg_phys(sg); @@ -2519,21 +2526,8 @@ out_err: return ret; } - -ssize_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova, - struct scatterlist *sg, unsigned int nents, int prot) -{ - might_sleep(); - return __iommu_map_sg(domain, iova, sg, nents, prot, GFP_KERNEL); -} EXPORT_SYMBOL_GPL(iommu_map_sg); -ssize_t iommu_map_sg_atomic(struct iommu_domain *domain, unsigned long iova, - struct scatterlist *sg, unsigned int nents, int prot) -{ - return __iommu_map_sg(domain, iova, sg, nents, prot, GFP_ATOMIC); -} - /** * report_iommu_fault() - report about an IOMMU fault to the IOMMU framework * @domain: the iommu domain where the fault has happened diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 521cd79700f4..d5c16dc33c87 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -474,10 +474,8 @@ extern size_t iommu_unmap_fast(struct iommu_domain *domain, unsigned long iova, size_t size, struct iommu_iotlb_gather *iotlb_gather); extern ssize_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova, - struct scatterlist *sg, unsigned int nents, int prot); -extern ssize_t iommu_map_sg_atomic(struct iommu_domain *domain, - unsigned long iova, struct scatterlist *sg, - unsigned int nents, int prot); + struct scatterlist *sg, unsigned int nents, + int prot, gfp_t gfp); extern phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova); extern void iommu_set_fault_handler(struct iommu_domain *domain, iommu_fault_handler_t handler, void *token); @@ -791,14 +789,7 @@ static inline size_t iommu_unmap_fast(struct iommu_domain *domain, static inline ssize_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova, struct scatterlist *sg, - unsigned int nents, int prot) -{ - return -ENODEV; -} - -static inline ssize_t iommu_map_sg_atomic(struct iommu_domain *domain, - unsigned long iova, struct scatterlist *sg, - unsigned int nents, int prot) + unsigned int nents, int prot, gfp_t gfp) { return -ENODEV; } @@ -1109,7 +1100,8 @@ iommu_get_domain_for_dev_pasid(struct device *dev, ioasid_t pasid, static inline size_t iommu_map_sgtable(struct iommu_domain *domain, unsigned long iova, struct sg_table *sgt, int prot) { - return iommu_map_sg(domain, iova, sgt->sgl, sgt->orig_nents, prot); + return iommu_map_sg(domain, iova, sgt->sgl, sgt->orig_nents, prot, + GFP_KERNEL); } #ifdef CONFIG_IOMMU_DEBUGFS -- cgit v1.2.3 From 9cad72dfc5567c66ab0e5a0a2474c5f36c268694 Mon Sep 17 00:00:00 2001 From: Biju Das Date: Sat, 21 Jan 2023 14:58:46 +0000 Subject: usb: gadget: Add support for RZ/V2M USB3DRD driver The RZ/V2M USB3.1 Gen1 Interface (USB) composed of a USB3.1 Gen1 Dual Role Device controller (USB3DRD), a USB3.1 Gen1 Host controller (USB3HOST), a USB3.1 Gen1 Peripheral controller (USB3PERI). The reset for both host and peri are located in USB3DRD block. The USB3DRD registers are mapped in the AXI address space of the Peripheral module. Add USB3DRD driver to handle reset for both host and peri modules. Signed-off-by: Biju Das Link: https://lore.kernel.org/r/20230121145853.4792-6-biju.das.jz@bp.renesas.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/udc/Kconfig | 13 +++ drivers/usb/gadget/udc/Makefile | 1 + drivers/usb/gadget/udc/renesas_usb3.c | 102 +++++++++++++++--------- drivers/usb/gadget/udc/rzv2m_usb3drd.c | 139 +++++++++++++++++++++++++++++++++ include/linux/usb/rzv2m_usb3drd.h | 20 +++++ 5 files changed, 238 insertions(+), 37 deletions(-) create mode 100644 drivers/usb/gadget/udc/rzv2m_usb3drd.c create mode 100644 include/linux/usb/rzv2m_usb3drd.h (limited to 'include/linux') diff --git a/drivers/usb/gadget/udc/Kconfig b/drivers/usb/gadget/udc/Kconfig index 12f7323869fe..1e32d1d7dfb7 100644 --- a/drivers/usb/gadget/udc/Kconfig +++ b/drivers/usb/gadget/udc/Kconfig @@ -180,10 +180,23 @@ config USB_RENESAS_USBHS_UDC dynamically linked module called "renesas_usbhs" and force all gadget drivers to also be dynamically linked. +config USB_RZV2M_USB3DRD + tristate 'Renesas USB3.1 DRD controller' + depends on ARCH_R9A09G011 || COMPILE_TEST + default USB_XHCI_RZV2M + default USB_RENESAS_USB3 + help + Renesas USB3.1 DRD controller is a USB DRD controller + that supports both host and device switching. + + Say "y" to link the driver statically, or "m" to build a + dynamically linked module called "rzv2m_usb3drd". + config USB_RENESAS_USB3 tristate 'Renesas USB3.0 Peripheral controller' depends on ARCH_RENESAS || COMPILE_TEST depends on EXTCON + select USB_RZV2M_USB3DRD if ARCH_R9A09G011 select USB_ROLE_SWITCH help Renesas USB3.0 Peripheral controller is a USB peripheral controller diff --git a/drivers/usb/gadget/udc/Makefile b/drivers/usb/gadget/udc/Makefile index 1e23627733eb..d40822a12bad 100644 --- a/drivers/usb/gadget/udc/Makefile +++ b/drivers/usb/gadget/udc/Makefile @@ -27,6 +27,7 @@ obj-$(CONFIG_USB_TEGRA_XUDC) += tegra-xudc.o obj-$(CONFIG_USB_M66592) += m66592-udc.o obj-$(CONFIG_USB_R8A66597) += r8a66597-udc.o obj-$(CONFIG_USB_RENESAS_USB3) += renesas_usb3.o +obj-$(CONFIG_USB_RZV2M_USB3DRD) += rzv2m_usb3drd.o obj-$(CONFIG_USB_RENESAS_USBF) += renesas_usbf.o obj-$(CONFIG_USB_FSL_QE) += fsl_qe_udc.o obj-$(CONFIG_USB_S3C_HSUDC) += s3c-hsudc.o diff --git a/drivers/usb/gadget/udc/renesas_usb3.c b/drivers/usb/gadget/udc/renesas_usb3.c index 615ba0a6fbee..8d694501bf02 100644 --- a/drivers/usb/gadget/udc/renesas_usb3.c +++ b/drivers/usb/gadget/udc/renesas_usb3.c @@ -27,6 +27,7 @@ #include #include #include +#include /* register definitions */ #define USB3_AXI_INT_STA 0x008 @@ -334,7 +335,7 @@ struct renesas_usb3_priv { struct renesas_usb3 { void __iomem *reg; - struct reset_control *drd_rstc; + void __iomem *drd_reg; struct reset_control *usbp_rstc; struct usb_gadget gadget; @@ -426,6 +427,46 @@ static void usb3_clear_bit(struct renesas_usb3 *usb3, u32 bits, u32 offs) usb3_write(usb3, val, offs); } +static void usb3_drd_write(struct renesas_usb3 *usb3, u32 data, u32 offs) +{ + void __iomem *reg; + + if (usb3->is_rzv2m) + reg = usb3->drd_reg + offs - USB3_DRD_CON(usb3); + else + reg = usb3->reg + offs; + + iowrite32(data, reg); +} + +static u32 usb3_drd_read(struct renesas_usb3 *usb3, u32 offs) +{ + void __iomem *reg; + + if (usb3->is_rzv2m) + reg = usb3->drd_reg + offs - USB3_DRD_CON(usb3); + else + reg = usb3->reg + offs; + + return ioread32(reg); +} + +static void usb3_drd_set_bit(struct renesas_usb3 *usb3, u32 bits, u32 offs) +{ + u32 val = usb3_drd_read(usb3, offs); + + val |= bits; + usb3_drd_write(usb3, val, offs); +} + +static void usb3_drd_clear_bit(struct renesas_usb3 *usb3, u32 bits, u32 offs) +{ + u32 val = usb3_drd_read(usb3, offs); + + val &= ~bits; + usb3_drd_write(usb3, val, offs); +} + static int usb3_wait(struct renesas_usb3 *usb3, u32 reg, u32 mask, u32 expected) { @@ -474,7 +515,7 @@ static void usb3_disable_pipe_irq(struct renesas_usb3 *usb3, int num) static bool usb3_is_host(struct renesas_usb3 *usb3) { - return !(usb3_read(usb3, USB3_DRD_CON(usb3)) & DRD_CON_PERI_CON); + return !(usb3_drd_read(usb3, USB3_DRD_CON(usb3)) & DRD_CON_PERI_CON); } static void usb3_init_axi_bridge(struct renesas_usb3 *usb3) @@ -683,18 +724,18 @@ static void usb3_set_mode(struct renesas_usb3 *usb3, bool host) { if (usb3->is_rzv2m) { if (host) { - usb3_set_bit(usb3, DRD_CON_PERI_RST, USB3_DRD_CON(usb3)); - usb3_clear_bit(usb3, DRD_CON_HOST_RST, USB3_DRD_CON(usb3)); + usb3_drd_set_bit(usb3, DRD_CON_PERI_RST, USB3_DRD_CON(usb3)); + usb3_drd_clear_bit(usb3, DRD_CON_HOST_RST, USB3_DRD_CON(usb3)); } else { - usb3_set_bit(usb3, DRD_CON_HOST_RST, USB3_DRD_CON(usb3)); - usb3_clear_bit(usb3, DRD_CON_PERI_RST, USB3_DRD_CON(usb3)); + usb3_drd_set_bit(usb3, DRD_CON_HOST_RST, USB3_DRD_CON(usb3)); + usb3_drd_clear_bit(usb3, DRD_CON_PERI_RST, USB3_DRD_CON(usb3)); } } if (host) - usb3_clear_bit(usb3, DRD_CON_PERI_CON, USB3_DRD_CON(usb3)); + usb3_drd_clear_bit(usb3, DRD_CON_PERI_CON, USB3_DRD_CON(usb3)); else - usb3_set_bit(usb3, DRD_CON_PERI_CON, USB3_DRD_CON(usb3)); + usb3_drd_set_bit(usb3, DRD_CON_PERI_CON, USB3_DRD_CON(usb3)); } static void usb3_set_mode_by_role_sw(struct renesas_usb3 *usb3, bool host) @@ -710,9 +751,9 @@ static void usb3_set_mode_by_role_sw(struct renesas_usb3 *usb3, bool host) static void usb3_vbus_out(struct renesas_usb3 *usb3, bool enable) { if (enable) - usb3_set_bit(usb3, DRD_CON_VBOUT, USB3_DRD_CON(usb3)); + usb3_drd_set_bit(usb3, DRD_CON_VBOUT, USB3_DRD_CON(usb3)); else - usb3_clear_bit(usb3, DRD_CON_VBOUT, USB3_DRD_CON(usb3)); + usb3_drd_clear_bit(usb3, DRD_CON_VBOUT, USB3_DRD_CON(usb3)); } static void usb3_mode_config(struct renesas_usb3 *usb3, bool host, bool a_dev) @@ -733,7 +774,7 @@ static void usb3_mode_config(struct renesas_usb3 *usb3, bool host, bool a_dev) static bool usb3_is_a_device(struct renesas_usb3 *usb3) { - return !(usb3_read(usb3, USB3_USB_OTG_STA(usb3)) & USB_OTG_IDMON(usb3)); + return !(usb3_drd_read(usb3, USB3_USB_OTG_STA(usb3)) & USB_OTG_IDMON(usb3)); } static void usb3_check_id(struct renesas_usb3 *usb3) @@ -756,8 +797,8 @@ static void renesas_usb3_init_controller(struct renesas_usb3 *usb3) usb3_set_bit(usb3, USB_COM_CON_PN_WDATAIF_NL | USB_COM_CON_PN_RDATAIF_NL | USB_COM_CON_PN_LSTTR_PP, USB3_USB_COM_CON); - usb3_write(usb3, USB_OTG_IDMON(usb3), USB3_USB_OTG_INT_STA(usb3)); - usb3_write(usb3, USB_OTG_IDMON(usb3), USB3_USB_OTG_INT_ENA(usb3)); + usb3_drd_write(usb3, USB_OTG_IDMON(usb3), USB3_USB_OTG_INT_STA(usb3)); + usb3_drd_write(usb3, USB_OTG_IDMON(usb3), USB3_USB_OTG_INT_ENA(usb3)); usb3_check_id(usb3); usb3_check_vbus(usb3); @@ -767,7 +808,7 @@ static void renesas_usb3_stop_controller(struct renesas_usb3 *usb3) { usb3_disconnect(usb3); usb3_write(usb3, 0, USB3_P0_INT_ENA); - usb3_write(usb3, 0, USB3_USB_OTG_INT_ENA(usb3)); + usb3_drd_write(usb3, 0, USB3_USB_OTG_INT_ENA(usb3)); usb3_write(usb3, 0, USB3_USB_INT_ENA_1); usb3_write(usb3, 0, USB3_USB_INT_ENA_2); usb3_write(usb3, 0, USB3_AXI_INT_ENA); @@ -2024,11 +2065,11 @@ static void usb3_irq_idmon_change(struct renesas_usb3 *usb3) static void usb3_irq_otg_int(struct renesas_usb3 *usb3) { - u32 otg_int_sta = usb3_read(usb3, USB3_USB_OTG_INT_STA(usb3)); + u32 otg_int_sta = usb3_drd_read(usb3, USB3_USB_OTG_INT_STA(usb3)); - otg_int_sta &= usb3_read(usb3, USB3_USB_OTG_INT_ENA(usb3)); + otg_int_sta &= usb3_drd_read(usb3, USB3_USB_OTG_INT_ENA(usb3)); if (otg_int_sta) - usb3_write(usb3, otg_int_sta, USB3_USB_OTG_INT_STA(usb3)); + usb3_drd_write(usb3, otg_int_sta, USB3_USB_OTG_INT_STA(usb3)); if (otg_int_sta & USB_OTG_IDMON(usb3)) usb3_irq_idmon_change(usb3); @@ -2600,7 +2641,6 @@ static int renesas_usb3_remove(struct platform_device *pdev) usb_del_gadget_udc(&usb3->gadget); reset_control_assert(usb3->usbp_rstc); - reset_control_assert(usb3->drd_rstc); renesas_usb3_dma_free_prd(usb3, &pdev->dev); __renesas_usb3_ep_free_request(usb3->ep0_req); @@ -2788,7 +2828,7 @@ static struct usb_role_switch_desc renesas_usb3_role_switch_desc = { static int renesas_usb3_probe(struct platform_device *pdev) { struct renesas_usb3 *usb3; - int irq, drd_irq, ret; + int irq, ret; const struct renesas_usb3_priv *priv; const struct soc_device_attribute *attr; @@ -2802,12 +2842,6 @@ static int renesas_usb3_probe(struct platform_device *pdev) if (irq < 0) return irq; - if (priv->is_rzv2m) { - drd_irq = platform_get_irq_byname(pdev, "drd"); - if (drd_irq < 0) - return drd_irq; - } - usb3 = devm_kzalloc(&pdev->dev, sizeof(*usb3), GFP_KERNEL); if (!usb3) return -ENOMEM; @@ -2836,9 +2870,12 @@ static int renesas_usb3_probe(struct platform_device *pdev) return ret; if (usb3->is_rzv2m) { - ret = devm_request_irq(&pdev->dev, drd_irq, + struct rzv2m_usb3drd *ddata = dev_get_drvdata(pdev->dev.parent); + + usb3->drd_reg = ddata->reg; + ret = devm_request_irq(ddata->dev, ddata->drd_irq, renesas_usb3_otg_irq, 0, - dev_name(&pdev->dev), usb3); + dev_name(ddata->dev), usb3); if (ret < 0) return ret; } @@ -2873,21 +2910,13 @@ static int renesas_usb3_probe(struct platform_device *pdev) goto err_add_udc; } - usb3->drd_rstc = devm_reset_control_get_optional_shared(&pdev->dev, - "drd_reset"); - if (IS_ERR(usb3->drd_rstc)) { - ret = PTR_ERR(usb3->drd_rstc); - goto err_add_udc; - } - usb3->usbp_rstc = devm_reset_control_get_optional_shared(&pdev->dev, - "aresetn_p"); + NULL); if (IS_ERR(usb3->usbp_rstc)) { ret = PTR_ERR(usb3->usbp_rstc); goto err_add_udc; } - reset_control_deassert(usb3->drd_rstc); reset_control_deassert(usb3->usbp_rstc); pm_runtime_enable(&pdev->dev); @@ -2933,7 +2962,6 @@ err_dev_create: err_reset: reset_control_assert(usb3->usbp_rstc); - reset_control_assert(usb3->drd_rstc); err_add_udc: renesas_usb3_dma_free_prd(usb3, &pdev->dev); diff --git a/drivers/usb/gadget/udc/rzv2m_usb3drd.c b/drivers/usb/gadget/udc/rzv2m_usb3drd.c new file mode 100644 index 000000000000..3c8bbf843038 --- /dev/null +++ b/drivers/usb/gadget/udc/rzv2m_usb3drd.c @@ -0,0 +1,139 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Renesas RZ/V2M USB3DRD driver + * + * Copyright (C) 2022 Renesas Electronics Corporation + */ + +#include +#include +#include +#include +#include +#include + +#define USB_PERI_DRD_CON 0x000 + +#define USB_PERI_DRD_CON_PERI_RST BIT(31) +#define USB_PERI_DRD_CON_HOST_RST BIT(30) +#define USB_PERI_DRD_CON_PERI_CON BIT(24) + +static void rzv2m_usb3drd_set_bit(struct rzv2m_usb3drd *usb3, u32 bits, + u32 offs) +{ + u32 val = readl(usb3->reg + offs); + + val |= bits; + writel(val, usb3->reg + offs); +} + +static void rzv2m_usb3drd_clear_bit(struct rzv2m_usb3drd *usb3, u32 bits, + u32 offs) +{ + u32 val = readl(usb3->reg + offs); + + val &= ~bits; + writel(val, usb3->reg + offs); +} + +void rzv2m_usb3drd_reset(struct device *dev, bool host) +{ + struct rzv2m_usb3drd *usb3 = dev_get_drvdata(dev); + + if (host) { + rzv2m_usb3drd_clear_bit(usb3, USB_PERI_DRD_CON_PERI_CON, + USB_PERI_DRD_CON); + rzv2m_usb3drd_clear_bit(usb3, USB_PERI_DRD_CON_HOST_RST, + USB_PERI_DRD_CON); + rzv2m_usb3drd_set_bit(usb3, USB_PERI_DRD_CON_PERI_RST, + USB_PERI_DRD_CON); + } else { + rzv2m_usb3drd_set_bit(usb3, USB_PERI_DRD_CON_PERI_CON, + USB_PERI_DRD_CON); + rzv2m_usb3drd_set_bit(usb3, USB_PERI_DRD_CON_HOST_RST, + USB_PERI_DRD_CON); + rzv2m_usb3drd_clear_bit(usb3, USB_PERI_DRD_CON_PERI_RST, + USB_PERI_DRD_CON); + } +} +EXPORT_SYMBOL_GPL(rzv2m_usb3drd_reset); + +static int rzv2m_usb3drd_remove(struct platform_device *pdev) +{ + struct rzv2m_usb3drd *usb3 = platform_get_drvdata(pdev); + + of_platform_depopulate(usb3->dev); + pm_runtime_put(usb3->dev); + pm_runtime_disable(&pdev->dev); + reset_control_assert(usb3->drd_rstc); + + return 0; +} + +static int rzv2m_usb3drd_probe(struct platform_device *pdev) +{ + struct rzv2m_usb3drd *usb3; + int ret; + + usb3 = devm_kzalloc(&pdev->dev, sizeof(*usb3), GFP_KERNEL); + if (!usb3) + return -ENOMEM; + + usb3->dev = &pdev->dev; + + usb3->drd_irq = platform_get_irq_byname(pdev, "drd"); + if (usb3->drd_irq < 0) + return usb3->drd_irq; + + usb3->reg = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(usb3->reg)) + return PTR_ERR(usb3->reg); + + platform_set_drvdata(pdev, usb3); + + usb3->drd_rstc = devm_reset_control_get_exclusive(&pdev->dev, NULL); + if (IS_ERR(usb3->drd_rstc)) + return dev_err_probe(&pdev->dev, PTR_ERR(usb3->drd_rstc), + "failed to get drd reset"); + + reset_control_deassert(usb3->drd_rstc); + pm_runtime_enable(&pdev->dev); + ret = pm_runtime_resume_and_get(usb3->dev); + if (ret) + goto err_rst; + + ret = of_platform_populate(usb3->dev->of_node, NULL, NULL, usb3->dev); + if (ret) + goto err_pm; + + return 0; + +err_pm: + pm_runtime_put(usb3->dev); + +err_rst: + pm_runtime_disable(&pdev->dev); + reset_control_assert(usb3->drd_rstc); + return ret; +} + +static const struct of_device_id rzv2m_usb3drd_of_match[] = { + { .compatible = "renesas,rzv2m-usb3drd", }, + { /* Sentinel */ } +}; +MODULE_DEVICE_TABLE(of, rzv2m_usb3drd_of_match); + +static struct platform_driver rzv2m_usb3drd_driver = { + .driver = { + .name = "rzv2m-usb3drd", + .of_match_table = of_match_ptr(rzv2m_usb3drd_of_match), + }, + .probe = rzv2m_usb3drd_probe, + .remove = rzv2m_usb3drd_remove, +}; +module_platform_driver(rzv2m_usb3drd_driver); + +MODULE_AUTHOR("Biju Das "); +MODULE_DESCRIPTION("Renesas RZ/V2M USB3DRD driver"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("platform:rzv2m_usb3drd"); diff --git a/include/linux/usb/rzv2m_usb3drd.h b/include/linux/usb/rzv2m_usb3drd.h new file mode 100644 index 000000000000..4cc848de229f --- /dev/null +++ b/include/linux/usb/rzv2m_usb3drd.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __RZV2M_USB3DRD_H +#define __RZV2M_USB3DRD_H + +#include + +struct rzv2m_usb3drd { + void __iomem *reg; + int drd_irq; + struct device *dev; + struct reset_control *drd_rstc; +}; + +#if IS_ENABLED(CONFIG_USB_RZV2M_USB3DRD) +void rzv2m_usb3drd_reset(struct device *dev, bool host); +#else +static inline void rzv2m_usb3drd_reset(struct device *dev, bool host) { } +#endif + +#endif /* __RZV2M_USB3DRD_H */ -- cgit v1.2.3 From be234d00240cbb53d5a1fa0e58b2d14ff121dca2 Mon Sep 17 00:00:00 2001 From: Nancy.Lin Date: Fri, 13 Jan 2023 18:44:26 +0800 Subject: soc: mediatek: add mtk-mmsys ethdr and mdp_rdma components Add new mmsys component: ethdr_mixer and mdp_rdma. These components will use in mt8195 vdosys1. Signed-off-by: Nancy.Lin Reviewed-by: AngeloGioacchino Del Regno Reviewed-by: CK Hu Tested-by: AngeloGioacchino Del Regno Tested-by: Bo-Chen Chen Link: https://lore.kernel.org/r/20230113104434.28023-4-nancy.lin@mediatek.com Signed-off-by: Matthias Brugger --- include/linux/soc/mediatek/mtk-mmsys.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soc/mediatek/mtk-mmsys.h b/include/linux/soc/mediatek/mtk-mmsys.h index b85f66db33e1..3e4b080627c3 100644 --- a/include/linux/soc/mediatek/mtk-mmsys.h +++ b/include/linux/soc/mediatek/mtk-mmsys.h @@ -36,7 +36,16 @@ enum mtk_ddp_comp_id { DDP_COMPONENT_DSI1, DDP_COMPONENT_DSI2, DDP_COMPONENT_DSI3, + DDP_COMPONENT_ETHDR_MIXER, DDP_COMPONENT_GAMMA, + DDP_COMPONENT_MDP_RDMA0, + DDP_COMPONENT_MDP_RDMA1, + DDP_COMPONENT_MDP_RDMA2, + DDP_COMPONENT_MDP_RDMA3, + DDP_COMPONENT_MDP_RDMA4, + DDP_COMPONENT_MDP_RDMA5, + DDP_COMPONENT_MDP_RDMA6, + DDP_COMPONENT_MDP_RDMA7, DDP_COMPONENT_MERGE0, DDP_COMPONENT_MERGE1, DDP_COMPONENT_MERGE2, -- cgit v1.2.3 From 3dd20b715c4483ae5d8ddb22cbc8e116944094e4 Mon Sep 17 00:00:00 2001 From: Nancy.Lin Date: Fri, 13 Jan 2023 18:44:29 +0800 Subject: soc: mediatek: add mtk-mmsys config API for mt8195 vdosys1 Add four mmsys config APIs. The config APIs are used for config mmsys reg. Some mmsys regs need to be set according to the HW engine binding to the mmsys simultaneously. 1. mtk_mmsys_merge_async_config: config merge async width/height. async is used for cross-clock domain synchronization. 2. mtk_mmsys_hdr_confing: config hdr backend async width/height. 3. mtk_mmsys_mixer_in_config and mtk_mmsys_mixer_in_config: config mixer related settings. Signed-off-by: Nancy.Lin Reviewed-by: AngeloGioacchino Del Regno Reviewed-by: CK Hu Tested-by: AngeloGioacchino Del Regno Tested-by: Bo-Chen Chen Link: https://lore.kernel.org/r/20230113104434.28023-7-nancy.lin@mediatek.com Signed-off-by: Matthias Brugger --- drivers/soc/mediatek/mt8195-mmsys.h | 6 ++++++ drivers/soc/mediatek/mtk-mmsys.c | 35 ++++++++++++++++++++++++++++++++++ include/linux/soc/mediatek/mtk-mmsys.h | 9 +++++++++ 3 files changed, 50 insertions(+) (limited to 'include/linux') diff --git a/drivers/soc/mediatek/mt8195-mmsys.h b/drivers/soc/mediatek/mt8195-mmsys.h index fd7b455bd675..454944a9409c 100644 --- a/drivers/soc/mediatek/mt8195-mmsys.h +++ b/drivers/soc/mediatek/mt8195-mmsys.h @@ -75,6 +75,12 @@ #define MT8195_SOUT_DSC_WRAP1_OUT_TO_SINA_VIRTUAL0 (2 << 16) #define MT8195_SOUT_DSC_WRAP1_OUT_TO_VPP_MERGE (3 << 16) +#define MT8195_VDO1_MERGE0_ASYNC_CFG_WD 0xe30 +#define MT8195_VDO1_HDRBE_ASYNC_CFG_WD 0xe70 +#define MT8195_VDO1_HDR_TOP_CFG 0xd00 +#define MT8195_VDO1_MIXER_IN1_ALPHA 0xd30 +#define MT8195_VDO1_MIXER_IN1_PAD 0xd40 + #define MT8195_VDO1_VPP_MERGE0_P0_SEL_IN 0xf04 #define MT8195_VPP_MERGE0_P0_SEL_IN_FROM_MDP_RDMA0 1 diff --git a/drivers/soc/mediatek/mtk-mmsys.c b/drivers/soc/mediatek/mtk-mmsys.c index 602197e95f67..2aeb739b8503 100644 --- a/drivers/soc/mediatek/mtk-mmsys.c +++ b/drivers/soc/mediatek/mtk-mmsys.c @@ -145,6 +145,41 @@ void mtk_mmsys_ddp_disconnect(struct device *dev, } EXPORT_SYMBOL_GPL(mtk_mmsys_ddp_disconnect); +void mtk_mmsys_merge_async_config(struct device *dev, int idx, int width, int height) +{ + mtk_mmsys_update_bits(dev_get_drvdata(dev), MT8195_VDO1_MERGE0_ASYNC_CFG_WD + 0x10 * idx, + ~0, height << 16 | width); +} +EXPORT_SYMBOL_GPL(mtk_mmsys_merge_async_config); + +void mtk_mmsys_hdr_config(struct device *dev, int be_width, int be_height) +{ + mtk_mmsys_update_bits(dev_get_drvdata(dev), MT8195_VDO1_HDRBE_ASYNC_CFG_WD, ~0, + be_height << 16 | be_width); +} +EXPORT_SYMBOL_GPL(mtk_mmsys_hdr_config); + +void mtk_mmsys_mixer_in_config(struct device *dev, int idx, bool alpha_sel, u16 alpha, + u8 mode, u32 biwidth) +{ + struct mtk_mmsys *mmsys = dev_get_drvdata(dev); + + mtk_mmsys_update_bits(mmsys, MT8195_VDO1_MIXER_IN1_ALPHA + (idx - 1) * 4, ~0, + alpha << 16 | alpha); + mtk_mmsys_update_bits(mmsys, MT8195_VDO1_HDR_TOP_CFG, BIT(19 + idx), + alpha_sel << (19 + idx)); + mtk_mmsys_update_bits(mmsys, MT8195_VDO1_MIXER_IN1_PAD + (idx - 1) * 4, + GENMASK(31, 16) | GENMASK(1, 0), biwidth << 16 | mode); +} +EXPORT_SYMBOL_GPL(mtk_mmsys_mixer_in_config); + +void mtk_mmsys_mixer_in_channel_swap(struct device *dev, int idx, bool channel_swap) +{ + mtk_mmsys_update_bits(dev_get_drvdata(dev), MT8195_VDO1_MIXER_IN1_PAD + (idx - 1) * 4, + BIT(4), channel_swap << 4); +} +EXPORT_SYMBOL_GPL(mtk_mmsys_mixer_in_channel_swap); + void mtk_mmsys_ddp_dpi_fmt_config(struct device *dev, u32 val) { struct mtk_mmsys *mmsys = dev_get_drvdata(dev); diff --git a/include/linux/soc/mediatek/mtk-mmsys.h b/include/linux/soc/mediatek/mtk-mmsys.h index 3e4b080627c3..5a6753aed482 100644 --- a/include/linux/soc/mediatek/mtk-mmsys.h +++ b/include/linux/soc/mediatek/mtk-mmsys.h @@ -83,4 +83,13 @@ void mtk_mmsys_ddp_disconnect(struct device *dev, void mtk_mmsys_ddp_dpi_fmt_config(struct device *dev, u32 val); +void mtk_mmsys_merge_async_config(struct device *dev, int idx, int width, int height); + +void mtk_mmsys_hdr_config(struct device *dev, int be_width, int be_height); + +void mtk_mmsys_mixer_in_config(struct device *dev, int idx, bool alpha_sel, u16 alpha, + u8 mode, u32 biwidth); + +void mtk_mmsys_mixer_in_channel_swap(struct device *dev, int idx, bool channel_swap); + #endif /* __MTK_MMSYS_H */ -- cgit v1.2.3 From 8af1f6b5bccb61edc40c3c00cefa7be07c1e5a91 Mon Sep 17 00:00:00 2001 From: Nancy.Lin Date: Fri, 13 Jan 2023 18:44:30 +0800 Subject: soc: mediatek: add cmdq support of mtk-mmsys config API for mt8195 vdosys1 Add cmdq support for mtk-mmsys config API. The mmsys config register settings need to take effect with the other HW settings(like OVL_ADAPTOR...) at the same vblanking time. If we use CPU to write the mmsys reg, we can't guarantee all the settings can be written in the same vblanking time. Cmdq is used for this purpose. We prepare all the related HW settings in one cmdq packet. The first command in the packet is "wait stream done", and then following with all the HW settings. After the cmdq packet is flush to GCE HW. The GCE waits for the "stream done event" to coming and then starts flushing all the HW settings. This can guarantee all the settings flush in the same vblanking. Signed-off-by: Nancy.Lin Reviewed-by: AngeloGioacchino Del Regno Reviewed-by: CK Hu Tested-by: AngeloGioacchino Del Regno Tested-by: Bo-Chen Chen Link: https://lore.kernel.org/r/20230113104434.28023-8-nancy.lin@mediatek.com Signed-off-by: Matthias Brugger --- drivers/soc/mediatek/mtk-mmsys.c | 63 ++++++++++++++++++++++++---------- include/linux/soc/mediatek/mtk-mmsys.h | 15 +++++--- 2 files changed, 55 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/drivers/soc/mediatek/mtk-mmsys.c b/drivers/soc/mediatek/mtk-mmsys.c index 2aeb739b8503..a0a584f16405 100644 --- a/drivers/soc/mediatek/mtk-mmsys.c +++ b/drivers/soc/mediatek/mtk-mmsys.c @@ -105,12 +105,27 @@ struct mtk_mmsys { const struct mtk_mmsys_driver_data *data; spinlock_t lock; /* protects mmsys_sw_rst_b reg */ struct reset_controller_dev rcdev; + struct cmdq_client_reg cmdq_base; }; -static void mtk_mmsys_update_bits(struct mtk_mmsys *mmsys, u32 offset, u32 mask, u32 val) +static void mtk_mmsys_update_bits(struct mtk_mmsys *mmsys, u32 offset, u32 mask, u32 val, + struct cmdq_pkt *cmdq_pkt) { u32 tmp; +#if IS_REACHABLE(CONFIG_MTK_CMDQ) + if (cmdq_pkt) { + if (mmsys->cmdq_base.size == 0) { + pr_err("mmsys lose gce property, failed to update mmsys bits with cmdq"); + return; + } + cmdq_pkt_write_mask(cmdq_pkt, mmsys->cmdq_base.subsys, + mmsys->cmdq_base.offset + offset, val, + mask); + return; + } +#endif + tmp = readl_relaxed(mmsys->regs + offset); tmp = (tmp & ~mask) | (val & mask); writel_relaxed(tmp, mmsys->regs + offset); @@ -127,7 +142,7 @@ void mtk_mmsys_ddp_connect(struct device *dev, for (i = 0; i < mmsys->data->num_routes; i++) if (cur == routes[i].from_comp && next == routes[i].to_comp) mtk_mmsys_update_bits(mmsys, routes[i].addr, routes[i].mask, - routes[i].val); + routes[i].val, NULL); } EXPORT_SYMBOL_GPL(mtk_mmsys_ddp_connect); @@ -141,42 +156,45 @@ void mtk_mmsys_ddp_disconnect(struct device *dev, for (i = 0; i < mmsys->data->num_routes; i++) if (cur == routes[i].from_comp && next == routes[i].to_comp) - mtk_mmsys_update_bits(mmsys, routes[i].addr, routes[i].mask, 0); + mtk_mmsys_update_bits(mmsys, routes[i].addr, routes[i].mask, 0, NULL); } EXPORT_SYMBOL_GPL(mtk_mmsys_ddp_disconnect); -void mtk_mmsys_merge_async_config(struct device *dev, int idx, int width, int height) +void mtk_mmsys_merge_async_config(struct device *dev, int idx, int width, int height, + struct cmdq_pkt *cmdq_pkt) { mtk_mmsys_update_bits(dev_get_drvdata(dev), MT8195_VDO1_MERGE0_ASYNC_CFG_WD + 0x10 * idx, - ~0, height << 16 | width); + ~0, height << 16 | width, cmdq_pkt); } EXPORT_SYMBOL_GPL(mtk_mmsys_merge_async_config); -void mtk_mmsys_hdr_config(struct device *dev, int be_width, int be_height) +void mtk_mmsys_hdr_config(struct device *dev, int be_width, int be_height, + struct cmdq_pkt *cmdq_pkt) { mtk_mmsys_update_bits(dev_get_drvdata(dev), MT8195_VDO1_HDRBE_ASYNC_CFG_WD, ~0, - be_height << 16 | be_width); + be_height << 16 | be_width, cmdq_pkt); } EXPORT_SYMBOL_GPL(mtk_mmsys_hdr_config); void mtk_mmsys_mixer_in_config(struct device *dev, int idx, bool alpha_sel, u16 alpha, - u8 mode, u32 biwidth) + u8 mode, u32 biwidth, struct cmdq_pkt *cmdq_pkt) { struct mtk_mmsys *mmsys = dev_get_drvdata(dev); mtk_mmsys_update_bits(mmsys, MT8195_VDO1_MIXER_IN1_ALPHA + (idx - 1) * 4, ~0, - alpha << 16 | alpha); + alpha << 16 | alpha, cmdq_pkt); mtk_mmsys_update_bits(mmsys, MT8195_VDO1_HDR_TOP_CFG, BIT(19 + idx), - alpha_sel << (19 + idx)); + alpha_sel << (19 + idx), cmdq_pkt); mtk_mmsys_update_bits(mmsys, MT8195_VDO1_MIXER_IN1_PAD + (idx - 1) * 4, - GENMASK(31, 16) | GENMASK(1, 0), biwidth << 16 | mode); + GENMASK(31, 16) | GENMASK(1, 0), biwidth << 16 | mode, cmdq_pkt); } EXPORT_SYMBOL_GPL(mtk_mmsys_mixer_in_config); -void mtk_mmsys_mixer_in_channel_swap(struct device *dev, int idx, bool channel_swap) +void mtk_mmsys_mixer_in_channel_swap(struct device *dev, int idx, bool channel_swap, + struct cmdq_pkt *cmdq_pkt) { mtk_mmsys_update_bits(dev_get_drvdata(dev), MT8195_VDO1_MIXER_IN1_PAD + (idx - 1) * 4, - BIT(4), channel_swap << 4); + BIT(4), channel_swap << 4, cmdq_pkt); } EXPORT_SYMBOL_GPL(mtk_mmsys_mixer_in_channel_swap); @@ -187,20 +205,20 @@ void mtk_mmsys_ddp_dpi_fmt_config(struct device *dev, u32 val) switch (val) { case MTK_DPI_RGB888_SDR_CON: mtk_mmsys_update_bits(mmsys, MT8186_MMSYS_DPI_OUTPUT_FORMAT, - MT8186_DPI_FORMAT_MASK, MT8186_DPI_RGB888_SDR_CON); + MT8186_DPI_FORMAT_MASK, MT8186_DPI_RGB888_SDR_CON, NULL); break; case MTK_DPI_RGB565_SDR_CON: mtk_mmsys_update_bits(mmsys, MT8186_MMSYS_DPI_OUTPUT_FORMAT, - MT8186_DPI_FORMAT_MASK, MT8186_DPI_RGB565_SDR_CON); + MT8186_DPI_FORMAT_MASK, MT8186_DPI_RGB565_SDR_CON, NULL); break; case MTK_DPI_RGB565_DDR_CON: mtk_mmsys_update_bits(mmsys, MT8186_MMSYS_DPI_OUTPUT_FORMAT, - MT8186_DPI_FORMAT_MASK, MT8186_DPI_RGB565_DDR_CON); + MT8186_DPI_FORMAT_MASK, MT8186_DPI_RGB565_DDR_CON, NULL); break; case MTK_DPI_RGB888_DDR_CON: default: mtk_mmsys_update_bits(mmsys, MT8186_MMSYS_DPI_OUTPUT_FORMAT, - MT8186_DPI_FORMAT_MASK, MT8186_DPI_RGB888_DDR_CON); + MT8186_DPI_FORMAT_MASK, MT8186_DPI_RGB888_DDR_CON, NULL); break; } } @@ -215,9 +233,9 @@ static int mtk_mmsys_reset_update(struct reset_controller_dev *rcdev, unsigned l spin_lock_irqsave(&mmsys->lock, flags); if (assert) - mtk_mmsys_update_bits(mmsys, mmsys->data->sw0_rst_offset, BIT(id), 0); + mtk_mmsys_update_bits(mmsys, mmsys->data->sw0_rst_offset, BIT(id), 0, NULL); else - mtk_mmsys_update_bits(mmsys, mmsys->data->sw0_rst_offset, BIT(id), BIT(id)); + mtk_mmsys_update_bits(mmsys, mmsys->data->sw0_rst_offset, BIT(id), BIT(id), NULL); spin_unlock_irqrestore(&mmsys->lock, flags); @@ -285,6 +303,13 @@ static int mtk_mmsys_probe(struct platform_device *pdev) } mmsys->data = of_device_get_match_data(&pdev->dev); + +#if IS_REACHABLE(CONFIG_MTK_CMDQ) + ret = cmdq_dev_get_client_reg(dev, &mmsys->cmdq_base, 0); + if (ret) + dev_dbg(dev, "No mediatek,gce-client-reg!\n"); +#endif + platform_set_drvdata(pdev, mmsys); clks = platform_device_register_data(&pdev->dev, mmsys->data->clk_driver, diff --git a/include/linux/soc/mediatek/mtk-mmsys.h b/include/linux/soc/mediatek/mtk-mmsys.h index 5a6753aed482..dc2963a0a0f7 100644 --- a/include/linux/soc/mediatek/mtk-mmsys.h +++ b/include/linux/soc/mediatek/mtk-mmsys.h @@ -6,6 +6,10 @@ #ifndef __MTK_MMSYS_H #define __MTK_MMSYS_H +#include +#include +#include + enum mtk_ddp_comp_id; struct device; @@ -83,13 +87,16 @@ void mtk_mmsys_ddp_disconnect(struct device *dev, void mtk_mmsys_ddp_dpi_fmt_config(struct device *dev, u32 val); -void mtk_mmsys_merge_async_config(struct device *dev, int idx, int width, int height); +void mtk_mmsys_merge_async_config(struct device *dev, int idx, int width, + int height, struct cmdq_pkt *cmdq_pkt); -void mtk_mmsys_hdr_config(struct device *dev, int be_width, int be_height); +void mtk_mmsys_hdr_config(struct device *dev, int be_width, int be_height, + struct cmdq_pkt *cmdq_pkt); void mtk_mmsys_mixer_in_config(struct device *dev, int idx, bool alpha_sel, u16 alpha, - u8 mode, u32 biwidth); + u8 mode, u32 biwidth, struct cmdq_pkt *cmdq_pkt); -void mtk_mmsys_mixer_in_channel_swap(struct device *dev, int idx, bool channel_swap); +void mtk_mmsys_mixer_in_channel_swap(struct device *dev, int idx, bool channel_swap, + struct cmdq_pkt *cmdq_pkt); #endif /* __MTK_MMSYS_H */ -- cgit v1.2.3 From c24973ed795fec5c12d8a822a0de99a4b7bab394 Mon Sep 17 00:00:00 2001 From: Mikko Perttunen Date: Thu, 19 Jan 2023 15:09:19 +0200 Subject: gpu: host1x: Implement job tracking using DMA fences In anticipation of removal of the intr API, implement job tracking using DMA fences instead. The main two things about this are making cdma_update schedule the work since fence completion can now be called from interrupt context, and some complication in ensuring the callback is not running when we free the fence. Signed-off-by: Mikko Perttunen Signed-off-by: Thierry Reding --- drivers/gpu/host1x/cdma.c | 14 ++++++++--- drivers/gpu/host1x/cdma.h | 2 ++ drivers/gpu/host1x/hw/channel_hw.c | 48 +++++++++++++++++++++----------------- drivers/gpu/host1x/job.c | 12 +++++++--- include/linux/host1x.h | 6 +++-- 5 files changed, 53 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpu/host1x/cdma.c b/drivers/gpu/host1x/cdma.c index 103fda055394..bc821b0ed908 100644 --- a/drivers/gpu/host1x/cdma.c +++ b/drivers/gpu/host1x/cdma.c @@ -490,6 +490,15 @@ resume: host1x_hw_cdma_resume(host1x, cdma, restart_addr); } +static void cdma_update_work(struct work_struct *work) +{ + struct host1x_cdma *cdma = container_of(work, struct host1x_cdma, update_work); + + mutex_lock(&cdma->lock); + update_cdma_locked(cdma); + mutex_unlock(&cdma->lock); +} + /* * Create a cdma */ @@ -499,6 +508,7 @@ int host1x_cdma_init(struct host1x_cdma *cdma) mutex_init(&cdma->lock); init_completion(&cdma->complete); + INIT_WORK(&cdma->update_work, cdma_update_work); INIT_LIST_HEAD(&cdma->sync_queue); @@ -679,7 +689,5 @@ void host1x_cdma_end(struct host1x_cdma *cdma, */ void host1x_cdma_update(struct host1x_cdma *cdma) { - mutex_lock(&cdma->lock); - update_cdma_locked(cdma); - mutex_unlock(&cdma->lock); + schedule_work(&cdma->update_work); } diff --git a/drivers/gpu/host1x/cdma.h b/drivers/gpu/host1x/cdma.h index 12c4327c4df0..7fd8168af4f9 100644 --- a/drivers/gpu/host1x/cdma.h +++ b/drivers/gpu/host1x/cdma.h @@ -11,6 +11,7 @@ #include #include #include +#include struct host1x_syncpt; struct host1x_userctx_timeout; @@ -69,6 +70,7 @@ struct host1x_cdma { struct buffer_timeout timeout; /* channel's timeout state/wq */ bool running; bool torndown; + struct work_struct update_work; }; #define cdma_to_channel(cdma) container_of(cdma, struct host1x_channel, cdma) diff --git a/drivers/gpu/host1x/hw/channel_hw.c b/drivers/gpu/host1x/hw/channel_hw.c index 732abe0750ff..8a3119fc5a77 100644 --- a/drivers/gpu/host1x/hw/channel_hw.c +++ b/drivers/gpu/host1x/hw/channel_hw.c @@ -278,6 +278,14 @@ static void channel_program_cdma(struct host1x_job *job) #endif } +static void job_complete_callback(struct dma_fence *fence, struct dma_fence_cb *cb) +{ + struct host1x_job *job = container_of(cb, struct host1x_job, fence_cb); + + /* Schedules CDMA update. */ + host1x_cdma_update(&job->channel->cdma); +} + static int channel_submit(struct host1x_job *job) { struct host1x_channel *ch = job->channel; @@ -285,7 +293,6 @@ static int channel_submit(struct host1x_job *job) u32 prev_max = 0; u32 syncval; int err; - struct host1x_waitlist *completed_waiter = NULL; struct host1x *host = dev_get_drvdata(ch->dev->parent); trace_host1x_channel_submit(dev_name(ch->dev), @@ -298,14 +305,7 @@ static int channel_submit(struct host1x_job *job) /* get submit lock */ err = mutex_lock_interruptible(&ch->submitlock); if (err) - goto error; - - completed_waiter = kzalloc(sizeof(*completed_waiter), GFP_KERNEL); - if (!completed_waiter) { - mutex_unlock(&ch->submitlock); - err = -ENOMEM; - goto error; - } + return err; host1x_channel_set_streamid(ch); host1x_enable_gather_filter(ch); @@ -315,31 +315,37 @@ static int channel_submit(struct host1x_job *job) err = host1x_cdma_begin(&ch->cdma, job); if (err) { mutex_unlock(&ch->submitlock); - goto error; + return err; } channel_program_cdma(job); syncval = host1x_syncpt_read_max(sp); + /* + * Create fence before submitting job to HW to avoid job completing + * before the fence is set up. + */ + job->fence = host1x_fence_create(sp, syncval); + if (WARN(IS_ERR(job->fence), "Failed to create submit complete fence")) { + job->fence = NULL; + } else { + err = dma_fence_add_callback(job->fence, &job->fence_cb, + job_complete_callback); + } + /* end CDMA submit & stash pinned hMems into sync queue */ host1x_cdma_end(&ch->cdma, job); trace_host1x_channel_submitted(dev_name(ch->dev), prev_max, syncval); - /* schedule a submit complete interrupt */ - err = host1x_intr_add_action(host, sp, syncval, - HOST1X_INTR_ACTION_SUBMIT_COMPLETE, ch, - completed_waiter, &job->waiter); - completed_waiter = NULL; - WARN(err, "Failed to set submit complete interrupt"); - mutex_unlock(&ch->submitlock); - return 0; + if (err == -ENOENT) + host1x_cdma_update(&ch->cdma); + else + WARN(err, "Failed to set submit complete interrupt"); -error: - kfree(completed_waiter); - return err; + return 0; } static int host1x_channel_init(struct host1x_channel *ch, struct host1x *dev, diff --git a/drivers/gpu/host1x/job.c b/drivers/gpu/host1x/job.c index b2761aa03b95..3ed49e1fd933 100644 --- a/drivers/gpu/host1x/job.c +++ b/drivers/gpu/host1x/job.c @@ -88,9 +88,15 @@ static void job_free(struct kref *ref) if (job->release) job->release(job); - if (job->waiter) - host1x_intr_put_ref(job->syncpt->host, job->syncpt->id, - job->waiter, false); + if (job->fence) { + /* + * remove_callback is atomic w.r.t. fence signaling, so + * after the call returns, we know that the callback is not + * in execution, and the fence can be safely freed. + */ + dma_fence_remove_callback(job->fence, &job->fence_cb); + dma_fence_put(job->fence); + } if (job->syncpt) host1x_syncpt_put(job->syncpt); diff --git a/include/linux/host1x.h b/include/linux/host1x.h index dc55d9d3b94f..db6cf6f34361 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -8,6 +8,7 @@ #include #include +#include #include #include @@ -288,8 +289,9 @@ struct host1x_job { u32 syncpt_incrs; u32 syncpt_end; - /* Completion waiter ref */ - void *waiter; + /* Completion fence for job tracking */ + struct dma_fence *fence; + struct dma_fence_cb fence_cb; /* Maximum time to wait for this job */ unsigned int timeout; -- cgit v1.2.3 From d5179020f5ce44fd449790a9c12ef6c1a90a2ca7 Mon Sep 17 00:00:00 2001 From: Mikko Perttunen Date: Thu, 19 Jan 2023 15:09:21 +0200 Subject: gpu: host1x: External timeout/cancellation for fences Currently all fences have a 30 second timeout to ensure they are cleaned up if the fence never completes otherwise. However, this one size fits all solution doesn't actually fit in every case, such as syncpoint waiting where we want to be able to have timeouts longer than 30 seconds. As such, we want to be able to give control over fence cancellation to the caller (and maybe eventually get rid of the internal timeout altogether). Here we add this cancellation mechanism by essentially adding a function for entering the timeout path by function call, and changing the syncpoint wait function to use it. Signed-off-by: Mikko Perttunen Signed-off-by: Thierry Reding --- drivers/gpu/drm/tegra/submit.c | 2 +- drivers/gpu/host1x/fence.c | 40 +++++++++++++++++++++++++------------- drivers/gpu/host1x/fence.h | 1 + drivers/gpu/host1x/hw/channel_hw.c | 2 +- drivers/gpu/host1x/syncpt.c | 4 +++- include/linux/host1x.h | 4 +++- 6 files changed, 36 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpu/drm/tegra/submit.c b/drivers/gpu/drm/tegra/submit.c index 066f88564169..f4688fcafe93 100644 --- a/drivers/gpu/drm/tegra/submit.c +++ b/drivers/gpu/drm/tegra/submit.c @@ -654,7 +654,7 @@ int tegra_drm_ioctl_channel_submit(struct drm_device *drm, void *data, args->syncpt.value = job->syncpt_end; if (syncobj) { - struct dma_fence *fence = host1x_fence_create(job->syncpt, job->syncpt_end); + struct dma_fence *fence = host1x_fence_create(job->syncpt, job->syncpt_end, true); if (IS_ERR(fence)) { err = PTR_ERR(fence); SUBMIT_ERR(context, "failed to create postfence: %d", err); diff --git a/drivers/gpu/host1x/fence.c b/drivers/gpu/host1x/fence.c index df5b56692d2c..139ad1afd935 100644 --- a/drivers/gpu/host1x/fence.c +++ b/drivers/gpu/host1x/fence.c @@ -37,8 +37,7 @@ static bool host1x_syncpt_fence_enable_signaling(struct dma_fence *f) if (host1x_syncpt_is_expired(sf->sp, sf->threshold)) return false; - /* One reference for interrupt path, one for timeout path. */ - dma_fence_get(f); + /* Reference for interrupt path. */ dma_fence_get(f); /* @@ -46,11 +45,15 @@ static bool host1x_syncpt_fence_enable_signaling(struct dma_fence *f) * reference to any fences for which 'enable_signaling' has been * called (and that have not been signalled). * - * We cannot (for now) normally guarantee that all fences get signalled. - * As such, setup a timeout, so that long-lasting fences will get - * reaped eventually. + * We cannot currently always guarantee that all fences get signalled + * or cancelled. As such, for such situations, set up a timeout, so + * that long-lasting fences will get reaped eventually. */ - schedule_delayed_work(&sf->timeout_work, msecs_to_jiffies(30000)); + if (sf->timeout) { + /* Reference for timeout path. */ + dma_fence_get(f); + schedule_delayed_work(&sf->timeout_work, msecs_to_jiffies(30000)); + } host1x_intr_add_fence_locked(sf->sp->host, sf); @@ -80,7 +83,7 @@ void host1x_fence_signal(struct host1x_syncpt_fence *f) return; } - if (cancel_delayed_work(&f->timeout_work)) { + if (f->timeout && cancel_delayed_work(&f->timeout_work)) { /* * We know that the timeout path will not be entered. * Safe to drop the timeout path's reference now. @@ -99,8 +102,9 @@ static void do_fence_timeout(struct work_struct *work) container_of(dwork, struct host1x_syncpt_fence, timeout_work); if (atomic_xchg(&f->signaling, 1)) { - /* Already on interrupt path, drop timeout path reference. */ - dma_fence_put(&f->base); + /* Already on interrupt path, drop timeout path reference if any. */ + if (f->timeout) + dma_fence_put(&f->base); return; } @@ -114,12 +118,12 @@ static void do_fence_timeout(struct work_struct *work) dma_fence_set_error(&f->base, -ETIMEDOUT); dma_fence_signal(&f->base); - - /* Drop timeout path reference. */ - dma_fence_put(&f->base); + if (f->timeout) + dma_fence_put(&f->base); } -struct dma_fence *host1x_fence_create(struct host1x_syncpt *sp, u32 threshold) +struct dma_fence *host1x_fence_create(struct host1x_syncpt *sp, u32 threshold, + bool timeout) { struct host1x_syncpt_fence *fence; @@ -129,6 +133,7 @@ struct dma_fence *host1x_fence_create(struct host1x_syncpt *sp, u32 threshold) fence->sp = sp; fence->threshold = threshold; + fence->timeout = timeout; dma_fence_init(&fence->base, &host1x_syncpt_fence_ops, &sp->fences.lock, dma_fence_context_alloc(1), 0); @@ -138,3 +143,12 @@ struct dma_fence *host1x_fence_create(struct host1x_syncpt *sp, u32 threshold) return &fence->base; } EXPORT_SYMBOL(host1x_fence_create); + +void host1x_fence_cancel(struct dma_fence *f) +{ + struct host1x_syncpt_fence *sf = to_host1x_fence(f); + + schedule_delayed_work(&sf->timeout_work, 0); + flush_delayed_work(&sf->timeout_work); +} +EXPORT_SYMBOL(host1x_fence_cancel); diff --git a/drivers/gpu/host1x/fence.h b/drivers/gpu/host1x/fence.h index 4352d046f92c..f3c644c73cad 100644 --- a/drivers/gpu/host1x/fence.h +++ b/drivers/gpu/host1x/fence.h @@ -13,6 +13,7 @@ struct host1x_syncpt_fence { struct host1x_syncpt *sp; u32 threshold; + bool timeout; struct delayed_work timeout_work; diff --git a/drivers/gpu/host1x/hw/channel_hw.c b/drivers/gpu/host1x/hw/channel_hw.c index 8a3119fc5a77..0a528573a792 100644 --- a/drivers/gpu/host1x/hw/channel_hw.c +++ b/drivers/gpu/host1x/hw/channel_hw.c @@ -325,7 +325,7 @@ static int channel_submit(struct host1x_job *job) * Create fence before submitting job to HW to avoid job completing * before the fence is set up. */ - job->fence = host1x_fence_create(sp, syncval); + job->fence = host1x_fence_create(sp, syncval, true); if (WARN(IS_ERR(job->fence), "Failed to create submit complete fence")) { job->fence = NULL; } else { diff --git a/drivers/gpu/host1x/syncpt.c b/drivers/gpu/host1x/syncpt.c index 75f58ec2ae23..2d2007760eac 100644 --- a/drivers/gpu/host1x/syncpt.c +++ b/drivers/gpu/host1x/syncpt.c @@ -236,11 +236,13 @@ int host1x_syncpt_wait(struct host1x_syncpt *sp, u32 thresh, long timeout, else if (timeout == 0) return -EAGAIN; - fence = host1x_fence_create(sp, thresh); + fence = host1x_fence_create(sp, thresh, false); if (IS_ERR(fence)) return PTR_ERR(fence); wait_err = dma_fence_wait_timeout(fence, true, timeout); + if (wait_err == 0) + host1x_fence_cancel(fence); dma_fence_put(fence); if (value) diff --git a/include/linux/host1x.h b/include/linux/host1x.h index db6cf6f34361..9a9de4b97a25 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -222,7 +222,9 @@ u32 host1x_syncpt_base_id(struct host1x_syncpt_base *base); void host1x_syncpt_release_vblank_reservation(struct host1x_client *client, u32 syncpt_id); -struct dma_fence *host1x_fence_create(struct host1x_syncpt *sp, u32 threshold); +struct dma_fence *host1x_fence_create(struct host1x_syncpt *sp, u32 threshold, + bool timeout); +void host1x_fence_cancel(struct dma_fence *fence); /* * host1x channel -- cgit v1.2.3 From 1ddc7618294084fff8d673217a9479550990ee84 Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Mon, 23 Jan 2023 12:59:45 +0530 Subject: bus: mhi: ep: Change state_lock to mutex state_lock, the spinlock type is meant to protect race against concurrent MHI state transitions. In mhi_ep_set_m0_state(), while the state_lock is being held, the channels are resumed in mhi_ep_resume_channels() if the previous state was M3. This causes sleeping in atomic bug, since mhi_ep_resume_channels() use mutex internally. Since the state_lock is supposed to be held throughout the state change, it is not ideal to drop the lock before calling mhi_ep_resume_channels(). So to fix this issue, let's change the type of state_lock to mutex. This would also allow holding the lock throughout all state transitions thereby avoiding any potential race. Cc: # 5.19 Fixes: e4b7b5f0f30a ("bus: mhi: ep: Add support for suspending and resuming channels") Reported-by: Dan Carpenter Reviewed-by: Jeffrey Hugo Signed-off-by: Manivannan Sadhasivam --- drivers/bus/mhi/ep/main.c | 8 +++++--- drivers/bus/mhi/ep/sm.c | 42 ++++++++++++++++++++++++------------------ include/linux/mhi_ep.h | 4 ++-- 3 files changed, 31 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/drivers/bus/mhi/ep/main.c b/drivers/bus/mhi/ep/main.c index bcaaba97ef63..528c00b232bf 100644 --- a/drivers/bus/mhi/ep/main.c +++ b/drivers/bus/mhi/ep/main.c @@ -1001,11 +1001,11 @@ static void mhi_ep_reset_worker(struct work_struct *work) mhi_ep_power_down(mhi_cntrl); - spin_lock_bh(&mhi_cntrl->state_lock); + mutex_lock(&mhi_cntrl->state_lock); + /* Reset MMIO to signal host that the MHI_RESET is completed in endpoint */ mhi_ep_mmio_reset(mhi_cntrl); cur_state = mhi_cntrl->mhi_state; - spin_unlock_bh(&mhi_cntrl->state_lock); /* * Only proceed further if the reset is due to SYS_ERR. The host will @@ -1014,6 +1014,8 @@ static void mhi_ep_reset_worker(struct work_struct *work) */ if (cur_state == MHI_STATE_SYS_ERR) mhi_ep_power_up(mhi_cntrl); + + mutex_unlock(&mhi_cntrl->state_lock); } /* @@ -1386,8 +1388,8 @@ int mhi_ep_register_controller(struct mhi_ep_cntrl *mhi_cntrl, INIT_LIST_HEAD(&mhi_cntrl->st_transition_list); INIT_LIST_HEAD(&mhi_cntrl->ch_db_list); - spin_lock_init(&mhi_cntrl->state_lock); spin_lock_init(&mhi_cntrl->list_lock); + mutex_init(&mhi_cntrl->state_lock); mutex_init(&mhi_cntrl->event_lock); /* Set MHI version and AMSS EE before enumeration */ diff --git a/drivers/bus/mhi/ep/sm.c b/drivers/bus/mhi/ep/sm.c index 3655c19e23c7..fd200b2ac0bb 100644 --- a/drivers/bus/mhi/ep/sm.c +++ b/drivers/bus/mhi/ep/sm.c @@ -63,24 +63,23 @@ int mhi_ep_set_m0_state(struct mhi_ep_cntrl *mhi_cntrl) int ret; /* If MHI is in M3, resume suspended channels */ - spin_lock_bh(&mhi_cntrl->state_lock); + mutex_lock(&mhi_cntrl->state_lock); + old_state = mhi_cntrl->mhi_state; if (old_state == MHI_STATE_M3) mhi_ep_resume_channels(mhi_cntrl); ret = mhi_ep_set_mhi_state(mhi_cntrl, MHI_STATE_M0); - spin_unlock_bh(&mhi_cntrl->state_lock); - if (ret) { mhi_ep_handle_syserr(mhi_cntrl); - return ret; + goto err_unlock; } /* Signal host that the device moved to M0 */ ret = mhi_ep_send_state_change_event(mhi_cntrl, MHI_STATE_M0); if (ret) { dev_err(dev, "Failed sending M0 state change event\n"); - return ret; + goto err_unlock; } if (old_state == MHI_STATE_READY) { @@ -88,11 +87,14 @@ int mhi_ep_set_m0_state(struct mhi_ep_cntrl *mhi_cntrl) ret = mhi_ep_send_ee_event(mhi_cntrl, MHI_EE_AMSS); if (ret) { dev_err(dev, "Failed sending AMSS EE event\n"); - return ret; + goto err_unlock; } } - return 0; +err_unlock: + mutex_unlock(&mhi_cntrl->state_lock); + + return ret; } int mhi_ep_set_m3_state(struct mhi_ep_cntrl *mhi_cntrl) @@ -100,13 +102,12 @@ int mhi_ep_set_m3_state(struct mhi_ep_cntrl *mhi_cntrl) struct device *dev = &mhi_cntrl->mhi_dev->dev; int ret; - spin_lock_bh(&mhi_cntrl->state_lock); - ret = mhi_ep_set_mhi_state(mhi_cntrl, MHI_STATE_M3); - spin_unlock_bh(&mhi_cntrl->state_lock); + mutex_lock(&mhi_cntrl->state_lock); + ret = mhi_ep_set_mhi_state(mhi_cntrl, MHI_STATE_M3); if (ret) { mhi_ep_handle_syserr(mhi_cntrl); - return ret; + goto err_unlock; } mhi_ep_suspend_channels(mhi_cntrl); @@ -115,10 +116,13 @@ int mhi_ep_set_m3_state(struct mhi_ep_cntrl *mhi_cntrl) ret = mhi_ep_send_state_change_event(mhi_cntrl, MHI_STATE_M3); if (ret) { dev_err(dev, "Failed sending M3 state change event\n"); - return ret; + goto err_unlock; } - return 0; +err_unlock: + mutex_unlock(&mhi_cntrl->state_lock); + + return ret; } int mhi_ep_set_ready_state(struct mhi_ep_cntrl *mhi_cntrl) @@ -127,22 +131,24 @@ int mhi_ep_set_ready_state(struct mhi_ep_cntrl *mhi_cntrl) enum mhi_state mhi_state; int ret, is_ready; - spin_lock_bh(&mhi_cntrl->state_lock); + mutex_lock(&mhi_cntrl->state_lock); + /* Ensure that the MHISTATUS is set to RESET by host */ mhi_state = mhi_ep_mmio_masked_read(mhi_cntrl, EP_MHISTATUS, MHISTATUS_MHISTATE_MASK); is_ready = mhi_ep_mmio_masked_read(mhi_cntrl, EP_MHISTATUS, MHISTATUS_READY_MASK); if (mhi_state != MHI_STATE_RESET || is_ready) { dev_err(dev, "READY state transition failed. MHI host not in RESET state\n"); - spin_unlock_bh(&mhi_cntrl->state_lock); - return -EIO; + ret = -EIO; + goto err_unlock; } ret = mhi_ep_set_mhi_state(mhi_cntrl, MHI_STATE_READY); - spin_unlock_bh(&mhi_cntrl->state_lock); - if (ret) mhi_ep_handle_syserr(mhi_cntrl); +err_unlock: + mutex_unlock(&mhi_cntrl->state_lock); + return ret; } diff --git a/include/linux/mhi_ep.h b/include/linux/mhi_ep.h index 478aece17046..f198a8ac7ee7 100644 --- a/include/linux/mhi_ep.h +++ b/include/linux/mhi_ep.h @@ -70,8 +70,8 @@ struct mhi_ep_db_info { * @cmd_ctx_cache_phys: Physical address of the host command context cache * @chdb: Array of channel doorbell interrupt info * @event_lock: Lock for protecting event rings - * @list_lock: Lock for protecting state transition and channel doorbell lists * @state_lock: Lock for protecting state transitions + * @list_lock: Lock for protecting state transition and channel doorbell lists * @st_transition_list: List of state transitions * @ch_db_list: List of queued channel doorbells * @wq: Dedicated workqueue for handling rings and state changes @@ -117,8 +117,8 @@ struct mhi_ep_cntrl { struct mhi_ep_db_info chdb[4]; struct mutex event_lock; + struct mutex state_lock; spinlock_t list_lock; - spinlock_t state_lock; struct list_head st_transition_list; struct list_head ch_db_list; -- cgit v1.2.3 From 206351c5c2d9906b0304c5b10d5162707d5d4bcb Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Mon, 16 Jan 2023 12:08:35 +0200 Subject: mfd: intel-m10-bmc: Add missing includes to header linux/mfd/intel-m10-bmc.h is using: - pr_err(), thus include also linux/dev_printk.h - FIELD_GET(), this include also linux/bitfield.h - GENMASK(), thus include also linux/bits.h Signed-off-by: Ilpo Järvinen Reviewed-by: Russ Weight Reviewed-by: Xu Yilun Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230116100845.6153-2-ilpo.jarvinen@linux.intel.com --- include/linux/mfd/intel-m10-bmc.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/intel-m10-bmc.h b/include/linux/mfd/intel-m10-bmc.h index f0044b14136e..0d4db5d9d5af 100644 --- a/include/linux/mfd/intel-m10-bmc.h +++ b/include/linux/mfd/intel-m10-bmc.h @@ -7,6 +7,9 @@ #ifndef __MFD_INTEL_M10_BMC_H #define __MFD_INTEL_M10_BMC_H +#include +#include +#include #include #define M10BMC_LEGACY_BUILD_VER 0x300468 -- cgit v1.2.3 From 16e5d95a5c451027a2e7ef89dd146a1c6c74ca6a Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Mon, 16 Jan 2023 12:08:36 +0200 Subject: mfd: intel-m10-bmc: Create m10bmc_platform_info for type specific info BMC type specific info is currently set by a switch/case block. The size of this info is expected to grow as more dev types and features are added which would have made the switch block bloaty. Store type specific info into struct and place them into .driver_data instead because it makes things a bit cleaner. The m10bmc_type enum can be dropped as the differentiation is now fully handled by the platform info. The info member of struct intel_m10bmc that is added here is not used yet in this change but its addition logically still belongs to this change. The CSR map change that comes after this change needs to have the info member. Reviewed-by: Russ Weight Reviewed-by: Xu Yilun Signed-off-by: Ilpo Järvinen Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230116100845.6153-3-ilpo.jarvinen@linux.intel.com --- drivers/mfd/intel-m10-bmc.c | 53 ++++++++++++++++++--------------------- include/linux/mfd/intel-m10-bmc.h | 12 +++++++++ 2 files changed, 36 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/drivers/mfd/intel-m10-bmc.c b/drivers/mfd/intel-m10-bmc.c index 7e3319e5b22f..12c522c16d83 100644 --- a/drivers/mfd/intel-m10-bmc.c +++ b/drivers/mfd/intel-m10-bmc.c @@ -13,12 +13,6 @@ #include #include -enum m10bmc_type { - M10_N3000, - M10_D5005, - M10_N5010, -}; - static struct mfd_cell m10bmc_d5005_subdevs[] = { { .name = "d5005bmc-hwmon" }, { .name = "d5005bmc-sec-update" } @@ -162,15 +156,17 @@ static int check_m10bmc_version(struct intel_m10bmc *ddata) static int intel_m10_bmc_spi_probe(struct spi_device *spi) { const struct spi_device_id *id = spi_get_device_id(spi); + const struct intel_m10bmc_platform_info *info; struct device *dev = &spi->dev; - struct mfd_cell *cells; struct intel_m10bmc *ddata; - int ret, n_cell; + int ret; ddata = devm_kzalloc(dev, sizeof(*ddata), GFP_KERNEL); if (!ddata) return -ENOMEM; + info = (struct intel_m10bmc_platform_info *)id->driver_data; + ddata->info = info; ddata->dev = dev; ddata->regmap = @@ -189,24 +185,8 @@ static int intel_m10_bmc_spi_probe(struct spi_device *spi) return ret; } - switch (id->driver_data) { - case M10_N3000: - cells = m10bmc_pacn3000_subdevs; - n_cell = ARRAY_SIZE(m10bmc_pacn3000_subdevs); - break; - case M10_D5005: - cells = m10bmc_d5005_subdevs; - n_cell = ARRAY_SIZE(m10bmc_d5005_subdevs); - break; - case M10_N5010: - cells = m10bmc_n5010_subdevs; - n_cell = ARRAY_SIZE(m10bmc_n5010_subdevs); - break; - default: - return -ENODEV; - } - - ret = devm_mfd_add_devices(dev, PLATFORM_DEVID_AUTO, cells, n_cell, + ret = devm_mfd_add_devices(dev, PLATFORM_DEVID_AUTO, + info->cells, info->n_cells, NULL, 0, NULL); if (ret) dev_err(dev, "Failed to register sub-devices: %d\n", ret); @@ -214,10 +194,25 @@ static int intel_m10_bmc_spi_probe(struct spi_device *spi) return ret; } +static const struct intel_m10bmc_platform_info m10bmc_spi_n3000 = { + .cells = m10bmc_pacn3000_subdevs, + .n_cells = ARRAY_SIZE(m10bmc_pacn3000_subdevs), +}; + +static const struct intel_m10bmc_platform_info m10bmc_spi_d5005 = { + .cells = m10bmc_d5005_subdevs, + .n_cells = ARRAY_SIZE(m10bmc_d5005_subdevs), +}; + +static const struct intel_m10bmc_platform_info m10bmc_spi_n5010 = { + .cells = m10bmc_n5010_subdevs, + .n_cells = ARRAY_SIZE(m10bmc_n5010_subdevs), +}; + static const struct spi_device_id m10bmc_spi_id[] = { - { "m10-n3000", M10_N3000 }, - { "m10-d5005", M10_D5005 }, - { "m10-n5010", M10_N5010 }, + { "m10-n3000", (kernel_ulong_t)&m10bmc_spi_n3000 }, + { "m10-d5005", (kernel_ulong_t)&m10bmc_spi_d5005 }, + { "m10-n5010", (kernel_ulong_t)&m10bmc_spi_n5010 }, { } }; MODULE_DEVICE_TABLE(spi, m10bmc_spi_id); diff --git a/include/linux/mfd/intel-m10-bmc.h b/include/linux/mfd/intel-m10-bmc.h index 0d4db5d9d5af..f418cad88e64 100644 --- a/include/linux/mfd/intel-m10-bmc.h +++ b/include/linux/mfd/intel-m10-bmc.h @@ -121,14 +121,26 @@ /* Address of 4KB inverted bit vector containing staging area FLASH count */ #define STAGING_FLASH_COUNT 0x17ffb000 +/** + * struct intel_m10bmc_platform_info - Intel MAX 10 BMC platform specific information + * @cells: MFD cells + * @n_cells: MFD cells ARRAY_SIZE() + */ +struct intel_m10bmc_platform_info { + struct mfd_cell *cells; + int n_cells; +}; + /** * struct intel_m10bmc - Intel MAX 10 BMC parent driver data structure * @dev: this device * @regmap: the regmap used to access registers by m10bmc itself + * @info: the platform information for MAX10 BMC */ struct intel_m10bmc { struct device *dev; struct regmap *regmap; + const struct intel_m10bmc_platform_info *info; }; /* -- cgit v1.2.3 From 603aed8ffd4c9cb633c05a514cfb5e8ca6b0751d Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Mon, 16 Jan 2023 12:08:38 +0200 Subject: mfd: intel-m10-bmc: Split into core and spi specific parts Split the common code from intel-m10-bmc driver into intel-m10-bmc-core and move the SPI bus parts into an interface specific file. intel-m10-bmc-core becomes the core MFD functions which can support multiple bus interface like SPI bus. Co-developed-by: Tianfei zhang Signed-off-by: Tianfei zhang Reviewed-by: Russ Weight Acked-by: Guenter Roeck # hwmon Reviewed-by: Xu Yilun Signed-off-by: Ilpo Järvinen Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230116100845.6153-5-ilpo.jarvinen@linux.intel.com --- MAINTAINERS | 2 +- drivers/fpga/Kconfig | 2 +- drivers/hwmon/Kconfig | 2 +- drivers/mfd/Kconfig | 30 +++-- drivers/mfd/Makefile | 4 +- drivers/mfd/intel-m10-bmc-core.c | 122 ++++++++++++++++++++ drivers/mfd/intel-m10-bmc-spi.c | 145 ++++++++++++++++++++++++ drivers/mfd/intel-m10-bmc.c | 233 -------------------------------------- include/linux/mfd/intel-m10-bmc.h | 6 + 9 files changed, 297 insertions(+), 249 deletions(-) create mode 100644 drivers/mfd/intel-m10-bmc-core.c create mode 100644 drivers/mfd/intel-m10-bmc-spi.c delete mode 100644 drivers/mfd/intel-m10-bmc.c (limited to 'include/linux') diff --git a/MAINTAINERS b/MAINTAINERS index f61eb221415b..261c1dc793bc 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -10576,7 +10576,7 @@ S: Maintained F: Documentation/ABI/testing/sysfs-driver-intel-m10-bmc F: Documentation/hwmon/intel-m10-bmc-hwmon.rst F: drivers/hwmon/intel-m10-bmc-hwmon.c -F: drivers/mfd/intel-m10-bmc.c +F: drivers/mfd/intel-m10-bmc* F: include/linux/mfd/intel-m10-bmc.h INTEL MENLOW THERMAL DRIVER diff --git a/drivers/fpga/Kconfig b/drivers/fpga/Kconfig index 6ce143dafd04..0a00763b9f28 100644 --- a/drivers/fpga/Kconfig +++ b/drivers/fpga/Kconfig @@ -246,7 +246,7 @@ config FPGA_MGR_VERSAL_FPGA config FPGA_M10_BMC_SEC_UPDATE tristate "Intel MAX10 BMC Secure Update driver" - depends on MFD_INTEL_M10_BMC + depends on MFD_INTEL_M10_BMC_CORE select FW_LOADER select FW_UPLOAD help diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig index 3176c33af6c6..42c28e887df3 100644 --- a/drivers/hwmon/Kconfig +++ b/drivers/hwmon/Kconfig @@ -2341,7 +2341,7 @@ config SENSORS_XGENE config SENSORS_INTEL_M10_BMC_HWMON tristate "Intel MAX10 BMC Hardware Monitoring" - depends on MFD_INTEL_M10_BMC + depends on MFD_INTEL_M10_BMC_CORE help This driver provides support for the hardware monitoring functionality on Intel MAX10 BMC chip. diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig index 30db49f31866..b6ab85831cde 100644 --- a/drivers/mfd/Kconfig +++ b/drivers/mfd/Kconfig @@ -2224,18 +2224,24 @@ config SGI_MFD_IOC3 If you have an SGI Origin, Octane, or a PCI IOC3 card, then say Y. Otherwise say N. -config MFD_INTEL_M10_BMC - tristate "Intel MAX 10 Board Management Controller" - depends on SPI_MASTER - select REGMAP_SPI_AVMM - select MFD_CORE - help - Support for the Intel MAX 10 board management controller using the - SPI interface. - - This driver provides common support for accessing the device, - additional drivers must be enabled in order to use the functionality - of the device. +config MFD_INTEL_M10_BMC_CORE + tristate + select MFD_CORE + select REGMAP + default n + +config MFD_INTEL_M10_BMC_SPI + tristate "Intel MAX 10 Board Management Controller with SPI" + depends on SPI_MASTER + select MFD_INTEL_M10_BMC_CORE + select REGMAP_SPI_AVMM + help + Support for the Intel MAX 10 board management controller using the + SPI interface. + + This driver provides common support for accessing the device, + additional drivers must be enabled in order to use the functionality + of the device. config MFD_RSMU_I2C tristate "Renesas Synchronization Management Unit with I2C" diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile index 457471478a93..b360b29150b5 100644 --- a/drivers/mfd/Makefile +++ b/drivers/mfd/Makefile @@ -269,7 +269,9 @@ obj-$(CONFIG_MFD_QCOM_PM8008) += qcom-pm8008.o obj-$(CONFIG_SGI_MFD_IOC3) += ioc3.o obj-$(CONFIG_MFD_SIMPLE_MFD_I2C) += simple-mfd-i2c.o obj-$(CONFIG_MFD_SMPRO) += smpro-core.o -obj-$(CONFIG_MFD_INTEL_M10_BMC) += intel-m10-bmc.o + +obj-$(CONFIG_MFD_INTEL_M10_BMC_CORE) += intel-m10-bmc-core.o +obj-$(CONFIG_MFD_INTEL_M10_BMC_SPI) += intel-m10-bmc-spi.o obj-$(CONFIG_MFD_ATC260X) += atc260x-core.o obj-$(CONFIG_MFD_ATC260X_I2C) += atc260x-i2c.o diff --git a/drivers/mfd/intel-m10-bmc-core.c b/drivers/mfd/intel-m10-bmc-core.c new file mode 100644 index 000000000000..dd26e3a6c3ab --- /dev/null +++ b/drivers/mfd/intel-m10-bmc-core.c @@ -0,0 +1,122 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Intel MAX 10 Board Management Controller chip - common code + * + * Copyright (C) 2018-2020 Intel Corporation. All rights reserved. + */ + +#include +#include +#include +#include +#include +#include + +static ssize_t bmc_version_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct intel_m10bmc *ddata = dev_get_drvdata(dev); + unsigned int val; + int ret; + + ret = m10bmc_sys_read(ddata, M10BMC_BUILD_VER, &val); + if (ret) + return ret; + + return sprintf(buf, "0x%x\n", val); +} +static DEVICE_ATTR_RO(bmc_version); + +static ssize_t bmcfw_version_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct intel_m10bmc *ddata = dev_get_drvdata(dev); + unsigned int val; + int ret; + + ret = m10bmc_sys_read(ddata, NIOS2_FW_VERSION, &val); + if (ret) + return ret; + + return sprintf(buf, "0x%x\n", val); +} +static DEVICE_ATTR_RO(bmcfw_version); + +static ssize_t mac_address_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct intel_m10bmc *ddata = dev_get_drvdata(dev); + unsigned int macaddr_low, macaddr_high; + int ret; + + ret = m10bmc_sys_read(ddata, M10BMC_MAC_LOW, &macaddr_low); + if (ret) + return ret; + + ret = m10bmc_sys_read(ddata, M10BMC_MAC_HIGH, &macaddr_high); + if (ret) + return ret; + + return sysfs_emit(buf, "%02x:%02x:%02x:%02x:%02x:%02x\n", + (u8)FIELD_GET(M10BMC_MAC_BYTE1, macaddr_low), + (u8)FIELD_GET(M10BMC_MAC_BYTE2, macaddr_low), + (u8)FIELD_GET(M10BMC_MAC_BYTE3, macaddr_low), + (u8)FIELD_GET(M10BMC_MAC_BYTE4, macaddr_low), + (u8)FIELD_GET(M10BMC_MAC_BYTE5, macaddr_high), + (u8)FIELD_GET(M10BMC_MAC_BYTE6, macaddr_high)); +} +static DEVICE_ATTR_RO(mac_address); + +static ssize_t mac_count_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct intel_m10bmc *ddata = dev_get_drvdata(dev); + unsigned int macaddr_high; + int ret; + + ret = m10bmc_sys_read(ddata, M10BMC_MAC_HIGH, &macaddr_high); + if (ret) + return ret; + + return sysfs_emit(buf, "%u\n", (u8)FIELD_GET(M10BMC_MAC_COUNT, macaddr_high)); +} +static DEVICE_ATTR_RO(mac_count); + +static struct attribute *m10bmc_attrs[] = { + &dev_attr_bmc_version.attr, + &dev_attr_bmcfw_version.attr, + &dev_attr_mac_address.attr, + &dev_attr_mac_count.attr, + NULL, +}; + +static const struct attribute_group m10bmc_group = { + .attrs = m10bmc_attrs, +}; + +const struct attribute_group *m10bmc_dev_groups[] = { + &m10bmc_group, + NULL, +}; +EXPORT_SYMBOL_GPL(m10bmc_dev_groups); + +int m10bmc_dev_init(struct intel_m10bmc *m10bmc, const struct intel_m10bmc_platform_info *info) +{ + int ret; + + m10bmc->info = info; + dev_set_drvdata(m10bmc->dev, m10bmc); + + ret = devm_mfd_add_devices(m10bmc->dev, PLATFORM_DEVID_AUTO, + info->cells, info->n_cells, + NULL, 0, NULL); + if (ret) + dev_err(m10bmc->dev, "Failed to register sub-devices: %d\n", ret); + + return ret; +} +EXPORT_SYMBOL_GPL(m10bmc_dev_init); + +MODULE_DESCRIPTION("Intel MAX 10 BMC core driver"); +MODULE_AUTHOR("Intel Corporation"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/mfd/intel-m10-bmc-spi.c b/drivers/mfd/intel-m10-bmc-spi.c new file mode 100644 index 000000000000..be1d4ddedabb --- /dev/null +++ b/drivers/mfd/intel-m10-bmc-spi.c @@ -0,0 +1,145 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Intel MAX 10 Board Management Controller chip + * + * Copyright (C) 2018-2020 Intel Corporation. All rights reserved. + */ +#include +#include +#include +#include +#include +#include +#include +#include + +static const struct regmap_range m10bmc_regmap_range[] = { + regmap_reg_range(M10BMC_LEGACY_BUILD_VER, M10BMC_LEGACY_BUILD_VER), + regmap_reg_range(M10BMC_SYS_BASE, M10BMC_SYS_END), + regmap_reg_range(M10BMC_FLASH_BASE, M10BMC_FLASH_END), +}; + +static const struct regmap_access_table m10bmc_access_table = { + .yes_ranges = m10bmc_regmap_range, + .n_yes_ranges = ARRAY_SIZE(m10bmc_regmap_range), +}; + +static struct regmap_config intel_m10bmc_regmap_config = { + .reg_bits = 32, + .val_bits = 32, + .reg_stride = 4, + .wr_table = &m10bmc_access_table, + .rd_table = &m10bmc_access_table, + .max_register = M10BMC_MEM_END, +}; + +static int check_m10bmc_version(struct intel_m10bmc *ddata) +{ + unsigned int v; + int ret; + + /* + * This check is to filter out the very old legacy BMC versions. In the + * old BMC chips, the BMC version info is stored in the old version + * register (M10BMC_LEGACY_BUILD_VER), so its read out value would have + * not been M10BMC_VER_LEGACY_INVALID (0xffffffff). But in new BMC + * chips that the driver supports, the value of this register should be + * M10BMC_VER_LEGACY_INVALID. + */ + ret = m10bmc_raw_read(ddata, M10BMC_LEGACY_BUILD_VER, &v); + if (ret) + return -ENODEV; + + if (v != M10BMC_VER_LEGACY_INVALID) { + dev_err(ddata->dev, "bad version M10BMC detected\n"); + return -ENODEV; + } + + return 0; +} + +static int intel_m10_bmc_spi_probe(struct spi_device *spi) +{ + const struct spi_device_id *id = spi_get_device_id(spi); + const struct intel_m10bmc_platform_info *info; + struct device *dev = &spi->dev; + struct intel_m10bmc *ddata; + int ret; + + ddata = devm_kzalloc(dev, sizeof(*ddata), GFP_KERNEL); + if (!ddata) + return -ENOMEM; + + info = (struct intel_m10bmc_platform_info *)id->driver_data; + ddata->dev = dev; + + ddata->regmap = devm_regmap_init_spi_avmm(spi, &intel_m10bmc_regmap_config); + if (IS_ERR(ddata->regmap)) { + ret = PTR_ERR(ddata->regmap); + dev_err(dev, "Failed to allocate regmap: %d\n", ret); + return ret; + } + + spi_set_drvdata(spi, ddata); + + ret = check_m10bmc_version(ddata); + if (ret) { + dev_err(dev, "Failed to identify m10bmc hardware\n"); + return ret; + } + + return m10bmc_dev_init(ddata, info); +} + +static struct mfd_cell m10bmc_d5005_subdevs[] = { + { .name = "d5005bmc-hwmon" }, + { .name = "d5005bmc-sec-update" }, +}; + +static struct mfd_cell m10bmc_pacn3000_subdevs[] = { + { .name = "n3000bmc-hwmon" }, + { .name = "n3000bmc-retimer" }, + { .name = "n3000bmc-sec-update" }, +}; + +static struct mfd_cell m10bmc_n5010_subdevs[] = { + { .name = "n5010bmc-hwmon" }, +}; + +static const struct intel_m10bmc_platform_info m10bmc_spi_n3000 = { + .cells = m10bmc_pacn3000_subdevs, + .n_cells = ARRAY_SIZE(m10bmc_pacn3000_subdevs), +}; + +static const struct intel_m10bmc_platform_info m10bmc_spi_d5005 = { + .cells = m10bmc_d5005_subdevs, + .n_cells = ARRAY_SIZE(m10bmc_d5005_subdevs), +}; + +static const struct intel_m10bmc_platform_info m10bmc_spi_n5010 = { + .cells = m10bmc_n5010_subdevs, + .n_cells = ARRAY_SIZE(m10bmc_n5010_subdevs), +}; + +static const struct spi_device_id m10bmc_spi_id[] = { + { "m10-n3000", (kernel_ulong_t)&m10bmc_spi_n3000 }, + { "m10-d5005", (kernel_ulong_t)&m10bmc_spi_d5005 }, + { "m10-n5010", (kernel_ulong_t)&m10bmc_spi_n5010 }, + { } +}; +MODULE_DEVICE_TABLE(spi, m10bmc_spi_id); + +static struct spi_driver intel_m10bmc_spi_driver = { + .driver = { + .name = "intel-m10-bmc", + .dev_groups = m10bmc_dev_groups, + }, + .probe = intel_m10_bmc_spi_probe, + .id_table = m10bmc_spi_id, +}; +module_spi_driver(intel_m10bmc_spi_driver); + +MODULE_DESCRIPTION("Intel MAX 10 BMC SPI bus interface"); +MODULE_AUTHOR("Intel Corporation"); +MODULE_LICENSE("GPL v2"); +MODULE_ALIAS("spi:intel-m10-bmc"); diff --git a/drivers/mfd/intel-m10-bmc.c b/drivers/mfd/intel-m10-bmc.c deleted file mode 100644 index 2c26203c4799..000000000000 --- a/drivers/mfd/intel-m10-bmc.c +++ /dev/null @@ -1,233 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Intel MAX 10 Board Management Controller chip - * - * Copyright (C) 2018-2020 Intel Corporation. All rights reserved. - */ -#include -#include -#include -#include -#include -#include -#include -#include - -static struct mfd_cell m10bmc_d5005_subdevs[] = { - { .name = "d5005bmc-hwmon" }, - { .name = "d5005bmc-sec-update" } -}; - -static struct mfd_cell m10bmc_pacn3000_subdevs[] = { - { .name = "n3000bmc-hwmon" }, - { .name = "n3000bmc-retimer" }, - { .name = "n3000bmc-sec-update" }, -}; - -static struct mfd_cell m10bmc_n5010_subdevs[] = { - { .name = "n5010bmc-hwmon" }, -}; - -static const struct regmap_range m10bmc_regmap_range[] = { - regmap_reg_range(M10BMC_LEGACY_BUILD_VER, M10BMC_LEGACY_BUILD_VER), - regmap_reg_range(M10BMC_SYS_BASE, M10BMC_SYS_END), - regmap_reg_range(M10BMC_FLASH_BASE, M10BMC_FLASH_END), -}; - -static const struct regmap_access_table m10bmc_access_table = { - .yes_ranges = m10bmc_regmap_range, - .n_yes_ranges = ARRAY_SIZE(m10bmc_regmap_range), -}; - -static struct regmap_config intel_m10bmc_regmap_config = { - .reg_bits = 32, - .val_bits = 32, - .reg_stride = 4, - .wr_table = &m10bmc_access_table, - .rd_table = &m10bmc_access_table, - .max_register = M10BMC_MEM_END, -}; - -static ssize_t bmc_version_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct intel_m10bmc *ddata = dev_get_drvdata(dev); - unsigned int val; - int ret; - - ret = m10bmc_sys_read(ddata, M10BMC_BUILD_VER, &val); - if (ret) - return ret; - - return sprintf(buf, "0x%x\n", val); -} -static DEVICE_ATTR_RO(bmc_version); - -static ssize_t bmcfw_version_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct intel_m10bmc *ddata = dev_get_drvdata(dev); - unsigned int val; - int ret; - - ret = m10bmc_sys_read(ddata, NIOS2_FW_VERSION, &val); - if (ret) - return ret; - - return sprintf(buf, "0x%x\n", val); -} -static DEVICE_ATTR_RO(bmcfw_version); - -static ssize_t mac_address_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct intel_m10bmc *ddata = dev_get_drvdata(dev); - unsigned int macaddr_low, macaddr_high; - int ret; - - ret = m10bmc_sys_read(ddata, M10BMC_MAC_LOW, &macaddr_low); - if (ret) - return ret; - - ret = m10bmc_sys_read(ddata, M10BMC_MAC_HIGH, &macaddr_high); - if (ret) - return ret; - - return sysfs_emit(buf, "%02x:%02x:%02x:%02x:%02x:%02x\n", - (u8)FIELD_GET(M10BMC_MAC_BYTE1, macaddr_low), - (u8)FIELD_GET(M10BMC_MAC_BYTE2, macaddr_low), - (u8)FIELD_GET(M10BMC_MAC_BYTE3, macaddr_low), - (u8)FIELD_GET(M10BMC_MAC_BYTE4, macaddr_low), - (u8)FIELD_GET(M10BMC_MAC_BYTE5, macaddr_high), - (u8)FIELD_GET(M10BMC_MAC_BYTE6, macaddr_high)); -} -static DEVICE_ATTR_RO(mac_address); - -static ssize_t mac_count_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct intel_m10bmc *ddata = dev_get_drvdata(dev); - unsigned int macaddr_high; - int ret; - - ret = m10bmc_sys_read(ddata, M10BMC_MAC_HIGH, &macaddr_high); - if (ret) - return ret; - - return sysfs_emit(buf, "%u\n", - (u8)FIELD_GET(M10BMC_MAC_COUNT, macaddr_high)); -} -static DEVICE_ATTR_RO(mac_count); - -static struct attribute *m10bmc_attrs[] = { - &dev_attr_bmc_version.attr, - &dev_attr_bmcfw_version.attr, - &dev_attr_mac_address.attr, - &dev_attr_mac_count.attr, - NULL, -}; -ATTRIBUTE_GROUPS(m10bmc); - -static int check_m10bmc_version(struct intel_m10bmc *ddata) -{ - unsigned int v; - int ret; - - /* - * This check is to filter out the very old legacy BMC versions. In the - * old BMC chips, the BMC version info is stored in the old version - * register (M10BMC_LEGACY_BUILD_VER), so its read out value would have - * not been M10BMC_VER_LEGACY_INVALID (0xffffffff). But in new BMC - * chips that the driver supports, the value of this register should be - * M10BMC_VER_LEGACY_INVALID. - */ - ret = m10bmc_raw_read(ddata, M10BMC_LEGACY_BUILD_VER, &v); - if (ret) - return -ENODEV; - - if (v != M10BMC_VER_LEGACY_INVALID) { - dev_err(ddata->dev, "bad version M10BMC detected\n"); - return -ENODEV; - } - - return 0; -} - -static int intel_m10_bmc_spi_probe(struct spi_device *spi) -{ - const struct spi_device_id *id = spi_get_device_id(spi); - const struct intel_m10bmc_platform_info *info; - struct device *dev = &spi->dev; - struct intel_m10bmc *ddata; - int ret; - - ddata = devm_kzalloc(dev, sizeof(*ddata), GFP_KERNEL); - if (!ddata) - return -ENOMEM; - - info = (struct intel_m10bmc_platform_info *)id->driver_data; - ddata->info = info; - ddata->dev = dev; - - ddata->regmap = - devm_regmap_init_spi_avmm(spi, &intel_m10bmc_regmap_config); - if (IS_ERR(ddata->regmap)) { - ret = PTR_ERR(ddata->regmap); - dev_err(dev, "Failed to allocate regmap: %d\n", ret); - return ret; - } - - spi_set_drvdata(spi, ddata); - - ret = check_m10bmc_version(ddata); - if (ret) { - dev_err(dev, "Failed to identify m10bmc hardware\n"); - return ret; - } - - ret = devm_mfd_add_devices(dev, PLATFORM_DEVID_AUTO, - info->cells, info->n_cells, - NULL, 0, NULL); - if (ret) - dev_err(dev, "Failed to register sub-devices: %d\n", ret); - - return ret; -} - -static const struct intel_m10bmc_platform_info m10bmc_spi_n3000 = { - .cells = m10bmc_pacn3000_subdevs, - .n_cells = ARRAY_SIZE(m10bmc_pacn3000_subdevs), -}; - -static const struct intel_m10bmc_platform_info m10bmc_spi_d5005 = { - .cells = m10bmc_d5005_subdevs, - .n_cells = ARRAY_SIZE(m10bmc_d5005_subdevs), -}; - -static const struct intel_m10bmc_platform_info m10bmc_spi_n5010 = { - .cells = m10bmc_n5010_subdevs, - .n_cells = ARRAY_SIZE(m10bmc_n5010_subdevs), -}; - -static const struct spi_device_id m10bmc_spi_id[] = { - { "m10-n3000", (kernel_ulong_t)&m10bmc_spi_n3000 }, - { "m10-d5005", (kernel_ulong_t)&m10bmc_spi_d5005 }, - { "m10-n5010", (kernel_ulong_t)&m10bmc_spi_n5010 }, - { } -}; -MODULE_DEVICE_TABLE(spi, m10bmc_spi_id); - -static struct spi_driver intel_m10bmc_spi_driver = { - .driver = { - .name = "intel-m10-bmc", - .dev_groups = m10bmc_groups, - }, - .probe = intel_m10_bmc_spi_probe, - .id_table = m10bmc_spi_id, -}; -module_spi_driver(intel_m10bmc_spi_driver); - -MODULE_DESCRIPTION("Intel MAX 10 BMC Device Driver"); -MODULE_AUTHOR("Intel Corporation"); -MODULE_LICENSE("GPL v2"); -MODULE_ALIAS("spi:intel-m10-bmc"); diff --git a/include/linux/mfd/intel-m10-bmc.h b/include/linux/mfd/intel-m10-bmc.h index f418cad88e64..a80deb61b69a 100644 --- a/include/linux/mfd/intel-m10-bmc.h +++ b/include/linux/mfd/intel-m10-bmc.h @@ -174,4 +174,10 @@ m10bmc_raw_read(struct intel_m10bmc *m10bmc, unsigned int addr, #define m10bmc_sys_read(m10bmc, offset, val) \ m10bmc_raw_read(m10bmc, M10BMC_SYS_BASE + (offset), val) +/* + * MAX10 BMC Core support + */ +int m10bmc_dev_init(struct intel_m10bmc *m10bmc, const struct intel_m10bmc_platform_info *info); +extern const struct attribute_group *m10bmc_dev_groups[]; + #endif /* __MFD_INTEL_M10_BMC_H */ -- cgit v1.2.3 From 6052a005caf9cd484fe6368a31c736ac17ebaf66 Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Mon, 16 Jan 2023 12:08:39 +0200 Subject: mfd: intel-m10-bmc: Support multiple CSR register layouts There are different addresses for the MAX10 CSR registers. Introducing a new data structure m10bmc_csr_map for the register definition of MAX10 CSR. Provide the csr_map for SPI. Co-developed-by: Tianfei zhang Signed-off-by: Tianfei zhang Reviewed-by: Russ Weight Reviewed-by: Xu Yilun Signed-off-by: Ilpo Järvinen Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230116100845.6153-6-ilpo.jarvinen@linux.intel.com --- drivers/fpga/intel-m10-bmc-sec-update.c | 73 ++++++++++++++++++++++----------- drivers/mfd/intel-m10-bmc-core.c | 10 ++--- drivers/mfd/intel-m10-bmc-spi.c | 23 +++++++++++ include/linux/mfd/intel-m10-bmc.h | 38 +++++++++++++++-- 4 files changed, 111 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/drivers/fpga/intel-m10-bmc-sec-update.c b/drivers/fpga/intel-m10-bmc-sec-update.c index 79d48852825e..dbe8aff95da3 100644 --- a/drivers/fpga/intel-m10-bmc-sec-update.c +++ b/drivers/fpga/intel-m10-bmc-sec-update.c @@ -73,16 +73,24 @@ show_root_entry_hash(struct device *dev, u32 exp_magic, return cnt; } -#define DEVICE_ATTR_SEC_REH_RO(_name, _magic, _prog_addr, _reh_addr) \ +#define DEVICE_ATTR_SEC_REH_RO(_name) \ static ssize_t _name##_root_entry_hash_show(struct device *dev, \ struct device_attribute *attr, \ char *buf) \ -{ return show_root_entry_hash(dev, _magic, _prog_addr, _reh_addr, buf); } \ +{ \ + struct m10bmc_sec *sec = dev_get_drvdata(dev); \ + const struct m10bmc_csr_map *csr_map = sec->m10bmc->info->csr_map; \ + \ + return show_root_entry_hash(dev, csr_map->_name##_magic, \ + csr_map->_name##_prog_addr, \ + csr_map->_name##_reh_addr, \ + buf); \ +} \ static DEVICE_ATTR_RO(_name##_root_entry_hash) -DEVICE_ATTR_SEC_REH_RO(bmc, BMC_PROG_MAGIC, BMC_PROG_ADDR, BMC_REH_ADDR); -DEVICE_ATTR_SEC_REH_RO(sr, SR_PROG_MAGIC, SR_PROG_ADDR, SR_REH_ADDR); -DEVICE_ATTR_SEC_REH_RO(pr, PR_PROG_MAGIC, PR_PROG_ADDR, PR_REH_ADDR); +DEVICE_ATTR_SEC_REH_RO(bmc); +DEVICE_ATTR_SEC_REH_RO(sr); +DEVICE_ATTR_SEC_REH_RO(pr); #define CSK_BIT_LEN 128U #define CSK_32ARRAY_SIZE DIV_ROUND_UP(CSK_BIT_LEN, 32) @@ -122,18 +130,25 @@ show_canceled_csk(struct device *dev, u32 addr, char *buf) return bitmap_print_to_pagebuf(1, buf, csk_map, CSK_BIT_LEN); } -#define DEVICE_ATTR_SEC_CSK_RO(_name, _addr) \ +#define DEVICE_ATTR_SEC_CSK_RO(_name) \ static ssize_t _name##_canceled_csks_show(struct device *dev, \ struct device_attribute *attr, \ char *buf) \ -{ return show_canceled_csk(dev, _addr, buf); } \ +{ \ + struct m10bmc_sec *sec = dev_get_drvdata(dev); \ + const struct m10bmc_csr_map *csr_map = sec->m10bmc->info->csr_map; \ + \ + return show_canceled_csk(dev, \ + csr_map->_name##_prog_addr + CSK_VEC_OFFSET, \ + buf); \ +} \ static DEVICE_ATTR_RO(_name##_canceled_csks) #define CSK_VEC_OFFSET 0x34 -DEVICE_ATTR_SEC_CSK_RO(bmc, BMC_PROG_ADDR + CSK_VEC_OFFSET); -DEVICE_ATTR_SEC_CSK_RO(sr, SR_PROG_ADDR + CSK_VEC_OFFSET); -DEVICE_ATTR_SEC_CSK_RO(pr, PR_PROG_ADDR + CSK_VEC_OFFSET); +DEVICE_ATTR_SEC_CSK_RO(bmc); +DEVICE_ATTR_SEC_CSK_RO(sr); +DEVICE_ATTR_SEC_CSK_RO(pr); #define FLASH_COUNT_SIZE 4096 /* count stored as inverted bit vector */ @@ -141,6 +156,7 @@ static ssize_t flash_count_show(struct device *dev, struct device_attribute *attr, char *buf) { struct m10bmc_sec *sec = dev_get_drvdata(dev); + const struct m10bmc_csr_map *csr_map = sec->m10bmc->info->csr_map; unsigned int stride, num_bits; u8 *flash_buf; int cnt, ret; @@ -160,12 +176,12 @@ static ssize_t flash_count_show(struct device *dev, if (!flash_buf) return -ENOMEM; - ret = regmap_bulk_read(sec->m10bmc->regmap, STAGING_FLASH_COUNT, + ret = regmap_bulk_read(sec->m10bmc->regmap, csr_map->rsu_update_counter, flash_buf, FLASH_COUNT_SIZE / stride); if (ret) { dev_err(sec->dev, "failed to read flash count: %x cnt %x: %d\n", - STAGING_FLASH_COUNT, FLASH_COUNT_SIZE / stride, ret); + csr_map->rsu_update_counter, FLASH_COUNT_SIZE / stride, ret); goto exit_free; } cnt = num_bits - bitmap_weight((unsigned long *)flash_buf, num_bits); @@ -200,20 +216,22 @@ static const struct attribute_group *m10bmc_sec_attr_groups[] = { static void log_error_regs(struct m10bmc_sec *sec, u32 doorbell) { + const struct m10bmc_csr_map *csr_map = sec->m10bmc->info->csr_map; u32 auth_result; dev_err(sec->dev, "RSU error status: 0x%08x\n", doorbell); - if (!m10bmc_sys_read(sec->m10bmc, M10BMC_AUTH_RESULT, &auth_result)) + if (!m10bmc_sys_read(sec->m10bmc, csr_map->auth_result, &auth_result)) dev_err(sec->dev, "RSU auth result: 0x%08x\n", auth_result); } static enum fw_upload_err rsu_check_idle(struct m10bmc_sec *sec) { + const struct m10bmc_csr_map *csr_map = sec->m10bmc->info->csr_map; u32 doorbell; int ret; - ret = m10bmc_sys_read(sec->m10bmc, M10BMC_DOORBELL, &doorbell); + ret = m10bmc_sys_read(sec->m10bmc, csr_map->doorbell, &doorbell); if (ret) return FW_UPLOAD_ERR_RW_ERROR; @@ -246,11 +264,12 @@ static inline bool rsu_start_done(u32 doorbell) static enum fw_upload_err rsu_update_init(struct m10bmc_sec *sec) { + const struct m10bmc_csr_map *csr_map = sec->m10bmc->info->csr_map; u32 doorbell, status; int ret; ret = regmap_update_bits(sec->m10bmc->regmap, - M10BMC_SYS_BASE + M10BMC_DOORBELL, + csr_map->base + csr_map->doorbell, DRBL_RSU_REQUEST | DRBL_HOST_STATUS, DRBL_RSU_REQUEST | FIELD_PREP(DRBL_HOST_STATUS, @@ -259,7 +278,7 @@ static enum fw_upload_err rsu_update_init(struct m10bmc_sec *sec) return FW_UPLOAD_ERR_RW_ERROR; ret = regmap_read_poll_timeout(sec->m10bmc->regmap, - M10BMC_SYS_BASE + M10BMC_DOORBELL, + csr_map->base + csr_map->doorbell, doorbell, rsu_start_done(doorbell), NIOS_HANDSHAKE_INTERVAL_US, @@ -286,11 +305,12 @@ static enum fw_upload_err rsu_update_init(struct m10bmc_sec *sec) static enum fw_upload_err rsu_prog_ready(struct m10bmc_sec *sec) { + const struct m10bmc_csr_map *csr_map = sec->m10bmc->info->csr_map; unsigned long poll_timeout; u32 doorbell, progress; int ret; - ret = m10bmc_sys_read(sec->m10bmc, M10BMC_DOORBELL, &doorbell); + ret = m10bmc_sys_read(sec->m10bmc, csr_map->doorbell, &doorbell); if (ret) return FW_UPLOAD_ERR_RW_ERROR; @@ -300,7 +320,7 @@ static enum fw_upload_err rsu_prog_ready(struct m10bmc_sec *sec) if (time_after(jiffies, poll_timeout)) break; - ret = m10bmc_sys_read(sec->m10bmc, M10BMC_DOORBELL, &doorbell); + ret = m10bmc_sys_read(sec->m10bmc, csr_map->doorbell, &doorbell); if (ret) return FW_UPLOAD_ERR_RW_ERROR; } @@ -319,11 +339,12 @@ static enum fw_upload_err rsu_prog_ready(struct m10bmc_sec *sec) static enum fw_upload_err rsu_send_data(struct m10bmc_sec *sec) { + const struct m10bmc_csr_map *csr_map = sec->m10bmc->info->csr_map; u32 doorbell; int ret; ret = regmap_update_bits(sec->m10bmc->regmap, - M10BMC_SYS_BASE + M10BMC_DOORBELL, + csr_map->base + csr_map->doorbell, DRBL_HOST_STATUS, FIELD_PREP(DRBL_HOST_STATUS, HOST_STATUS_WRITE_DONE)); @@ -331,7 +352,7 @@ static enum fw_upload_err rsu_send_data(struct m10bmc_sec *sec) return FW_UPLOAD_ERR_RW_ERROR; ret = regmap_read_poll_timeout(sec->m10bmc->regmap, - M10BMC_SYS_BASE + M10BMC_DOORBELL, + csr_map->base + csr_map->doorbell, doorbell, rsu_prog(doorbell) != RSU_PROG_READY, NIOS_HANDSHAKE_INTERVAL_US, @@ -360,7 +381,9 @@ static enum fw_upload_err rsu_send_data(struct m10bmc_sec *sec) static int rsu_check_complete(struct m10bmc_sec *sec, u32 *doorbell) { - if (m10bmc_sys_read(sec->m10bmc, M10BMC_DOORBELL, doorbell)) + const struct m10bmc_csr_map *csr_map = sec->m10bmc->info->csr_map; + + if (m10bmc_sys_read(sec->m10bmc, csr_map->doorbell, doorbell)) return -EIO; switch (rsu_stat(*doorbell)) { @@ -389,10 +412,11 @@ static int rsu_check_complete(struct m10bmc_sec *sec, u32 *doorbell) static enum fw_upload_err rsu_cancel(struct m10bmc_sec *sec) { + const struct m10bmc_csr_map *csr_map = sec->m10bmc->info->csr_map; u32 doorbell; int ret; - ret = m10bmc_sys_read(sec->m10bmc, M10BMC_DOORBELL, &doorbell); + ret = m10bmc_sys_read(sec->m10bmc, csr_map->doorbell, &doorbell); if (ret) return FW_UPLOAD_ERR_RW_ERROR; @@ -400,7 +424,7 @@ static enum fw_upload_err rsu_cancel(struct m10bmc_sec *sec) return FW_UPLOAD_ERR_BUSY; ret = regmap_update_bits(sec->m10bmc->regmap, - M10BMC_SYS_BASE + M10BMC_DOORBELL, + csr_map->base + csr_map->doorbell, DRBL_HOST_STATUS, FIELD_PREP(DRBL_HOST_STATUS, HOST_STATUS_ABORT_RSU)); @@ -445,6 +469,7 @@ static enum fw_upload_err m10bmc_sec_write(struct fw_upload *fwl, const u8 *data u32 offset, u32 size, u32 *written) { struct m10bmc_sec *sec = fwl->dd_handle; + const struct m10bmc_csr_map *csr_map = sec->m10bmc->info->csr_map; u32 blk_size, doorbell, extra_offset; unsigned int stride, extra = 0; int ret; @@ -453,7 +478,7 @@ static enum fw_upload_err m10bmc_sec_write(struct fw_upload *fwl, const u8 *data if (sec->cancel_request) return rsu_cancel(sec); - ret = m10bmc_sys_read(sec->m10bmc, M10BMC_DOORBELL, &doorbell); + ret = m10bmc_sys_read(sec->m10bmc, csr_map->doorbell, &doorbell); if (ret) { return FW_UPLOAD_ERR_RW_ERROR; } else if (rsu_prog(doorbell) != RSU_PROG_READY) { diff --git a/drivers/mfd/intel-m10-bmc-core.c b/drivers/mfd/intel-m10-bmc-core.c index dd26e3a6c3ab..cbea8d4f68fa 100644 --- a/drivers/mfd/intel-m10-bmc-core.c +++ b/drivers/mfd/intel-m10-bmc-core.c @@ -19,7 +19,7 @@ static ssize_t bmc_version_show(struct device *dev, unsigned int val; int ret; - ret = m10bmc_sys_read(ddata, M10BMC_BUILD_VER, &val); + ret = m10bmc_sys_read(ddata, ddata->info->csr_map->build_version, &val); if (ret) return ret; @@ -34,7 +34,7 @@ static ssize_t bmcfw_version_show(struct device *dev, unsigned int val; int ret; - ret = m10bmc_sys_read(ddata, NIOS2_FW_VERSION, &val); + ret = m10bmc_sys_read(ddata, ddata->info->csr_map->fw_version, &val); if (ret) return ret; @@ -49,11 +49,11 @@ static ssize_t mac_address_show(struct device *dev, unsigned int macaddr_low, macaddr_high; int ret; - ret = m10bmc_sys_read(ddata, M10BMC_MAC_LOW, &macaddr_low); + ret = m10bmc_sys_read(ddata, ddata->info->csr_map->mac_low, &macaddr_low); if (ret) return ret; - ret = m10bmc_sys_read(ddata, M10BMC_MAC_HIGH, &macaddr_high); + ret = m10bmc_sys_read(ddata, ddata->info->csr_map->mac_high, &macaddr_high); if (ret) return ret; @@ -74,7 +74,7 @@ static ssize_t mac_count_show(struct device *dev, unsigned int macaddr_high; int ret; - ret = m10bmc_sys_read(ddata, M10BMC_MAC_HIGH, &macaddr_high); + ret = m10bmc_sys_read(ddata, ddata->info->csr_map->mac_high, &macaddr_high); if (ret) return ret; diff --git a/drivers/mfd/intel-m10-bmc-spi.c b/drivers/mfd/intel-m10-bmc-spi.c index be1d4ddedabb..3ed7a71a3267 100644 --- a/drivers/mfd/intel-m10-bmc-spi.c +++ b/drivers/mfd/intel-m10-bmc-spi.c @@ -91,6 +91,26 @@ static int intel_m10_bmc_spi_probe(struct spi_device *spi) return m10bmc_dev_init(ddata, info); } +static const struct m10bmc_csr_map m10bmc_n3000_csr_map = { + .base = M10BMC_SYS_BASE, + .build_version = M10BMC_BUILD_VER, + .fw_version = NIOS2_FW_VERSION, + .mac_low = M10BMC_MAC_LOW, + .mac_high = M10BMC_MAC_HIGH, + .doorbell = M10BMC_DOORBELL, + .auth_result = M10BMC_AUTH_RESULT, + .bmc_prog_addr = BMC_PROG_ADDR, + .bmc_reh_addr = BMC_REH_ADDR, + .bmc_magic = BMC_PROG_MAGIC, + .sr_prog_addr = SR_PROG_ADDR, + .sr_reh_addr = SR_REH_ADDR, + .sr_magic = SR_PROG_MAGIC, + .pr_prog_addr = PR_PROG_ADDR, + .pr_reh_addr = PR_REH_ADDR, + .pr_magic = PR_PROG_MAGIC, + .rsu_update_counter = STAGING_FLASH_COUNT, +}; + static struct mfd_cell m10bmc_d5005_subdevs[] = { { .name = "d5005bmc-hwmon" }, { .name = "d5005bmc-sec-update" }, @@ -109,16 +129,19 @@ static struct mfd_cell m10bmc_n5010_subdevs[] = { static const struct intel_m10bmc_platform_info m10bmc_spi_n3000 = { .cells = m10bmc_pacn3000_subdevs, .n_cells = ARRAY_SIZE(m10bmc_pacn3000_subdevs), + .csr_map = &m10bmc_n3000_csr_map, }; static const struct intel_m10bmc_platform_info m10bmc_spi_d5005 = { .cells = m10bmc_d5005_subdevs, .n_cells = ARRAY_SIZE(m10bmc_d5005_subdevs), + .csr_map = &m10bmc_n3000_csr_map, }; static const struct intel_m10bmc_platform_info m10bmc_spi_n5010 = { .cells = m10bmc_n5010_subdevs, .n_cells = ARRAY_SIZE(m10bmc_n5010_subdevs), + .csr_map = &m10bmc_n3000_csr_map, }; static const struct spi_device_id m10bmc_spi_id[] = { diff --git a/include/linux/mfd/intel-m10-bmc.h b/include/linux/mfd/intel-m10-bmc.h index a80deb61b69a..d569a72c7d4f 100644 --- a/include/linux/mfd/intel-m10-bmc.h +++ b/include/linux/mfd/intel-m10-bmc.h @@ -121,14 +121,39 @@ /* Address of 4KB inverted bit vector containing staging area FLASH count */ #define STAGING_FLASH_COUNT 0x17ffb000 +/** + * struct m10bmc_csr_map - Intel MAX 10 BMC CSR register map + */ +struct m10bmc_csr_map { + unsigned int base; + unsigned int build_version; + unsigned int fw_version; + unsigned int mac_low; + unsigned int mac_high; + unsigned int doorbell; + unsigned int auth_result; + unsigned int bmc_prog_addr; + unsigned int bmc_reh_addr; + unsigned int bmc_magic; + unsigned int sr_prog_addr; + unsigned int sr_reh_addr; + unsigned int sr_magic; + unsigned int pr_prog_addr; + unsigned int pr_reh_addr; + unsigned int pr_magic; + unsigned int rsu_update_counter; +}; + /** * struct intel_m10bmc_platform_info - Intel MAX 10 BMC platform specific information * @cells: MFD cells * @n_cells: MFD cells ARRAY_SIZE() + * @csr_map: the mappings for register definition of MAX10 BMC */ struct intel_m10bmc_platform_info { struct mfd_cell *cells; int n_cells; + const struct m10bmc_csr_map *csr_map; }; /** @@ -167,12 +192,17 @@ m10bmc_raw_read(struct intel_m10bmc *m10bmc, unsigned int addr, * The base of the system registers could be configured by HW developers, and * in HW SPEC, the base is not added to the addresses of the system registers. * - * This macro helps to simplify the accessing of the system registers. And if + * This function helps to simplify the accessing of the system registers. And if * the base is reconfigured in HW, SW developers could simply change the - * M10BMC_SYS_BASE accordingly. + * csr_map's base accordingly. */ -#define m10bmc_sys_read(m10bmc, offset, val) \ - m10bmc_raw_read(m10bmc, M10BMC_SYS_BASE + (offset), val) +static inline int m10bmc_sys_read(struct intel_m10bmc *m10bmc, unsigned int offset, + unsigned int *val) +{ + const struct m10bmc_csr_map *csr_map = m10bmc->info->csr_map; + + return m10bmc_raw_read(m10bmc, csr_map->base + offset, val); +} /* * MAX10 BMC Core support -- cgit v1.2.3 From bcababfc60ccc622268b2317a22fabd879fbc0a3 Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Mon, 16 Jan 2023 12:08:41 +0200 Subject: mfd: intel-m10-bmc: Prefix register defines with M10BMC_N3000 Prefix the M10BMC defines register defines with M10BMC_N3000 to make it more obvious these are related to some board type. All current non-N3000 board types have the same layout so they'll be reused. The less generic makes it more obvious they're not meant for the generic/interface agnostic code. Reviewed-by: Russ Weight Reviewed-by: Xu Yilun Signed-off-by: Ilpo Järvinen Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230116100845.6153-8-ilpo.jarvinen@linux.intel.com --- drivers/mfd/intel-m10-bmc-core.c | 14 ++++----- drivers/mfd/intel-m10-bmc-spi.c | 52 +++++++++++++++--------------- include/linux/mfd/intel-m10-bmc.h | 66 +++++++++++++++++++-------------------- 3 files changed, 66 insertions(+), 66 deletions(-) (limited to 'include/linux') diff --git a/drivers/mfd/intel-m10-bmc-core.c b/drivers/mfd/intel-m10-bmc-core.c index cbea8d4f68fa..dac9cf7bcb4a 100644 --- a/drivers/mfd/intel-m10-bmc-core.c +++ b/drivers/mfd/intel-m10-bmc-core.c @@ -58,12 +58,12 @@ static ssize_t mac_address_show(struct device *dev, return ret; return sysfs_emit(buf, "%02x:%02x:%02x:%02x:%02x:%02x\n", - (u8)FIELD_GET(M10BMC_MAC_BYTE1, macaddr_low), - (u8)FIELD_GET(M10BMC_MAC_BYTE2, macaddr_low), - (u8)FIELD_GET(M10BMC_MAC_BYTE3, macaddr_low), - (u8)FIELD_GET(M10BMC_MAC_BYTE4, macaddr_low), - (u8)FIELD_GET(M10BMC_MAC_BYTE5, macaddr_high), - (u8)FIELD_GET(M10BMC_MAC_BYTE6, macaddr_high)); + (u8)FIELD_GET(M10BMC_N3000_MAC_BYTE1, macaddr_low), + (u8)FIELD_GET(M10BMC_N3000_MAC_BYTE2, macaddr_low), + (u8)FIELD_GET(M10BMC_N3000_MAC_BYTE3, macaddr_low), + (u8)FIELD_GET(M10BMC_N3000_MAC_BYTE4, macaddr_low), + (u8)FIELD_GET(M10BMC_N3000_MAC_BYTE5, macaddr_high), + (u8)FIELD_GET(M10BMC_N3000_MAC_BYTE6, macaddr_high)); } static DEVICE_ATTR_RO(mac_address); @@ -78,7 +78,7 @@ static ssize_t mac_count_show(struct device *dev, if (ret) return ret; - return sysfs_emit(buf, "%u\n", (u8)FIELD_GET(M10BMC_MAC_COUNT, macaddr_high)); + return sysfs_emit(buf, "%u\n", (u8)FIELD_GET(M10BMC_N3000_MAC_COUNT, macaddr_high)); } static DEVICE_ATTR_RO(mac_count); diff --git a/drivers/mfd/intel-m10-bmc-spi.c b/drivers/mfd/intel-m10-bmc-spi.c index 3ed7a71a3267..957200e17fed 100644 --- a/drivers/mfd/intel-m10-bmc-spi.c +++ b/drivers/mfd/intel-m10-bmc-spi.c @@ -14,9 +14,9 @@ #include static const struct regmap_range m10bmc_regmap_range[] = { - regmap_reg_range(M10BMC_LEGACY_BUILD_VER, M10BMC_LEGACY_BUILD_VER), - regmap_reg_range(M10BMC_SYS_BASE, M10BMC_SYS_END), - regmap_reg_range(M10BMC_FLASH_BASE, M10BMC_FLASH_END), + regmap_reg_range(M10BMC_N3000_LEGACY_BUILD_VER, M10BMC_N3000_LEGACY_BUILD_VER), + regmap_reg_range(M10BMC_N3000_SYS_BASE, M10BMC_N3000_SYS_END), + regmap_reg_range(M10BMC_N3000_FLASH_BASE, M10BMC_N3000_FLASH_END), }; static const struct regmap_access_table m10bmc_access_table = { @@ -30,7 +30,7 @@ static struct regmap_config intel_m10bmc_regmap_config = { .reg_stride = 4, .wr_table = &m10bmc_access_table, .rd_table = &m10bmc_access_table, - .max_register = M10BMC_MEM_END, + .max_register = M10BMC_N3000_MEM_END, }; static int check_m10bmc_version(struct intel_m10bmc *ddata) @@ -41,16 +41,16 @@ static int check_m10bmc_version(struct intel_m10bmc *ddata) /* * This check is to filter out the very old legacy BMC versions. In the * old BMC chips, the BMC version info is stored in the old version - * register (M10BMC_LEGACY_BUILD_VER), so its read out value would have - * not been M10BMC_VER_LEGACY_INVALID (0xffffffff). But in new BMC + * register (M10BMC_N3000_LEGACY_BUILD_VER), so its read out value would have + * not been M10BMC_N3000_VER_LEGACY_INVALID (0xffffffff). But in new BMC * chips that the driver supports, the value of this register should be - * M10BMC_VER_LEGACY_INVALID. + * M10BMC_N3000_VER_LEGACY_INVALID. */ - ret = m10bmc_raw_read(ddata, M10BMC_LEGACY_BUILD_VER, &v); + ret = m10bmc_raw_read(ddata, M10BMC_N3000_LEGACY_BUILD_VER, &v); if (ret) return -ENODEV; - if (v != M10BMC_VER_LEGACY_INVALID) { + if (v != M10BMC_N3000_VER_LEGACY_INVALID) { dev_err(ddata->dev, "bad version M10BMC detected\n"); return -ENODEV; } @@ -92,23 +92,23 @@ static int intel_m10_bmc_spi_probe(struct spi_device *spi) } static const struct m10bmc_csr_map m10bmc_n3000_csr_map = { - .base = M10BMC_SYS_BASE, - .build_version = M10BMC_BUILD_VER, - .fw_version = NIOS2_FW_VERSION, - .mac_low = M10BMC_MAC_LOW, - .mac_high = M10BMC_MAC_HIGH, - .doorbell = M10BMC_DOORBELL, - .auth_result = M10BMC_AUTH_RESULT, - .bmc_prog_addr = BMC_PROG_ADDR, - .bmc_reh_addr = BMC_REH_ADDR, - .bmc_magic = BMC_PROG_MAGIC, - .sr_prog_addr = SR_PROG_ADDR, - .sr_reh_addr = SR_REH_ADDR, - .sr_magic = SR_PROG_MAGIC, - .pr_prog_addr = PR_PROG_ADDR, - .pr_reh_addr = PR_REH_ADDR, - .pr_magic = PR_PROG_MAGIC, - .rsu_update_counter = STAGING_FLASH_COUNT, + .base = M10BMC_N3000_SYS_BASE, + .build_version = M10BMC_N3000_BUILD_VER, + .fw_version = NIOS2_N3000_FW_VERSION, + .mac_low = M10BMC_N3000_MAC_LOW, + .mac_high = M10BMC_N3000_MAC_HIGH, + .doorbell = M10BMC_N3000_DOORBELL, + .auth_result = M10BMC_N3000_AUTH_RESULT, + .bmc_prog_addr = M10BMC_N3000_BMC_PROG_ADDR, + .bmc_reh_addr = M10BMC_N3000_BMC_REH_ADDR, + .bmc_magic = M10BMC_N3000_BMC_PROG_MAGIC, + .sr_prog_addr = M10BMC_N3000_SR_PROG_ADDR, + .sr_reh_addr = M10BMC_N3000_SR_REH_ADDR, + .sr_magic = M10BMC_N3000_SR_PROG_MAGIC, + .pr_prog_addr = M10BMC_N3000_PR_PROG_ADDR, + .pr_reh_addr = M10BMC_N3000_PR_REH_ADDR, + .pr_magic = M10BMC_N3000_PR_PROG_MAGIC, + .rsu_update_counter = M10BMC_N3000_STAGING_FLASH_COUNT, }; static struct mfd_cell m10bmc_d5005_subdevs[] = { diff --git a/include/linux/mfd/intel-m10-bmc.h b/include/linux/mfd/intel-m10-bmc.h index d569a72c7d4f..470dc3773c01 100644 --- a/include/linux/mfd/intel-m10-bmc.h +++ b/include/linux/mfd/intel-m10-bmc.h @@ -12,38 +12,38 @@ #include #include -#define M10BMC_LEGACY_BUILD_VER 0x300468 -#define M10BMC_SYS_BASE 0x300800 -#define M10BMC_SYS_END 0x300fff -#define M10BMC_FLASH_BASE 0x10000000 -#define M10BMC_FLASH_END 0x1fffffff -#define M10BMC_MEM_END M10BMC_FLASH_END +#define M10BMC_N3000_LEGACY_BUILD_VER 0x300468 +#define M10BMC_N3000_SYS_BASE 0x300800 +#define M10BMC_N3000_SYS_END 0x300fff +#define M10BMC_N3000_FLASH_BASE 0x10000000 +#define M10BMC_N3000_FLASH_END 0x1fffffff +#define M10BMC_N3000_MEM_END M10BMC_N3000_FLASH_END #define M10BMC_STAGING_BASE 0x18000000 #define M10BMC_STAGING_SIZE 0x3800000 /* Register offset of system registers */ -#define NIOS2_FW_VERSION 0x0 -#define M10BMC_MAC_LOW 0x10 -#define M10BMC_MAC_BYTE4 GENMASK(7, 0) -#define M10BMC_MAC_BYTE3 GENMASK(15, 8) -#define M10BMC_MAC_BYTE2 GENMASK(23, 16) -#define M10BMC_MAC_BYTE1 GENMASK(31, 24) -#define M10BMC_MAC_HIGH 0x14 -#define M10BMC_MAC_BYTE6 GENMASK(7, 0) -#define M10BMC_MAC_BYTE5 GENMASK(15, 8) -#define M10BMC_MAC_COUNT GENMASK(23, 16) -#define M10BMC_TEST_REG 0x3c -#define M10BMC_BUILD_VER 0x68 -#define M10BMC_VER_MAJOR_MSK GENMASK(23, 16) -#define M10BMC_VER_PCB_INFO_MSK GENMASK(31, 24) -#define M10BMC_VER_LEGACY_INVALID 0xffffffff +#define NIOS2_N3000_FW_VERSION 0x0 +#define M10BMC_N3000_MAC_LOW 0x10 +#define M10BMC_N3000_MAC_BYTE4 GENMASK(7, 0) +#define M10BMC_N3000_MAC_BYTE3 GENMASK(15, 8) +#define M10BMC_N3000_MAC_BYTE2 GENMASK(23, 16) +#define M10BMC_N3000_MAC_BYTE1 GENMASK(31, 24) +#define M10BMC_N3000_MAC_HIGH 0x14 +#define M10BMC_N3000_MAC_BYTE6 GENMASK(7, 0) +#define M10BMC_N3000_MAC_BYTE5 GENMASK(15, 8) +#define M10BMC_N3000_MAC_COUNT GENMASK(23, 16) +#define M10BMC_N3000_TEST_REG 0x3c +#define M10BMC_N3000_BUILD_VER 0x68 +#define M10BMC_N3000_VER_MAJOR_MSK GENMASK(23, 16) +#define M10BMC_N3000_VER_PCB_INFO_MSK GENMASK(31, 24) +#define M10BMC_N3000_VER_LEGACY_INVALID 0xffffffff /* Secure update doorbell register, in system register region */ -#define M10BMC_DOORBELL 0x400 +#define M10BMC_N3000_DOORBELL 0x400 /* Authorization Result register, in system register region */ -#define M10BMC_AUTH_RESULT 0x404 +#define M10BMC_N3000_AUTH_RESULT 0x404 /* Doorbell register fields */ #define DRBL_RSU_REQUEST BIT(0) @@ -106,20 +106,20 @@ #define RSU_COMPLETE_TIMEOUT_MS (40 * 60 * 1000) /* Addresses for security related data in FLASH */ -#define BMC_REH_ADDR 0x17ffc004 -#define BMC_PROG_ADDR 0x17ffc000 -#define BMC_PROG_MAGIC 0x5746 +#define M10BMC_N3000_BMC_REH_ADDR 0x17ffc004 +#define M10BMC_N3000_BMC_PROG_ADDR 0x17ffc000 +#define M10BMC_N3000_BMC_PROG_MAGIC 0x5746 -#define SR_REH_ADDR 0x17ffd004 -#define SR_PROG_ADDR 0x17ffd000 -#define SR_PROG_MAGIC 0x5253 +#define M10BMC_N3000_SR_REH_ADDR 0x17ffd004 +#define M10BMC_N3000_SR_PROG_ADDR 0x17ffd000 +#define M10BMC_N3000_SR_PROG_MAGIC 0x5253 -#define PR_REH_ADDR 0x17ffe004 -#define PR_PROG_ADDR 0x17ffe000 -#define PR_PROG_MAGIC 0x5250 +#define M10BMC_N3000_PR_REH_ADDR 0x17ffe004 +#define M10BMC_N3000_PR_PROG_ADDR 0x17ffe000 +#define M10BMC_N3000_PR_PROG_MAGIC 0x5250 /* Address of 4KB inverted bit vector containing staging area FLASH count */ -#define STAGING_FLASH_COUNT 0x17ffb000 +#define M10BMC_N3000_STAGING_FLASH_COUNT 0x17ffb000 /** * struct m10bmc_csr_map - Intel MAX 10 BMC CSR register map -- cgit v1.2.3 From 001a734a55d09aa1716eb2cd5ccab8b4d7a068a2 Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Mon, 16 Jan 2023 12:08:43 +0200 Subject: fpga: m10bmc-sec: Make rsu status type specific The rsu status field moves from the doorbell register to the auth result register in the PMCI implementation of the MAX10 BMC. In order to prepare for that, refactor the sec update driver code to have a type specific ops that provides ->rsu_status(). Co-developed-by: Tianfei zhang Signed-off-by: Tianfei zhang Co-developed-by: Russ Weight Signed-off-by: Russ Weight Signed-off-by: Ilpo Järvinen Acked-by: Xu Yilun Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230116100845.6153-10-ilpo.jarvinen@linux.intel.com --- drivers/fpga/intel-m10-bmc-sec-update.c | 109 +++++++++++++++++++++++--------- include/linux/mfd/intel-m10-bmc.h | 1 - 2 files changed, 78 insertions(+), 32 deletions(-) (limited to 'include/linux') diff --git a/drivers/fpga/intel-m10-bmc-sec-update.c b/drivers/fpga/intel-m10-bmc-sec-update.c index 43d9598d6077..92145ee7333e 100644 --- a/drivers/fpga/intel-m10-bmc-sec-update.c +++ b/drivers/fpga/intel-m10-bmc-sec-update.c @@ -14,6 +14,12 @@ #include #include +struct m10bmc_sec; + +struct m10bmc_sec_ops { + int (*rsu_status)(struct m10bmc_sec *sec); +}; + struct m10bmc_sec { struct device *dev; struct intel_m10bmc *m10bmc; @@ -21,6 +27,7 @@ struct m10bmc_sec { char *fw_name; u32 fw_name_id; bool cancel_request; + const struct m10bmc_sec_ops *ops; }; static DEFINE_XARRAY_ALLOC(fw_upload_xa); @@ -251,12 +258,25 @@ static void log_error_regs(struct m10bmc_sec *sec, u32 doorbell) const struct m10bmc_csr_map *csr_map = sec->m10bmc->info->csr_map; u32 auth_result; - dev_err(sec->dev, "RSU error status: 0x%08x\n", doorbell); + dev_err(sec->dev, "Doorbell: 0x%08x\n", doorbell); if (!m10bmc_sys_read(sec->m10bmc, csr_map->auth_result, &auth_result)) dev_err(sec->dev, "RSU auth result: 0x%08x\n", auth_result); } +static int m10bmc_sec_n3000_rsu_status(struct m10bmc_sec *sec) +{ + const struct m10bmc_csr_map *csr_map = sec->m10bmc->info->csr_map; + u32 doorbell; + int ret; + + ret = m10bmc_sys_read(sec->m10bmc, csr_map->doorbell, &doorbell); + if (ret) + return ret; + + return FIELD_GET(DRBL_RSU_STATUS, doorbell); +} + static bool rsu_status_ok(u32 status) { return (status == RSU_STAT_NORMAL || @@ -279,6 +299,26 @@ static bool rsu_progress_busy(u32 progress) progress == RSU_PROG_PROGRAM_KEY_HASH); } +static int m10bmc_sec_progress_status(struct m10bmc_sec *sec, u32 *doorbell_reg, + u32 *progress, u32 *status) +{ + const struct m10bmc_csr_map *csr_map = sec->m10bmc->info->csr_map; + int ret; + + ret = m10bmc_sys_read(sec->m10bmc, csr_map->doorbell, doorbell_reg); + if (ret) + return ret; + + ret = sec->ops->rsu_status(sec); + if (ret < 0) + return ret; + + *status = ret; + *progress = rsu_prog(*doorbell_reg); + + return 0; +} + static enum fw_upload_err rsu_check_idle(struct m10bmc_sec *sec) { const struct m10bmc_csr_map *csr_map = sec->m10bmc->info->csr_map; @@ -297,18 +337,14 @@ static enum fw_upload_err rsu_check_idle(struct m10bmc_sec *sec) return FW_UPLOAD_ERR_NONE; } -static inline bool rsu_start_done(u32 doorbell) +static inline bool rsu_start_done(u32 doorbell_reg, u32 progress, u32 status) { - u32 status, progress; - - if (doorbell & DRBL_RSU_REQUEST) + if (doorbell_reg & DRBL_RSU_REQUEST) return false; - status = rsu_stat(doorbell); if (status == RSU_STAT_ERASE_FAIL || status == RSU_STAT_WEAROUT) return true; - progress = rsu_prog(doorbell); if (!rsu_progress_done(progress)) return true; @@ -318,8 +354,8 @@ static inline bool rsu_start_done(u32 doorbell) static enum fw_upload_err rsu_update_init(struct m10bmc_sec *sec) { const struct m10bmc_csr_map *csr_map = sec->m10bmc->info->csr_map; - u32 doorbell, status; - int ret; + u32 doorbell_reg, progress, status; + int ret, err; ret = regmap_update_bits(sec->m10bmc->regmap, csr_map->base + csr_map->doorbell, @@ -330,26 +366,25 @@ static enum fw_upload_err rsu_update_init(struct m10bmc_sec *sec) if (ret) return FW_UPLOAD_ERR_RW_ERROR; - ret = regmap_read_poll_timeout(sec->m10bmc->regmap, - csr_map->base + csr_map->doorbell, - doorbell, - rsu_start_done(doorbell), - NIOS_HANDSHAKE_INTERVAL_US, - NIOS_HANDSHAKE_TIMEOUT_US); + ret = read_poll_timeout(m10bmc_sec_progress_status, err, + err < 0 || rsu_start_done(doorbell_reg, progress, status), + NIOS_HANDSHAKE_INTERVAL_US, + NIOS_HANDSHAKE_TIMEOUT_US, + false, + sec, &doorbell_reg, &progress, &status); if (ret == -ETIMEDOUT) { - log_error_regs(sec, doorbell); + log_error_regs(sec, doorbell_reg); return FW_UPLOAD_ERR_TIMEOUT; - } else if (ret) { + } else if (err) { return FW_UPLOAD_ERR_RW_ERROR; } - status = rsu_stat(doorbell); if (status == RSU_STAT_WEAROUT) { dev_warn(sec->dev, "Excessive flash update count detected\n"); return FW_UPLOAD_ERR_WEAROUT; } else if (status == RSU_STAT_ERASE_FAIL) { - log_error_regs(sec, doorbell); + log_error_regs(sec, doorbell_reg); return FW_UPLOAD_ERR_HW_ERROR; } @@ -393,7 +428,7 @@ static enum fw_upload_err rsu_prog_ready(struct m10bmc_sec *sec) static enum fw_upload_err rsu_send_data(struct m10bmc_sec *sec) { const struct m10bmc_csr_map *csr_map = sec->m10bmc->info->csr_map; - u32 doorbell; + u32 doorbell_reg, status; int ret; ret = regmap_update_bits(sec->m10bmc->regmap, @@ -406,40 +441,45 @@ static enum fw_upload_err rsu_send_data(struct m10bmc_sec *sec) ret = regmap_read_poll_timeout(sec->m10bmc->regmap, csr_map->base + csr_map->doorbell, - doorbell, - rsu_prog(doorbell) != RSU_PROG_READY, + doorbell_reg, + rsu_prog(doorbell_reg) != RSU_PROG_READY, NIOS_HANDSHAKE_INTERVAL_US, NIOS_HANDSHAKE_TIMEOUT_US); if (ret == -ETIMEDOUT) { - log_error_regs(sec, doorbell); + log_error_regs(sec, doorbell_reg); return FW_UPLOAD_ERR_TIMEOUT; } else if (ret) { return FW_UPLOAD_ERR_RW_ERROR; } - if (!rsu_status_ok(rsu_stat(doorbell))) { - log_error_regs(sec, doorbell); + ret = sec->ops->rsu_status(sec); + if (ret < 0) + return ret; + status = ret; + + if (!rsu_status_ok(status)) { + log_error_regs(sec, doorbell_reg); return FW_UPLOAD_ERR_HW_ERROR; } return FW_UPLOAD_ERR_NONE; } -static int rsu_check_complete(struct m10bmc_sec *sec, u32 *doorbell) +static int rsu_check_complete(struct m10bmc_sec *sec, u32 *doorbell_reg) { - const struct m10bmc_csr_map *csr_map = sec->m10bmc->info->csr_map; + u32 progress, status; - if (m10bmc_sys_read(sec->m10bmc, csr_map->doorbell, doorbell)) + if (m10bmc_sec_progress_status(sec, doorbell_reg, &progress, &status)) return -EIO; - if (!rsu_status_ok(rsu_stat(*doorbell))) + if (!rsu_status_ok(status)) return -EINVAL; - if (rsu_progress_done(rsu_prog(*doorbell))) + if (rsu_progress_done(progress)) return 0; - if (rsu_progress_busy(rsu_prog(*doorbell))) + if (rsu_progress_busy(progress)) return -EAGAIN; return -EINVAL; @@ -592,6 +632,10 @@ static const struct fw_upload_ops m10bmc_ops = { .cleanup = m10bmc_sec_cleanup, }; +static const struct m10bmc_sec_ops m10sec_n3000_ops = { + .rsu_status = m10bmc_sec_n3000_rsu_status, +}; + #define SEC_UPDATE_LEN_MAX 32 static int m10bmc_sec_probe(struct platform_device *pdev) { @@ -607,6 +651,7 @@ static int m10bmc_sec_probe(struct platform_device *pdev) sec->dev = &pdev->dev; sec->m10bmc = dev_get_drvdata(pdev->dev.parent); + sec->ops = (struct m10bmc_sec_ops *)platform_get_device_id(pdev)->driver_data; dev_set_drvdata(&pdev->dev, sec); ret = xa_alloc(&fw_upload_xa, &sec->fw_name_id, sec, @@ -647,9 +692,11 @@ static int m10bmc_sec_remove(struct platform_device *pdev) static const struct platform_device_id intel_m10bmc_sec_ids[] = { { .name = "n3000bmc-sec-update", + .driver_data = (kernel_ulong_t)&m10sec_n3000_ops, }, { .name = "d5005bmc-sec-update", + .driver_data = (kernel_ulong_t)&m10sec_n3000_ops, }, { } }; diff --git a/include/linux/mfd/intel-m10-bmc.h b/include/linux/mfd/intel-m10-bmc.h index 470dc3773c01..1f75b33240ad 100644 --- a/include/linux/mfd/intel-m10-bmc.h +++ b/include/linux/mfd/intel-m10-bmc.h @@ -91,7 +91,6 @@ #define HOST_STATUS_ABORT_RSU 0x2 #define rsu_prog(doorbell) FIELD_GET(DRBL_RSU_PROGRESS, doorbell) -#define rsu_stat(doorbell) FIELD_GET(DRBL_RSU_STATUS, doorbell) /* interval 100ms and timeout 5s */ #define NIOS_HANDSHAKE_INTERVAL_US (100 * 1000) -- cgit v1.2.3 From 869b9eddf0b38a22c27a400e2fa849d2ff2aa7e1 Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Mon, 16 Jan 2023 12:08:44 +0200 Subject: mfd: intel-m10-bmc: Add PMCI driver Add the mfd driver for the Platform Management Component Interface (PMCI) based interface of Intel MAX10 BMC controller. PMCI is a software-visible interface, connected to card BMC which provided the basic functionality of read/write BMC register. The access to the register is done indirectly via a hardware controller/bridge that handles read/write/clear commands and acknowledgments for the commands. Previously, intel-m10-bmc provided sysfs under /sys/bus/spi/devices/... which is generalized in this change because not all MAX10 BMC appear under SPI anymore. Co-developed-by: Tianfei zhang Signed-off-by: Tianfei zhang Co-developed-by: Russ Weight Signed-off-by: Russ Weight Co-developed-by: Matthew Gerlach Signed-off-by: Matthew Gerlach Reviewed-by: Xu Yilun Signed-off-by: Ilpo Järvinen Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230116100845.6153-11-ilpo.jarvinen@linux.intel.com --- .../ABI/testing/sysfs-driver-intel-m10-bmc | 8 +- drivers/mfd/Kconfig | 12 ++ drivers/mfd/Makefile | 1 + drivers/mfd/intel-m10-bmc-pmci.c | 219 +++++++++++++++++++++ include/linux/mfd/intel-m10-bmc.h | 28 +++ 5 files changed, 264 insertions(+), 4 deletions(-) create mode 100644 drivers/mfd/intel-m10-bmc-pmci.c (limited to 'include/linux') diff --git a/Documentation/ABI/testing/sysfs-driver-intel-m10-bmc b/Documentation/ABI/testing/sysfs-driver-intel-m10-bmc index 9773925138af..a8ab58035c95 100644 --- a/Documentation/ABI/testing/sysfs-driver-intel-m10-bmc +++ b/Documentation/ABI/testing/sysfs-driver-intel-m10-bmc @@ -1,4 +1,4 @@ -What: /sys/bus/spi/devices/.../bmc_version +What: /sys/bus/.../drivers/intel-m10-bmc/.../bmc_version Date: June 2020 KernelVersion: 5.10 Contact: Xu Yilun @@ -6,7 +6,7 @@ Description: Read only. Returns the hardware build version of Intel MAX10 BMC chip. Format: "0x%x". -What: /sys/bus/spi/devices/.../bmcfw_version +What: /sys/bus/.../drivers/intel-m10-bmc/.../bmcfw_version Date: June 2020 KernelVersion: 5.10 Contact: Xu Yilun @@ -14,7 +14,7 @@ Description: Read only. Returns the firmware version of Intel MAX10 BMC chip. Format: "0x%x". -What: /sys/bus/spi/devices/.../mac_address +What: /sys/bus/.../drivers/intel-m10-bmc/.../mac_address Date: January 2021 KernelVersion: 5.12 Contact: Russ Weight @@ -25,7 +25,7 @@ Description: Read only. Returns the first MAC address in a block space. Format: "%02x:%02x:%02x:%02x:%02x:%02x". -What: /sys/bus/spi/devices/.../mac_count +What: /sys/bus/.../drivers/intel-m10-bmc/.../mac_count Date: January 2021 KernelVersion: 5.12 Contact: Russ Weight diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig index b6ab85831cde..2632ca2162de 100644 --- a/drivers/mfd/Kconfig +++ b/drivers/mfd/Kconfig @@ -2243,6 +2243,18 @@ config MFD_INTEL_M10_BMC_SPI additional drivers must be enabled in order to use the functionality of the device. +config MFD_INTEL_M10_BMC_PMCI + tristate "Intel MAX 10 Board Management Controller with PMCI" + depends on FPGA_DFL + select MFD_INTEL_M10_BMC_CORE + select REGMAP + help + Support for the Intel MAX 10 board management controller via PMCI. + + This driver provides common support for accessing the device, + additional drivers must be enabled in order to use the functionality + of the device. + config MFD_RSMU_I2C tristate "Renesas Synchronization Management Unit with I2C" depends on I2C && OF diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile index b360b29150b5..81c30d7cf5d4 100644 --- a/drivers/mfd/Makefile +++ b/drivers/mfd/Makefile @@ -272,6 +272,7 @@ obj-$(CONFIG_MFD_SMPRO) += smpro-core.o obj-$(CONFIG_MFD_INTEL_M10_BMC_CORE) += intel-m10-bmc-core.o obj-$(CONFIG_MFD_INTEL_M10_BMC_SPI) += intel-m10-bmc-spi.o +obj-$(CONFIG_MFD_INTEL_M10_BMC_PMCI) += intel-m10-bmc-pmci.o obj-$(CONFIG_MFD_ATC260X) += atc260x-core.o obj-$(CONFIG_MFD_ATC260X_I2C) += atc260x-i2c.o diff --git a/drivers/mfd/intel-m10-bmc-pmci.c b/drivers/mfd/intel-m10-bmc-pmci.c new file mode 100644 index 000000000000..975019f644b5 --- /dev/null +++ b/drivers/mfd/intel-m10-bmc-pmci.c @@ -0,0 +1,219 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * MAX10 BMC Platform Management Component Interface (PMCI) based + * interface. + * + * Copyright (C) 2020-2023 Intel Corporation. + */ + +#include +#include +#include +#include +#include +#include + +struct m10bmc_pmci_device { + void __iomem *base; + struct intel_m10bmc m10bmc; +}; + +/* + * Intel FGPA indirect register access via hardware controller/bridge. + */ +#define INDIRECT_CMD_OFF 0 +#define INDIRECT_CMD_CLR 0 +#define INDIRECT_CMD_RD BIT(0) +#define INDIRECT_CMD_WR BIT(1) +#define INDIRECT_CMD_ACK BIT(2) + +#define INDIRECT_ADDR_OFF 0x4 +#define INDIRECT_RD_OFF 0x8 +#define INDIRECT_WR_OFF 0xc + +#define INDIRECT_INT_US 1 +#define INDIRECT_TIMEOUT_US 10000 + +struct indirect_ctx { + void __iomem *base; + struct device *dev; +}; + +static int indirect_clear_cmd(struct indirect_ctx *ctx) +{ + unsigned int cmd; + int ret; + + writel(INDIRECT_CMD_CLR, ctx->base + INDIRECT_CMD_OFF); + + ret = readl_poll_timeout(ctx->base + INDIRECT_CMD_OFF, cmd, + cmd == INDIRECT_CMD_CLR, + INDIRECT_INT_US, INDIRECT_TIMEOUT_US); + if (ret) + dev_err(ctx->dev, "timed out waiting clear cmd (residual cmd=0x%x)\n", cmd); + + return ret; +} + +static int indirect_reg_read(void *context, unsigned int reg, unsigned int *val) +{ + struct indirect_ctx *ctx = context; + unsigned int cmd, ack, tmpval; + int ret, ret2; + + cmd = readl(ctx->base + INDIRECT_CMD_OFF); + if (cmd != INDIRECT_CMD_CLR) + dev_warn(ctx->dev, "residual cmd 0x%x on read entry\n", cmd); + + writel(reg, ctx->base + INDIRECT_ADDR_OFF); + writel(INDIRECT_CMD_RD, ctx->base + INDIRECT_CMD_OFF); + + ret = readl_poll_timeout(ctx->base + INDIRECT_CMD_OFF, ack, + (ack & INDIRECT_CMD_ACK) == INDIRECT_CMD_ACK, + INDIRECT_INT_US, INDIRECT_TIMEOUT_US); + if (ret) + dev_err(ctx->dev, "read timed out on reg 0x%x ack 0x%x\n", reg, ack); + else + tmpval = readl(ctx->base + INDIRECT_RD_OFF); + + ret2 = indirect_clear_cmd(ctx); + + if (ret) + return ret; + if (ret2) + return ret2; + + *val = tmpval; + return 0; +} + +static int indirect_reg_write(void *context, unsigned int reg, unsigned int val) +{ + struct indirect_ctx *ctx = context; + unsigned int cmd, ack; + int ret, ret2; + + cmd = readl(ctx->base + INDIRECT_CMD_OFF); + if (cmd != INDIRECT_CMD_CLR) + dev_warn(ctx->dev, "residual cmd 0x%x on write entry\n", cmd); + + writel(val, ctx->base + INDIRECT_WR_OFF); + writel(reg, ctx->base + INDIRECT_ADDR_OFF); + writel(INDIRECT_CMD_WR, ctx->base + INDIRECT_CMD_OFF); + + ret = readl_poll_timeout(ctx->base + INDIRECT_CMD_OFF, ack, + (ack & INDIRECT_CMD_ACK) == INDIRECT_CMD_ACK, + INDIRECT_INT_US, INDIRECT_TIMEOUT_US); + if (ret) + dev_err(ctx->dev, "write timed out on reg 0x%x ack 0x%x\n", reg, ack); + + ret2 = indirect_clear_cmd(ctx); + + if (ret) + return ret; + return ret2; +} + +static const struct regmap_range m10bmc_pmci_regmap_range[] = { + regmap_reg_range(M10BMC_N6000_SYS_BASE, M10BMC_N6000_SYS_END), +}; + +static const struct regmap_access_table m10bmc_pmci_access_table = { + .yes_ranges = m10bmc_pmci_regmap_range, + .n_yes_ranges = ARRAY_SIZE(m10bmc_pmci_regmap_range), +}; + +static struct regmap_config m10bmc_pmci_regmap_config = { + .reg_bits = 32, + .reg_stride = 4, + .val_bits = 32, + .wr_table = &m10bmc_pmci_access_table, + .rd_table = &m10bmc_pmci_access_table, + .reg_read = &indirect_reg_read, + .reg_write = &indirect_reg_write, + .max_register = M10BMC_N6000_SYS_END, +}; + +static struct mfd_cell m10bmc_pmci_n6000_bmc_subdevs[] = { + { .name = "n6000bmc-hwmon" }, +}; + +static const struct m10bmc_csr_map m10bmc_n6000_csr_map = { + .base = M10BMC_N6000_SYS_BASE, + .build_version = M10BMC_N6000_BUILD_VER, + .fw_version = NIOS2_N6000_FW_VERSION, + .mac_low = M10BMC_N6000_MAC_LOW, + .mac_high = M10BMC_N6000_MAC_HIGH, + .doorbell = M10BMC_N6000_DOORBELL, + .auth_result = M10BMC_N6000_AUTH_RESULT, + .bmc_prog_addr = M10BMC_N6000_BMC_PROG_ADDR, + .bmc_reh_addr = M10BMC_N6000_BMC_REH_ADDR, + .bmc_magic = M10BMC_N6000_BMC_PROG_MAGIC, + .sr_prog_addr = M10BMC_N6000_SR_PROG_ADDR, + .sr_reh_addr = M10BMC_N6000_SR_REH_ADDR, + .sr_magic = M10BMC_N6000_SR_PROG_MAGIC, + .pr_prog_addr = M10BMC_N6000_PR_PROG_ADDR, + .pr_reh_addr = M10BMC_N6000_PR_REH_ADDR, + .pr_magic = M10BMC_N6000_PR_PROG_MAGIC, + .rsu_update_counter = M10BMC_N6000_STAGING_FLASH_COUNT, +}; + +static const struct intel_m10bmc_platform_info m10bmc_pmci_n6000 = { + .cells = m10bmc_pmci_n6000_bmc_subdevs, + .n_cells = ARRAY_SIZE(m10bmc_pmci_n6000_bmc_subdevs), + .csr_map = &m10bmc_n6000_csr_map, +}; + +static int m10bmc_pmci_probe(struct dfl_device *ddev) +{ + struct device *dev = &ddev->dev; + struct m10bmc_pmci_device *pmci; + struct indirect_ctx *ctx; + + pmci = devm_kzalloc(dev, sizeof(*pmci), GFP_KERNEL); + if (!pmci) + return -ENOMEM; + + pmci->m10bmc.dev = dev; + + pmci->base = devm_ioremap_resource(dev, &ddev->mmio_res); + if (IS_ERR(pmci->base)) + return PTR_ERR(pmci->base); + + ctx = devm_kzalloc(dev, sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + + ctx->base = pmci->base + M10BMC_N6000_INDIRECT_BASE; + ctx->dev = dev; + indirect_clear_cmd(ctx); + pmci->m10bmc.regmap = devm_regmap_init(dev, NULL, ctx, &m10bmc_pmci_regmap_config); + + if (IS_ERR(pmci->m10bmc.regmap)) + return PTR_ERR(pmci->m10bmc.regmap); + + return m10bmc_dev_init(&pmci->m10bmc, &m10bmc_pmci_n6000); +} + +#define FME_FEATURE_ID_M10BMC_PMCI 0x12 + +static const struct dfl_device_id m10bmc_pmci_ids[] = { + { FME_ID, FME_FEATURE_ID_M10BMC_PMCI }, + { } +}; +MODULE_DEVICE_TABLE(dfl, m10bmc_pmci_ids); + +static struct dfl_driver m10bmc_pmci_driver = { + .drv = { + .name = "intel-m10-bmc", + .dev_groups = m10bmc_dev_groups, + }, + .id_table = m10bmc_pmci_ids, + .probe = m10bmc_pmci_probe, +}; + +module_dfl_driver(m10bmc_pmci_driver); + +MODULE_DESCRIPTION("MAX10 BMC PMCI-based interface"); +MODULE_AUTHOR("Intel Corporation"); +MODULE_LICENSE("GPL"); diff --git a/include/linux/mfd/intel-m10-bmc.h b/include/linux/mfd/intel-m10-bmc.h index 1f75b33240ad..810534b1bd12 100644 --- a/include/linux/mfd/intel-m10-bmc.h +++ b/include/linux/mfd/intel-m10-bmc.h @@ -120,6 +120,34 @@ /* Address of 4KB inverted bit vector containing staging area FLASH count */ #define M10BMC_N3000_STAGING_FLASH_COUNT 0x17ffb000 +#define M10BMC_N6000_INDIRECT_BASE 0x400 + +#define M10BMC_N6000_SYS_BASE 0x0 +#define M10BMC_N6000_SYS_END 0xfff + +#define M10BMC_N6000_DOORBELL 0x1c0 +#define M10BMC_N6000_AUTH_RESULT 0x1c4 + +#define M10BMC_N6000_BUILD_VER 0x0 +#define NIOS2_N6000_FW_VERSION 0x4 +#define M10BMC_N6000_MAC_LOW 0x20 +#define M10BMC_N6000_MAC_HIGH (M10BMC_N6000_MAC_LOW + 4) + +/* Addresses for security related data in FLASH */ +#define M10BMC_N6000_BMC_REH_ADDR 0x7ffc004 +#define M10BMC_N6000_BMC_PROG_ADDR 0x7ffc000 +#define M10BMC_N6000_BMC_PROG_MAGIC 0x5746 + +#define M10BMC_N6000_SR_REH_ADDR 0x7ffd004 +#define M10BMC_N6000_SR_PROG_ADDR 0x7ffd000 +#define M10BMC_N6000_SR_PROG_MAGIC 0x5253 + +#define M10BMC_N6000_PR_REH_ADDR 0x7ffe004 +#define M10BMC_N6000_PR_PROG_ADDR 0x7ffe000 +#define M10BMC_N6000_PR_PROG_MAGIC 0x5250 + +#define M10BMC_N6000_STAGING_FLASH_COUNT 0x7ff5000 + /** * struct m10bmc_csr_map - Intel MAX 10 BMC CSR register map */ -- cgit v1.2.3 From a77ad4bf792652340ab334956e69b46ec2fdaefb Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 11 Jan 2023 12:30:03 +0100 Subject: of: device: make of_device_uevent_modalias() take a const device * of_device_uevent_modalias() does not modify the device pointer passed to it, so mark it constant. In order to properly do this, a number of busses need to have a modalias function added as they were attempting to just point to of_device_uevent_modalias instead of their bus-specific modalias function. This is fine except if the prototype for a bus and device type modalias function diverges and then problems could happen. To prevent all of that, just wrap the call to of_device_uevent_modalias() directly for each bus and device type individually. Cc: Michael Ellerman Cc: Nicholas Piggin Cc: Christophe Leroy Cc: Chen-Yu Tsai Cc: Jernej Skrabec Cc: Samuel Holland Cc: David Airlie Cc: Daniel Vetter Cc: Benjamin Herrenschmidt Cc: Rob Herring Cc: Frank Rowand Cc: Liang He Cc: Thomas Gleixner Cc: Christophe JAILLET Cc: Thomas Zimmermann Cc: Dmitry Baryshkov Cc: Douglas Anderson Cc: Lyude Paul Cc: Corentin Labbe Cc: Zou Wei Cc: linuxppc-dev@lists.ozlabs.org Cc: linux-kernel@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-sunxi@lists.linux.dev Cc: dri-devel@lists.freedesktop.org Cc: devicetree@vger.kernel.org Acked-by: Hans de Goede Link: https://lore.kernel.org/r/20230111113018.459199-2-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- arch/powerpc/platforms/pseries/ibmebus.c | 7 ++++++- drivers/bus/sunxi-rsb.c | 7 ++++++- drivers/gpu/drm/display/drm_dp_aux_bus.c | 7 ++++++- drivers/macintosh/macio_asic.c | 7 ++++++- drivers/of/device.c | 4 ++-- include/linux/of_device.h | 4 ++-- 6 files changed, 28 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/arch/powerpc/platforms/pseries/ibmebus.c b/arch/powerpc/platforms/pseries/ibmebus.c index a870cada7acd..58b798a0e879 100644 --- a/arch/powerpc/platforms/pseries/ibmebus.c +++ b/arch/powerpc/platforms/pseries/ibmebus.c @@ -426,9 +426,14 @@ static struct attribute *ibmebus_bus_device_attrs[] = { }; ATTRIBUTE_GROUPS(ibmebus_bus_device); +static int ibmebus_bus_modalias(struct device *dev, struct kobj_uevent_env *env) +{ + return of_device_uevent_modalias(dev, env); +} + struct bus_type ibmebus_bus_type = { .name = "ibmebus", - .uevent = of_device_uevent_modalias, + .uevent = ibmebus_bus_modalias, .bus_groups = ibmbus_bus_groups, .match = ibmebus_bus_bus_match, .probe = ibmebus_bus_device_probe, diff --git a/drivers/bus/sunxi-rsb.c b/drivers/bus/sunxi-rsb.c index 3aa91aed3bf7..a180af11e034 100644 --- a/drivers/bus/sunxi-rsb.c +++ b/drivers/bus/sunxi-rsb.c @@ -172,12 +172,17 @@ static void sunxi_rsb_device_remove(struct device *dev) drv->remove(to_sunxi_rsb_device(dev)); } +static int sunxi_rsb_device_modalias(struct device *dev, struct kobj_uevent_env *env) +{ + return of_device_uevent_modalias(dev, env); +} + static struct bus_type sunxi_rsb_bus = { .name = RSB_CTRL_NAME, .match = sunxi_rsb_device_match, .probe = sunxi_rsb_device_probe, .remove = sunxi_rsb_device_remove, - .uevent = of_device_uevent_modalias, + .uevent = sunxi_rsb_device_modalias, }; static void sunxi_rsb_dev_release(struct device *dev) diff --git a/drivers/gpu/drm/display/drm_dp_aux_bus.c b/drivers/gpu/drm/display/drm_dp_aux_bus.c index f5741b45ca07..e31a0261c53e 100644 --- a/drivers/gpu/drm/display/drm_dp_aux_bus.c +++ b/drivers/gpu/drm/display/drm_dp_aux_bus.c @@ -161,9 +161,14 @@ static void dp_aux_ep_dev_release(struct device *dev) kfree(aux_ep_with_data); } +static int dp_aux_ep_dev_modalias(struct device *dev, struct kobj_uevent_env *env) +{ + return of_device_uevent_modalias(dev, env); +} + static struct device_type dp_aux_device_type_type = { .groups = dp_aux_ep_dev_groups, - .uevent = of_device_uevent_modalias, + .uevent = dp_aux_ep_dev_modalias, .release = dp_aux_ep_dev_release, }; diff --git a/drivers/macintosh/macio_asic.c b/drivers/macintosh/macio_asic.c index 3bc1f374e657..7f2b0107c733 100644 --- a/drivers/macintosh/macio_asic.c +++ b/drivers/macintosh/macio_asic.c @@ -128,12 +128,17 @@ static int macio_device_resume(struct device * dev) return 0; } +static int macio_device_modalias(struct device *dev, struct kobj_uevent_env *env) +{ + return of_device_uevent_modalias(dev, env); +} + extern const struct attribute_group *macio_dev_groups[]; struct bus_type macio_bus_type = { .name = "macio", .match = macio_bus_match, - .uevent = of_device_uevent_modalias, + .uevent = macio_device_modalias, .probe = macio_device_probe, .remove = macio_device_remove, .shutdown = macio_device_shutdown, diff --git a/drivers/of/device.c b/drivers/of/device.c index c674a13c3055..dda51b7ce597 100644 --- a/drivers/of/device.c +++ b/drivers/of/device.c @@ -248,7 +248,7 @@ const void *of_device_get_match_data(const struct device *dev) } EXPORT_SYMBOL(of_device_get_match_data); -static ssize_t of_device_get_modalias(struct device *dev, char *str, ssize_t len) +static ssize_t of_device_get_modalias(const struct device *dev, char *str, ssize_t len) { const char *compat; char *c; @@ -372,7 +372,7 @@ void of_device_uevent(const struct device *dev, struct kobj_uevent_env *env) mutex_unlock(&of_mutex); } -int of_device_uevent_modalias(struct device *dev, struct kobj_uevent_env *env) +int of_device_uevent_modalias(const struct device *dev, struct kobj_uevent_env *env) { int sl; diff --git a/include/linux/of_device.h b/include/linux/of_device.h index ab7d557d541d..f4b57614979d 100644 --- a/include/linux/of_device.h +++ b/include/linux/of_device.h @@ -36,7 +36,7 @@ extern ssize_t of_device_modalias(struct device *dev, char *str, ssize_t len); extern int of_device_request_module(struct device *dev); extern void of_device_uevent(const struct device *dev, struct kobj_uevent_env *env); -extern int of_device_uevent_modalias(struct device *dev, struct kobj_uevent_env *env); +extern int of_device_uevent_modalias(const struct device *dev, struct kobj_uevent_env *env); static inline struct device_node *of_cpu_device_node_get(int cpu) { @@ -83,7 +83,7 @@ static inline int of_device_request_module(struct device *dev) return -ENODEV; } -static inline int of_device_uevent_modalias(struct device *dev, +static inline int of_device_uevent_modalias(const struct device *dev, struct kobj_uevent_env *env) { return -ENODEV; -- cgit v1.2.3 From fa838c8ce53714eba788ea877520788bc72c27bd Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 11 Jan 2023 12:30:04 +0100 Subject: i3c: move dev_to_i3cdev() to use container_of_const() The driver core is changing to pass some pointers as const, so move dev_to_i3cdev() to use container_of_const() to handle this change. dev_to_i3cdev() now properly keeps the const-ness of the pointer passed into it, while as before it could be lost. Acked-by: Alexandre Belloni Acked-by: Hans de Goede Link: https://lore.kernel.org/r/20230111113018.459199-3-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/i3c/device.c | 12 ------------ include/linux/i3c/device.h | 9 ++++++++- 2 files changed, 8 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/drivers/i3c/device.c b/drivers/i3c/device.c index 9762630b917e..d111499061b2 100644 --- a/drivers/i3c/device.c +++ b/drivers/i3c/device.c @@ -208,18 +208,6 @@ struct device *i3cdev_to_dev(struct i3c_device *i3cdev) } EXPORT_SYMBOL_GPL(i3cdev_to_dev); -/** - * dev_to_i3cdev() - Returns the I3C device containing @dev - * @dev: device object - * - * Return: a pointer to an I3C device object. - */ -struct i3c_device *dev_to_i3cdev(struct device *dev) -{ - return container_of(dev, struct i3c_device, dev); -} -EXPORT_SYMBOL_GPL(dev_to_i3cdev); - /** * i3c_device_match_id() - Returns the i3c_device_id entry matching @i3cdev * @i3cdev: I3C device diff --git a/include/linux/i3c/device.h b/include/linux/i3c/device.h index 1c997abe868c..68b558929aec 100644 --- a/include/linux/i3c/device.h +++ b/include/linux/i3c/device.h @@ -186,7 +186,14 @@ static inline struct i3c_driver *drv_to_i3cdrv(struct device_driver *drv) } struct device *i3cdev_to_dev(struct i3c_device *i3cdev); -struct i3c_device *dev_to_i3cdev(struct device *dev); + +/** + * dev_to_i3cdev() - Returns the I3C device containing @dev + * @dev: device object + * + * Return: a pointer to an I3C device object. + */ +#define dev_to_i3cdev(__dev) container_of_const(__dev, struct i3c_device, dev) const struct i3c_device_id * i3c_device_match_id(struct i3c_device *i3cdev, -- cgit v1.2.3 From 34be683add6ccdbc9d589b79077ea7f48ff7ee0c Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 11 Jan 2023 12:30:05 +0100 Subject: platform/surface: aggregator: move to_ssam_device() to use container_of_const() The driver core is changing to pass some pointers as const, so move to_ssam_device() to use container_of_const() to handle this change. to_ssam_device() now properly keeps the const-ness of the pointer passed into it, while as before it could be lost. Reviewed-by: Maximilian Luz Acked-by: Hans de Goede Link: https://lore.kernel.org/r/20230111113018.459199-4-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/surface_aggregator/device.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/surface_aggregator/device.h b/include/linux/surface_aggregator/device.h index 46c45d1b6368..24151a0e2c96 100644 --- a/include/linux/surface_aggregator/device.h +++ b/include/linux/surface_aggregator/device.h @@ -229,10 +229,7 @@ static inline bool is_ssam_device(struct device *d) * Return: Returns a pointer to the &struct ssam_device wrapping the given * device @d. */ -static inline struct ssam_device *to_ssam_device(struct device *d) -{ - return container_of(d, struct ssam_device, dev); -} +#define to_ssam_device(d) container_of_const(d, struct ssam_device, dev) /** * to_ssam_device_driver() - Casts the given device driver to a SSAM client -- cgit v1.2.3 From 49b7fc1c25481c823e391b5617546b1ad4af0852 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 11 Jan 2023 12:30:06 +0100 Subject: firewire: move fw_device() and fw_unit() to use container_of_const() The driver core is changing to pass some pointers as const, so move fw_device() and fw_unit() functions to use container_of_const() to handle this change. fw_device() and fw_unit() now properly keeps the const-ness of the pointer passed into it, while as before it could be lost. This also required turning fw_parent_device() into a macro to preserve the const-ness of the pointer passed into it if necessary. Cc: Stefan Richter Acked-by: Hans de Goede Link: https://lore.kernel.org/r/20230111113018.459199-5-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/firewire.h | 15 +++------------ 1 file changed, 3 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/firewire.h b/include/linux/firewire.h index 980019053e54..03ac31ada5e6 100644 --- a/include/linux/firewire.h +++ b/include/linux/firewire.h @@ -208,10 +208,7 @@ struct fw_device { struct fw_attribute_group attribute_group; }; -static inline struct fw_device *fw_device(struct device *dev) -{ - return container_of(dev, struct fw_device, device); -} +#define fw_device(dev) container_of_const(dev, struct fw_device, device) static inline int fw_device_is_shutdown(struct fw_device *device) { @@ -229,10 +226,7 @@ struct fw_unit { struct fw_attribute_group attribute_group; }; -static inline struct fw_unit *fw_unit(struct device *dev) -{ - return container_of(dev, struct fw_unit, device); -} +#define fw_unit(dev) container_of_const(dev, struct fw_unit, device) static inline struct fw_unit *fw_unit_get(struct fw_unit *unit) { @@ -246,10 +240,7 @@ static inline void fw_unit_put(struct fw_unit *unit) put_device(&unit->device); } -static inline struct fw_device *fw_parent_device(struct fw_unit *unit) -{ - return fw_device(unit->device.parent); -} +#define fw_parent_device(unit) fw_device(unit->device.parent) struct ieee1394_device_id; -- cgit v1.2.3 From 162736b0d71a9630f7c99dda7cefd5600fa03d69 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 11 Jan 2023 12:30:07 +0100 Subject: driver core: make struct device_type.uevent() take a const * The uevent() callback in struct device_type should not be modifying the device that is passed into it, so mark it as a const * and propagate the function signature changes out into all relevant subsystems that use this callback. Cc: Alan Stern Cc: Andreas Noever Cc: Andy Shevchenko Cc: Bard Liao Cc: Chaitanya Kulkarni Cc: Dan Williams Cc: Dmitry Torokhov Cc: Frank Rowand Cc: Ira Weiny Cc: Jason Gunthorpe Cc: Jens Axboe Cc: Jilin Yuan Cc: Jiri Slaby Cc: Len Brown Cc: Mark Gross Cc: "Martin K. Petersen" Cc: "Matthew Wilcox (Oracle)" Cc: Maximilian Luz Cc: Michael Jamet Cc: Ming Lei Cc: Pierre-Louis Bossart Cc: Rob Herring Cc: Sakari Ailus Cc: Sanyog Kale Cc: Sean Young Cc: Stefan Richter Cc: Thomas Gleixner Cc: Won Chung Cc: Yehezkel Bernat Acked-by: Rafael J. Wysocki Acked-by: Mika Westerberg # for Thunderbolt Acked-by: Mauro Carvalho Chehab Acked-by: Alexandre Belloni Acked-by: Heikki Krogerus Acked-by: Wolfram Sang Acked-by: Vinod Koul Acked-by: Hans de Goede Link: https://lore.kernel.org/r/20230111113018.459199-6-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- block/partitions/core.c | 4 ++-- drivers/acpi/device_sysfs.c | 8 ++++---- drivers/acpi/internal.h | 2 +- drivers/firewire/core-device.c | 8 ++++---- drivers/gpu/drm/display/drm_dp_aux_bus.c | 2 +- drivers/i2c/i2c-core-base.c | 4 ++-- drivers/i3c/device.c | 2 +- drivers/i3c/master.c | 4 ++-- drivers/input/input.c | 16 ++++++++-------- drivers/media/rc/rc-main.c | 2 +- drivers/platform/surface/aggregator/bus.c | 4 ++-- drivers/soundwire/bus_type.c | 4 ++-- drivers/thunderbolt/switch.c | 4 ++-- drivers/thunderbolt/tb.h | 2 +- drivers/thunderbolt/xdomain.c | 6 +++--- drivers/tty/serdev/core.c | 2 +- drivers/usb/core/message.c | 8 ++++---- drivers/usb/core/usb.c | 4 ++-- drivers/usb/phy/phy.c | 6 +++--- drivers/usb/roles/class.c | 3 +-- drivers/usb/typec/class.c | 2 +- include/linux/acpi.h | 4 ++-- include/linux/device.h | 2 +- include/linux/i3c/device.h | 2 +- include/linux/soundwire/sdw_type.h | 2 +- 25 files changed, 53 insertions(+), 54 deletions(-) (limited to 'include/linux') diff --git a/block/partitions/core.c b/block/partitions/core.c index b8112f52d388..7b8ef6296abd 100644 --- a/block/partitions/core.c +++ b/block/partitions/core.c @@ -254,9 +254,9 @@ static void part_release(struct device *dev) iput(dev_to_bdev(dev)->bd_inode); } -static int part_uevent(struct device *dev, struct kobj_uevent_env *env) +static int part_uevent(const struct device *dev, struct kobj_uevent_env *env) { - struct block_device *part = dev_to_bdev(dev); + const struct block_device *part = dev_to_bdev(dev); add_uevent_var(env, "PARTN=%u", part->bd_partno); if (part->bd_meta_info && part->bd_meta_info->volname[0]) diff --git a/drivers/acpi/device_sysfs.c b/drivers/acpi/device_sysfs.c index 120873dad2cc..daff2c0c5c52 100644 --- a/drivers/acpi/device_sysfs.c +++ b/drivers/acpi/device_sysfs.c @@ -133,7 +133,7 @@ static void acpi_hide_nondev_subnodes(struct acpi_device_data *data) * -EINVAL: output error * -ENOMEM: output is truncated */ -static int create_pnp_modalias(struct acpi_device *acpi_dev, char *modalias, +static int create_pnp_modalias(const struct acpi_device *acpi_dev, char *modalias, int size) { int len; @@ -191,7 +191,7 @@ static int create_pnp_modalias(struct acpi_device *acpi_dev, char *modalias, * only be called for devices having ACPI_DT_NAMESPACE_HID in their list of * ACPI/PNP IDs. */ -static int create_of_modalias(struct acpi_device *acpi_dev, char *modalias, +static int create_of_modalias(const struct acpi_device *acpi_dev, char *modalias, int size) { struct acpi_buffer buf = { ACPI_ALLOCATE_BUFFER }; @@ -239,7 +239,7 @@ static int create_of_modalias(struct acpi_device *acpi_dev, char *modalias, return len; } -int __acpi_device_uevent_modalias(struct acpi_device *adev, +int __acpi_device_uevent_modalias(const struct acpi_device *adev, struct kobj_uevent_env *env) { int len; @@ -277,7 +277,7 @@ int __acpi_device_uevent_modalias(struct acpi_device *adev, * Because other buses do not support ACPI HIDs & CIDs, e.g. for a device with * hid:IBM0001 and cid:ACPI0001 you get: "acpi:IBM0001:ACPI0001". */ -int acpi_device_uevent_modalias(struct device *dev, struct kobj_uevent_env *env) +int acpi_device_uevent_modalias(const struct device *dev, struct kobj_uevent_env *env) { return __acpi_device_uevent_modalias(acpi_companion_match(dev), env); } diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h index ec584442fb29..06ad497067ac 100644 --- a/drivers/acpi/internal.h +++ b/drivers/acpi/internal.h @@ -120,7 +120,7 @@ int acpi_bus_register_early_device(int type); Device Matching and Notification -------------------------------------------------------------------------- */ struct acpi_device *acpi_companion_match(const struct device *dev); -int __acpi_device_uevent_modalias(struct acpi_device *adev, +int __acpi_device_uevent_modalias(const struct acpi_device *adev, struct kobj_uevent_env *env); /* -------------------------------------------------------------------------- diff --git a/drivers/firewire/core-device.c b/drivers/firewire/core-device.c index adddd8c45d0c..aa597cda0d88 100644 --- a/drivers/firewire/core-device.c +++ b/drivers/firewire/core-device.c @@ -133,7 +133,7 @@ static void get_ids(const u32 *directory, int *id) } } -static void get_modalias_ids(struct fw_unit *unit, int *id) +static void get_modalias_ids(const struct fw_unit *unit, int *id) { get_ids(&fw_parent_device(unit)->config_rom[5], id); get_ids(unit->directory, id); @@ -195,7 +195,7 @@ static void fw_unit_remove(struct device *dev) driver->remove(fw_unit(dev)); } -static int get_modalias(struct fw_unit *unit, char *buffer, size_t buffer_size) +static int get_modalias(const struct fw_unit *unit, char *buffer, size_t buffer_size) { int id[] = {0, 0, 0, 0}; @@ -206,9 +206,9 @@ static int get_modalias(struct fw_unit *unit, char *buffer, size_t buffer_size) id[0], id[1], id[2], id[3]); } -static int fw_unit_uevent(struct device *dev, struct kobj_uevent_env *env) +static int fw_unit_uevent(const struct device *dev, struct kobj_uevent_env *env) { - struct fw_unit *unit = fw_unit(dev); + const struct fw_unit *unit = fw_unit(dev); char modalias[64]; get_modalias(unit, modalias, sizeof(modalias)); diff --git a/drivers/gpu/drm/display/drm_dp_aux_bus.c b/drivers/gpu/drm/display/drm_dp_aux_bus.c index e31a0261c53e..8a165be1a821 100644 --- a/drivers/gpu/drm/display/drm_dp_aux_bus.c +++ b/drivers/gpu/drm/display/drm_dp_aux_bus.c @@ -161,7 +161,7 @@ static void dp_aux_ep_dev_release(struct device *dev) kfree(aux_ep_with_data); } -static int dp_aux_ep_dev_modalias(struct device *dev, struct kobj_uevent_env *env) +static int dp_aux_ep_dev_modalias(const struct device *dev, struct kobj_uevent_env *env) { return of_device_uevent_modalias(dev, env); } diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c index 087e480b624c..51b78a52ab7f 100644 --- a/drivers/i2c/i2c-core-base.c +++ b/drivers/i2c/i2c-core-base.c @@ -136,9 +136,9 @@ static int i2c_device_match(struct device *dev, struct device_driver *drv) return 0; } -static int i2c_device_uevent(struct device *dev, struct kobj_uevent_env *env) +static int i2c_device_uevent(const struct device *dev, struct kobj_uevent_env *env) { - struct i2c_client *client = to_i2c_client(dev); + const struct i2c_client *client = to_i2c_client(dev); int rc; rc = of_device_uevent_modalias(dev, env); diff --git a/drivers/i3c/device.c b/drivers/i3c/device.c index d111499061b2..1a6a8703dbc3 100644 --- a/drivers/i3c/device.c +++ b/drivers/i3c/device.c @@ -78,7 +78,7 @@ EXPORT_SYMBOL_GPL(i3c_device_do_setdasa); * * Retrieve I3C dev info. */ -void i3c_device_get_info(struct i3c_device *dev, +void i3c_device_get_info(const struct i3c_device *dev, struct i3c_device_info *info) { if (!info) diff --git a/drivers/i3c/master.c b/drivers/i3c/master.c index d7e6f6c99aea..7a60e1c5e587 100644 --- a/drivers/i3c/master.c +++ b/drivers/i3c/master.c @@ -273,9 +273,9 @@ static struct attribute *i3c_device_attrs[] = { }; ATTRIBUTE_GROUPS(i3c_device); -static int i3c_device_uevent(struct device *dev, struct kobj_uevent_env *env) +static int i3c_device_uevent(const struct device *dev, struct kobj_uevent_env *env) { - struct i3c_device *i3cdev = dev_to_i3cdev(dev); + const struct i3c_device *i3cdev = dev_to_i3cdev(dev); struct i3c_device_info devinfo; u16 manuf, part, ext; diff --git a/drivers/input/input.c b/drivers/input/input.c index ca2e3dd7188b..0336e799d713 100644 --- a/drivers/input/input.c +++ b/drivers/input/input.c @@ -1372,7 +1372,7 @@ INPUT_DEV_STRING_ATTR_SHOW(phys); INPUT_DEV_STRING_ATTR_SHOW(uniq); static int input_print_modalias_bits(char *buf, int size, - char name, unsigned long *bm, + char name, const unsigned long *bm, unsigned int min_bit, unsigned int max_bit) { int len = 0, i; @@ -1384,7 +1384,7 @@ static int input_print_modalias_bits(char *buf, int size, return len; } -static int input_print_modalias(char *buf, int size, struct input_dev *id, +static int input_print_modalias(char *buf, int size, const struct input_dev *id, int add_cr) { int len; @@ -1432,7 +1432,7 @@ static ssize_t input_dev_show_modalias(struct device *dev, } static DEVICE_ATTR(modalias, S_IRUGO, input_dev_show_modalias, NULL); -static int input_print_bitmap(char *buf, int buf_size, unsigned long *bitmap, +static int input_print_bitmap(char *buf, int buf_size, const unsigned long *bitmap, int max, int add_cr); static ssize_t input_dev_show_properties(struct device *dev, @@ -1524,7 +1524,7 @@ static const struct attribute_group input_dev_id_attr_group = { .attrs = input_dev_id_attrs, }; -static int input_print_bitmap(char *buf, int buf_size, unsigned long *bitmap, +static int input_print_bitmap(char *buf, int buf_size, const unsigned long *bitmap, int max, int add_cr) { int i; @@ -1621,7 +1621,7 @@ static void input_dev_release(struct device *device) * device bitfields. */ static int input_add_uevent_bm_var(struct kobj_uevent_env *env, - const char *name, unsigned long *bitmap, int max) + const char *name, const unsigned long *bitmap, int max) { int len; @@ -1639,7 +1639,7 @@ static int input_add_uevent_bm_var(struct kobj_uevent_env *env, } static int input_add_uevent_modalias_var(struct kobj_uevent_env *env, - struct input_dev *dev) + const struct input_dev *dev) { int len; @@ -1677,9 +1677,9 @@ static int input_add_uevent_modalias_var(struct kobj_uevent_env *env, return err; \ } while (0) -static int input_dev_uevent(struct device *device, struct kobj_uevent_env *env) +static int input_dev_uevent(const struct device *device, struct kobj_uevent_env *env) { - struct input_dev *dev = to_input_dev(device); + const struct input_dev *dev = to_input_dev(device); INPUT_ADD_HOTPLUG_VAR("PRODUCT=%x/%x/%x/%x", dev->id.bustype, dev->id.vendor, diff --git a/drivers/media/rc/rc-main.c b/drivers/media/rc/rc-main.c index 527d9324742b..6bdad6341844 100644 --- a/drivers/media/rc/rc-main.c +++ b/drivers/media/rc/rc-main.c @@ -1614,7 +1614,7 @@ static void rc_dev_release(struct device *device) kfree(dev); } -static int rc_dev_uevent(struct device *device, struct kobj_uevent_env *env) +static int rc_dev_uevent(const struct device *device, struct kobj_uevent_env *env) { struct rc_dev *dev = to_rc_dev(device); int ret = 0; diff --git a/drivers/platform/surface/aggregator/bus.c b/drivers/platform/surface/aggregator/bus.c index de539938896e..407eb55050a6 100644 --- a/drivers/platform/surface/aggregator/bus.c +++ b/drivers/platform/surface/aggregator/bus.c @@ -35,9 +35,9 @@ static struct attribute *ssam_device_attrs[] = { }; ATTRIBUTE_GROUPS(ssam_device); -static int ssam_device_uevent(struct device *dev, struct kobj_uevent_env *env) +static int ssam_device_uevent(const struct device *dev, struct kobj_uevent_env *env) { - struct ssam_device *sdev = to_ssam_device(dev); + const struct ssam_device *sdev = to_ssam_device(dev); return add_uevent_var(env, "MODALIAS=ssam:d%02Xc%02Xt%02Xi%02Xf%02X", sdev->uid.domain, sdev->uid.category, diff --git a/drivers/soundwire/bus_type.c b/drivers/soundwire/bus_type.c index 04b3529f8929..26c9a0a85d49 100644 --- a/drivers/soundwire/bus_type.c +++ b/drivers/soundwire/bus_type.c @@ -58,9 +58,9 @@ int sdw_slave_modalias(const struct sdw_slave *slave, char *buf, size_t size) slave->id.sdw_version, slave->id.class_id); } -int sdw_slave_uevent(struct device *dev, struct kobj_uevent_env *env) +int sdw_slave_uevent(const struct device *dev, struct kobj_uevent_env *env) { - struct sdw_slave *slave = dev_to_sdw_dev(dev); + const struct sdw_slave *slave = dev_to_sdw_dev(dev); char modalias[32]; sdw_slave_modalias(slave, modalias, sizeof(modalias)); diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c index 363d712aa364..cb6c304c445e 100644 --- a/drivers/thunderbolt/switch.c +++ b/drivers/thunderbolt/switch.c @@ -2176,9 +2176,9 @@ static void tb_switch_release(struct device *dev) kfree(sw); } -static int tb_switch_uevent(struct device *dev, struct kobj_uevent_env *env) +static int tb_switch_uevent(const struct device *dev, struct kobj_uevent_env *env) { - struct tb_switch *sw = tb_to_switch(dev); + const struct tb_switch *sw = tb_to_switch(dev); const char *type; if (sw->config.thunderbolt_version == USB4_VERSION_1_0) { diff --git a/drivers/thunderbolt/tb.h b/drivers/thunderbolt/tb.h index f9786976f5ec..909da0a98134 100644 --- a/drivers/thunderbolt/tb.h +++ b/drivers/thunderbolt/tb.h @@ -815,7 +815,7 @@ static inline bool tb_is_switch(const struct device *dev) return dev->type == &tb_switch_type; } -static inline struct tb_switch *tb_to_switch(struct device *dev) +static inline struct tb_switch *tb_to_switch(const struct device *dev) { if (tb_is_switch(dev)) return container_of(dev, struct tb_switch, dev); diff --git a/drivers/thunderbolt/xdomain.c b/drivers/thunderbolt/xdomain.c index 3c51e47dd86b..a48335c95d39 100644 --- a/drivers/thunderbolt/xdomain.c +++ b/drivers/thunderbolt/xdomain.c @@ -881,7 +881,7 @@ static ssize_t key_show(struct device *dev, struct device_attribute *attr, } static DEVICE_ATTR_RO(key); -static int get_modalias(struct tb_service *svc, char *buf, size_t size) +static int get_modalias(const struct tb_service *svc, char *buf, size_t size) { return snprintf(buf, size, "tbsvc:k%sp%08Xv%08Xr%08X", svc->key, svc->prtcid, svc->prtcvers, svc->prtcrevs); @@ -953,9 +953,9 @@ static const struct attribute_group *tb_service_attr_groups[] = { NULL, }; -static int tb_service_uevent(struct device *dev, struct kobj_uevent_env *env) +static int tb_service_uevent(const struct device *dev, struct kobj_uevent_env *env) { - struct tb_service *svc = container_of(dev, struct tb_service, dev); + const struct tb_service *svc = container_of_const(dev, struct tb_service, dev); char modalias[64]; get_modalias(svc, modalias, sizeof(modalias)); diff --git a/drivers/tty/serdev/core.c b/drivers/tty/serdev/core.c index 0180e1e4e75d..aa80de3a8194 100644 --- a/drivers/tty/serdev/core.c +++ b/drivers/tty/serdev/core.c @@ -42,7 +42,7 @@ static struct attribute *serdev_device_attrs[] = { }; ATTRIBUTE_GROUPS(serdev_device); -static int serdev_device_uevent(struct device *dev, struct kobj_uevent_env *env) +static int serdev_device_uevent(const struct device *dev, struct kobj_uevent_env *env) { int rc; diff --git a/drivers/usb/core/message.c b/drivers/usb/core/message.c index 127fac1af676..cc404bb7e8f7 100644 --- a/drivers/usb/core/message.c +++ b/drivers/usb/core/message.c @@ -1819,11 +1819,11 @@ void usb_authorize_interface(struct usb_interface *intf) } } -static int usb_if_uevent(struct device *dev, struct kobj_uevent_env *env) +static int usb_if_uevent(const struct device *dev, struct kobj_uevent_env *env) { - struct usb_device *usb_dev; - struct usb_interface *intf; - struct usb_host_interface *alt; + const struct usb_device *usb_dev; + const struct usb_interface *intf; + const struct usb_host_interface *alt; intf = to_usb_interface(dev); usb_dev = interface_to_usbdev(intf); diff --git a/drivers/usb/core/usb.c b/drivers/usb/core/usb.c index 11b15d7b357a..8527c06b65e6 100644 --- a/drivers/usb/core/usb.c +++ b/drivers/usb/core/usb.c @@ -423,9 +423,9 @@ static void usb_release_dev(struct device *dev) kfree(udev); } -static int usb_dev_uevent(struct device *dev, struct kobj_uevent_env *env) +static int usb_dev_uevent(const struct device *dev, struct kobj_uevent_env *env) { - struct usb_device *usb_dev; + const struct usb_device *usb_dev; usb_dev = to_usb_device(dev); diff --git a/drivers/usb/phy/phy.c b/drivers/usb/phy/phy.c index 1b24492bb4e5..4b468bde19cf 100644 --- a/drivers/usb/phy/phy.c +++ b/drivers/usb/phy/phy.c @@ -80,7 +80,7 @@ static struct usb_phy *__of_usb_find_phy(struct device_node *node) return ERR_PTR(-EPROBE_DEFER); } -static struct usb_phy *__device_to_usb_phy(struct device *dev) +static struct usb_phy *__device_to_usb_phy(const struct device *dev) { struct usb_phy *usb_phy; @@ -145,9 +145,9 @@ static void usb_phy_notify_charger_work(struct work_struct *work) kobject_uevent(&usb_phy->dev->kobj, KOBJ_CHANGE); } -static int usb_phy_uevent(struct device *dev, struct kobj_uevent_env *env) +static int usb_phy_uevent(const struct device *dev, struct kobj_uevent_env *env) { - struct usb_phy *usb_phy; + const struct usb_phy *usb_phy; char uchger_state[50] = { 0 }; char uchger_type[50] = { 0 }; unsigned long flags; diff --git a/drivers/usb/roles/class.c b/drivers/usb/roles/class.c index eacb46ec2ab3..56814ef80c24 100644 --- a/drivers/usb/roles/class.c +++ b/drivers/usb/roles/class.c @@ -274,8 +274,7 @@ static const struct attribute_group *usb_role_switch_groups[] = { NULL, }; -static int -usb_role_switch_uevent(struct device *dev, struct kobj_uevent_env *env) +static int usb_role_switch_uevent(const struct device *dev, struct kobj_uevent_env *env) { int ret; diff --git a/drivers/usb/typec/class.c b/drivers/usb/typec/class.c index 5897905cb4f0..a89d8fd3f46c 100644 --- a/drivers/usb/typec/class.c +++ b/drivers/usb/typec/class.c @@ -1737,7 +1737,7 @@ static const struct attribute_group *typec_groups[] = { NULL }; -static int typec_uevent(struct device *dev, struct kobj_uevent_env *env) +static int typec_uevent(const struct device *dev, struct kobj_uevent_env *env) { int ret; diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 5e6a876e17ba..564b62f13bd0 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -723,7 +723,7 @@ const struct acpi_device_id *acpi_match_device(const struct acpi_device_id *ids, const void *acpi_device_get_match_data(const struct device *dev); extern bool acpi_driver_match_device(struct device *dev, const struct device_driver *drv); -int acpi_device_uevent_modalias(struct device *, struct kobj_uevent_env *); +int acpi_device_uevent_modalias(const struct device *, struct kobj_uevent_env *); int acpi_device_modalias(struct device *, char *, int); struct platform_device *acpi_create_platform_device(struct acpi_device *, @@ -958,7 +958,7 @@ static inline union acpi_object *acpi_evaluate_dsm(acpi_handle handle, return NULL; } -static inline int acpi_device_uevent_modalias(struct device *dev, +static inline int acpi_device_uevent_modalias(const struct device *dev, struct kobj_uevent_env *env) { return -ENODEV; diff --git a/include/linux/device.h b/include/linux/device.h index 44e3acae7b36..dad0614aad96 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -88,7 +88,7 @@ int subsys_virtual_register(struct bus_type *subsys, struct device_type { const char *name; const struct attribute_group **groups; - int (*uevent)(struct device *dev, struct kobj_uevent_env *env); + int (*uevent)(const struct device *dev, struct kobj_uevent_env *env); char *(*devnode)(struct device *dev, umode_t *mode, kuid_t *uid, kgid_t *gid); void (*release)(struct device *dev); diff --git a/include/linux/i3c/device.h b/include/linux/i3c/device.h index 68b558929aec..ce115ef08fec 100644 --- a/include/linux/i3c/device.h +++ b/include/linux/i3c/device.h @@ -303,7 +303,7 @@ int i3c_device_do_priv_xfers(struct i3c_device *dev, int i3c_device_do_setdasa(struct i3c_device *dev); -void i3c_device_get_info(struct i3c_device *dev, struct i3c_device_info *info); +void i3c_device_get_info(const struct i3c_device *dev, struct i3c_device_info *info); struct i3c_ibi_payload { unsigned int len; diff --git a/include/linux/soundwire/sdw_type.h b/include/linux/soundwire/sdw_type.h index 52eb66cd11bc..d8c27f1e5559 100644 --- a/include/linux/soundwire/sdw_type.h +++ b/include/linux/soundwire/sdw_type.h @@ -21,7 +21,7 @@ static inline int is_sdw_slave(const struct device *dev) int __sdw_register_driver(struct sdw_driver *drv, struct module *owner); void sdw_unregister_driver(struct sdw_driver *drv); -int sdw_slave_uevent(struct device *dev, struct kobj_uevent_env *env); +int sdw_slave_uevent(const struct device *dev, struct kobj_uevent_env *env); /** * module_sdw_driver() - Helper macro for registering a Soundwire driver -- cgit v1.2.3 From a9b12f8b4e3309c4c25d39e7ab818943b9c48c1c Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 11 Jan 2023 12:30:08 +0100 Subject: driver core: make struct device_type.devnode() take a const * The devnode() callback in struct device_type should not be modifying the device that is passed into it, so mark it as a const * and propagate the function signature changes out into all relevant subsystems that use this callback. Cc: Jens Axboe Cc: Alison Schofield Cc: Vishal Verma Cc: Ira Weiny Cc: Ben Widawsky Cc: Jeremy Kerr Cc: Joel Stanley Cc: Alistar Popple Cc: Eddie James Cc: Jonathan Cameron Cc: Jilin Yuan Cc: Heikki Krogerus Cc: Alan Stern Cc: Andy Shevchenko Cc: Thomas Gleixner Cc: Jason Gunthorpe Cc: "Rafael J. Wysocki" Cc: Won Chung Acked-by: Dan Williams Acked-by: Alexander Shishkin Acked-by: Hans de Goede Link: https://lore.kernel.org/r/20230111113018.459199-7-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- block/genhd.c | 2 +- drivers/cxl/core/memdev.c | 2 +- drivers/fsi/fsi-core.c | 6 +++--- drivers/hwtracing/intel_th/core.c | 6 +++--- drivers/hwtracing/intel_th/intel_th.h | 4 ++-- drivers/usb/core/usb.c | 4 ++-- include/linux/device.h | 2 +- 7 files changed, 13 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/block/genhd.c b/block/genhd.c index 23cf83b3331c..09f2ac548832 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -1201,7 +1201,7 @@ struct class block_class = { .dev_uevent = block_uevent, }; -static char *block_devnode(struct device *dev, umode_t *mode, +static char *block_devnode(const struct device *dev, umode_t *mode, kuid_t *uid, kgid_t *gid) { struct gendisk *disk = dev_to_disk(dev); diff --git a/drivers/cxl/core/memdev.c b/drivers/cxl/core/memdev.c index a74a93310d26..a38a0cc20d47 100644 --- a/drivers/cxl/core/memdev.c +++ b/drivers/cxl/core/memdev.c @@ -27,7 +27,7 @@ static void cxl_memdev_release(struct device *dev) kfree(cxlmd); } -static char *cxl_memdev_devnode(struct device *dev, umode_t *mode, kuid_t *uid, +static char *cxl_memdev_devnode(const struct device *dev, umode_t *mode, kuid_t *uid, kgid_t *gid) { return kasprintf(GFP_KERNEL, "cxl/%s", dev_name(dev)); diff --git a/drivers/fsi/fsi-core.c b/drivers/fsi/fsi-core.c index 694e80c06665..0b927c9f4267 100644 --- a/drivers/fsi/fsi-core.c +++ b/drivers/fsi/fsi-core.c @@ -897,10 +897,10 @@ static const struct attribute_group *cfam_attr_groups[] = { NULL, }; -static char *cfam_devnode(struct device *dev, umode_t *mode, +static char *cfam_devnode(const struct device *dev, umode_t *mode, kuid_t *uid, kgid_t *gid) { - struct fsi_slave *slave = to_fsi_slave(dev); + const struct fsi_slave *slave = to_fsi_slave(dev); #ifdef CONFIG_FSI_NEW_DEV_NODE return kasprintf(GFP_KERNEL, "fsi/cfam%d", slave->cdev_idx); @@ -915,7 +915,7 @@ static const struct device_type cfam_type = { .groups = cfam_attr_groups }; -static char *fsi_cdev_devnode(struct device *dev, umode_t *mode, +static char *fsi_cdev_devnode(const struct device *dev, umode_t *mode, kuid_t *uid, kgid_t *gid) { #ifdef CONFIG_FSI_NEW_DEV_NODE diff --git a/drivers/hwtracing/intel_th/core.c b/drivers/hwtracing/intel_th/core.c index 7e753a75d23b..cc7f879bb175 100644 --- a/drivers/hwtracing/intel_th/core.c +++ b/drivers/hwtracing/intel_th/core.c @@ -185,11 +185,11 @@ static struct device_type intel_th_source_device_type = { .release = intel_th_device_release, }; -static char *intel_th_output_devnode(struct device *dev, umode_t *mode, +static char *intel_th_output_devnode(const struct device *dev, umode_t *mode, kuid_t *uid, kgid_t *gid) { - struct intel_th_device *thdev = to_intel_th_device(dev); - struct intel_th *th = to_intel_th(thdev); + const struct intel_th_device *thdev = to_intel_th_device(dev); + const struct intel_th *th = to_intel_th(thdev); char *node; if (thdev->id >= 0) diff --git a/drivers/hwtracing/intel_th/intel_th.h b/drivers/hwtracing/intel_th/intel_th.h index 0ffb42990175..6cbba733f259 100644 --- a/drivers/hwtracing/intel_th/intel_th.h +++ b/drivers/hwtracing/intel_th/intel_th.h @@ -205,7 +205,7 @@ struct intel_th_driver { * INTEL_TH_SWITCH and INTEL_TH_SOURCE are children of the intel_th device. */ static inline struct intel_th_device * -to_intel_th_parent(struct intel_th_device *thdev) +to_intel_th_parent(const struct intel_th_device *thdev) { struct device *parent = thdev->dev.parent; @@ -215,7 +215,7 @@ to_intel_th_parent(struct intel_th_device *thdev) return to_intel_th_device(parent); } -static inline struct intel_th *to_intel_th(struct intel_th_device *thdev) +static inline struct intel_th *to_intel_th(const struct intel_th_device *thdev) { if (thdev->type == INTEL_TH_OUTPUT) thdev = to_intel_th_parent(thdev); diff --git a/drivers/usb/core/usb.c b/drivers/usb/core/usb.c index 8527c06b65e6..4df26f4f76e6 100644 --- a/drivers/usb/core/usb.c +++ b/drivers/usb/core/usb.c @@ -505,10 +505,10 @@ static const struct dev_pm_ops usb_device_pm_ops = { #endif /* CONFIG_PM */ -static char *usb_devnode(struct device *dev, +static char *usb_devnode(const struct device *dev, umode_t *mode, kuid_t *uid, kgid_t *gid) { - struct usb_device *usb_dev; + const struct usb_device *usb_dev; usb_dev = to_usb_device(dev); return kasprintf(GFP_KERNEL, "bus/usb/%03d/%03d", diff --git a/include/linux/device.h b/include/linux/device.h index dad0614aad96..318861000b83 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -89,7 +89,7 @@ struct device_type { const char *name; const struct attribute_group **groups; int (*uevent)(const struct device *dev, struct kobj_uevent_env *env); - char *(*devnode)(struct device *dev, umode_t *mode, + char *(*devnode)(const struct device *dev, umode_t *mode, kuid_t *uid, kgid_t *gid); void (*release)(struct device *dev); -- cgit v1.2.3 From 42bb5be8936f40a1d0e618766645e7fd0cbfe591 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 11 Jan 2023 12:30:09 +0100 Subject: driver core: device_get_devnode() should take a const * device_get_devnode() should take a constant * to struct device as it does not modify it in any way, so modify the function definition to do this and move it out of device.h as it does not need to be exposed to the whole kernel tree. Cc: Thomas Gleixner Cc: Jason Gunthorpe Cc: Ira Weiny Cc: Dan Williams Cc: Won Chung Acked-by: Rafael J. Wysocki Reviewed-by: Andy Shevchenko Acked-by: Hans de Goede Link: https://lore.kernel.org/r/20230111113018.459199-8-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/base/base.h | 2 ++ drivers/base/core.c | 2 +- include/linux/device.h | 2 -- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/base.h b/drivers/base/base.h index 3d1da1027206..2208af509ce8 100644 --- a/drivers/base/base.h +++ b/drivers/base/base.h @@ -159,6 +159,8 @@ extern void device_block_probing(void); extern void device_unblock_probing(void); extern void deferred_probe_extend_timeout(void); extern void driver_deferred_probe_trigger(void); +const char *device_get_devnode(const struct device *dev, umode_t *mode, + kuid_t *uid, kgid_t *gid, const char **tmp); /* /sys/devices directory */ extern struct kset *devices_kset; diff --git a/drivers/base/core.c b/drivers/base/core.c index 39dbd532cfb3..e39b6fa0eda6 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -3733,7 +3733,7 @@ static struct device *next_device(struct klist_iter *i) * a name. This memory is returned in tmp and needs to be * freed by the caller. */ -const char *device_get_devnode(struct device *dev, +const char *device_get_devnode(const struct device *dev, umode_t *mode, kuid_t *uid, kgid_t *gid, const char **tmp) { diff --git a/include/linux/device.h b/include/linux/device.h index 318861000b83..90aaf308c259 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -907,8 +907,6 @@ int device_rename(struct device *dev, const char *new_name); int device_move(struct device *dev, struct device *new_parent, enum dpm_order dpm_order); int device_change_owner(struct device *dev, kuid_t kuid, kgid_t kgid); -const char *device_get_devnode(struct device *dev, umode_t *mode, kuid_t *uid, - kgid_t *gid, const char **tmp); int device_is_dependent(struct device *dev, void *target); static inline bool device_supports_offline(struct device *dev) -- cgit v1.2.3 From 8afdae83e318f3cfb6eb1ee2ce289356936a663c Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 11 Jan 2023 12:30:12 +0100 Subject: drivers: hv: move device_to_hv_device to use container_of_const() The driver core is changing to pass some pointers as const, so move device_to_hv_device() to use container_of_const() to handle this change. device_to_hv_device() now properly keeps the const-ness of the pointer passed into it, while as before it could be lost. Cc: "K. Y. Srinivasan" Cc: Haiyang Zhang Cc: Dexuan Cui Acked-by: Wei Liu Acked-by: Hans de Goede Link: https://lore.kernel.org/r/20230111113018.459199-11-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/hyperv.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 85f7c5a63aa6..8430e27f3c3f 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1309,10 +1309,7 @@ struct hv_device { }; -static inline struct hv_device *device_to_hv_device(struct device *d) -{ - return container_of(d, struct hv_device, device); -} +#define device_to_hv_device(d) container_of_const(d, struct hv_device, device) static inline struct hv_driver *drv_to_hv_drv(struct device_driver *d) { -- cgit v1.2.3 From af3011b6637cd7e94b2420455d41ba9e66c03aed Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 11 Jan 2023 12:30:13 +0100 Subject: virtio: move dev_to_virtio() to use container_of_const() The driver core is changing to pass some pointers as const, so move dev_to_virtio() to use container_of_const() to handle this change. dev_to_virtio() now properly keeps the const-ness of the pointer passed into it, while as before it could be lost. Cc: "Michael S. Tsirkin" Cc: Jason Wang Acked-by: Hans de Goede Link: https://lore.kernel.org/r/20230111113018.459199-12-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/virtio.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/virtio.h b/include/linux/virtio.h index dcab9c7e8784..2b472514c49b 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -127,10 +127,7 @@ struct virtio_device { void *priv; }; -static inline struct virtio_device *dev_to_virtio(struct device *_dev) -{ - return container_of(_dev, struct virtio_device, dev); -} +#define dev_to_virtio(_dev) container_of_const(_dev, struct virtio_device, dev) void virtio_add_status(struct virtio_device *dev, unsigned int status); int register_virtio_device(struct virtio_device *dev); -- cgit v1.2.3 From deaf8b21c803b3932071a7cf9b11f36e13000f5c Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 11 Jan 2023 12:30:15 +0100 Subject: mcb: move to_mcb_device() to use container_of_const() The driver core is changing to pass some pointers as const, so move to_mcb_device() to use container_of_const() to handle this change. to_mcb_device() now properly keeps the const-ness of the pointer passed into it, while as before it could be lost. Cc: Johannes Thumshirn Acked-by: Hans de Goede Link: https://lore.kernel.org/r/20230111113018.459199-14-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mcb.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mcb.h b/include/linux/mcb.h index f6efb16f9d1b..1e5893138afe 100644 --- a/include/linux/mcb.h +++ b/include/linux/mcb.h @@ -76,10 +76,7 @@ struct mcb_device { struct device *dma_dev; }; -static inline struct mcb_device *to_mcb_device(struct device *dev) -{ - return container_of(dev, struct mcb_device, dev); -} +#define to_mcb_device(__dev) container_of_const(__dev, struct mcb_device, dev) /** * struct mcb_driver - MEN Chameleon Bus device driver -- cgit v1.2.3 From 2a81ada32f0e584fc0c943e0d3a8c9f4fae411d6 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 11 Jan 2023 12:30:17 +0100 Subject: driver core: make struct bus_type.uevent() take a const * The uevent() callback in struct bus_type should not be modifying the device that is passed into it, so mark it as a const * and propagate the function signature changes out into all relevant subsystems that use this callback. Acked-by: Rafael J. Wysocki Acked-by: Hans de Goede Link: https://lore.kernel.org/r/20230111113018.459199-16-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- arch/mips/sgi-ip22/ip22-gio.c | 4 ++-- arch/parisc/kernel/drivers.c | 4 ++-- arch/powerpc/platforms/pseries/vio.c | 4 ++-- arch/sparc/kernel/vio.c | 2 +- drivers/acpi/bus.c | 2 +- drivers/amba/bus.c | 4 ++-- drivers/base/auxiliary.c | 2 +- drivers/base/cpu.c | 2 +- drivers/base/platform.c | 4 ++-- drivers/bcma/main.c | 6 +++--- drivers/bus/fsl-mc/fsl-mc-bus.c | 4 ++-- drivers/bus/mhi/ep/main.c | 4 ++-- drivers/bus/mhi/host/init.c | 4 ++-- drivers/bus/mips_cdmm.c | 4 ++-- drivers/bus/sunxi-rsb.c | 2 +- drivers/cxl/core/memdev.c | 2 +- drivers/cxl/core/port.c | 8 ++++---- drivers/cxl/cxl.h | 4 ++-- drivers/cxl/cxlmem.h | 2 +- drivers/dax/bus.c | 2 +- drivers/eisa/eisa-bus.c | 4 ++-- drivers/firmware/arm_ffa/bus.c | 4 ++-- drivers/fpga/dfl.c | 4 ++-- drivers/gpu/drm/drm_mipi_dsi.c | 4 ++-- drivers/gpu/host1x/bus.c | 2 +- drivers/greybus/core.c | 14 +++++++------- drivers/hid/hid-core.c | 4 ++-- drivers/hid/intel-ish-hid/ishtp/bus.c | 2 +- drivers/hsi/hsi_core.c | 2 +- drivers/hv/vmbus_drv.c | 4 ++-- drivers/input/serio/serio.c | 4 ++-- drivers/ipack/ipack.c | 4 ++-- drivers/macintosh/macio_asic.c | 2 +- drivers/mcb/mcb-core.c | 4 ++-- drivers/memstick/core/memstick.c | 6 +++--- drivers/misc/mei/bus.c | 4 ++-- drivers/misc/tifm_core.c | 4 ++-- drivers/mmc/core/bus.c | 4 ++-- drivers/mmc/core/sdio_bus.c | 4 ++-- drivers/net/phy/mdio_bus.c | 2 +- drivers/net/xen-netback/xenbus.c | 2 +- drivers/nvdimm/bus.c | 4 ++-- drivers/nvdimm/dax_devs.c | 2 +- drivers/nvdimm/dimm_devs.c | 2 +- drivers/nvdimm/nd-core.h | 10 +++++----- drivers/nvdimm/nd.h | 4 ++-- drivers/nvdimm/region_devs.c | 4 ++-- drivers/pci/pci-driver.c | 4 ++-- drivers/pcmcia/ds.c | 4 ++-- drivers/platform/x86/wmi.c | 4 ++-- drivers/rapidio/rio-driver.c | 4 ++-- drivers/rpmsg/rpmsg_core.c | 4 ++-- drivers/s390/cio/css.c | 4 ++-- drivers/s390/cio/device.c | 8 ++++---- drivers/s390/cio/scm.c | 2 +- drivers/s390/crypto/ap_bus.c | 4 ++-- drivers/scsi/scsi_sysfs.c | 4 ++-- drivers/slimbus/core.c | 4 ++-- drivers/soc/qcom/apr.c | 4 ++-- drivers/spi/spi.c | 2 +- drivers/spmi/spmi.c | 2 +- drivers/ssb/main.c | 4 ++-- drivers/staging/greybus/gbphy.c | 14 +++++++------- drivers/tee/tee_core.c | 2 +- drivers/usb/common/ulpi.c | 4 ++-- drivers/usb/core/driver.c | 6 +++--- drivers/usb/typec/bus.c | 4 ++-- drivers/virtio/virtio.c | 4 ++-- drivers/w1/w1.c | 10 +++++----- drivers/xen/pvcalls-back.c | 2 +- drivers/xen/xenbus/xenbus_probe_backend.c | 8 ++++---- drivers/xen/xenbus/xenbus_probe_frontend.c | 4 ++-- drivers/zorro/zorro-driver.c | 4 ++-- include/linux/device/bus.h | 2 +- include/linux/spi/spi.h | 2 +- include/linux/ssb/ssb.h | 2 +- include/sound/hdaudio.h | 2 +- include/xen/xenbus.h | 2 +- sound/aoa/soundbus/core.c | 6 +++--- sound/hda/hda_bus_type.c | 2 +- sound/hda/hdac_device.c | 2 +- 81 files changed, 160 insertions(+), 160 deletions(-) (limited to 'include/linux') diff --git a/arch/mips/sgi-ip22/ip22-gio.c b/arch/mips/sgi-ip22/ip22-gio.c index 8686e8c1c4e5..81c9f0a8880b 100644 --- a/arch/mips/sgi-ip22/ip22-gio.c +++ b/arch/mips/sgi-ip22/ip22-gio.c @@ -199,9 +199,9 @@ static struct attribute *gio_dev_attrs[] = { }; ATTRIBUTE_GROUPS(gio_dev); -static int gio_device_uevent(struct device *dev, struct kobj_uevent_env *env) +static int gio_device_uevent(const struct device *dev, struct kobj_uevent_env *env) { - struct gio_device *gio_dev = to_gio_device(dev); + const struct gio_device *gio_dev = to_gio_device(dev); add_uevent_var(env, "MODALIAS=gio:%x", gio_dev->id.id); return 0; diff --git a/arch/parisc/kernel/drivers.c b/arch/parisc/kernel/drivers.c index e7ee0c0c91d3..28f47285d448 100644 --- a/arch/parisc/kernel/drivers.c +++ b/arch/parisc/kernel/drivers.c @@ -552,7 +552,7 @@ static int parisc_generic_match(struct device *dev, struct device_driver *drv) return match_device(to_parisc_driver(drv), to_parisc_device(dev)); } -static ssize_t make_modalias(struct device *dev, char *buf) +static ssize_t make_modalias(const struct device *dev, char *buf) { const struct parisc_device *padev = to_parisc_device(dev); const struct parisc_device_id *id = &padev->id; @@ -562,7 +562,7 @@ static ssize_t make_modalias(struct device *dev, char *buf) (u32)id->sversion); } -static int parisc_uevent(struct device *dev, struct kobj_uevent_env *env) +static int parisc_uevent(const struct device *dev, struct kobj_uevent_env *env) { const struct parisc_device *padev; char modalias[40]; diff --git a/arch/powerpc/platforms/pseries/vio.c b/arch/powerpc/platforms/pseries/vio.c index 00ecac2c205b..770df9351aaa 100644 --- a/arch/powerpc/platforms/pseries/vio.c +++ b/arch/powerpc/platforms/pseries/vio.c @@ -1609,10 +1609,10 @@ static int vio_bus_match(struct device *dev, struct device_driver *drv) return (ids != NULL) && (vio_match_device(ids, vio_dev) != NULL); } -static int vio_hotplug(struct device *dev, struct kobj_uevent_env *env) +static int vio_hotplug(const struct device *dev, struct kobj_uevent_env *env) { const struct vio_dev *vio_dev = to_vio_dev(dev); - struct device_node *dn; + const struct device_node *dn; const char *cp; dn = dev->of_node; diff --git a/arch/sparc/kernel/vio.c b/arch/sparc/kernel/vio.c index 01122a208f94..b78df3a15a72 100644 --- a/arch/sparc/kernel/vio.c +++ b/arch/sparc/kernel/vio.c @@ -46,7 +46,7 @@ static const struct vio_device_id *vio_match_device( return NULL; } -static int vio_hotplug(struct device *dev, struct kobj_uevent_env *env) +static int vio_hotplug(const struct device *dev, struct kobj_uevent_env *env) { const struct vio_dev *vio_dev = to_vio_dev(dev); diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c index 0c05ccde1f7a..9531dd0fef50 100644 --- a/drivers/acpi/bus.c +++ b/drivers/acpi/bus.c @@ -1014,7 +1014,7 @@ static int acpi_bus_match(struct device *dev, struct device_driver *drv) && !acpi_match_device_ids(acpi_dev, acpi_drv->ids); } -static int acpi_device_uevent(struct device *dev, struct kobj_uevent_env *env) +static int acpi_device_uevent(const struct device *dev, struct kobj_uevent_env *env) { return __acpi_device_uevent_modalias(to_acpi_device(dev), env); } diff --git a/drivers/amba/bus.c b/drivers/amba/bus.c index ff7454a38058..ce88af9eb562 100644 --- a/drivers/amba/bus.c +++ b/drivers/amba/bus.c @@ -235,9 +235,9 @@ static int amba_match(struct device *dev, struct device_driver *drv) return amba_lookup(pcdrv->id_table, pcdev) != NULL; } -static int amba_uevent(struct device *dev, struct kobj_uevent_env *env) +static int amba_uevent(const struct device *dev, struct kobj_uevent_env *env) { - struct amba_device *pcdev = to_amba_device(dev); + const struct amba_device *pcdev = to_amba_device(dev); int retval = 0; retval = add_uevent_var(env, "AMBA_ID=%08x", pcdev->periphid); diff --git a/drivers/base/auxiliary.c b/drivers/base/auxiliary.c index 8c5e65930617..4d4c2c8d26c4 100644 --- a/drivers/base/auxiliary.c +++ b/drivers/base/auxiliary.c @@ -185,7 +185,7 @@ static int auxiliary_match(struct device *dev, struct device_driver *drv) return !!auxiliary_match_id(auxdrv->id_table, auxdev); } -static int auxiliary_uevent(struct device *dev, struct kobj_uevent_env *env) +static int auxiliary_uevent(const struct device *dev, struct kobj_uevent_env *env) { const char *name, *p; diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index 4c98849577d4..441eb5bdec7d 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -336,7 +336,7 @@ static ssize_t print_cpu_modalias(struct device *dev, return len; } -static int cpu_uevent(struct device *dev, struct kobj_uevent_env *env) +static int cpu_uevent(const struct device *dev, struct kobj_uevent_env *env) { char *buf = kzalloc(PAGE_SIZE, GFP_KERNEL); if (buf) { diff --git a/drivers/base/platform.c b/drivers/base/platform.c index b10a130cd433..262555b83bed 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -1353,9 +1353,9 @@ static int platform_match(struct device *dev, struct device_driver *drv) return (strcmp(pdev->name, drv->name) == 0); } -static int platform_uevent(struct device *dev, struct kobj_uevent_env *env) +static int platform_uevent(const struct device *dev, struct kobj_uevent_env *env) { - struct platform_device *pdev = to_platform_device(dev); + const struct platform_device *pdev = to_platform_device(dev); int rc; /* Some devices have extra OF data and an OF-style MODALIAS */ diff --git a/drivers/bcma/main.c b/drivers/bcma/main.c index 0a8469e0b13a..7b39f010bbb3 100644 --- a/drivers/bcma/main.c +++ b/drivers/bcma/main.c @@ -28,7 +28,7 @@ static DEFINE_MUTEX(bcma_buses_mutex); static int bcma_bus_match(struct device *dev, struct device_driver *drv); static int bcma_device_probe(struct device *dev); static void bcma_device_remove(struct device *dev); -static int bcma_device_uevent(struct device *dev, struct kobj_uevent_env *env); +static int bcma_device_uevent(const struct device *dev, struct kobj_uevent_env *env); static ssize_t manuf_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -627,9 +627,9 @@ static void bcma_device_remove(struct device *dev) put_device(dev); } -static int bcma_device_uevent(struct device *dev, struct kobj_uevent_env *env) +static int bcma_device_uevent(const struct device *dev, struct kobj_uevent_env *env) { - struct bcma_device *core = container_of(dev, struct bcma_device, dev); + const struct bcma_device *core = container_of_const(dev, struct bcma_device, dev); return add_uevent_var(env, "MODALIAS=bcma:m%04Xid%04Xrev%02Xcl%02X", diff --git a/drivers/bus/fsl-mc/fsl-mc-bus.c b/drivers/bus/fsl-mc/fsl-mc-bus.c index 774f307844b4..36cb091a33b4 100644 --- a/drivers/bus/fsl-mc/fsl-mc-bus.c +++ b/drivers/bus/fsl-mc/fsl-mc-bus.c @@ -124,9 +124,9 @@ out: /* * fsl_mc_bus_uevent - callback invoked when a device is added */ -static int fsl_mc_bus_uevent(struct device *dev, struct kobj_uevent_env *env) +static int fsl_mc_bus_uevent(const struct device *dev, struct kobj_uevent_env *env) { - struct fsl_mc_device *mc_dev = to_fsl_mc_device(dev); + const struct fsl_mc_device *mc_dev = to_fsl_mc_device(dev); if (add_uevent_var(env, "MODALIAS=fsl-mc:v%08Xd%s", mc_dev->obj_desc.vendor, diff --git a/drivers/bus/mhi/ep/main.c b/drivers/bus/mhi/ep/main.c index 1dc8a3557a46..4819369faa8b 100644 --- a/drivers/bus/mhi/ep/main.c +++ b/drivers/bus/mhi/ep/main.c @@ -1543,9 +1543,9 @@ void mhi_ep_driver_unregister(struct mhi_ep_driver *mhi_drv) } EXPORT_SYMBOL_GPL(mhi_ep_driver_unregister); -static int mhi_ep_uevent(struct device *dev, struct kobj_uevent_env *env) +static int mhi_ep_uevent(const struct device *dev, struct kobj_uevent_env *env) { - struct mhi_ep_device *mhi_dev = to_mhi_ep_device(dev); + const struct mhi_ep_device *mhi_dev = to_mhi_ep_device(dev); return add_uevent_var(env, "MODALIAS=" MHI_EP_DEVICE_MODALIAS_FMT, mhi_dev->name); diff --git a/drivers/bus/mhi/host/init.c b/drivers/bus/mhi/host/init.c index bf672de35131..770fc81b7e96 100644 --- a/drivers/bus/mhi/host/init.c +++ b/drivers/bus/mhi/host/init.c @@ -1395,9 +1395,9 @@ void mhi_driver_unregister(struct mhi_driver *mhi_drv) } EXPORT_SYMBOL_GPL(mhi_driver_unregister); -static int mhi_uevent(struct device *dev, struct kobj_uevent_env *env) +static int mhi_uevent(const struct device *dev, struct kobj_uevent_env *env) { - struct mhi_device *mhi_dev = to_mhi_device(dev); + const struct mhi_device *mhi_dev = to_mhi_device(dev); return add_uevent_var(env, "MODALIAS=" MHI_DEVICE_MODALIAS_FMT, mhi_dev->name); diff --git a/drivers/bus/mips_cdmm.c b/drivers/bus/mips_cdmm.c index fca0d0669aa9..554e1992edd4 100644 --- a/drivers/bus/mips_cdmm.c +++ b/drivers/bus/mips_cdmm.c @@ -67,9 +67,9 @@ static int mips_cdmm_match(struct device *dev, struct device_driver *drv) return mips_cdmm_lookup(cdrv->id_table, cdev) != NULL; } -static int mips_cdmm_uevent(struct device *dev, struct kobj_uevent_env *env) +static int mips_cdmm_uevent(const struct device *dev, struct kobj_uevent_env *env) { - struct mips_cdmm_device *cdev = to_mips_cdmm_device(dev); + const struct mips_cdmm_device *cdev = to_mips_cdmm_device(dev); int retval = 0; retval = add_uevent_var(env, "CDMM_CPU=%u", cdev->cpu); diff --git a/drivers/bus/sunxi-rsb.c b/drivers/bus/sunxi-rsb.c index a180af11e034..9aa99c369e48 100644 --- a/drivers/bus/sunxi-rsb.c +++ b/drivers/bus/sunxi-rsb.c @@ -172,7 +172,7 @@ static void sunxi_rsb_device_remove(struct device *dev) drv->remove(to_sunxi_rsb_device(dev)); } -static int sunxi_rsb_device_modalias(struct device *dev, struct kobj_uevent_env *env) +static int sunxi_rsb_device_modalias(const struct device *dev, struct kobj_uevent_env *env) { return of_device_uevent_modalias(dev, env); } diff --git a/drivers/cxl/core/memdev.c b/drivers/cxl/core/memdev.c index a38a0cc20d47..b75dd77df7ce 100644 --- a/drivers/cxl/core/memdev.c +++ b/drivers/cxl/core/memdev.c @@ -162,7 +162,7 @@ static const struct device_type cxl_memdev_type = { .groups = cxl_memdev_attribute_groups, }; -bool is_cxl_memdev(struct device *dev) +bool is_cxl_memdev(const struct device *dev) { return dev->type == &cxl_memdev_type; } diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c index b631a0520456..3f02dc135a12 100644 --- a/drivers/cxl/core/port.c +++ b/drivers/cxl/core/port.c @@ -38,7 +38,7 @@ static ssize_t devtype_show(struct device *dev, struct device_attribute *attr, } static DEVICE_ATTR_RO(devtype); -static int cxl_device_id(struct device *dev) +static int cxl_device_id(const struct device *dev) { if (dev->type == &cxl_nvdimm_bridge_type) return CXL_DEVICE_NVDIMM_BRIDGE; @@ -523,13 +523,13 @@ static const struct device_type cxl_port_type = { .groups = cxl_port_attribute_groups, }; -bool is_cxl_port(struct device *dev) +bool is_cxl_port(const struct device *dev) { return dev->type == &cxl_port_type; } EXPORT_SYMBOL_NS_GPL(is_cxl_port, CXL); -struct cxl_port *to_cxl_port(struct device *dev) +struct cxl_port *to_cxl_port(const struct device *dev) { if (dev_WARN_ONCE(dev, dev->type != &cxl_port_type, "not a cxl_port device\n")) @@ -1826,7 +1826,7 @@ void cxl_driver_unregister(struct cxl_driver *cxl_drv) } EXPORT_SYMBOL_NS_GPL(cxl_driver_unregister, CXL); -static int cxl_bus_uevent(struct device *dev, struct kobj_uevent_env *env) +static int cxl_bus_uevent(const struct device *dev, struct kobj_uevent_env *env) { return add_uevent_var(env, "MODALIAS=" CXL_MODALIAS_FMT, cxl_device_id(dev)); diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h index 1b1cf459ac77..c9e1b48a1a53 100644 --- a/drivers/cxl/cxl.h +++ b/drivers/cxl/cxl.h @@ -588,8 +588,8 @@ static inline bool is_cxl_root(struct cxl_port *port) return port->uport == port->dev.parent; } -bool is_cxl_port(struct device *dev); -struct cxl_port *to_cxl_port(struct device *dev); +bool is_cxl_port(const struct device *dev); +struct cxl_port *to_cxl_port(const struct device *dev); struct pci_bus; int devm_cxl_register_pci_bus(struct device *host, struct device *uport, struct pci_bus *bus); diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h index ab138004f644..6749f2afb1b7 100644 --- a/drivers/cxl/cxlmem.h +++ b/drivers/cxl/cxlmem.h @@ -72,7 +72,7 @@ cxled_to_memdev(struct cxl_endpoint_decoder *cxled) return to_cxl_memdev(port->uport); } -bool is_cxl_memdev(struct device *dev); +bool is_cxl_memdev(const struct device *dev); static inline bool is_cxl_endpoint(struct cxl_port *port) { return is_cxl_memdev(port->uport); diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c index 1dad813ee4a6..e3a384182fe7 100644 --- a/drivers/dax/bus.c +++ b/drivers/dax/bus.c @@ -18,7 +18,7 @@ struct dax_id { char dev_name[DAX_NAME_LEN]; }; -static int dax_bus_uevent(struct device *dev, struct kobj_uevent_env *env) +static int dax_bus_uevent(const struct device *dev, struct kobj_uevent_env *env) { /* * We only ever expect to handle device-dax instances, i.e. the diff --git a/drivers/eisa/eisa-bus.c b/drivers/eisa/eisa-bus.c index 65bffde137e3..713582cc27d1 100644 --- a/drivers/eisa/eisa-bus.c +++ b/drivers/eisa/eisa-bus.c @@ -127,9 +127,9 @@ static int eisa_bus_match(struct device *dev, struct device_driver *drv) return 0; } -static int eisa_bus_uevent(struct device *dev, struct kobj_uevent_env *env) +static int eisa_bus_uevent(const struct device *dev, struct kobj_uevent_env *env) { - struct eisa_device *edev = to_eisa_device(dev); + const struct eisa_device *edev = to_eisa_device(dev); add_uevent_var(env, "MODALIAS=" EISA_DEVICE_MODALIAS_FMT, edev->id.sig); return 0; diff --git a/drivers/firmware/arm_ffa/bus.c b/drivers/firmware/arm_ffa/bus.c index 99d439480612..f29d77ecf72d 100644 --- a/drivers/firmware/arm_ffa/bus.c +++ b/drivers/firmware/arm_ffa/bus.c @@ -56,9 +56,9 @@ static void ffa_device_remove(struct device *dev) ffa_drv->remove(to_ffa_dev(dev)); } -static int ffa_device_uevent(struct device *dev, struct kobj_uevent_env *env) +static int ffa_device_uevent(const struct device *dev, struct kobj_uevent_env *env) { - struct ffa_device *ffa_dev = to_ffa_dev(dev); + const struct ffa_device *ffa_dev = to_ffa_dev(dev); return add_uevent_var(env, "MODALIAS=arm_ffa:%04x:%pUb", ffa_dev->vm_id, &ffa_dev->uuid); diff --git a/drivers/fpga/dfl.c b/drivers/fpga/dfl.c index b9aae85ba930..4d32c98c82fc 100644 --- a/drivers/fpga/dfl.c +++ b/drivers/fpga/dfl.c @@ -293,9 +293,9 @@ static void dfl_bus_remove(struct device *dev) ddrv->remove(ddev); } -static int dfl_bus_uevent(struct device *dev, struct kobj_uevent_env *env) +static int dfl_bus_uevent(const struct device *dev, struct kobj_uevent_env *env) { - struct dfl_device *ddev = to_dfl_dev(dev); + const struct dfl_device *ddev = to_dfl_dev(dev); return add_uevent_var(env, "MODALIAS=dfl:t%04Xf%04X", ddev->type, ddev->feature_id); diff --git a/drivers/gpu/drm/drm_mipi_dsi.c b/drivers/gpu/drm/drm_mipi_dsi.c index 497ef4b6a90a..36c24c2b0899 100644 --- a/drivers/gpu/drm/drm_mipi_dsi.c +++ b/drivers/gpu/drm/drm_mipi_dsi.c @@ -62,9 +62,9 @@ static int mipi_dsi_device_match(struct device *dev, struct device_driver *drv) return 0; } -static int mipi_dsi_uevent(struct device *dev, struct kobj_uevent_env *env) +static int mipi_dsi_uevent(const struct device *dev, struct kobj_uevent_env *env) { - struct mipi_dsi_device *dsi = to_mipi_dsi_device(dev); + const struct mipi_dsi_device *dsi = to_mipi_dsi_device(dev); int err; err = of_device_uevent_modalias(dev, env); diff --git a/drivers/gpu/host1x/bus.c b/drivers/gpu/host1x/bus.c index bdee16a0bb8e..bc7271a00a94 100644 --- a/drivers/gpu/host1x/bus.c +++ b/drivers/gpu/host1x/bus.c @@ -338,7 +338,7 @@ static int host1x_device_match(struct device *dev, struct device_driver *drv) return strcmp(dev_name(dev), drv->name) == 0; } -static int host1x_device_uevent(struct device *dev, +static int host1x_device_uevent(const struct device *dev, struct kobj_uevent_env *env) { struct device_node *np = dev->parent->of_node; diff --git a/drivers/greybus/core.c b/drivers/greybus/core.c index e546c6431877..5714be740470 100644 --- a/drivers/greybus/core.c +++ b/drivers/greybus/core.c @@ -78,14 +78,14 @@ static int greybus_match_device(struct device *dev, struct device_driver *drv) return 0; } -static int greybus_uevent(struct device *dev, struct kobj_uevent_env *env) +static int greybus_uevent(const struct device *dev, struct kobj_uevent_env *env) { - struct gb_host_device *hd; - struct gb_module *module = NULL; - struct gb_interface *intf = NULL; - struct gb_control *control = NULL; - struct gb_bundle *bundle = NULL; - struct gb_svc *svc = NULL; + const struct gb_host_device *hd; + const struct gb_module *module = NULL; + const struct gb_interface *intf = NULL; + const struct gb_control *control = NULL; + const struct gb_bundle *bundle = NULL; + const struct gb_svc *svc = NULL; if (is_gb_host_device(dev)) { hd = to_gb_host_device(dev); diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 3e1803592bd4..a45e7034f085 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -2664,9 +2664,9 @@ static const struct attribute_group hid_dev_group = { }; __ATTRIBUTE_GROUPS(hid_dev); -static int hid_uevent(struct device *dev, struct kobj_uevent_env *env) +static int hid_uevent(const struct device *dev, struct kobj_uevent_env *env) { - struct hid_device *hdev = to_hid_device(dev); + const struct hid_device *hdev = to_hid_device(dev); if (add_uevent_var(env, "HID_ID=%04X:%08X:%08X", hdev->bus, hdev->vendor, hdev->product)) diff --git a/drivers/hid/intel-ish-hid/ishtp/bus.c b/drivers/hid/intel-ish-hid/ishtp/bus.c index f68aba8794fe..81385ab37fa9 100644 --- a/drivers/hid/intel-ish-hid/ishtp/bus.c +++ b/drivers/hid/intel-ish-hid/ishtp/bus.c @@ -361,7 +361,7 @@ static struct attribute *ishtp_cl_dev_attrs[] = { }; ATTRIBUTE_GROUPS(ishtp_cl_dev); -static int ishtp_cl_uevent(struct device *dev, struct kobj_uevent_env *env) +static int ishtp_cl_uevent(const struct device *dev, struct kobj_uevent_env *env) { if (add_uevent_var(env, "MODALIAS=" ISHTP_MODULE_PREFIX "%s", dev_name(dev))) return -ENOMEM; diff --git a/drivers/hsi/hsi_core.c b/drivers/hsi/hsi_core.c index 884066109699..8fda8f1d064d 100644 --- a/drivers/hsi/hsi_core.c +++ b/drivers/hsi/hsi_core.c @@ -30,7 +30,7 @@ static struct attribute *hsi_bus_dev_attrs[] = { }; ATTRIBUTE_GROUPS(hsi_bus_dev); -static int hsi_bus_uevent(struct device *dev, struct kobj_uevent_env *env) +static int hsi_bus_uevent(const struct device *dev, struct kobj_uevent_env *env) { add_uevent_var(env, "MODALIAS=hsi:%s", dev_name(dev)); diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 3146710d4ac6..f50aaa189df6 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -711,9 +711,9 @@ __ATTRIBUTE_GROUPS(vmbus_bus); * representation of the device guid (each byte of the guid will be * represented with two hex characters. */ -static int vmbus_uevent(struct device *device, struct kobj_uevent_env *env) +static int vmbus_uevent(const struct device *device, struct kobj_uevent_env *env) { - struct hv_device *dev = device_to_hv_device(device); + const struct hv_device *dev = device_to_hv_device(device); const char *format = "MODALIAS=vmbus:%*phN"; return add_uevent_var(env, format, UUID_SIZE, &dev->dev_type); diff --git a/drivers/input/serio/serio.c b/drivers/input/serio/serio.c index 15ce3202322f..767fc9efb4a8 100644 --- a/drivers/input/serio/serio.c +++ b/drivers/input/serio/serio.c @@ -895,9 +895,9 @@ static int serio_bus_match(struct device *dev, struct device_driver *drv) return err; \ } while (0) -static int serio_uevent(struct device *dev, struct kobj_uevent_env *env) +static int serio_uevent(const struct device *dev, struct kobj_uevent_env *env) { - struct serio *serio; + const struct serio *serio; if (!dev) return -ENODEV; diff --git a/drivers/ipack/ipack.c b/drivers/ipack/ipack.c index 74d449858a61..cc1ecfd49928 100644 --- a/drivers/ipack/ipack.c +++ b/drivers/ipack/ipack.c @@ -76,9 +76,9 @@ static void ipack_bus_remove(struct device *device) drv->ops->remove(dev); } -static int ipack_uevent(struct device *dev, struct kobj_uevent_env *env) +static int ipack_uevent(const struct device *dev, struct kobj_uevent_env *env) { - struct ipack_device *idev; + const struct ipack_device *idev; if (!dev) return -ENODEV; diff --git a/drivers/macintosh/macio_asic.c b/drivers/macintosh/macio_asic.c index 7f2b0107c733..211ed9aa9edc 100644 --- a/drivers/macintosh/macio_asic.c +++ b/drivers/macintosh/macio_asic.c @@ -128,7 +128,7 @@ static int macio_device_resume(struct device * dev) return 0; } -static int macio_device_modalias(struct device *dev, struct kobj_uevent_env *env) +static int macio_device_modalias(const struct device *dev, struct kobj_uevent_env *env) { return of_device_uevent_modalias(dev, env); } diff --git a/drivers/mcb/mcb-core.c b/drivers/mcb/mcb-core.c index b8ad4f16b4ac..978fdfc19a06 100644 --- a/drivers/mcb/mcb-core.c +++ b/drivers/mcb/mcb-core.c @@ -41,9 +41,9 @@ static int mcb_match(struct device *dev, struct device_driver *drv) return 0; } -static int mcb_uevent(struct device *dev, struct kobj_uevent_env *env) +static int mcb_uevent(const struct device *dev, struct kobj_uevent_env *env) { - struct mcb_device *mdev = to_mcb_device(dev); + const struct mcb_device *mdev = to_mcb_device(dev); int ret; ret = add_uevent_var(env, "MODALIAS=mcb:16z%03d", mdev->id); diff --git a/drivers/memstick/core/memstick.c b/drivers/memstick/core/memstick.c index 660df7d269fa..bf7667845459 100644 --- a/drivers/memstick/core/memstick.c +++ b/drivers/memstick/core/memstick.c @@ -57,10 +57,10 @@ static int memstick_bus_match(struct device *dev, struct device_driver *drv) return 0; } -static int memstick_uevent(struct device *dev, struct kobj_uevent_env *env) +static int memstick_uevent(const struct device *dev, struct kobj_uevent_env *env) { - struct memstick_dev *card = container_of(dev, struct memstick_dev, - dev); + const struct memstick_dev *card = container_of_const(dev, struct memstick_dev, + dev); if (add_uevent_var(env, "MEMSTICK_TYPE=%02X", card->id.type)) return -ENOMEM; diff --git a/drivers/misc/mei/bus.c b/drivers/misc/mei/bus.c index a81b890c7ee6..706ae85ca8f5 100644 --- a/drivers/misc/mei/bus.c +++ b/drivers/misc/mei/bus.c @@ -1227,9 +1227,9 @@ ATTRIBUTE_GROUPS(mei_cldev); * * Return: 0 on success -ENOMEM on when add_uevent_var fails */ -static int mei_cl_device_uevent(struct device *dev, struct kobj_uevent_env *env) +static int mei_cl_device_uevent(const struct device *dev, struct kobj_uevent_env *env) { - struct mei_cl_device *cldev = to_mei_cl_device(dev); + const struct mei_cl_device *cldev = to_mei_cl_device(dev); const uuid_le *uuid = mei_me_cl_uuid(cldev->me_cl); u8 version = mei_me_cl_ver(cldev->me_cl); diff --git a/drivers/misc/tifm_core.c b/drivers/misc/tifm_core.c index a3098fea3bf7..eee9b6581604 100644 --- a/drivers/misc/tifm_core.c +++ b/drivers/misc/tifm_core.c @@ -55,9 +55,9 @@ static int tifm_bus_match(struct device *dev, struct device_driver *drv) return 0; } -static int tifm_uevent(struct device *dev, struct kobj_uevent_env *env) +static int tifm_uevent(const struct device *dev, struct kobj_uevent_env *env) { - struct tifm_dev *sock = container_of(dev, struct tifm_dev, dev); + const struct tifm_dev *sock = container_of_const(dev, struct tifm_dev, dev); if (add_uevent_var(env, "TIFM_CARD_TYPE=%s", tifm_media_type_name(sock->type, 1))) return -ENOMEM; diff --git a/drivers/mmc/core/bus.c b/drivers/mmc/core/bus.c index 36679f4e9acc..2c3074a605fc 100644 --- a/drivers/mmc/core/bus.c +++ b/drivers/mmc/core/bus.c @@ -55,9 +55,9 @@ static struct attribute *mmc_dev_attrs[] = { ATTRIBUTE_GROUPS(mmc_dev); static int -mmc_bus_uevent(struct device *dev, struct kobj_uevent_env *env) +mmc_bus_uevent(const struct device *dev, struct kobj_uevent_env *env) { - struct mmc_card *card = mmc_dev_to_card(dev); + const struct mmc_card *card = mmc_dev_to_card(dev); const char *type; unsigned int i; int retval = 0; diff --git a/drivers/mmc/core/sdio_bus.c b/drivers/mmc/core/sdio_bus.c index babf21a0adeb..5ec4e4ca52f0 100644 --- a/drivers/mmc/core/sdio_bus.c +++ b/drivers/mmc/core/sdio_bus.c @@ -120,9 +120,9 @@ static int sdio_bus_match(struct device *dev, struct device_driver *drv) } static int -sdio_bus_uevent(struct device *dev, struct kobj_uevent_env *env) +sdio_bus_uevent(const struct device *dev, struct kobj_uevent_env *env) { - struct sdio_func *func = dev_to_sdio_func(dev); + const struct sdio_func *func = dev_to_sdio_func(dev); unsigned int i; if (add_uevent_var(env, diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index 16e021b477f0..22b352c57ca2 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -1000,7 +1000,7 @@ static int mdio_bus_match(struct device *dev, struct device_driver *drv) return 0; } -static int mdio_uevent(struct device *dev, struct kobj_uevent_env *env) +static int mdio_uevent(const struct device *dev, struct kobj_uevent_env *env) { int rc; diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c index 001636901dda..a78a25b87240 100644 --- a/drivers/net/xen-netback/xenbus.c +++ b/drivers/net/xen-netback/xenbus.c @@ -200,7 +200,7 @@ static void xenvif_debugfs_delif(struct xenvif *vif) * and vif variables to the environment, for the benefit of the vif-* hotplug * scripts. */ -static int netback_uevent(struct xenbus_device *xdev, +static int netback_uevent(const struct xenbus_device *xdev, struct kobj_uevent_env *env) { struct backend_info *be = dev_get_drvdata(&xdev->dev); diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c index b38d0355b0ac..92ce92fc9932 100644 --- a/drivers/nvdimm/bus.c +++ b/drivers/nvdimm/bus.c @@ -28,7 +28,7 @@ static int nvdimm_bus_major; struct class *nd_class; static DEFINE_IDA(nd_ida); -static int to_nd_device_type(struct device *dev) +static int to_nd_device_type(const struct device *dev) { if (is_nvdimm(dev)) return ND_DEVICE_DIMM; @@ -42,7 +42,7 @@ static int to_nd_device_type(struct device *dev) return 0; } -static int nvdimm_bus_uevent(struct device *dev, struct kobj_uevent_env *env) +static int nvdimm_bus_uevent(const struct device *dev, struct kobj_uevent_env *env) { return add_uevent_var(env, "MODALIAS=" ND_DEVICE_MODALIAS_FMT, to_nd_device_type(dev)); diff --git a/drivers/nvdimm/dax_devs.c b/drivers/nvdimm/dax_devs.c index 7f4a9d28b670..3bd61f245788 100644 --- a/drivers/nvdimm/dax_devs.c +++ b/drivers/nvdimm/dax_devs.c @@ -38,7 +38,7 @@ static const struct device_type nd_dax_device_type = { .groups = nd_pfn_attribute_groups, }; -bool is_nd_dax(struct device *dev) +bool is_nd_dax(const struct device *dev) { return dev ? dev->type == &nd_dax_device_type : false; } diff --git a/drivers/nvdimm/dimm_devs.c b/drivers/nvdimm/dimm_devs.c index 1fc081dcf631..fb571666d33b 100644 --- a/drivers/nvdimm/dimm_devs.c +++ b/drivers/nvdimm/dimm_devs.c @@ -572,7 +572,7 @@ static const struct device_type nvdimm_device_type = { .groups = nvdimm_attribute_groups, }; -bool is_nvdimm(struct device *dev) +bool is_nvdimm(const struct device *dev) { return dev->type == &nvdimm_device_type; } diff --git a/drivers/nvdimm/nd-core.h b/drivers/nvdimm/nd-core.h index cc86ee09d7c0..ca2bbc57e755 100644 --- a/drivers/nvdimm/nd-core.h +++ b/drivers/nvdimm/nd-core.h @@ -82,14 +82,14 @@ static inline void nvdimm_security_overwrite_query(struct work_struct *work) } #endif -bool is_nvdimm(struct device *dev); -bool is_nd_pmem(struct device *dev); -bool is_nd_volatile(struct device *dev); -static inline bool is_nd_region(struct device *dev) +bool is_nvdimm(const struct device *dev); +bool is_nd_pmem(const struct device *dev); +bool is_nd_volatile(const struct device *dev); +static inline bool is_nd_region(const struct device *dev) { return is_nd_pmem(dev) || is_nd_volatile(dev); } -static inline bool is_memory(struct device *dev) +static inline bool is_memory(const struct device *dev) { return is_nd_pmem(dev) || is_nd_volatile(dev); } diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h index 85ca5b4da3cf..cc166f99b005 100644 --- a/drivers/nvdimm/nd.h +++ b/drivers/nvdimm/nd.h @@ -599,7 +599,7 @@ static inline int nd_pfn_validate(struct nd_pfn *nd_pfn, const char *sig) struct nd_dax *to_nd_dax(struct device *dev); #if IS_ENABLED(CONFIG_NVDIMM_DAX) int nd_dax_probe(struct device *dev, struct nd_namespace_common *ndns); -bool is_nd_dax(struct device *dev); +bool is_nd_dax(const struct device *dev); struct device *nd_dax_create(struct nd_region *nd_region); #else static inline int nd_dax_probe(struct device *dev, @@ -608,7 +608,7 @@ static inline int nd_dax_probe(struct device *dev, return -ENODEV; } -static inline bool is_nd_dax(struct device *dev) +static inline bool is_nd_dax(const struct device *dev) { return false; } diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c index 83dbf398ea84..8f134d63af13 100644 --- a/drivers/nvdimm/region_devs.c +++ b/drivers/nvdimm/region_devs.c @@ -839,12 +839,12 @@ static const struct device_type nd_volatile_device_type = { .groups = nd_region_attribute_groups, }; -bool is_nd_pmem(struct device *dev) +bool is_nd_pmem(const struct device *dev) { return dev ? dev->type == &nd_pmem_device_type : false; } -bool is_nd_volatile(struct device *dev) +bool is_nd_volatile(const struct device *dev) { return dev ? dev->type == &nd_volatile_device_type : false; } diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index a2ceeacc33eb..d934c27491c4 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -1545,9 +1545,9 @@ void pci_dev_put(struct pci_dev *dev) } EXPORT_SYMBOL(pci_dev_put); -static int pci_uevent(struct device *dev, struct kobj_uevent_env *env) +static int pci_uevent(const struct device *dev, struct kobj_uevent_env *env) { - struct pci_dev *pdev; + const struct pci_dev *pdev; if (!dev) return -ENODEV; diff --git a/drivers/pcmcia/ds.c b/drivers/pcmcia/ds.c index ace133b9f7d4..c8087efa5e4a 100644 --- a/drivers/pcmcia/ds.c +++ b/drivers/pcmcia/ds.c @@ -927,9 +927,9 @@ static int pcmcia_bus_match(struct device *dev, struct device_driver *drv) return 0; } -static int pcmcia_bus_uevent(struct device *dev, struct kobj_uevent_env *env) +static int pcmcia_bus_uevent(const struct device *dev, struct kobj_uevent_env *env) { - struct pcmcia_device *p_dev; + const struct pcmcia_device *p_dev; int i; u32 hash[4] = { 0, 0, 0, 0}; diff --git a/drivers/platform/x86/wmi.c b/drivers/platform/x86/wmi.c index 46d1edc08f20..4fe7650dd014 100644 --- a/drivers/platform/x86/wmi.c +++ b/drivers/platform/x86/wmi.c @@ -797,9 +797,9 @@ static struct attribute *wmi_method_attrs[] = { }; ATTRIBUTE_GROUPS(wmi_method); -static int wmi_dev_uevent(struct device *dev, struct kobj_uevent_env *env) +static int wmi_dev_uevent(const struct device *dev, struct kobj_uevent_env *env) { - struct wmi_block *wblock = dev_to_wblock(dev); + const struct wmi_block *wblock = dev_to_wblock(dev); if (add_uevent_var(env, "MODALIAS=wmi:%pUL", &wblock->gblock.guid)) return -ENOMEM; diff --git a/drivers/rapidio/rio-driver.c b/drivers/rapidio/rio-driver.c index a72bb0a40fcf..e60e49769bed 100644 --- a/drivers/rapidio/rio-driver.c +++ b/drivers/rapidio/rio-driver.c @@ -204,9 +204,9 @@ static int rio_match_bus(struct device *dev, struct device_driver *drv) out:return 0; } -static int rio_uevent(struct device *dev, struct kobj_uevent_env *env) +static int rio_uevent(const struct device *dev, struct kobj_uevent_env *env) { - struct rio_dev *rdev; + const struct rio_dev *rdev; if (!dev) return -ENODEV; diff --git a/drivers/rpmsg/rpmsg_core.c b/drivers/rpmsg/rpmsg_core.c index d6dde00efdae..a2207c0cf432 100644 --- a/drivers/rpmsg/rpmsg_core.c +++ b/drivers/rpmsg/rpmsg_core.c @@ -492,9 +492,9 @@ static int rpmsg_dev_match(struct device *dev, struct device_driver *drv) return of_driver_match_device(dev, drv); } -static int rpmsg_uevent(struct device *dev, struct kobj_uevent_env *env) +static int rpmsg_uevent(const struct device *dev, struct kobj_uevent_env *env) { - struct rpmsg_device *rpdev = to_rpmsg_device(dev); + const struct rpmsg_device *rpdev = to_rpmsg_device(dev); int ret; ret = of_device_uevent_modalias(dev, env); diff --git a/drivers/s390/cio/css.c b/drivers/s390/cio/css.c index c7db95398500..0723921902da 100644 --- a/drivers/s390/cio/css.c +++ b/drivers/s390/cio/css.c @@ -1402,9 +1402,9 @@ static void css_shutdown(struct device *dev) sch->driver->shutdown(sch); } -static int css_uevent(struct device *dev, struct kobj_uevent_env *env) +static int css_uevent(const struct device *dev, struct kobj_uevent_env *env) { - struct subchannel *sch = to_subchannel(dev); + const struct subchannel *sch = to_subchannel(dev); int ret; ret = add_uevent_var(env, "ST=%01X", sch->st); diff --git a/drivers/s390/cio/device.c b/drivers/s390/cio/device.c index 9e0cf44ff9d4..b07ffd9ff117 100644 --- a/drivers/s390/cio/device.c +++ b/drivers/s390/cio/device.c @@ -80,7 +80,7 @@ ccw_bus_match (struct device * dev, struct device_driver * drv) * specified size. Return length of resulting string (excluding trailing '\0') * even if string doesn't fit buffer (snprintf semantics). */ static int snprint_alias(char *buf, size_t size, - struct ccw_device_id *id, const char *suffix) + const struct ccw_device_id *id, const char *suffix) { int len; @@ -101,10 +101,10 @@ static int snprint_alias(char *buf, size_t size, /* Set up environment variables for ccw device uevent. Return 0 on success, * non-zero otherwise. */ -static int ccw_uevent(struct device *dev, struct kobj_uevent_env *env) +static int ccw_uevent(const struct device *dev, struct kobj_uevent_env *env) { - struct ccw_device *cdev = to_ccwdev(dev); - struct ccw_device_id *id = &(cdev->id); + const struct ccw_device *cdev = to_ccwdev(dev); + const struct ccw_device_id *id = &(cdev->id); int ret; char modalias_buf[30]; diff --git a/drivers/s390/cio/scm.c b/drivers/s390/cio/scm.c index b6b4589c70bd..6b21ba68c1fe 100644 --- a/drivers/s390/cio/scm.c +++ b/drivers/s390/cio/scm.c @@ -37,7 +37,7 @@ static void scmdev_remove(struct device *dev) scmdrv->remove(scmdev); } -static int scmdev_uevent(struct device *dev, struct kobj_uevent_env *env) +static int scmdev_uevent(const struct device *dev, struct kobj_uevent_env *env) { return add_uevent_var(env, "MODALIAS=scm:scmdev"); } diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c index b02c631f3b71..f4cc1720156f 100644 --- a/drivers/s390/crypto/ap_bus.c +++ b/drivers/s390/crypto/ap_bus.c @@ -613,10 +613,10 @@ static int ap_bus_match(struct device *dev, struct device_driver *drv) * It sets up a single environment variable DEV_TYPE which contains the * hardware device type. */ -static int ap_uevent(struct device *dev, struct kobj_uevent_env *env) +static int ap_uevent(const struct device *dev, struct kobj_uevent_env *env) { int rc = 0; - struct ap_device *ap_dev = to_ap_dev(dev); + const struct ap_device *ap_dev = to_ap_dev(dev); /* Uevents from ap bus core don't need extensions to the env */ if (dev == ap_root_device) diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c index 981d1bab2120..a0dd711eb408 100644 --- a/drivers/scsi/scsi_sysfs.c +++ b/drivers/scsi/scsi_sysfs.c @@ -534,9 +534,9 @@ static int scsi_bus_match(struct device *dev, struct device_driver *gendrv) return (sdp->inq_periph_qual == SCSI_INQ_PQ_CON)? 1: 0; } -static int scsi_bus_uevent(struct device *dev, struct kobj_uevent_env *env) +static int scsi_bus_uevent(const struct device *dev, struct kobj_uevent_env *env) { - struct scsi_device *sdev; + const struct scsi_device *sdev; if (dev->type != &scsi_dev_type) return 0; diff --git a/drivers/slimbus/core.c b/drivers/slimbus/core.c index 219483b79c09..d43873bb5fe6 100644 --- a/drivers/slimbus/core.c +++ b/drivers/slimbus/core.c @@ -93,9 +93,9 @@ static void slim_device_remove(struct device *dev) } } -static int slim_device_uevent(struct device *dev, struct kobj_uevent_env *env) +static int slim_device_uevent(const struct device *dev, struct kobj_uevent_env *env) { - struct slim_device *sbdev = to_slim_device(dev); + const struct slim_device *sbdev = to_slim_device(dev); return add_uevent_var(env, "MODALIAS=slim:%s", dev_name(&sbdev->dev)); } diff --git a/drivers/soc/qcom/apr.c b/drivers/soc/qcom/apr.c index d51abb462ae5..30f81d6d9d9d 100644 --- a/drivers/soc/qcom/apr.c +++ b/drivers/soc/qcom/apr.c @@ -387,9 +387,9 @@ static void apr_device_remove(struct device *dev) spin_unlock(&apr->svcs_lock); } -static int apr_uevent(struct device *dev, struct kobj_uevent_env *env) +static int apr_uevent(const struct device *dev, struct kobj_uevent_env *env) { - struct apr_device *adev = to_apr_device(dev); + const struct apr_device *adev = to_apr_device(dev); int ret; ret = of_device_uevent_modalias(dev, env); diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 15f174f4e056..b85e41a9dc34 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -395,7 +395,7 @@ static int spi_match_device(struct device *dev, struct device_driver *drv) return strcmp(spi->modalias, drv->name) == 0; } -static int spi_uevent(struct device *dev, struct kobj_uevent_env *env) +static int spi_uevent(const struct device *dev, struct kobj_uevent_env *env) { const struct spi_device *spi = to_spi_device(dev); int rc; diff --git a/drivers/spmi/spmi.c b/drivers/spmi/spmi.c index 55381592bb5a..73551531ed43 100644 --- a/drivers/spmi/spmi.c +++ b/drivers/spmi/spmi.c @@ -366,7 +366,7 @@ static void spmi_drv_shutdown(struct device *dev) sdrv->shutdown(to_spmi_device(dev)); } -static int spmi_drv_uevent(struct device *dev, struct kobj_uevent_env *env) +static int spmi_drv_uevent(const struct device *dev, struct kobj_uevent_env *env) { int ret; diff --git a/drivers/ssb/main.c b/drivers/ssb/main.c index 8a93c83cb6f8..ab080cf26c9f 100644 --- a/drivers/ssb/main.c +++ b/drivers/ssb/main.c @@ -339,9 +339,9 @@ static int ssb_bus_match(struct device *dev, struct device_driver *drv) return 0; } -static int ssb_device_uevent(struct device *dev, struct kobj_uevent_env *env) +static int ssb_device_uevent(const struct device *dev, struct kobj_uevent_env *env) { - struct ssb_device *ssb_dev = dev_to_ssb_dev(dev); + const struct ssb_device *ssb_dev = dev_to_ssb_dev(dev); if (!dev) return -ENODEV; diff --git a/drivers/staging/greybus/gbphy.c b/drivers/staging/greybus/gbphy.c index 5a5c17a4519b..6a7d8cf2a1eb 100644 --- a/drivers/staging/greybus/gbphy.c +++ b/drivers/staging/greybus/gbphy.c @@ -71,14 +71,14 @@ static const struct device_type greybus_gbphy_dev_type = { .pm = &gb_gbphy_pm_ops, }; -static int gbphy_dev_uevent(struct device *dev, struct kobj_uevent_env *env) +static int gbphy_dev_uevent(const struct device *dev, struct kobj_uevent_env *env) { - struct gbphy_device *gbphy_dev = to_gbphy_dev(dev); - struct greybus_descriptor_cport *cport_desc = gbphy_dev->cport_desc; - struct gb_bundle *bundle = gbphy_dev->bundle; - struct gb_interface *intf = bundle->intf; - struct gb_module *module = intf->module; - struct gb_host_device *hd = intf->hd; + const struct gbphy_device *gbphy_dev = to_gbphy_dev(dev); + const struct greybus_descriptor_cport *cport_desc = gbphy_dev->cport_desc; + const struct gb_bundle *bundle = gbphy_dev->bundle; + const struct gb_interface *intf = bundle->intf; + const struct gb_module *module = intf->module; + const struct gb_host_device *hd = intf->hd; if (add_uevent_var(env, "BUS=%u", hd->bus_id)) return -ENOMEM; diff --git a/drivers/tee/tee_core.c b/drivers/tee/tee_core.c index 98da206cd761..452cbb8ad484 100644 --- a/drivers/tee/tee_core.c +++ b/drivers/tee/tee_core.c @@ -1207,7 +1207,7 @@ static int tee_client_device_match(struct device *dev, return 0; } -static int tee_client_device_uevent(struct device *dev, +static int tee_client_device_uevent(const struct device *dev, struct kobj_uevent_env *env) { uuid_t *dev_id = &to_tee_client_device(dev)->id.uuid; diff --git a/drivers/usb/common/ulpi.c b/drivers/usb/common/ulpi.c index d7c8461976ce..67b780b256a9 100644 --- a/drivers/usb/common/ulpi.c +++ b/drivers/usb/common/ulpi.c @@ -55,9 +55,9 @@ static int ulpi_match(struct device *dev, struct device_driver *driver) return 0; } -static int ulpi_uevent(struct device *dev, struct kobj_uevent_env *env) +static int ulpi_uevent(const struct device *dev, struct kobj_uevent_env *env) { - struct ulpi *ulpi = to_ulpi_dev(dev); + const struct ulpi *ulpi = to_ulpi_dev(dev); int ret; ret = of_device_uevent_modalias(dev, env); diff --git a/drivers/usb/core/driver.c b/drivers/usb/core/driver.c index 7e7e119c253f..a0e076c6f3a4 100644 --- a/drivers/usb/core/driver.c +++ b/drivers/usb/core/driver.c @@ -899,14 +899,14 @@ static int usb_device_match(struct device *dev, struct device_driver *drv) return 0; } -static int usb_uevent(struct device *dev, struct kobj_uevent_env *env) +static int usb_uevent(const struct device *dev, struct kobj_uevent_env *env) { - struct usb_device *usb_dev; + const struct usb_device *usb_dev; if (is_usb_device(dev)) { usb_dev = to_usb_device(dev); } else if (is_usb_interface(dev)) { - struct usb_interface *intf = to_usb_interface(dev); + const struct usb_interface *intf = to_usb_interface(dev); usb_dev = interface_to_usbdev(intf); } else { diff --git a/drivers/usb/typec/bus.c b/drivers/usb/typec/bus.c index 31c2a3130cad..dbcb96151558 100644 --- a/drivers/usb/typec/bus.c +++ b/drivers/usb/typec/bus.c @@ -321,9 +321,9 @@ static int typec_match(struct device *dev, struct device_driver *driver) return 0; } -static int typec_uevent(struct device *dev, struct kobj_uevent_env *env) +static int typec_uevent(const struct device *dev, struct kobj_uevent_env *env) { - struct typec_altmode *altmode = to_typec_altmode(dev); + const struct typec_altmode *altmode = to_typec_altmode(dev); if (add_uevent_var(env, "SVID=%04X", altmode->svid)) return -ENOMEM; diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c index b9a80aedee1b..3893dc29eb26 100644 --- a/drivers/virtio/virtio.c +++ b/drivers/virtio/virtio.c @@ -95,9 +95,9 @@ static int virtio_dev_match(struct device *_dv, struct device_driver *_dr) return 0; } -static int virtio_uevent(struct device *_dv, struct kobj_uevent_env *env) +static int virtio_uevent(const struct device *_dv, struct kobj_uevent_env *env) { - struct virtio_device *dev = dev_to_virtio(_dv); + const struct virtio_device *dev = dev_to_virtio(_dv); return add_uevent_var(env, "MODALIAS=virtio:d%08Xv%08X", dev->id.device, dev->id.vendor); diff --git a/drivers/w1/w1.c b/drivers/w1/w1.c index 4a2ddf730a3a..9d199fed9628 100644 --- a/drivers/w1/w1.c +++ b/drivers/w1/w1.c @@ -170,7 +170,7 @@ static struct w1_family w1_default_family = { .fops = &w1_default_fops, }; -static int w1_uevent(struct device *dev, struct kobj_uevent_env *env); +static int w1_uevent(const struct device *dev, struct kobj_uevent_env *env); static struct bus_type w1_bus_type = { .name = "w1", @@ -577,11 +577,11 @@ void w1_destroy_master_attributes(struct w1_master *master) sysfs_remove_group(&master->dev.kobj, &w1_master_defattr_group); } -static int w1_uevent(struct device *dev, struct kobj_uevent_env *env) +static int w1_uevent(const struct device *dev, struct kobj_uevent_env *env) { - struct w1_master *md = NULL; - struct w1_slave *sl = NULL; - char *event_owner, *name; + const struct w1_master *md = NULL; + const struct w1_slave *sl = NULL; + const char *event_owner, *name; int err = 0; if (dev->driver == &w1_master_driver) { diff --git a/drivers/xen/pvcalls-back.c b/drivers/xen/pvcalls-back.c index 0d4f8f4f4948..8bf19bca5d3d 100644 --- a/drivers/xen/pvcalls-back.c +++ b/drivers/xen/pvcalls-back.c @@ -1185,7 +1185,7 @@ static void pvcalls_back_remove(struct xenbus_device *dev) { } -static int pvcalls_back_uevent(struct xenbus_device *xdev, +static int pvcalls_back_uevent(const struct xenbus_device *xdev, struct kobj_uevent_env *env) { return 0; diff --git a/drivers/xen/xenbus/xenbus_probe_backend.c b/drivers/xen/xenbus/xenbus_probe_backend.c index 9c09f89d8278..da96c260e26b 100644 --- a/drivers/xen/xenbus/xenbus_probe_backend.c +++ b/drivers/xen/xenbus/xenbus_probe_backend.c @@ -92,12 +92,12 @@ static int backend_bus_id(char bus_id[XEN_BUS_ID_SIZE], const char *nodename) return 0; } -static int xenbus_uevent_backend(struct device *dev, +static int xenbus_uevent_backend(const struct device *dev, struct kobj_uevent_env *env) { - struct xenbus_device *xdev; - struct xenbus_driver *drv; - struct xen_bus_type *bus; + const struct xenbus_device *xdev; + const struct xenbus_driver *drv; + const struct xen_bus_type *bus; DPRINTK(""); diff --git a/drivers/xen/xenbus/xenbus_probe_frontend.c b/drivers/xen/xenbus/xenbus_probe_frontend.c index f44d5a64351e..3f3836cb7279 100644 --- a/drivers/xen/xenbus/xenbus_probe_frontend.c +++ b/drivers/xen/xenbus/xenbus_probe_frontend.c @@ -73,10 +73,10 @@ static int xenbus_probe_frontend(struct xen_bus_type *bus, const char *type, return err; } -static int xenbus_uevent_frontend(struct device *_dev, +static int xenbus_uevent_frontend(const struct device *_dev, struct kobj_uevent_env *env) { - struct xenbus_device *dev = to_xenbus_device(_dev); + const struct xenbus_device *dev = to_xenbus_device(_dev); if (add_uevent_var(env, "MODALIAS=xen:%s", dev->devicetype)) return -ENOMEM; diff --git a/drivers/zorro/zorro-driver.c b/drivers/zorro/zorro-driver.c index 96f068830549..025edfccedcf 100644 --- a/drivers/zorro/zorro-driver.c +++ b/drivers/zorro/zorro-driver.c @@ -130,9 +130,9 @@ static int zorro_bus_match(struct device *dev, struct device_driver *drv) return !!zorro_match_device(ids, z); } -static int zorro_uevent(struct device *dev, struct kobj_uevent_env *env) +static int zorro_uevent(const struct device *dev, struct kobj_uevent_env *env) { - struct zorro_dev *z; + const struct zorro_dev *z; if (!dev) return -ENODEV; diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h index 7b4a48b5159b..87e4d029c915 100644 --- a/include/linux/device/bus.h +++ b/include/linux/device/bus.h @@ -90,7 +90,7 @@ struct bus_type { const struct attribute_group **drv_groups; int (*match)(struct device *dev, struct device_driver *drv); - int (*uevent)(struct device *dev, struct kobj_uevent_env *env); + int (*uevent)(const struct device *dev, struct kobj_uevent_env *env); int (*probe)(struct device *dev); void (*sync_state)(struct device *dev); void (*remove)(struct device *dev); diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 9a32495fbb1f..2edf7f09239e 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -223,7 +223,7 @@ struct spi_device { static_assert((SPI_MODE_KERNEL_MASK & SPI_MODE_USER_MASK) == 0, "SPI_MODE_USER_MASK & SPI_MODE_KERNEL_MASK must not overlap"); -static inline struct spi_device *to_spi_device(struct device *dev) +static inline struct spi_device *to_spi_device(const struct device *dev) { return dev ? container_of(dev, struct spi_device, dev) : NULL; } diff --git a/include/linux/ssb/ssb.h b/include/linux/ssb/ssb.h index f9b53acb4e02..1f326da289d3 100644 --- a/include/linux/ssb/ssb.h +++ b/include/linux/ssb/ssb.h @@ -285,7 +285,7 @@ struct ssb_device { /* Go from struct device to struct ssb_device. */ static inline -struct ssb_device * dev_to_ssb_dev(struct device *dev) +struct ssb_device * dev_to_ssb_dev(const struct device *dev) { struct __ssb_dev_wrapper *wrap; wrap = container_of(dev, struct __ssb_dev_wrapper, dev); diff --git a/include/sound/hdaudio.h b/include/sound/hdaudio.h index a6872537724d..1c45664e0e5a 100644 --- a/include/sound/hdaudio.h +++ b/include/sound/hdaudio.h @@ -123,7 +123,7 @@ void snd_hdac_device_exit(struct hdac_device *dev); int snd_hdac_device_register(struct hdac_device *codec); void snd_hdac_device_unregister(struct hdac_device *codec); int snd_hdac_device_set_chip_name(struct hdac_device *codec, const char *name); -int snd_hdac_codec_modalias(struct hdac_device *hdac, char *buf, size_t size); +int snd_hdac_codec_modalias(const struct hdac_device *hdac, char *buf, size_t size); int snd_hdac_refresh_widgets(struct hdac_device *codec); diff --git a/include/xen/xenbus.h b/include/xen/xenbus.h index ef0505e72c27..ac22cf08c09f 100644 --- a/include/xen/xenbus.h +++ b/include/xen/xenbus.h @@ -117,7 +117,7 @@ struct xenbus_driver { void (*remove)(struct xenbus_device *dev); int (*suspend)(struct xenbus_device *dev); int (*resume)(struct xenbus_device *dev); - int (*uevent)(struct xenbus_device *, struct kobj_uevent_env *); + int (*uevent)(const struct xenbus_device *, struct kobj_uevent_env *); struct device_driver driver; int (*read_otherend_details)(struct xenbus_device *dev); int (*is_ready)(struct xenbus_device *dev); diff --git a/sound/aoa/soundbus/core.c b/sound/aoa/soundbus/core.c index c9579d97fbab..39fb8fe4e6ab 100644 --- a/sound/aoa/soundbus/core.c +++ b/sound/aoa/soundbus/core.c @@ -55,10 +55,10 @@ static int soundbus_probe(struct device *dev) } -static int soundbus_uevent(struct device *dev, struct kobj_uevent_env *env) +static int soundbus_uevent(const struct device *dev, struct kobj_uevent_env *env) { - struct soundbus_dev * soundbus_dev; - struct platform_device * of; + const struct soundbus_dev * soundbus_dev; + const struct platform_device * of; const char *compat; int retval = 0; int cplen, seen = 0; diff --git a/sound/hda/hda_bus_type.c b/sound/hda/hda_bus_type.c index eea6b63f8305..4cd94178df9f 100644 --- a/sound/hda/hda_bus_type.c +++ b/sound/hda/hda_bus_type.c @@ -65,7 +65,7 @@ static int hda_bus_match(struct device *dev, struct device_driver *drv) return 1; } -static int hda_uevent(struct device *dev, struct kobj_uevent_env *env) +static int hda_uevent(const struct device *dev, struct kobj_uevent_env *env) { char modalias[32]; diff --git a/sound/hda/hdac_device.c b/sound/hda/hdac_device.c index b7e5032b61c9..accc9d279ce5 100644 --- a/sound/hda/hdac_device.c +++ b/sound/hda/hdac_device.c @@ -204,7 +204,7 @@ EXPORT_SYMBOL_GPL(snd_hdac_device_set_chip_name); * * Returns the size of string, like snprintf(), or a negative error code. */ -int snd_hdac_codec_modalias(struct hdac_device *codec, char *buf, size_t size) +int snd_hdac_codec_modalias(const struct hdac_device *codec, char *buf, size_t size) { return scnprintf(buf, size, "hdaudio:v%08Xr%08Xa%02X\n", codec->vendor_id, codec->revision_id, codec->type); -- cgit v1.2.3 From 56d5f362ad0f8f60bc7c6fd5d7bc2b528d6963f5 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 11 Jan 2023 12:30:18 +0100 Subject: kobject: kset_uevent_ops: make uevent() callback take a const * The uevent() callback in struct kset_uevent_ops does not modify the kobject passed into it, so make the pointer const to enforce this restriction. When doing so, fix up all existing uevent() callbacks to have the correct signature to preserve the build. Cc: Christine Caulfield Cc: David Teigland Cc: Bob Peterson Cc: Andreas Gruenbacher Acked-by: Rafael J. Wysocki Acked-by: Hans de Goede Link: https://lore.kernel.org/r/20230111113018.459199-17-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/base/core.c | 4 ++-- fs/dlm/lockspace.c | 4 ++-- fs/gfs2/sys.c | 6 +++--- include/linux/kobject.h | 2 +- 4 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/core.c b/drivers/base/core.c index e39b6fa0eda6..e4b18f7ac58a 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -2387,9 +2387,9 @@ static const char *dev_uevent_name(const struct kobject *kobj) return NULL; } -static int dev_uevent(struct kobject *kobj, struct kobj_uevent_env *env) +static int dev_uevent(const struct kobject *kobj, struct kobj_uevent_env *env) { - struct device *dev = kobj_to_dev(kobj); + const struct device *dev = kobj_to_dev(kobj); int retval = 0; /* add device node properties if present */ diff --git a/fs/dlm/lockspace.c b/fs/dlm/lockspace.c index d0b4e2181a5f..9b6cfc4c30e3 100644 --- a/fs/dlm/lockspace.c +++ b/fs/dlm/lockspace.c @@ -215,9 +215,9 @@ static int do_uevent(struct dlm_ls *ls, int in) return ls->ls_uevent_result; } -static int dlm_uevent(struct kobject *kobj, struct kobj_uevent_env *env) +static int dlm_uevent(const struct kobject *kobj, struct kobj_uevent_env *env) { - struct dlm_ls *ls = container_of(kobj, struct dlm_ls, ls_kobj); + const struct dlm_ls *ls = container_of(kobj, struct dlm_ls, ls_kobj); add_uevent_var(env, "LOCKSPACE=%s", ls->ls_name); return 0; diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c index d87ea98cf535..d8dfabb0bc12 100644 --- a/fs/gfs2/sys.c +++ b/fs/gfs2/sys.c @@ -767,10 +767,10 @@ void gfs2_sys_fs_del(struct gfs2_sbd *sdp) wait_for_completion(&sdp->sd_kobj_unregister); } -static int gfs2_uevent(struct kobject *kobj, struct kobj_uevent_env *env) +static int gfs2_uevent(const struct kobject *kobj, struct kobj_uevent_env *env) { - struct gfs2_sbd *sdp = container_of(kobj, struct gfs2_sbd, sd_kobj); - struct super_block *s = sdp->sd_vfs; + const struct gfs2_sbd *sdp = container_of(kobj, struct gfs2_sbd, sd_kobj); + const struct super_block *s = sdp->sd_vfs; add_uevent_var(env, "LOCKTABLE=%s", sdp->sd_table_name); add_uevent_var(env, "LOCKPROTO=%s", sdp->sd_proto_name); diff --git a/include/linux/kobject.h b/include/linux/kobject.h index 58a5b75612e3..bdab370a24f4 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -137,7 +137,7 @@ struct kobj_uevent_env { struct kset_uevent_ops { int (* const filter)(const struct kobject *kobj); const char *(* const name)(const struct kobject *kobj); - int (* const uevent)(struct kobject *kobj, struct kobj_uevent_env *env); + int (* const uevent)(const struct kobject *kobj, struct kobj_uevent_env *env); }; struct kobj_attribute { -- cgit v1.2.3 From 37fe46051dc94c589b616018ba9d2fd4bacfbd8a Mon Sep 17 00:00:00 2001 From: Serge Semin Date: Fri, 13 Jan 2023 20:13:43 +0300 Subject: dmaengine: Fix dma_slave_config.dst_addr description The dst_addr member of the dma_slave_config structure has been mistakenly marked as ignored if the *source* address belongs to the memory. That is relevant to the src_addr field of the structure, while the dst_addr field contains a destination device address that should be ignored if the destination is the CPU memory. Correct the @dst_addr description accordingly. Link: https://lore.kernel.org/r/20230113171409.30470-2-Sergey.Semin@baikalelectronics.ru Tested-by: Manivannan Sadhasivam Signed-off-by: Serge Semin Signed-off-by: Lorenzo Pieralisi Signed-off-by: Bjorn Helgaas Reviewed-by: Manivannan Sadhasivam Acked-by: Vinod Koul --- include/linux/dmaengine.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index c923f4e60f24..0c020682d894 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -394,7 +394,7 @@ enum dma_slave_buswidth { * should be read (RX), if the source is memory this argument is * ignored. * @dst_addr: this is the physical address where DMA slave data - * should be written (TX), if the source is memory this argument + * should be written (TX), if the destination is memory this argument * is ignored. * @src_addr_width: this is the width in bytes of the source (RX) * register where DMA data shall be read. If the source -- cgit v1.2.3 From 002bbaa2f60e07d465f92a163365569481d34108 Mon Sep 17 00:00:00 2001 From: Serge Semin Date: Fri, 13 Jan 2023 20:13:45 +0300 Subject: dmaengine: dw-edma: Convert ll/dt phys address to PCI bus/DMA address The dw_edma_region.paddr field should be a memory base address visible by the DW eDMA controller. If the DMA engine is embedded in the DW PCIe Host/Endpoint controller, the address should belong to the Local CPU/ Application memory. If eDMA is remotely accessible across the PCI bus via PCI memory IOs, the address should be part of the PCI bus memory space. The latter case hasn't been well covered in the corresponding glue-driver. Since pci_dev.resource[] contains resources defined in the CPU memory space, they need to be converted to the PCI bus address space. Convert the LL, DT and CSRs PCI memory ranges with pci_bus_address(). In addition, extend the dw_edma_region.paddr field size. The field normally contains a memory range base address to be set in the DW eDMA Linked-List pointer register or as a base address of the Linked-List data buffer. In accordance with [1] the LL range is supposed to be created in the Local CPU/Application memory, but depending on the DW eDMA utilization the memory can be created as a part of the PCI bus address space (as in the case of the DW PCIe Endpoint prototype kit). In the former case dw_edma_region.paddr should be a dma_addr_t, while in the latter one it should be a pci_bus_addr_t. Since the corresponding CSRs are always 64 bits wide, convert dw_edma_region.paddr to be u64, and let the client make sure it has a valid address visible by the DW eDMA controller. For instance, the DW eDMA PCIe glue-driver initializes the field with addresses from the PCI bus memory space. [1] DesignWare Cores PCI Express Controller Databook - DWC PCIe Root Port, v.5.40a, March 2019, p.1103 Link: https://lore.kernel.org/r/20230113171409.30470-4-Sergey.Semin@baikalelectronics.ru Fixes: 41aaff2a2ac0 ("dmaengine: Add Synopsys eDMA IP PCIe glue-logic") Tested-by: Manivannan Sadhasivam Signed-off-by: Serge Semin Signed-off-by: Lorenzo Pieralisi Signed-off-by: Bjorn Helgaas Reviewed-by: Manivannan Sadhasivam Acked-by: Vinod Koul --- drivers/dma/dw-edma/dw-edma-pcie.c | 8 ++++---- include/linux/dma/edma.h | 2 +- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/dma/dw-edma/dw-edma-pcie.c b/drivers/dma/dw-edma/dw-edma-pcie.c index d6b5e2463884..04c95cba1244 100644 --- a/drivers/dma/dw-edma/dw-edma-pcie.c +++ b/drivers/dma/dw-edma/dw-edma-pcie.c @@ -231,7 +231,7 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev, return -ENOMEM; ll_region->vaddr += ll_block->off; - ll_region->paddr = pdev->resource[ll_block->bar].start; + ll_region->paddr = pci_bus_address(pdev, ll_block->bar); ll_region->paddr += ll_block->off; ll_region->sz = ll_block->sz; @@ -240,7 +240,7 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev, return -ENOMEM; dt_region->vaddr += dt_block->off; - dt_region->paddr = pdev->resource[dt_block->bar].start; + dt_region->paddr = pci_bus_address(pdev, dt_block->bar); dt_region->paddr += dt_block->off; dt_region->sz = dt_block->sz; } @@ -256,7 +256,7 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev, return -ENOMEM; ll_region->vaddr += ll_block->off; - ll_region->paddr = pdev->resource[ll_block->bar].start; + ll_region->paddr = pci_bus_address(pdev, ll_block->bar); ll_region->paddr += ll_block->off; ll_region->sz = ll_block->sz; @@ -265,7 +265,7 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev, return -ENOMEM; dt_region->vaddr += dt_block->off; - dt_region->paddr = pdev->resource[dt_block->bar].start; + dt_region->paddr = pci_bus_address(pdev, dt_block->bar); dt_region->paddr += dt_block->off; dt_region->sz = dt_block->sz; } diff --git a/include/linux/dma/edma.h b/include/linux/dma/edma.h index 7d8062e9c544..a864978ddd27 100644 --- a/include/linux/dma/edma.h +++ b/include/linux/dma/edma.h @@ -18,7 +18,7 @@ struct dw_edma; struct dw_edma_region { - phys_addr_t paddr; + u64 paddr; void __iomem *vaddr; size_t sz; }; -- cgit v1.2.3 From 993d57bbaacf7ad7a742e51cb717e21e0eb4ef72 Mon Sep 17 00:00:00 2001 From: Serge Semin Date: Fri, 13 Jan 2023 20:13:49 +0300 Subject: dmaengine: dw-edma: Add CPU to PCI bus address translation Since 9575632052ba ("dmaengine: make slave address physical"), the source and destination addresses of the DMA slave device have been converted to physical addresses in the CPU address space. It's the DMA device driver's responsibility to convert them to the DMA bus address space. In case of the DW eDMA device, the source or destination peripheral (slave) devices reside in PCI bus space. Thus we need to perform the PCI Host/Endpoint windows- based (i.e. DT "ranges" property) address translation; otherwise the eDMA transactions won't work as expected (or can be even harmful) if the CPU and PCI address spaces don't match. Note 1: Even though the DMA interleaved template has both source and destination addresses declared as dma_addr_t, only the CPU memory range should be mapped to be seen by the DMA device since it's a subject of the DMA getting towards the system side. The device part must not be mapped since the slave device resides in the PCI bus space, which isn't affected by IOMMUs or iATU translations. DW PCIe eDMA generates corresponding MWr/MRd TLPs on its own. Note 2: This functionality is mainly required for the remote eDMA setup since the CPU address must be manually translated into the PCI bus space before being written to LLI.{SAR,DAR}. If eDMA is embedded in the locally accessible DW PCIe Root Port/Endpoint, software-based translation isn't required since hardware will translate it via the Outbound iATU as long as the DMA_BYPASS flag is cleared. If DMA_BYPASS is set or there is no Outbound iATU entry that contains the SAR or DAR (for Read and Write channel respectively), there won't be any translation performed but DMA will proceed with the corresponding source/destination address as-is. Link: https://lore.kernel.org/r/20230113171409.30470-8-Sergey.Semin@baikalelectronics.ru Tested-by: Manivannan Sadhasivam Signed-off-by: Serge Semin Signed-off-by: Lorenzo Pieralisi Signed-off-by: Bjorn Helgaas Reviewed-by: Manivannan Sadhasivam Acked-by: Vinod Koul --- drivers/dma/dw-edma/dw-edma-core.c | 18 +++++++++++++++++- include/linux/dma/edma.h | 15 +++++++++++++++ 2 files changed, 32 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/dma/dw-edma/dw-edma-core.c b/drivers/dma/dw-edma/dw-edma-core.c index d5c4192141ef..6c9f95a8e397 100644 --- a/drivers/dma/dw-edma/dw-edma-core.c +++ b/drivers/dma/dw-edma/dw-edma-core.c @@ -39,6 +39,17 @@ struct dw_edma_desc *vd2dw_edma_desc(struct virt_dma_desc *vd) return container_of(vd, struct dw_edma_desc, vd); } +static inline +u64 dw_edma_get_pci_address(struct dw_edma_chan *chan, phys_addr_t cpu_addr) +{ + struct dw_edma_chip *chip = chan->dw->chip; + + if (chip->ops->pci_address) + return chip->ops->pci_address(chip->dev, cpu_addr); + + return cpu_addr; +} + static struct dw_edma_burst *dw_edma_alloc_burst(struct dw_edma_chunk *chunk) { struct dw_edma_burst *burst; @@ -327,11 +338,11 @@ dw_edma_device_transfer(struct dw_edma_transfer *xfer) { struct dw_edma_chan *chan = dchan2dw_edma_chan(xfer->dchan); enum dma_transfer_direction dir = xfer->direction; - phys_addr_t src_addr, dst_addr; struct scatterlist *sg = NULL; struct dw_edma_chunk *chunk; struct dw_edma_burst *burst; struct dw_edma_desc *desc; + u64 src_addr, dst_addr; size_t fsz = 0; u32 cnt = 0; int i; @@ -406,6 +417,11 @@ dw_edma_device_transfer(struct dw_edma_transfer *xfer) dst_addr = chan->config.dst_addr; } + if (dir == DMA_DEV_TO_MEM) + src_addr = dw_edma_get_pci_address(chan, (phys_addr_t)src_addr); + else + dst_addr = dw_edma_get_pci_address(chan, (phys_addr_t)dst_addr); + if (xfer->type == EDMA_XFER_CYCLIC) { cnt = xfer->xfer.cyclic.cnt; } else if (xfer->type == EDMA_XFER_SCATTER_GATHER) { diff --git a/include/linux/dma/edma.h b/include/linux/dma/edma.h index a864978ddd27..07a23ecc834f 100644 --- a/include/linux/dma/edma.h +++ b/include/linux/dma/edma.h @@ -23,8 +23,23 @@ struct dw_edma_region { size_t sz; }; +/** + * struct dw_edma_core_ops - platform-specific eDMA methods + * @irq_vector: Get IRQ number of the passed eDMA channel. Note the + * method accepts the channel id in the end-to-end + * numbering with the eDMA write channels being placed + * first in the row. + * @pci_address: Get PCIe bus address corresponding to the passed CPU + * address. Note there is no need in specifying this + * function if the address translation is performed by + * the DW PCIe RP/EP controller with the DW eDMA device in + * subject and DMA_BYPASS isn't set for all the outbound + * iATU windows. That will be done by the controller + * automatically. + */ struct dw_edma_core_ops { int (*irq_vector)(struct device *dev, unsigned int nr); + u64 (*pci_address)(struct device *dev, phys_addr_t cpu_addr); }; enum dw_edma_map_format { -- cgit v1.2.3 From 18b1746bddf5e7f6b2618966596d9517172a5cd7 Mon Sep 17 00:00:00 2001 From: Aharon Landau Date: Thu, 26 Jan 2023 00:28:03 +0200 Subject: RDMA/mlx5: Remove implicit ODP cache entry Implicit ODP mkey doesn't have unique properties. It shares the same properties as the order 18 cache entry. There is no need to devote a special entry for that. Link: https://lore.kernel.org/r/20230125222807.6921-3-michaelgur@nvidia.com Signed-off-by: Aharon Landau Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/mlx5/odp.c | 20 +++++--------------- include/linux/mlx5/driver.h | 1 - 2 files changed, 5 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c index 8a78580a2a72..72044f8ec883 100644 --- a/drivers/infiniband/hw/mlx5/odp.c +++ b/drivers/infiniband/hw/mlx5/odp.c @@ -405,6 +405,7 @@ static void mlx5_ib_page_fault_resume(struct mlx5_ib_dev *dev, static struct mlx5_ib_mr *implicit_get_child_mr(struct mlx5_ib_mr *imr, unsigned long idx) { + int order = order_base_2(MLX5_IMR_MTT_ENTRIES); struct mlx5_ib_dev *dev = mr_to_mdev(imr); struct ib_umem_odp *odp; struct mlx5_ib_mr *mr; @@ -417,7 +418,8 @@ static struct mlx5_ib_mr *implicit_get_child_mr(struct mlx5_ib_mr *imr, if (IS_ERR(odp)) return ERR_CAST(odp); - mr = mlx5_mr_cache_alloc(dev, &dev->cache.ent[MLX5_IMR_MTT_CACHE_ENTRY], + BUILD_BUG_ON(order > MKEY_CACHE_LAST_STD_ENTRY); + mr = mlx5_mr_cache_alloc(dev, &dev->cache.ent[order], imr->access_flags); if (IS_ERR(mr)) { ib_umem_odp_release(odp); @@ -1591,20 +1593,8 @@ void mlx5_odp_init_mkey_cache_entry(struct mlx5_cache_ent *ent) { if (!(ent->dev->odp_caps.general_caps & IB_ODP_SUPPORT_IMPLICIT)) return; - - switch (ent->order - 2) { - case MLX5_IMR_MTT_CACHE_ENTRY: - ent->ndescs = MLX5_IMR_MTT_ENTRIES; - ent->access_mode = MLX5_MKC_ACCESS_MODE_MTT; - ent->limit = 0; - break; - - case MLX5_IMR_KSM_CACHE_ENTRY: - ent->ndescs = mlx5_imr_ksm_entries; - ent->access_mode = MLX5_MKC_ACCESS_MODE_KSM; - ent->limit = 0; - break; - } + ent->ndescs = mlx5_imr_ksm_entries; + ent->access_mode = MLX5_MKC_ACCESS_MODE_KSM; } static const struct ib_device_ops mlx5_ib_dev_odp_ops = { diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index d476255c9a3f..f79c20d50eb4 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -734,7 +734,6 @@ enum { enum { MKEY_CACHE_LAST_STD_ENTRY = 20, - MLX5_IMR_MTT_CACHE_ENTRY, MLX5_IMR_KSM_CACHE_ENTRY, MAX_MKEY_CACHE_ENTRIES }; -- cgit v1.2.3 From da27f796a832122ee533c7685438dad1c4e338dd Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Fri, 27 Jan 2023 13:46:51 -0500 Subject: ipc,namespace: batch free ipc_namespace structures Instead of waiting for an RCU grace period between each ipc_namespace structure that is being freed, wait an RCU grace period for every batch of ipc_namespace structures. Thanks to Al Viro for the suggestion of the helper function. This speeds up the run time of the test case that allocates ipc_namespaces in a loop from 6 minutes, to a little over 1 second: real 0m1.192s user 0m0.038s sys 0m1.152s Signed-off-by: Rik van Riel Reported-by: Chris Mason Tested-by: Giuseppe Scrivano Suggested-by: Al Viro Signed-off-by: Al Viro --- fs/namespace.c | 18 ++++++++++++++---- include/linux/mount.h | 1 + ipc/mqueue.c | 5 ----- ipc/namespace.c | 13 ++++++++++--- ipc/util.h | 2 -- 5 files changed, 25 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/fs/namespace.c b/fs/namespace.c index ab467ee58341..1ad4e5acef06 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1397,6 +1397,17 @@ struct vfsmount *mntget(struct vfsmount *mnt) } EXPORT_SYMBOL(mntget); +/* + * Make a mount point inaccessible to new lookups. + * Because there may still be current users, the caller MUST WAIT + * for an RCU grace period before destroying the mount point. + */ +void mnt_make_shortterm(struct vfsmount *mnt) +{ + if (mnt) + real_mount(mnt)->mnt_ns = NULL; +} + /** * path_is_mountpoint() - Check if path is a mount in the current namespace. * @path: path to check @@ -4573,8 +4584,8 @@ EXPORT_SYMBOL_GPL(kern_mount); void kern_unmount(struct vfsmount *mnt) { /* release long term mount so mount point can be released */ - if (!IS_ERR_OR_NULL(mnt)) { - real_mount(mnt)->mnt_ns = NULL; + if (!IS_ERR(mnt)) { + mnt_make_shortterm(mnt); synchronize_rcu(); /* yecchhh... */ mntput(mnt); } @@ -4586,8 +4597,7 @@ void kern_unmount_array(struct vfsmount *mnt[], unsigned int num) unsigned int i; for (i = 0; i < num; i++) - if (mnt[i]) - real_mount(mnt[i])->mnt_ns = NULL; + mnt_make_shortterm(mnt[i]); synchronize_rcu_expedited(); for (i = 0; i < num; i++) mntput(mnt[i]); diff --git a/include/linux/mount.h b/include/linux/mount.h index 62475996fac6..ec55a031aa8c 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -88,6 +88,7 @@ extern void mnt_drop_write(struct vfsmount *mnt); extern void mnt_drop_write_file(struct file *file); extern void mntput(struct vfsmount *mnt); extern struct vfsmount *mntget(struct vfsmount *mnt); +extern void mnt_make_shortterm(struct vfsmount *mnt); extern struct vfsmount *mnt_clone_internal(const struct path *path); extern bool __mnt_is_readonly(struct vfsmount *mnt); extern bool mnt_may_suid(struct vfsmount *mnt); diff --git a/ipc/mqueue.c b/ipc/mqueue.c index d09aa1c1e3e6..6c5bf7cce7fe 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -1709,11 +1709,6 @@ void mq_clear_sbinfo(struct ipc_namespace *ns) ns->mq_mnt->mnt_sb->s_fs_info = NULL; } -void mq_put_mnt(struct ipc_namespace *ns) -{ - kern_unmount(ns->mq_mnt); -} - static int __init init_mqueue_fs(void) { int error; diff --git a/ipc/namespace.c b/ipc/namespace.c index a26860a41dac..6ecc30effd3e 100644 --- a/ipc/namespace.c +++ b/ipc/namespace.c @@ -145,10 +145,11 @@ void free_ipcs(struct ipc_namespace *ns, struct ipc_ids *ids, static void free_ipc_ns(struct ipc_namespace *ns) { - /* mq_put_mnt() waits for a grace period as kern_unmount() - * uses synchronize_rcu(). + /* + * Caller needs to wait for an RCU grace period to have passed + * after making the mount point inaccessible to new accesses. */ - mq_put_mnt(ns); + mntput(ns->mq_mnt); sem_exit_ns(ns); msg_exit_ns(ns); shm_exit_ns(ns); @@ -168,6 +169,12 @@ static void free_ipc(struct work_struct *unused) struct llist_node *node = llist_del_all(&free_ipc_list); struct ipc_namespace *n, *t; + llist_for_each_entry_safe(n, t, node, mnt_llist) + mnt_make_shortterm(n->mq_mnt); + + /* Wait for any last users to have gone away. */ + synchronize_rcu(); + llist_for_each_entry_safe(n, t, node, mnt_llist) free_ipc_ns(n); } diff --git a/ipc/util.h b/ipc/util.h index b2906e366539..67bdd2aa2c28 100644 --- a/ipc/util.h +++ b/ipc/util.h @@ -56,10 +56,8 @@ struct pid_namespace; #ifdef CONFIG_POSIX_MQUEUE extern void mq_clear_sbinfo(struct ipc_namespace *ns); -extern void mq_put_mnt(struct ipc_namespace *ns); #else static inline void mq_clear_sbinfo(struct ipc_namespace *ns) { } -static inline void mq_put_mnt(struct ipc_namespace *ns) { } #endif #ifdef CONFIG_SYSVIPC -- cgit v1.2.3 From d35d0c9de762e003129dfc1240df7152a4bc31e8 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 3 Jan 2023 15:12:46 +0200 Subject: leds: Add missing includes and forward declarations in leds.h Add missing includes and forward declarations to leds.h. While at it, replace headers by forward declarations and vise versa. Signed-off-by: Andy Shevchenko Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230103131256.33894-2-andriy.shevchenko@linux.intel.com --- include/linux/leds.h | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/leds.h b/include/linux/leds.h index 31cb74b90ffc..4df46a85e5c2 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -10,17 +10,21 @@ #include #include -#include -#include #include #include #include #include +#include #include -struct device; -struct led_pattern; +struct attribute_group; struct device_node; +struct fwnode_handle; +struct gpio_desc; +struct kernfs_node; +struct led_pattern; +struct platform_device; + /* * LED Core */ @@ -529,7 +533,6 @@ struct led_properties { const char *label; }; -struct gpio_desc; typedef int (*gpio_blink_set_t)(struct gpio_desc *desc, int state, unsigned long *delay_on, unsigned long *delay_off); -- cgit v1.2.3 From 156a5bb89ca6f3edd2be0bfd0de15e575442927e Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 3 Jan 2023 15:12:47 +0200 Subject: leds: Move led_init_default_state_get() to the global header There are users inside and outside LED framework that have implemented a local copy of led_init_default_state_get(). In order to deduplicate that, as the first step move the declaration from LED header to the global one. Signed-off-by: Andy Shevchenko Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230103131256.33894-3-andriy.shevchenko@linux.intel.com --- drivers/leds/leds.h | 1 - include/linux/leds.h | 2 ++ 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/leds/leds.h b/drivers/leds/leds.h index aa64757a4d89..345062ccabda 100644 --- a/drivers/leds/leds.h +++ b/drivers/leds/leds.h @@ -27,7 +27,6 @@ ssize_t led_trigger_read(struct file *filp, struct kobject *kobj, ssize_t led_trigger_write(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t pos, size_t count); -enum led_default_state led_init_default_state_get(struct fwnode_handle *fwnode); extern struct rw_semaphore leds_list_lock; extern struct list_head leds_list; diff --git a/include/linux/leds.h b/include/linux/leds.h index 4df46a85e5c2..d71201a968b6 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -82,6 +82,8 @@ struct led_init_data { bool devname_mandatory; }; +enum led_default_state led_init_default_state_get(struct fwnode_handle *fwnode); + struct led_hw_trigger_type { int dummy; }; -- cgit v1.2.3 From acf63c458b55ecfb2015b33dd6ba3cc8fbc1c5d3 Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Mon, 16 Jan 2023 12:08:45 +0200 Subject: fpga: m10bmc-sec: Add support for N6000 Add support for PMCI-based flash access path and N6000 sec update support. Access to flash staging area is different for N6000 from that of the SPI interfaced counterparts. Introduce intel_m10bmc_flash_bulk_ops to allow interface specific differentiations for the flash access path for sec update and make m10bmc_sec_read/write() in sec update driver to use the new operations. The .flash_mutex serializes read/read. Flash update (erase+write) must use ->lock/unlock_write() to prevent reads during update (reads would timeout on setting flash MUX as BMC will prevent it). Create a type specific RSU status reg handler for N6000 because the field has moved from doorbell to auth result register. If a failure is detected while altering the flash MUX, it seems safer to try to set it back and doesn't seem harmful. Likely there are enough troubles in that case anyway so setting it back fails too (which is harmless sans the small extra delay) or just confirms that the value wasn't changed. Co-developed-by: Tianfei zhang Signed-off-by: Tianfei zhang Co-developed-by: Russ Weight Signed-off-by: Russ Weight Acked-by: Xu Yilun Signed-off-by: Ilpo Järvinen Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230116100845.6153-12-ilpo.jarvinen@linux.intel.com --- drivers/fpga/intel-m10-bmc-sec-update.c | 51 ++++++- drivers/mfd/intel-m10-bmc-pmci.c | 242 +++++++++++++++++++++++++++++++- include/linux/mfd/intel-m10-bmc.h | 51 +++++++ 3 files changed, 336 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/fpga/intel-m10-bmc-sec-update.c b/drivers/fpga/intel-m10-bmc-sec-update.c index 92145ee7333e..9b4cc75b48c5 100644 --- a/drivers/fpga/intel-m10-bmc-sec-update.c +++ b/drivers/fpga/intel-m10-bmc-sec-update.c @@ -48,6 +48,9 @@ static int m10bmc_sec_write(struct m10bmc_sec *sec, const u8 *buf, u32 offset, u u32 leftover_tmp = 0; int ret; + if (sec->m10bmc->flash_bulk_ops) + return sec->m10bmc->flash_bulk_ops->write(m10bmc, buf, offset, size); + if (WARN_ON_ONCE(stride > sizeof(leftover_tmp))) return -EINVAL; @@ -78,6 +81,9 @@ static int m10bmc_sec_read(struct m10bmc_sec *sec, u8 *buf, u32 addr, u32 size) u32 leftover_tmp; int ret; + if (sec->m10bmc->flash_bulk_ops) + return sec->m10bmc->flash_bulk_ops->read(m10bmc, buf, addr, size); + if (WARN_ON_ONCE(stride > sizeof(leftover_tmp))) return -EINVAL; @@ -277,6 +283,19 @@ static int m10bmc_sec_n3000_rsu_status(struct m10bmc_sec *sec) return FIELD_GET(DRBL_RSU_STATUS, doorbell); } +static int m10bmc_sec_n6000_rsu_status(struct m10bmc_sec *sec) +{ + const struct m10bmc_csr_map *csr_map = sec->m10bmc->info->csr_map; + u32 auth_result; + int ret; + + ret = m10bmc_sys_read(sec->m10bmc, csr_map->auth_result, &auth_result); + if (ret) + return ret; + + return FIELD_GET(AUTH_RESULT_RSU_STATUS, auth_result); +} + static bool rsu_status_ok(u32 status) { return (status == RSU_STAT_NORMAL || @@ -520,22 +539,33 @@ static enum fw_upload_err m10bmc_sec_prepare(struct fw_upload *fwl, if (!size || size > M10BMC_STAGING_SIZE) return FW_UPLOAD_ERR_INVALID_SIZE; + if (sec->m10bmc->flash_bulk_ops) + if (sec->m10bmc->flash_bulk_ops->lock_write(sec->m10bmc)) + return FW_UPLOAD_ERR_BUSY; + ret = rsu_check_idle(sec); if (ret != FW_UPLOAD_ERR_NONE) - return ret; + goto unlock_flash; ret = rsu_update_init(sec); if (ret != FW_UPLOAD_ERR_NONE) - return ret; + goto unlock_flash; ret = rsu_prog_ready(sec); if (ret != FW_UPLOAD_ERR_NONE) - return ret; + goto unlock_flash; - if (sec->cancel_request) - return rsu_cancel(sec); + if (sec->cancel_request) { + ret = rsu_cancel(sec); + goto unlock_flash; + } return FW_UPLOAD_ERR_NONE; + +unlock_flash: + if (sec->m10bmc->flash_bulk_ops) + sec->m10bmc->flash_bulk_ops->unlock_write(sec->m10bmc); + return ret; } #define WRITE_BLOCK_SIZE 0x4000 /* Default write-block size is 0x4000 bytes */ @@ -622,6 +652,9 @@ static void m10bmc_sec_cleanup(struct fw_upload *fwl) struct m10bmc_sec *sec = fwl->dd_handle; (void)rsu_cancel(sec); + + if (sec->m10bmc->flash_bulk_ops) + sec->m10bmc->flash_bulk_ops->unlock_write(sec->m10bmc); } static const struct fw_upload_ops m10bmc_ops = { @@ -636,6 +669,10 @@ static const struct m10bmc_sec_ops m10sec_n3000_ops = { .rsu_status = m10bmc_sec_n3000_rsu_status, }; +static const struct m10bmc_sec_ops m10sec_n6000_ops = { + .rsu_status = m10bmc_sec_n6000_rsu_status, +}; + #define SEC_UPDATE_LEN_MAX 32 static int m10bmc_sec_probe(struct platform_device *pdev) { @@ -698,6 +735,10 @@ static const struct platform_device_id intel_m10bmc_sec_ids[] = { .name = "d5005bmc-sec-update", .driver_data = (kernel_ulong_t)&m10sec_n3000_ops, }, + { + .name = "n6000bmc-sec-update", + .driver_data = (kernel_ulong_t)&m10sec_n6000_ops, + }, { } }; MODULE_DEVICE_TABLE(platform, intel_m10bmc_sec_ids); diff --git a/drivers/mfd/intel-m10-bmc-pmci.c b/drivers/mfd/intel-m10-bmc-pmci.c index 975019f644b5..8821f1876dd6 100644 --- a/drivers/mfd/intel-m10-bmc-pmci.c +++ b/drivers/mfd/intel-m10-bmc-pmci.c @@ -6,16 +6,20 @@ * Copyright (C) 2020-2023 Intel Corporation. */ +#include #include #include #include #include +#include #include #include struct m10bmc_pmci_device { void __iomem *base; struct intel_m10bmc m10bmc; + struct mutex flash_mutex; /* protects flash_busy and serializes flash read/read */ + bool flash_busy; }; /* @@ -114,6 +118,215 @@ static int indirect_reg_write(void *context, unsigned int reg, unsigned int val) return ret2; } +static void pmci_write_fifo(void __iomem *base, const u32 *buf, size_t count) +{ + while (count--) + writel(*buf++, base); +} + +static void pmci_read_fifo(void __iomem *base, u32 *buf, size_t count) +{ + while (count--) + *buf++ = readl(base); +} + +static u32 pmci_get_write_space(struct m10bmc_pmci_device *pmci) +{ + u32 val; + int ret; + + ret = read_poll_timeout(readl, val, + FIELD_GET(M10BMC_N6000_FLASH_FIFO_SPACE, val) == + M10BMC_N6000_FIFO_MAX_WORDS, + M10BMC_FLASH_INT_US, M10BMC_FLASH_TIMEOUT_US, + false, pmci->base + M10BMC_N6000_FLASH_CTRL); + if (ret == -ETIMEDOUT) + return 0; + + return FIELD_GET(M10BMC_N6000_FLASH_FIFO_SPACE, val) * M10BMC_N6000_FIFO_WORD_SIZE; +} + +static int pmci_flash_bulk_write(struct intel_m10bmc *m10bmc, const u8 *buf, u32 size) +{ + struct m10bmc_pmci_device *pmci = container_of(m10bmc, struct m10bmc_pmci_device, m10bmc); + u32 blk_size, offset = 0, write_count; + + while (size) { + blk_size = min(pmci_get_write_space(pmci), size); + if (blk_size == 0) { + dev_err(m10bmc->dev, "get FIFO available size fail\n"); + return -EIO; + } + + if (size < M10BMC_N6000_FIFO_WORD_SIZE) + break; + + write_count = blk_size / M10BMC_N6000_FIFO_WORD_SIZE; + pmci_write_fifo(pmci->base + M10BMC_N6000_FLASH_FIFO, + (u32 *)(buf + offset), write_count); + + size -= blk_size; + offset += blk_size; + } + + /* Handle remainder (less than M10BMC_N6000_FIFO_WORD_SIZE bytes) */ + if (size) { + u32 tmp = 0; + + memcpy(&tmp, buf + offset, size); + pmci_write_fifo(pmci->base + M10BMC_N6000_FLASH_FIFO, &tmp, 1); + } + + return 0; +} + +static int pmci_flash_bulk_read(struct intel_m10bmc *m10bmc, u8 *buf, u32 addr, u32 size) +{ + struct m10bmc_pmci_device *pmci = container_of(m10bmc, struct m10bmc_pmci_device, m10bmc); + u32 blk_size, offset = 0, val, full_read_count, read_count; + int ret; + + while (size) { + blk_size = min_t(u32, size, M10BMC_N6000_READ_BLOCK_SIZE); + full_read_count = blk_size / M10BMC_N6000_FIFO_WORD_SIZE; + + read_count = full_read_count; + if (full_read_count * M10BMC_N6000_FIFO_WORD_SIZE < blk_size) + read_count++; + + writel(addr + offset, pmci->base + M10BMC_N6000_FLASH_ADDR); + writel(FIELD_PREP(M10BMC_N6000_FLASH_READ_COUNT, read_count) | + M10BMC_N6000_FLASH_RD_MODE, + pmci->base + M10BMC_N6000_FLASH_CTRL); + + ret = readl_poll_timeout((pmci->base + M10BMC_N6000_FLASH_CTRL), val, + !(val & M10BMC_N6000_FLASH_BUSY), + M10BMC_FLASH_INT_US, M10BMC_FLASH_TIMEOUT_US); + if (ret) { + dev_err(m10bmc->dev, "read timed out on reading flash 0x%xn", val); + return ret; + } + + pmci_read_fifo(pmci->base + M10BMC_N6000_FLASH_FIFO, + (u32 *)(buf + offset), full_read_count); + + size -= blk_size; + offset += blk_size; + + if (full_read_count < read_count) + break; + + writel(0, pmci->base + M10BMC_N6000_FLASH_CTRL); + } + + /* Handle remainder (less than M10BMC_N6000_FIFO_WORD_SIZE bytes) */ + if (size) { + u32 tmp; + + pmci_read_fifo(pmci->base + M10BMC_N6000_FLASH_FIFO, &tmp, 1); + memcpy(buf + offset, &tmp, size); + + writel(0, pmci->base + M10BMC_N6000_FLASH_CTRL); + } + + return 0; +} + +static int m10bmc_pmci_set_flash_host_mux(struct intel_m10bmc *m10bmc, bool request) +{ + u32 ctrl; + int ret; + + ret = regmap_update_bits(m10bmc->regmap, M10BMC_N6000_FLASH_MUX_CTRL, + M10BMC_N6000_FLASH_HOST_REQUEST, + FIELD_PREP(M10BMC_N6000_FLASH_HOST_REQUEST, request)); + if (ret) + return ret; + + return regmap_read_poll_timeout(m10bmc->regmap, + M10BMC_N6000_FLASH_MUX_CTRL, ctrl, + request ? + (get_flash_mux(ctrl) == M10BMC_N6000_FLASH_MUX_HOST) : + (get_flash_mux(ctrl) != M10BMC_N6000_FLASH_MUX_HOST), + M10BMC_FLASH_INT_US, M10BMC_FLASH_TIMEOUT_US); +} + +static int m10bmc_pmci_flash_read(struct intel_m10bmc *m10bmc, u8 *buf, u32 addr, u32 size) +{ + struct m10bmc_pmci_device *pmci = container_of(m10bmc, struct m10bmc_pmci_device, m10bmc); + int ret, ret2; + + mutex_lock(&pmci->flash_mutex); + if (pmci->flash_busy) { + ret = -EBUSY; + goto unlock; + } + + ret = m10bmc_pmci_set_flash_host_mux(m10bmc, true); + if (ret) + goto mux_fail; + + ret = pmci_flash_bulk_read(m10bmc, buf, addr, size); + +mux_fail: + ret2 = m10bmc_pmci_set_flash_host_mux(m10bmc, false); + +unlock: + mutex_unlock(&pmci->flash_mutex); + if (ret) + return ret; + return ret2; +} + +static int m10bmc_pmci_flash_write(struct intel_m10bmc *m10bmc, const u8 *buf, u32 offset, u32 size) +{ + struct m10bmc_pmci_device *pmci = container_of(m10bmc, struct m10bmc_pmci_device, m10bmc); + int ret; + + mutex_lock(&pmci->flash_mutex); + WARN_ON_ONCE(!pmci->flash_busy); + /* On write, firmware manages flash MUX */ + ret = pmci_flash_bulk_write(m10bmc, buf + offset, size); + mutex_unlock(&pmci->flash_mutex); + + return ret; +} + +static int m10bmc_pmci_flash_lock(struct intel_m10bmc *m10bmc) +{ + struct m10bmc_pmci_device *pmci = container_of(m10bmc, struct m10bmc_pmci_device, m10bmc); + int ret = 0; + + mutex_lock(&pmci->flash_mutex); + if (pmci->flash_busy) { + ret = -EBUSY; + goto unlock; + } + + pmci->flash_busy = true; + +unlock: + mutex_unlock(&pmci->flash_mutex); + return ret; +} + +static void m10bmc_pmci_flash_unlock(struct intel_m10bmc *m10bmc) +{ + struct m10bmc_pmci_device *pmci = container_of(m10bmc, struct m10bmc_pmci_device, m10bmc); + + mutex_lock(&pmci->flash_mutex); + WARN_ON_ONCE(!pmci->flash_busy); + pmci->flash_busy = false; + mutex_unlock(&pmci->flash_mutex); +} + +static const struct intel_m10bmc_flash_bulk_ops m10bmc_pmci_flash_bulk_ops = { + .read = m10bmc_pmci_flash_read, + .write = m10bmc_pmci_flash_write, + .lock_write = m10bmc_pmci_flash_lock, + .unlock_write = m10bmc_pmci_flash_unlock, +}; + static const struct regmap_range m10bmc_pmci_regmap_range[] = { regmap_reg_range(M10BMC_N6000_SYS_BASE, M10BMC_N6000_SYS_END), }; @@ -136,6 +349,7 @@ static struct regmap_config m10bmc_pmci_regmap_config = { static struct mfd_cell m10bmc_pmci_n6000_bmc_subdevs[] = { { .name = "n6000bmc-hwmon" }, + { .name = "n6000bmc-sec-update" }, }; static const struct m10bmc_csr_map m10bmc_n6000_csr_map = { @@ -169,11 +383,13 @@ static int m10bmc_pmci_probe(struct dfl_device *ddev) struct device *dev = &ddev->dev; struct m10bmc_pmci_device *pmci; struct indirect_ctx *ctx; + int ret; pmci = devm_kzalloc(dev, sizeof(*pmci), GFP_KERNEL); if (!pmci) return -ENOMEM; + pmci->m10bmc.flash_bulk_ops = &m10bmc_pmci_flash_bulk_ops; pmci->m10bmc.dev = dev; pmci->base = devm_ioremap_resource(dev, &ddev->mmio_res); @@ -184,15 +400,34 @@ static int m10bmc_pmci_probe(struct dfl_device *ddev) if (!ctx) return -ENOMEM; + mutex_init(&pmci->flash_mutex); + ctx->base = pmci->base + M10BMC_N6000_INDIRECT_BASE; ctx->dev = dev; indirect_clear_cmd(ctx); pmci->m10bmc.regmap = devm_regmap_init(dev, NULL, ctx, &m10bmc_pmci_regmap_config); - if (IS_ERR(pmci->m10bmc.regmap)) - return PTR_ERR(pmci->m10bmc.regmap); + if (IS_ERR(pmci->m10bmc.regmap)) { + ret = PTR_ERR(pmci->m10bmc.regmap); + goto destroy_mutex; + } + + ret = m10bmc_dev_init(&pmci->m10bmc, &m10bmc_pmci_n6000); + if (ret) + goto destroy_mutex; + return 0; + +destroy_mutex: + mutex_destroy(&pmci->flash_mutex); + return ret; +} + +static void m10bmc_pmci_remove(struct dfl_device *ddev) +{ + struct intel_m10bmc *m10bmc = dev_get_drvdata(&ddev->dev); + struct m10bmc_pmci_device *pmci = container_of(m10bmc, struct m10bmc_pmci_device, m10bmc); - return m10bmc_dev_init(&pmci->m10bmc, &m10bmc_pmci_n6000); + mutex_destroy(&pmci->flash_mutex); } #define FME_FEATURE_ID_M10BMC_PMCI 0x12 @@ -210,6 +445,7 @@ static struct dfl_driver m10bmc_pmci_driver = { }, .id_table = m10bmc_pmci_ids, .probe = m10bmc_pmci_probe, + .remove = m10bmc_pmci_remove, }; module_dfl_driver(m10bmc_pmci_driver); diff --git a/include/linux/mfd/intel-m10-bmc.h b/include/linux/mfd/intel-m10-bmc.h index 810534b1bd12..1812ebfa11a8 100644 --- a/include/linux/mfd/intel-m10-bmc.h +++ b/include/linux/mfd/intel-m10-bmc.h @@ -127,6 +127,7 @@ #define M10BMC_N6000_DOORBELL 0x1c0 #define M10BMC_N6000_AUTH_RESULT 0x1c4 +#define AUTH_RESULT_RSU_STATUS GENMASK(23, 16) #define M10BMC_N6000_BUILD_VER 0x0 #define NIOS2_N6000_FW_VERSION 0x4 @@ -148,6 +149,35 @@ #define M10BMC_N6000_STAGING_FLASH_COUNT 0x7ff5000 +#define M10BMC_N6000_FLASH_MUX_CTRL 0x1d0 +#define M10BMC_N6000_FLASH_MUX_SELECTION GENMASK(2, 0) +#define M10BMC_N6000_FLASH_MUX_IDLE 0 +#define M10BMC_N6000_FLASH_MUX_NIOS 1 +#define M10BMC_N6000_FLASH_MUX_HOST 2 +#define M10BMC_N6000_FLASH_MUX_PFL 4 +#define get_flash_mux(mux) FIELD_GET(M10BMC_N6000_FLASH_MUX_SELECTION, mux) + +#define M10BMC_N6000_FLASH_NIOS_REQUEST BIT(4) +#define M10BMC_N6000_FLASH_HOST_REQUEST BIT(5) + +#define M10BMC_N6000_FLASH_CTRL 0x40 +#define M10BMC_N6000_FLASH_WR_MODE BIT(0) +#define M10BMC_N6000_FLASH_RD_MODE BIT(1) +#define M10BMC_N6000_FLASH_BUSY BIT(2) +#define M10BMC_N6000_FLASH_FIFO_SPACE GENMASK(13, 4) +#define M10BMC_N6000_FLASH_READ_COUNT GENMASK(25, 16) + +#define M10BMC_N6000_FLASH_ADDR 0x44 +#define M10BMC_N6000_FLASH_FIFO 0x800 +#define M10BMC_N6000_READ_BLOCK_SIZE 0x800 +#define M10BMC_N6000_FIFO_MAX_BYTES 0x800 +#define M10BMC_N6000_FIFO_WORD_SIZE 4 +#define M10BMC_N6000_FIFO_MAX_WORDS (M10BMC_N6000_FIFO_MAX_BYTES / \ + M10BMC_N6000_FIFO_WORD_SIZE) + +#define M10BMC_FLASH_INT_US 1 +#define M10BMC_FLASH_TIMEOUT_US 10000 + /** * struct m10bmc_csr_map - Intel MAX 10 BMC CSR register map */ @@ -183,16 +213,37 @@ struct intel_m10bmc_platform_info { const struct m10bmc_csr_map *csr_map; }; +struct intel_m10bmc; + +/** + * struct intel_m10bmc_flash_bulk_ops - device specific operations for flash R/W + * @read: read a block of data from flash + * @write: write a block of data to flash + * @lock_write: locks flash access for erase+write + * @unlock_write: unlock flash access + * + * Write must be protected with @lock_write and @unlock_write. While the flash + * is locked, @read returns -EBUSY. + */ +struct intel_m10bmc_flash_bulk_ops { + int (*read)(struct intel_m10bmc *m10bmc, u8 *buf, u32 addr, u32 size); + int (*write)(struct intel_m10bmc *m10bmc, const u8 *buf, u32 offset, u32 size); + int (*lock_write)(struct intel_m10bmc *m10bmc); + void (*unlock_write)(struct intel_m10bmc *m10bmc); +}; + /** * struct intel_m10bmc - Intel MAX 10 BMC parent driver data structure * @dev: this device * @regmap: the regmap used to access registers by m10bmc itself * @info: the platform information for MAX10 BMC + * @flash_bulk_ops: optional device specific operations for flash R/W */ struct intel_m10bmc { struct device *dev; struct regmap *regmap; const struct intel_m10bmc_platform_info *info; + const struct intel_m10bmc_flash_bulk_ops *flash_bulk_ops; }; /* -- cgit v1.2.3 From 79729f26b074a5d2722c27fa76cc45ef721e65cd Mon Sep 17 00:00:00 2001 From: Evgeniy Baskov Date: Tue, 22 Nov 2022 14:12:31 +0300 Subject: efi/libstub: Add memory attribute protocol definitions EFI_MEMORY_ATTRIBUTE_PROTOCOL servers as a better alternative to DXE services for setting memory attributes in EFI Boot Services environment. This protocol is better since it is a part of UEFI specification itself and not UEFI PI specification like DXE services. Add EFI_MEMORY_ATTRIBUTE_PROTOCOL definitions. Support mixed mode properly for its calls. Tested-by: Mario Limonciello Signed-off-by: Evgeniy Baskov Signed-off-by: Ard Biesheuvel --- arch/x86/include/asm/efi.h | 7 +++++++ drivers/firmware/efi/libstub/efistub.h | 20 ++++++++++++++++++++ include/linux/efi.h | 1 + 3 files changed, 28 insertions(+) (limited to 'include/linux') diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index a63154e049d7..cd19b9eca3f6 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -335,6 +335,13 @@ static inline u32 efi64_convert_status(efi_status_t status) #define __efi64_argmap_open_volume(prot, file) \ ((prot), efi64_zero_upper(file)) +/* Memory Attribute Protocol */ +#define __efi64_argmap_set_memory_attributes(protocol, phys, size, flags) \ + ((protocol), __efi64_split(phys), __efi64_split(size), __efi64_split(flags)) + +#define __efi64_argmap_clear_memory_attributes(protocol, phys, size, flags) \ + ((protocol), __efi64_split(phys), __efi64_split(size), __efi64_split(flags)) + /* * The macros below handle the plumbing for the argument mapping. To add a * mapping for a specific EFI method, simply define a macro diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h index 5b8f2c411ed8..5388c7a9eb16 100644 --- a/drivers/firmware/efi/libstub/efistub.h +++ b/drivers/firmware/efi/libstub/efistub.h @@ -442,6 +442,26 @@ union efi_dxe_services_table { } mixed_mode; }; +typedef union efi_memory_attribute_protocol efi_memory_attribute_protocol_t; + +union efi_memory_attribute_protocol { + struct { + efi_status_t (__efiapi *get_memory_attributes)( + efi_memory_attribute_protocol_t *, efi_physical_addr_t, u64, u64 *); + + efi_status_t (__efiapi *set_memory_attributes)( + efi_memory_attribute_protocol_t *, efi_physical_addr_t, u64, u64); + + efi_status_t (__efiapi *clear_memory_attributes)( + efi_memory_attribute_protocol_t *, efi_physical_addr_t, u64, u64); + }; + struct { + u32 get_memory_attributes; + u32 set_memory_attributes; + u32 clear_memory_attributes; + } mixed_mode; +}; + typedef union efi_uga_draw_protocol efi_uga_draw_protocol_t; union efi_uga_draw_protocol { diff --git a/include/linux/efi.h b/include/linux/efi.h index 1a1adc8d3ba3..507390dda8b9 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -391,6 +391,7 @@ void efi_native_runtime_setup(void); #define EFI_RT_PROPERTIES_TABLE_GUID EFI_GUID(0xeb66918a, 0x7eef, 0x402a, 0x84, 0x2e, 0x93, 0x1d, 0x21, 0xc3, 0x8a, 0xe9) #define EFI_DXE_SERVICES_TABLE_GUID EFI_GUID(0x05ad34ba, 0x6f02, 0x4214, 0x95, 0x2e, 0x4d, 0xa0, 0x39, 0x8e, 0x2b, 0xb9) #define EFI_SMBIOS_PROTOCOL_GUID EFI_GUID(0x03583ff6, 0xcb36, 0x4940, 0x94, 0x7e, 0xb9, 0xb3, 0x9f, 0x4a, 0xfa, 0xf7) +#define EFI_MEMORY_ATTRIBUTE_PROTOCOL_GUID EFI_GUID(0xf4560cf6, 0x40ec, 0x4b4a, 0xa1, 0x92, 0xbf, 0x1d, 0x57, 0xd0, 0xb1, 0x89) #define EFI_IMAGE_SECURITY_DATABASE_GUID EFI_GUID(0xd719b2cb, 0x3d3a, 0x4596, 0xa3, 0xbc, 0xda, 0xd0, 0x0e, 0x67, 0x65, 0x6f) #define EFI_SHIM_LOCK_GUID EFI_GUID(0x605dab50, 0xe046, 0x4300, 0xab, 0xb6, 0x3d, 0xd8, 0x10, 0xdd, 0x8b, 0x23) -- cgit v1.2.3 From dbd7a2a941b8cbf9e5f79a777ed9fe0090eebb61 Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Mon, 23 Jan 2023 07:37:45 -0800 Subject: PM / devfreq: Fix build issues with devfreq disabled The existing no-op shims for when PM_DEVFREQ (or an individual governor) only do half the job. The governor specific config/tuning structs need to be available to avoid compile errors in drivers using devfreq. Fixes: 6563f60f14cb ("drm/msm/gpu: Add devfreq tuning debugfs") Signed-off-by: Rob Clark Acked-by: MyungJoo Ham Acked-by: Chanwoo Choi Patchwork: https://patchwork.freedesktop.org/patch/519801/ Link: https://lore.kernel.org/r/20230123153745.3185032-1-robdclark@gmail.com --- include/linux/devfreq.h | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h index 4dc7cda4fd46..7fd704bb8f3d 100644 --- a/include/linux/devfreq.h +++ b/include/linux/devfreq.h @@ -273,8 +273,8 @@ void devm_devfreq_unregister_notifier(struct device *dev, struct devfreq *devfreq_get_devfreq_by_node(struct device_node *node); struct devfreq *devfreq_get_devfreq_by_phandle(struct device *dev, const char *phandle_name, int index); +#endif /* CONFIG_PM_DEVFREQ */ -#if IS_ENABLED(CONFIG_DEVFREQ_GOV_SIMPLE_ONDEMAND) /** * struct devfreq_simple_ondemand_data - ``void *data`` fed to struct devfreq * and devfreq_add_device @@ -292,9 +292,7 @@ struct devfreq_simple_ondemand_data { unsigned int upthreshold; unsigned int downdifferential; }; -#endif -#if IS_ENABLED(CONFIG_DEVFREQ_GOV_PASSIVE) enum devfreq_parent_dev_type { DEVFREQ_PARENT_DEV, CPUFREQ_PARENT_DEV, @@ -337,9 +335,8 @@ struct devfreq_passive_data { struct notifier_block nb; struct list_head cpu_data_list; }; -#endif -#else /* !CONFIG_PM_DEVFREQ */ +#if !defined(CONFIG_PM_DEVFREQ) static inline struct devfreq *devfreq_add_device(struct device *dev, struct devfreq_dev_profile *profile, const char *governor_name, -- cgit v1.2.3 From b3c650ad9bb88ecf36b9aeacf9e7eb7478258da7 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 21 Nov 2022 17:15:41 +0100 Subject: pwm: Move pwm_capture() dummy to restore order Move the dummy pwm_capture(), to make the declaration order of all dummies to match the declaration order of the real functions. Signed-off-by: Geert Uytterhoeven Acked-by: Uwe Kleine-König Signed-off-by: Thierry Reding --- include/linux/pwm.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pwm.h b/include/linux/pwm.h index 161e91167b9c..7b7b93b6fb81 100644 --- a/include/linux/pwm.h +++ b/include/linux/pwm.h @@ -440,13 +440,6 @@ static inline int pwm_config(struct pwm_device *pwm, int duty_ns, return -EINVAL; } -static inline int pwm_capture(struct pwm_device *pwm, - struct pwm_capture *result, - unsigned long timeout) -{ - return -EINVAL; -} - static inline int pwm_enable(struct pwm_device *pwm) { might_sleep(); @@ -458,6 +451,13 @@ static inline void pwm_disable(struct pwm_device *pwm) might_sleep(); } +static inline int pwm_capture(struct pwm_device *pwm, + struct pwm_capture *result, + unsigned long timeout) +{ + return -EINVAL; +} + static inline int pwm_set_chip_data(struct pwm_device *pwm, void *data) { return -EINVAL; -- cgit v1.2.3 From 724ef01569519d1e7a95231688b6a5f8eaba29f2 Mon Sep 17 00:00:00 2001 From: Mario Kicherer Date: Thu, 26 Jan 2023 15:40:50 +0100 Subject: mtd: spinand: Add support for AllianceMemory AS5F34G04SND Add support for AllianceMemory AS5F34G04SND SPI NAND flash Datasheet: - https://www.alliancememory.com/wp-content/uploads/pdf/flash/AllianceMemory_SPI_NAND_Flash_July2020_Rev1.0.pdf Signed-off-by: Mario Kicherer Reviewed-by: Dhruva Gole Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20230126144050.2656358-1-dev@kicherer.org --- drivers/mtd/nand/spi/Makefile | 2 +- drivers/mtd/nand/spi/alliancememory.c | 153 ++++++++++++++++++++++++++++++++++ drivers/mtd/nand/spi/core.c | 1 + include/linux/mtd/spinand.h | 1 + 4 files changed, 156 insertions(+), 1 deletion(-) create mode 100644 drivers/mtd/nand/spi/alliancememory.c (limited to 'include/linux') diff --git a/drivers/mtd/nand/spi/Makefile b/drivers/mtd/nand/spi/Makefile index b520fe634041..4ec973b8b6bf 100644 --- a/drivers/mtd/nand/spi/Makefile +++ b/drivers/mtd/nand/spi/Makefile @@ -1,3 +1,3 @@ # SPDX-License-Identifier: GPL-2.0 -spinand-objs := core.o ato.o gigadevice.o macronix.o micron.o paragon.o toshiba.o winbond.o xtx.o +spinand-objs := core.o alliancememory.o ato.o gigadevice.o macronix.o micron.o paragon.o toshiba.o winbond.o xtx.o obj-$(CONFIG_MTD_SPI_NAND) += spinand.o diff --git a/drivers/mtd/nand/spi/alliancememory.c b/drivers/mtd/nand/spi/alliancememory.c new file mode 100644 index 000000000000..7936ea546b03 --- /dev/null +++ b/drivers/mtd/nand/spi/alliancememory.c @@ -0,0 +1,153 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Author: Mario Kicherer + */ + +#include +#include +#include + +#define SPINAND_MFR_ALLIANCEMEMORY 0x52 + +#define AM_STATUS_ECC_BITMASK (3 << 4) + +#define AM_STATUS_ECC_NONE_DETECTED (0 << 4) +#define AM_STATUS_ECC_CORRECTED (1 << 4) +#define AM_STATUS_ECC_ERRORED (2 << 4) +#define AM_STATUS_ECC_MAX_CORRECTED (3 << 4) + +static SPINAND_OP_VARIANTS(read_cache_variants, + SPINAND_PAGE_READ_FROM_CACHE_QUADIO_OP(0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_X4_OP(0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_DUALIO_OP(0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_X2_OP(0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_OP(true, 0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_OP(false, 0, 1, NULL, 0)); + +static SPINAND_OP_VARIANTS(write_cache_variants, + SPINAND_PROG_LOAD_X4(true, 0, NULL, 0), + SPINAND_PROG_LOAD(true, 0, NULL, 0)); + +static SPINAND_OP_VARIANTS(update_cache_variants, + SPINAND_PROG_LOAD_X4(false, 0, NULL, 0), + SPINAND_PROG_LOAD(false, 0, NULL, 0)); + +static int am_get_eccsize(struct mtd_info *mtd) +{ + if (mtd->oobsize == 64) + return 0x20; + else if (mtd->oobsize == 128) + return 0x38; + else if (mtd->oobsize == 256) + return 0x70; + else + return -EINVAL; +} + +static int am_ooblayout_ecc(struct mtd_info *mtd, int section, + struct mtd_oob_region *region) +{ + int ecc_bytes; + + ecc_bytes = am_get_eccsize(mtd); + if (ecc_bytes < 0) + return ecc_bytes; + + region->offset = mtd->oobsize - ecc_bytes; + region->length = ecc_bytes; + + return 0; +} + +static int am_ooblayout_free(struct mtd_info *mtd, int section, + struct mtd_oob_region *region) +{ + int ecc_bytes; + + if (section) + return -ERANGE; + + ecc_bytes = am_get_eccsize(mtd); + if (ecc_bytes < 0) + return ecc_bytes; + + /* + * It is unclear how many bytes are used for the bad block marker. We + * reserve the common two bytes here. + * + * The free area in this kind of flash is divided into chunks where the + * first 4 bytes of each chunk are unprotected. The number of chunks + * depends on the specific model. The models with 4096+256 bytes pages + * have 8 chunks, the others 4 chunks. + */ + + region->offset = 2; + region->length = mtd->oobsize - 2 - ecc_bytes; + + return 0; +} + +static const struct mtd_ooblayout_ops am_ooblayout = { + .ecc = am_ooblayout_ecc, + .free = am_ooblayout_free, +}; + +static int am_ecc_get_status(struct spinand_device *spinand, u8 status) +{ + switch (status & AM_STATUS_ECC_BITMASK) { + case AM_STATUS_ECC_NONE_DETECTED: + return 0; + + case AM_STATUS_ECC_CORRECTED: + /* + * use oobsize to determine the flash model and the maximum of + * correctable errors and return maximum - 1 by convention + */ + if (spinand->base.mtd.oobsize == 64) + return 3; + else + return 7; + + case AM_STATUS_ECC_ERRORED: + return -EBADMSG; + + case AM_STATUS_ECC_MAX_CORRECTED: + /* + * use oobsize to determine the flash model and the maximum of + * correctable errors + */ + if (spinand->base.mtd.oobsize == 64) + return 4; + else + return 8; + + default: + break; + } + + return -EINVAL; +} + +static const struct spinand_info alliancememory_spinand_table[] = { + SPINAND_INFO("AS5F34G04SND", + SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0x2f), + NAND_MEMORG(1, 2048, 128, 64, 4096, 80, 1, 1, 1), + NAND_ECCREQ(4, 512), + SPINAND_INFO_OP_VARIANTS(&read_cache_variants, + &write_cache_variants, + &update_cache_variants), + SPINAND_HAS_QE_BIT, + SPINAND_ECCINFO(&am_ooblayout, + am_ecc_get_status)), +}; + +static const struct spinand_manufacturer_ops alliancememory_spinand_manuf_ops = { +}; + +const struct spinand_manufacturer alliancememory_spinand_manufacturer = { + .id = SPINAND_MFR_ALLIANCEMEMORY, + .name = "AllianceMemory", + .chips = alliancememory_spinand_table, + .nchips = ARRAY_SIZE(alliancememory_spinand_table), + .ops = &alliancememory_spinand_manuf_ops, +}; diff --git a/drivers/mtd/nand/spi/core.c b/drivers/mtd/nand/spi/core.c index dacd9c0e8b20..638391f77d8c 100644 --- a/drivers/mtd/nand/spi/core.c +++ b/drivers/mtd/nand/spi/core.c @@ -937,6 +937,7 @@ static const struct nand_ops spinand_ops = { }; static const struct spinand_manufacturer *spinand_manufacturers[] = { + &alliancememory_spinand_manufacturer, &ato_spinand_manufacturer, &gigadevice_spinand_manufacturer, ¯onix_spinand_manufacturer, diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h index 6d3392a7edc6..01be9f0f008a 100644 --- a/include/linux/mtd/spinand.h +++ b/include/linux/mtd/spinand.h @@ -260,6 +260,7 @@ struct spinand_manufacturer { }; /* SPI NAND manufacturers */ +extern const struct spinand_manufacturer alliancememory_spinand_manufacturer; extern const struct spinand_manufacturer ato_spinand_manufacturer; extern const struct spinand_manufacturer gigadevice_spinand_manufacturer; extern const struct spinand_manufacturer macronix_spinand_manufacturer; -- cgit v1.2.3 From 246a1c4c6b7ffba88a2553d2b88f7b6280f253a2 Mon Sep 17 00:00:00 2001 From: Ondrej Zary Date: Mon, 23 Jan 2023 20:09:54 +0100 Subject: ata: pata_parport: add driver (PARIDE replacement) The pata_parport is a libata-based replacement of the old PARIDE subsystem - driver for parallel port IDE devices. It uses the original paride low-level protocol drivers but does not need the high-level drivers (pd, pcd, pf, pt, pg). The IDE devices behind parallel port adapters are handled by the ATA layer. This will allow paride and its high-level drivers to be removed. Unfortunately, libata drivers cannot sleep so pata_parport claims parport before activating the ata host and keeps it claimed (and protocol connected) until the ata host is removed. This means that no devices can be chained (neither other pata_parport devices nor a printer). paride and pata_parport are mutually exclusive because the compiled protocol drivers are incompatible. Tested with: - Imation SuperDisk LS-120 and HP C4381A (EPAT) - Freecom Parallel CD (FRPW) - Toshiba Mobile CD-RW 2793008 w/Freecom Parallel Cable rev.903 (FRIQ) - Backpack CD-RW 222011 and CD-RW 19350 (BPCK6) The following bugs in low-level protocol drivers were found and will be fixed later: Note: EPP-32 mode is buggy in EPAT - and also in all other protocol drivers - they don't handle non-multiple-of-4 block transfers correctly. This causes problems with LS-120 drive. There is also another bug in EPAT: EPP modes don't work unless a 4-bit or 8-bit mode is used first (probably some initialization missing?). Once the device is initialized, EPP works until power cycle. So after device power on, you have to: echo "parport0 epat 0" >/sys/bus/pata_parport/new_device echo pata_parport.0 >/sys/bus/pata_parport/delete_device echo "parport0 epat 4" >/sys/bus/pata_parport/new_device (autoprobe will initialize correctly as it tries the slowest modes first but you'll get the broken EPP-32 mode) Note: EPP modes are buggy in FRPW, only modes 0 and 1 work. Signed-off-by: Ondrej Zary Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Acked-by: Jens Axboe Signed-off-by: Damien Le Moal --- Documentation/admin-guide/blockdev/paride.rst | 52 ++ drivers/Makefile | 2 +- drivers/ata/Kconfig | 14 + drivers/ata/Makefile | 2 + drivers/ata/pata_parport.c | 759 ++++++++++++++++++++++++++ drivers/block/paride/Kconfig | 32 +- drivers/block/paride/paride.h | 13 + include/linux/pata_parport.h | 111 ++++ 8 files changed, 968 insertions(+), 17 deletions(-) create mode 100644 drivers/ata/pata_parport.c create mode 100644 include/linux/pata_parport.h (limited to 'include/linux') diff --git a/Documentation/admin-guide/blockdev/paride.rst b/Documentation/admin-guide/blockdev/paride.rst index e1ce90af602a..e431a1ef41eb 100644 --- a/Documentation/admin-guide/blockdev/paride.rst +++ b/Documentation/admin-guide/blockdev/paride.rst @@ -2,6 +2,9 @@ Linux and parallel port IDE devices =================================== +Most of this document describes the old paride driver. For the new libata +pata_parport drivrer, jump to the section 4 at the end. + PARIDE v1.03 (c) 1997-8 Grant Guenther 1. Introduction @@ -437,3 +440,52 @@ You might also find some useful information on the linux-parport web pages (although they are not always up to date) at http://web.archive.org/web/%2E/http://www.torque.net/parport/ + +4. pata_parport driver +====================== +pata_parport is a libata-based driver that uses the same low-level protocol +drivers as PARIDE but there are no high-level drivers (pd, pcd, pf, pt, pg). +The IDE devices behind parallel port adapters are handled by the ATA layer. + +The device creation is also changed - no protocol numbers or parport I/O +addresses are used. + +All parports and all protocol drivers are probed automatically unless probe=0 +parameter is used. So just "modprobe epat" is enough for a Imation SuperDisk +drive to work. + +Manual device creation:: + + # echo "port protocol mode unit delay" >/sys/bus/pata_parport/new_device + +where: + + ======== ================================================ + port parport name (or "auto" for all parports) + protocol protocol name (or "auto" for all protocols) + mode mode number (protocol-specific) or -1 for probe + unit unit number (see the paride documentation above) + delay I/O delay (see the paride documentation above) + ======== ================================================ + +If you omit the parameters from the end, defaults will be used, e.g.: + +Probe all parports with all protocols:: + + # echo auto >/sys/bus/pata_parport/new_device + +Probe parport0 using protocol epat and mode 4 (EPP-16):: + + # echo "parport0 epat 4" >/sys/bus/pata_parport/new_device + +Probe parport0 using all protocols:: + + # echo "parport0 auto" >/sys/bus/pata_parport/new_device + +Probe all parports using protoocol epat:: + + # echo "auto epat" >/sys/bus/pata_parport/new_device + +Deleting devices:: + + # echo pata_parport.0 >/sys/bus/pata_parport/delete_device diff --git a/drivers/Makefile b/drivers/Makefile index bdf1c66141c9..f1365608bc8c 100644 --- a/drivers/Makefile +++ b/drivers/Makefile @@ -98,7 +98,7 @@ obj-$(CONFIG_DIO) += dio/ obj-$(CONFIG_SBUS) += sbus/ obj-$(CONFIG_ZORRO) += zorro/ obj-$(CONFIG_ATA_OVER_ETH) += block/aoe/ -obj-$(CONFIG_PARIDE) += block/paride/ +obj-y += block/paride/ obj-$(CONFIG_TC) += tc/ obj-$(CONFIG_USB_PHY) += usb/ obj-$(CONFIG_USB) += usb/ diff --git a/drivers/ata/Kconfig b/drivers/ata/Kconfig index eceaec33af65..fb646480635c 100644 --- a/drivers/ata/Kconfig +++ b/drivers/ata/Kconfig @@ -1162,6 +1162,20 @@ config PATA_WINBOND_VLB Support for the Winbond W83759A controller on Vesa Local Bus systems. +config PATA_PARPORT + tristate "Parallel port IDE device support" + depends on PARPORT_PC && PARIDE=n + help + There are many external CD-ROM and disk devices that connect through + your computer's parallel port. Most of them are actually IDE devices + using a parallel port IDE adapter. This option enables the + PATA_PARPORT subsystem which contains drivers for many of these + external drives. + Read for more + information. + + Use the old PARIDE protocol modules. + comment "Generic fallback / legacy drivers" config PATA_ACPI diff --git a/drivers/ata/Makefile b/drivers/ata/Makefile index d2e36d367274..23588738cff0 100644 --- a/drivers/ata/Makefile +++ b/drivers/ata/Makefile @@ -114,6 +114,8 @@ obj-$(CONFIG_PATA_SAMSUNG_CF) += pata_samsung_cf.o obj-$(CONFIG_PATA_PXA) += pata_pxa.o +obj-$(CONFIG_PATA_PARPORT) += pata_parport.o + # Should be last but two libata driver obj-$(CONFIG_PATA_ACPI) += pata_acpi.o # Should be last but one libata driver diff --git a/drivers/ata/pata_parport.c b/drivers/ata/pata_parport.c new file mode 100644 index 000000000000..9e8ad93d7e59 --- /dev/null +++ b/drivers/ata/pata_parport.c @@ -0,0 +1,759 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2023 Ondrej Zary + * based on paride.c by Grant R. Guenther + */ +#include +#include +#include +#include + +#define DRV_NAME "pata_parport" + +static DEFINE_IDR(parport_list); +static DEFINE_IDR(protocols); +static DEFINE_IDA(pata_parport_bus_dev_ids); +static DEFINE_MUTEX(pi_mutex); + +static bool probe = true; +module_param(probe, bool, 0644); +MODULE_PARM_DESC(probe, "Enable automatic device probing (0=off, 1=on [default])"); + +/* + * libata drivers cannot sleep so this driver claims parport before activating + * the ata host and keeps it claimed (and protocol connected) until the ata + * host is removed. Unfortunately, this means that you cannot use any chained + * devices (neither other pata_parport devices nor a printer). + */ +static void pi_connect(struct pi_adapter *pi) +{ + parport_claim_or_block(pi->pardev); + pi->proto->connect(pi); +} + +static void pi_disconnect(struct pi_adapter *pi) +{ + pi->proto->disconnect(pi); + parport_release(pi->pardev); +} + +static void pata_parport_dev_select(struct ata_port *ap, unsigned int device) +{ + struct pi_adapter *pi = ap->host->private_data; + u8 tmp; + + if (device == 0) + tmp = ATA_DEVICE_OBS; + else + tmp = ATA_DEVICE_OBS | ATA_DEV1; + + pi->proto->write_regr(pi, 0, ATA_REG_DEVICE, tmp); + ata_sff_pause(ap); +} + +static bool pata_parport_devchk(struct ata_port *ap, unsigned int device) +{ + struct pi_adapter *pi = ap->host->private_data; + u8 nsect, lbal; + + pata_parport_dev_select(ap, device); + + pi->proto->write_regr(pi, 0, ATA_REG_NSECT, 0x55); + pi->proto->write_regr(pi, 0, ATA_REG_LBAL, 0xaa); + + pi->proto->write_regr(pi, 0, ATA_REG_NSECT, 0xaa); + pi->proto->write_regr(pi, 0, ATA_REG_LBAL, 0x55); + + pi->proto->write_regr(pi, 0, ATA_REG_NSECT, 055); + pi->proto->write_regr(pi, 0, ATA_REG_LBAL, 0xaa); + + nsect = pi->proto->read_regr(pi, 0, ATA_REG_NSECT); + lbal = pi->proto->read_regr(pi, 0, ATA_REG_LBAL); + + return (nsect == 0x55) && (lbal == 0xaa); +} + +static int pata_parport_bus_softreset(struct ata_port *ap, unsigned int devmask, + unsigned long deadline) +{ + struct pi_adapter *pi = ap->host->private_data; + + /* software reset. causes dev0 to be selected */ + pi->proto->write_regr(pi, 1, 6, ap->ctl); + udelay(20); + pi->proto->write_regr(pi, 1, 6, ap->ctl | ATA_SRST); + udelay(20); + pi->proto->write_regr(pi, 1, 6, ap->ctl); + ap->last_ctl = ap->ctl; + + /* wait the port to become ready */ + return ata_sff_wait_after_reset(&ap->link, devmask, deadline); +} + +static int pata_parport_softreset(struct ata_link *link, unsigned int *classes, + unsigned long deadline) +{ + struct ata_port *ap = link->ap; + unsigned int devmask = 0; + int rc; + u8 err; + + /* determine if device 0/1 are present */ + if (pata_parport_devchk(ap, 0)) + devmask |= (1 << 0); + if (pata_parport_devchk(ap, 1)) + devmask |= (1 << 1); + + /* select device 0 again */ + pata_parport_dev_select(ap, 0); + + /* issue bus reset */ + rc = pata_parport_bus_softreset(ap, devmask, deadline); + if (rc && rc != -ENODEV) { + ata_link_err(link, "SRST failed (errno=%d)\n", rc); + return rc; + } + + /* determine by signature whether we have ATA or ATAPI devices */ + classes[0] = ata_sff_dev_classify(&link->device[0], + devmask & (1 << 0), &err); + if (err != 0x81) + classes[1] = ata_sff_dev_classify(&link->device[1], + devmask & (1 << 1), &err); + + return 0; +} + +static u8 pata_parport_check_status(struct ata_port *ap) +{ + struct pi_adapter *pi = ap->host->private_data; + + return pi->proto->read_regr(pi, 0, ATA_REG_STATUS); +} + +static u8 pata_parport_check_altstatus(struct ata_port *ap) +{ + struct pi_adapter *pi = ap->host->private_data; + + return pi->proto->read_regr(pi, 1, 6); +} + +static void pata_parport_tf_load(struct ata_port *ap, + const struct ata_taskfile *tf) +{ + struct pi_adapter *pi = ap->host->private_data; + + if (tf->ctl != ap->last_ctl) { + pi->proto->write_regr(pi, 1, 6, tf->ctl); + ap->last_ctl = tf->ctl; + ata_wait_idle(ap); + } + + if (tf->flags & ATA_TFLAG_ISADDR) { + if (tf->flags & ATA_TFLAG_LBA48) { + pi->proto->write_regr(pi, 0, ATA_REG_FEATURE, + tf->hob_feature); + pi->proto->write_regr(pi, 0, ATA_REG_NSECT, + tf->hob_nsect); + pi->proto->write_regr(pi, 0, ATA_REG_LBAL, + tf->hob_lbal); + pi->proto->write_regr(pi, 0, ATA_REG_LBAM, + tf->hob_lbam); + pi->proto->write_regr(pi, 0, ATA_REG_LBAH, + tf->hob_lbah); + } + pi->proto->write_regr(pi, 0, ATA_REG_FEATURE, tf->feature); + pi->proto->write_regr(pi, 0, ATA_REG_NSECT, tf->nsect); + pi->proto->write_regr(pi, 0, ATA_REG_LBAL, tf->lbal); + pi->proto->write_regr(pi, 0, ATA_REG_LBAM, tf->lbam); + pi->proto->write_regr(pi, 0, ATA_REG_LBAH, tf->lbah); + } + + if (tf->flags & ATA_TFLAG_DEVICE) + pi->proto->write_regr(pi, 0, ATA_REG_DEVICE, tf->device); + + ata_wait_idle(ap); +} + +static void pata_parport_tf_read(struct ata_port *ap, struct ata_taskfile *tf) +{ + struct pi_adapter *pi = ap->host->private_data; + + tf->status = pi->proto->read_regr(pi, 0, ATA_REG_STATUS); + tf->error = pi->proto->read_regr(pi, 0, ATA_REG_ERR); + tf->nsect = pi->proto->read_regr(pi, 0, ATA_REG_NSECT); + tf->lbal = pi->proto->read_regr(pi, 0, ATA_REG_LBAL); + tf->lbam = pi->proto->read_regr(pi, 0, ATA_REG_LBAM); + tf->lbah = pi->proto->read_regr(pi, 0, ATA_REG_LBAH); + tf->device = pi->proto->read_regr(pi, 0, ATA_REG_DEVICE); + + if (tf->flags & ATA_TFLAG_LBA48) { + pi->proto->write_regr(pi, 1, 6, tf->ctl | ATA_HOB); + tf->hob_feature = pi->proto->read_regr(pi, 0, ATA_REG_ERR); + tf->hob_nsect = pi->proto->read_regr(pi, 0, ATA_REG_NSECT); + tf->hob_lbal = pi->proto->read_regr(pi, 0, ATA_REG_LBAL); + tf->hob_lbam = pi->proto->read_regr(pi, 0, ATA_REG_LBAM); + tf->hob_lbah = pi->proto->read_regr(pi, 0, ATA_REG_LBAH); + pi->proto->write_regr(pi, 1, 6, tf->ctl); + ap->last_ctl = tf->ctl; + } +} + +static void pata_parport_exec_command(struct ata_port *ap, + const struct ata_taskfile *tf) +{ + struct pi_adapter *pi = ap->host->private_data; + + pi->proto->write_regr(pi, 0, ATA_REG_CMD, tf->command); + ata_sff_pause(ap); +} + +static unsigned int pata_parport_data_xfer(struct ata_queued_cmd *qc, + unsigned char *buf, unsigned int buflen, int rw) +{ + struct ata_port *ap = qc->dev->link->ap; + struct pi_adapter *pi = ap->host->private_data; + + if (rw == READ) + pi->proto->read_block(pi, buf, buflen); + else + pi->proto->write_block(pi, buf, buflen); + + return buflen; +} + +static void pata_parport_drain_fifo(struct ata_queued_cmd *qc) +{ + int count; + struct ata_port *ap; + struct pi_adapter *pi; + char junk[2]; + + /* We only need to flush incoming data when a command was running */ + if (qc == NULL || qc->dma_dir == DMA_TO_DEVICE) + return; + + ap = qc->ap; + pi = ap->host->private_data; + /* Drain up to 64K of data before we give up this recovery method */ + for (count = 0; (pata_parport_check_status(ap) & ATA_DRQ) + && count < 65536; count += 2) { + pi->proto->read_block(pi, junk, 2); + } + + if (count) + ata_port_dbg(ap, "drained %d bytes to clear DRQ\n", count); +} + +static struct ata_port_operations pata_parport_port_ops = { + .inherits = &ata_sff_port_ops, + + .softreset = pata_parport_softreset, + .hardreset = NULL, + + .sff_dev_select = pata_parport_dev_select, + .sff_check_status = pata_parport_check_status, + .sff_check_altstatus = pata_parport_check_altstatus, + .sff_tf_load = pata_parport_tf_load, + .sff_tf_read = pata_parport_tf_read, + .sff_exec_command = pata_parport_exec_command, + .sff_data_xfer = pata_parport_data_xfer, + .sff_drain_fifo = pata_parport_drain_fifo, +}; + +static const struct ata_port_info pata_parport_port_info = { + .flags = ATA_FLAG_SLAVE_POSS | ATA_FLAG_PIO_POLLING, + .pio_mask = ATA_PIO0, + /* No DMA */ + .port_ops = &pata_parport_port_ops, +}; + +static void pi_release(struct pi_adapter *pi) +{ + parport_unregister_device(pi->pardev); + if (pi->proto->release_proto) + pi->proto->release_proto(pi); + module_put(pi->proto->owner); +} + +static int default_test_proto(struct pi_adapter *pi, char *scratch) +{ + int j, k; + int e[2] = { 0, 0 }; + + pi->proto->connect(pi); + + for (j = 0; j < 2; j++) { + pi->proto->write_regr(pi, 0, 6, 0xa0 + j * 0x10); + for (k = 0; k < 256; k++) { + pi->proto->write_regr(pi, 0, 2, k ^ 0xaa); + pi->proto->write_regr(pi, 0, 3, k ^ 0x55); + if (pi->proto->read_regr(pi, 0, 2) != (k ^ 0xaa)) + e[j]++; + } + } + pi->proto->disconnect(pi); + + dev_dbg(&pi->dev, "%s: port 0x%x, mode %d, test=(%d,%d)\n", + pi->proto->name, pi->port, pi->mode, e[0], e[1]); + + return e[0] && e[1]; /* not here if both > 0 */ +} + +static int pi_test_proto(struct pi_adapter *pi, char *scratch) +{ + int res; + + parport_claim_or_block(pi->pardev); + if (pi->proto->test_proto) + res = pi->proto->test_proto(pi, scratch, 1); + else + res = default_test_proto(pi, scratch); + parport_release(pi->pardev); + + return res; +} + +static bool pi_probe_mode(struct pi_adapter *pi, int max, char *scratch) +{ + int best, range; + + if (pi->mode != -1) { + if (pi->mode >= max) + return false; + range = 3; + if (pi->mode >= pi->proto->epp_first) + range = 8; + if (range == 8 && pi->port % 8) + return false; + return !pi_test_proto(pi, scratch); + } + best = -1; + for (pi->mode = 0; pi->mode < max; pi->mode++) { + range = 3; + if (pi->mode >= pi->proto->epp_first) + range = 8; + if (range == 8 && pi->port % 8) + break; + if (!pi_test_proto(pi, scratch)) + best = pi->mode; + } + pi->mode = best; + return best > -1; +} + +static bool pi_probe_unit(struct pi_adapter *pi, int unit, char *scratch) +{ + int max, s, e; + + s = unit; + e = s + 1; + + if (s == -1) { + s = 0; + e = pi->proto->max_units; + } + + if (pi->proto->test_port) { + parport_claim_or_block(pi->pardev); + max = pi->proto->test_port(pi); + parport_release(pi->pardev); + } else { + max = pi->proto->max_mode; + } + + if (pi->proto->probe_unit) { + parport_claim_or_block(pi->pardev); + for (pi->unit = s; pi->unit < e; pi->unit++) { + if (pi->proto->probe_unit(pi)) { + parport_release(pi->pardev); + return pi_probe_mode(pi, max, scratch); + } + } + parport_release(pi->pardev); + return false; + } + + return pi_probe_mode(pi, max, scratch); +} + +static void pata_parport_dev_release(struct device *dev) +{ + struct pi_adapter *pi = container_of(dev, struct pi_adapter, dev); + + kfree(pi); +} + +static void pata_parport_bus_release(struct device *dev) +{ + /* nothing to do here but required to avoid warning on device removal */ +} + +static struct bus_type pata_parport_bus_type = { + .name = DRV_NAME, +}; + +static struct device pata_parport_bus = { + .init_name = DRV_NAME, + .release = pata_parport_bus_release, +}; + +static struct scsi_host_template pata_parport_sht = { + PATA_PARPORT_SHT("pata_parport") +}; + +struct pi_device_match { + struct parport *parport; + struct pi_protocol *proto; +}; + +static int pi_find_dev(struct device *dev, void *data) +{ + struct pi_adapter *pi = container_of(dev, struct pi_adapter, dev); + struct pi_device_match *match = data; + + return pi->pardev->port == match->parport && pi->proto == match->proto; +} + +static struct pi_adapter *pi_init_one(struct parport *parport, + struct pi_protocol *pr, int mode, int unit, int delay) +{ + struct pardev_cb par_cb = { }; + char scratch[512]; + const struct ata_port_info *ppi[] = { &pata_parport_port_info }; + struct ata_host *host; + struct pi_adapter *pi; + struct pi_device_match match = { .parport = parport, .proto = pr }; + + /* + * Abort if there's a device already registered on the same parport + * using the same protocol. + */ + if (bus_for_each_dev(&pata_parport_bus_type, NULL, &match, pi_find_dev)) + return NULL; + + pi = kzalloc(sizeof(struct pi_adapter), GFP_KERNEL); + if (!pi) + return NULL; + + /* set up pi->dev before pi_probe_unit() so it can use dev_printk() */ + pi->dev.parent = &pata_parport_bus; + pi->dev.bus = &pata_parport_bus_type; + pi->dev.driver = &pr->driver; + pi->dev.release = pata_parport_dev_release; + pi->dev.id = ida_alloc(&pata_parport_bus_dev_ids, GFP_KERNEL); + if (pi->dev.id < 0) + return NULL; /* pata_parport_dev_release will do kfree(pi) */ + dev_set_name(&pi->dev, "pata_parport.%u", pi->dev.id); + if (device_register(&pi->dev)) { + put_device(&pi->dev); + goto out_ida_free; + } + + pi->proto = pr; + + if (!try_module_get(pi->proto->owner)) + goto out_unreg_dev; + if (pi->proto->init_proto && pi->proto->init_proto(pi) < 0) + goto out_module_put; + + pi->delay = (delay == -1) ? pi->proto->default_delay : delay; + pi->mode = mode; + pi->port = parport->base; + + par_cb.private = pi; + pi->pardev = parport_register_dev_model(parport, DRV_NAME, &par_cb, + pi->dev.id); + if (!pi->pardev) + goto out_module_put; + + if (!pi_probe_unit(pi, unit, scratch)) { + dev_info(&pi->dev, "Adapter not found\n"); + goto out_unreg_parport; + } + + pi->proto->log_adapter(pi, scratch, 1); + + host = ata_host_alloc_pinfo(&pi->pardev->dev, ppi, 1); + if (!host) + goto out_unreg_parport; + dev_set_drvdata(&pi->dev, host); + host->private_data = pi; + + ata_port_desc(host->ports[0], "port %s", pi->pardev->port->name); + ata_port_desc(host->ports[0], "protocol %s", pi->proto->name); + + pi_connect(pi); + if (ata_host_activate(host, 0, NULL, 0, &pata_parport_sht)) + goto out_unreg_parport; + + return pi; + +out_unreg_parport: + pi_disconnect(pi); + parport_unregister_device(pi->pardev); + if (pi->proto->release_proto) + pi->proto->release_proto(pi); +out_module_put: + module_put(pi->proto->owner); +out_unreg_dev: + device_unregister(&pi->dev); +out_ida_free: + ida_free(&pata_parport_bus_dev_ids, pi->dev.id); + return NULL; +} + +int pata_parport_register_driver(struct pi_protocol *pr) +{ + int error; + struct parport *parport; + int port_num; + + pr->driver.bus = &pata_parport_bus_type; + pr->driver.name = pr->name; + error = driver_register(&pr->driver); + if (error) + return error; + + mutex_lock(&pi_mutex); + error = idr_alloc(&protocols, pr, 0, 0, GFP_KERNEL); + if (error < 0) { + driver_unregister(&pr->driver); + mutex_unlock(&pi_mutex); + return error; + } + + pr_info("pata_parport: protocol %s registered\n", pr->name); + + if (probe) { + /* probe all parports using this protocol */ + idr_for_each_entry(&parport_list, parport, port_num) + pi_init_one(parport, pr, -1, 0, -1); + } + mutex_unlock(&pi_mutex); + + return 0; +} +EXPORT_SYMBOL_GPL(pata_parport_register_driver); + +void pata_parport_unregister_driver(struct pi_protocol *pr) +{ + struct pi_protocol *pr_iter; + int id = -1; + + mutex_lock(&pi_mutex); + idr_for_each_entry(&protocols, pr_iter, id) { + if (pr_iter == pr) + break; + } + idr_remove(&protocols, id); + mutex_unlock(&pi_mutex); + driver_unregister(&pr->driver); +} +EXPORT_SYMBOL_GPL(pata_parport_unregister_driver); + +static ssize_t new_device_store(struct bus_type *bus, const char *buf, + size_t count) +{ + char port[12] = "auto"; + char protocol[8] = "auto"; + int mode = -1, unit = -1, delay = -1; + struct pi_protocol *pr, *pr_wanted; + struct device_driver *drv; + struct parport *parport; + int port_num, port_wanted, pr_num; + bool ok = false; + + if (sscanf(buf, "%11s %7s %d %d %d", + port, protocol, &mode, &unit, &delay) < 1) + return -EINVAL; + + if (sscanf(port, "parport%u", &port_wanted) < 1) { + if (strcmp(port, "auto")) { + pr_err("invalid port name %s\n", port); + return -EINVAL; + } + port_wanted = -1; + } + + drv = driver_find(protocol, &pata_parport_bus_type); + if (!drv) { + if (strcmp(protocol, "auto")) { + pr_err("protocol %s not found\n", protocol); + return -EINVAL; + } + pr_wanted = NULL; + } else { + pr_wanted = container_of(drv, struct pi_protocol, driver); + } + + mutex_lock(&pi_mutex); + /* walk all parports */ + idr_for_each_entry(&parport_list, parport, port_num) { + if (port_num == port_wanted || port_wanted == -1) { + parport = parport_find_number(port_num); + if (!parport) { + pr_err("no such port %s\n", port); + mutex_unlock(&pi_mutex); + return -ENODEV; + } + /* walk all protocols */ + idr_for_each_entry(&protocols, pr, pr_num) { + if (pr == pr_wanted || !pr_wanted) + if (pi_init_one(parport, pr, mode, unit, + delay)) + ok = true; + } + parport_put_port(parport); + } + } + mutex_unlock(&pi_mutex); + if (!ok) + return -ENODEV; + + return count; +} +static BUS_ATTR_WO(new_device); + +static void pi_remove_one(struct device *dev) +{ + struct ata_host *host = dev_get_drvdata(dev); + struct pi_adapter *pi = host->private_data; + + ata_host_detach(host); + pi_disconnect(pi); + pi_release(pi); + device_unregister(dev); + ida_free(&pata_parport_bus_dev_ids, dev->id); + /* pata_parport_dev_release will do kfree(pi) */ +} + +static ssize_t delete_device_store(struct bus_type *bus, const char *buf, + size_t count) +{ + struct device *dev; + + mutex_lock(&pi_mutex); + dev = bus_find_device_by_name(bus, NULL, buf); + if (!dev) { + mutex_unlock(&pi_mutex); + return -ENODEV; + } + + pi_remove_one(dev); + mutex_unlock(&pi_mutex); + + return count; +} +static BUS_ATTR_WO(delete_device); + +static void pata_parport_attach(struct parport *port) +{ + struct pi_protocol *pr; + int pr_num, id; + + mutex_lock(&pi_mutex); + id = idr_alloc(&parport_list, port, port->number, port->number, + GFP_KERNEL); + if (id < 0) { + mutex_unlock(&pi_mutex); + return; + } + + if (probe) { + /* probe this port using all protocols */ + idr_for_each_entry(&protocols, pr, pr_num) + pi_init_one(port, pr, -1, 0, -1); + } + mutex_unlock(&pi_mutex); +} + +static int pi_remove_port(struct device *dev, void *p) +{ + struct ata_host *host = dev_get_drvdata(dev); + struct pi_adapter *pi = host->private_data; + + if (pi->pardev->port == p) + pi_remove_one(dev); + + return 0; +} + +static void pata_parport_detach(struct parport *port) +{ + mutex_lock(&pi_mutex); + bus_for_each_dev(&pata_parport_bus_type, NULL, port, pi_remove_port); + idr_remove(&parport_list, port->number); + mutex_unlock(&pi_mutex); +} + +static struct parport_driver pata_parport_driver = { + .name = DRV_NAME, + .match_port = pata_parport_attach, + .detach = pata_parport_detach, + .devmodel = true, +}; + +static __init int pata_parport_init(void) +{ + int error; + + error = bus_register(&pata_parport_bus_type); + if (error) { + pr_err("failed to register pata_parport bus, error: %d\n", error); + return error; + } + + error = device_register(&pata_parport_bus); + if (error) { + pr_err("failed to register pata_parport bus, error: %d\n", error); + goto out_unregister_bus; + } + + error = bus_create_file(&pata_parport_bus_type, &bus_attr_new_device); + if (error) { + pr_err("unable to create sysfs file, error: %d\n", error); + goto out_unregister_dev; + } + + error = bus_create_file(&pata_parport_bus_type, &bus_attr_delete_device); + if (error) { + pr_err("unable to create sysfs file, error: %d\n", error); + goto out_remove_new; + } + + error = parport_register_driver(&pata_parport_driver); + if (error) { + pr_err("unable to register parport driver, error: %d\n", error); + goto out_remove_del; + } + + return 0; + +out_remove_del: + bus_remove_file(&pata_parport_bus_type, &bus_attr_delete_device); +out_remove_new: + bus_remove_file(&pata_parport_bus_type, &bus_attr_new_device); +out_unregister_dev: + device_unregister(&pata_parport_bus); +out_unregister_bus: + bus_unregister(&pata_parport_bus_type); + return error; +} + +static __exit void pata_parport_exit(void) +{ + parport_unregister_driver(&pata_parport_driver); + bus_remove_file(&pata_parport_bus_type, &bus_attr_new_device); + bus_remove_file(&pata_parport_bus_type, &bus_attr_delete_device); + device_unregister(&pata_parport_bus); + bus_unregister(&pata_parport_bus_type); +} + +MODULE_AUTHOR("Ondrej Zary"); +MODULE_DESCRIPTION("driver for parallel port ATA adapters"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("paride"); + +module_init(pata_parport_init); +module_exit(pata_parport_exit); diff --git a/drivers/block/paride/Kconfig b/drivers/block/paride/Kconfig index a295634597ba..01e4ef3655c1 100644 --- a/drivers/block/paride/Kconfig +++ b/drivers/block/paride/Kconfig @@ -92,11 +92,11 @@ config PARIDE_PG later fully support this driver. comment "Parallel IDE protocol modules" - depends on PARIDE + depends on PARIDE || PATA_PARPORT config PARIDE_ATEN tristate "ATEN EH-100 protocol" - depends on PARIDE + depends on PARIDE || PATA_PARPORT help This option enables support for the ATEN EH-100 parallel port IDE protocol. This protocol is used in some inexpensive low performance @@ -109,7 +109,7 @@ config PARIDE_ATEN config PARIDE_BPCK tristate "MicroSolutions backpack (Series 5) protocol" - depends on PARIDE + depends on PARIDE || PATA_PARPORT help This option enables support for the Micro Solutions BACKPACK parallel port Series 5 IDE protocol. (Most BACKPACK drives made @@ -127,7 +127,7 @@ config PARIDE_BPCK config PARIDE_BPCK6 tristate "MicroSolutions backpack (Series 6) protocol" - depends on PARIDE && !64BIT + depends on (PARIDE || PATA_PARPORT) && !64BIT help This option enables support for the Micro Solutions BACKPACK parallel port Series 6 IDE protocol. (Most BACKPACK drives made @@ -146,7 +146,7 @@ config PARIDE_BPCK6 config PARIDE_COMM tristate "DataStor Commuter protocol" - depends on PARIDE + depends on PARIDE || PATA_PARPORT help This option enables support for the Commuter parallel port IDE protocol from DataStor. If you chose to build PARIDE support @@ -157,7 +157,7 @@ config PARIDE_COMM config PARIDE_DSTR tristate "DataStor EP-2000 protocol" - depends on PARIDE + depends on PARIDE || PATA_PARPORT help This option enables support for the EP-2000 parallel port IDE protocol from DataStor. If you chose to build PARIDE support @@ -168,7 +168,7 @@ config PARIDE_DSTR config PARIDE_FIT2 tristate "FIT TD-2000 protocol" - depends on PARIDE + depends on PARIDE || PATA_PARPORT help This option enables support for the TD-2000 parallel port IDE protocol from Fidelity International Technology. This is a simple @@ -181,7 +181,7 @@ config PARIDE_FIT2 config PARIDE_FIT3 tristate "FIT TD-3000 protocol" - depends on PARIDE + depends on PARIDE || PATA_PARPORT help This option enables support for the TD-3000 parallel port IDE protocol from Fidelity International Technology. This protocol is @@ -194,7 +194,7 @@ config PARIDE_FIT3 config PARIDE_EPAT tristate "Shuttle EPAT/EPEZ protocol" - depends on PARIDE + depends on PARIDE || PATA_PARPORT help This option enables support for the EPAT parallel port IDE protocol. EPAT is a parallel port IDE adapter manufactured by Shuttle @@ -216,7 +216,7 @@ config PARIDE_EPATC8 config PARIDE_EPIA tristate "Shuttle EPIA protocol" - depends on PARIDE + depends on PARIDE || PATA_PARPORT help This option enables support for the (obsolete) EPIA parallel port IDE protocol from Shuttle Technology. This adapter can still be @@ -228,7 +228,7 @@ config PARIDE_EPIA config PARIDE_FRIQ tristate "Freecom IQ ASIC-2 protocol" - depends on PARIDE + depends on PARIDE || PATA_PARPORT help This option enables support for version 2 of the Freecom IQ parallel port IDE adapter. This adapter is used by the Maxell Superdisk @@ -240,7 +240,7 @@ config PARIDE_FRIQ config PARIDE_FRPW tristate "FreeCom power protocol" - depends on PARIDE + depends on PARIDE || PATA_PARPORT help This option enables support for the Freecom power parallel port IDE protocol. If you chose to build PARIDE support into your kernel, you @@ -251,7 +251,7 @@ config PARIDE_FRPW config PARIDE_KBIC tristate "KingByte KBIC-951A/971A protocols" - depends on PARIDE + depends on PARIDE || PATA_PARPORT help This option enables support for the KBIC-951A and KBIC-971A parallel port IDE protocols from KingByte Information Corp. KingByte's @@ -264,7 +264,7 @@ config PARIDE_KBIC config PARIDE_KTTI tristate "KT PHd protocol" - depends on PARIDE + depends on PARIDE || PATA_PARPORT help This option enables support for the "PHd" parallel port IDE protocol from KT Technology. This is a simple (low speed) adapter that is @@ -277,7 +277,7 @@ config PARIDE_KTTI config PARIDE_ON20 tristate "OnSpec 90c20 protocol" - depends on PARIDE + depends on PARIDE || PATA_PARPORT help This option enables support for the (obsolete) 90c20 parallel port IDE protocol from OnSpec (often marketed under the ValuStore brand @@ -289,7 +289,7 @@ config PARIDE_ON20 config PARIDE_ON26 tristate "OnSpec 90c26 protocol" - depends on PARIDE + depends on PARIDE || PATA_PARPORT help This option enables support for the 90c26 parallel port IDE protocol from OnSpec Electronics (often marketed under the ValuStore brand diff --git a/drivers/block/paride/paride.h b/drivers/block/paride/paride.h index ddb9e589da7f..24dcfadb782d 100644 --- a/drivers/block/paride/paride.h +++ b/drivers/block/paride/paride.h @@ -1,3 +1,15 @@ +/* + * The low-level protocol modules are used by either paride or pata_parport. + * These two are mutually exclusive because the compiled low-level protocol + * modules are not compatible. + * When PATA_PARPORT is enabled, include pata_parport.h instead of the rest + * of this file. + */ + +#if IS_ENABLED(CONFIG_PATA_PARPORT) +#include + +#else #ifndef __DRIVERS_PARIDE_H__ #define __DRIVERS_PARIDE_H__ @@ -170,3 +182,4 @@ void pi_unregister_driver(void *); #endif /* __DRIVERS_PARIDE_H__ */ /* end of paride.h */ +#endif /* IS_ENABLED(CONFIG_PATA_PARPORT) */ diff --git a/include/linux/pata_parport.h b/include/linux/pata_parport.h new file mode 100644 index 000000000000..58781846f282 --- /dev/null +++ b/include/linux/pata_parport.h @@ -0,0 +1,111 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * pata_parport.h (c) 1997-8 Grant R. Guenther + * Under the terms of the GPL. + * + * This file defines the interface for parallel port IDE adapter chip drivers. + */ + +#ifndef LINUX_PATA_PARPORT_H +#define LINUX_PATA_PARPORT_H + +#include + +#define PI_PCD 1 /* dummy for paride protocol modules */ + +struct pi_adapter { + struct device dev; + struct pi_protocol *proto; /* adapter protocol */ + int port; /* base address of parallel port */ + int mode; /* transfer mode in use */ + int delay; /* adapter delay setting */ + int devtype; /* dummy for paride protocol modules */ + char *device; /* dummy for paride protocol modules */ + int unit; /* unit number for chained adapters */ + int saved_r0; /* saved port state */ + int saved_r2; /* saved port state */ + unsigned long private; /* for protocol module */ + struct pardevice *pardev; /* pointer to pardevice */ +}; + +typedef struct pi_adapter PIA; /* for paride protocol modules */ + +/* registers are addressed as (cont,regr) + * cont: 0 for command register file, 1 for control register(s) + * regr: 0-7 for register number. + */ + +/* macros and functions exported to the protocol modules */ +#define delay_p (pi->delay ? udelay(pi->delay) : (void)0) +#define out_p(offs, byte) do { outb(byte, pi->port + offs); delay_p; } while (0) +#define in_p(offs) (delay_p, inb(pi->port + offs)) + +#define w0(byte) out_p(0, byte) +#define r0() in_p(0) +#define w1(byte) out_p(1, byte) +#define r1() in_p(1) +#define w2(byte) out_p(2, byte) +#define r2() in_p(2) +#define w3(byte) out_p(3, byte) +#define w4(byte) out_p(4, byte) +#define r4() in_p(4) +#define w4w(data) do { outw(data, pi->port + 4); delay_p; } while (0) +#define w4l(data) do { outl(data, pi->port + 4); delay_p; } while (0) +#define r4w() (delay_p, inw(pi->port + 4)) +#define r4l() (delay_p, inl(pi->port + 4)) + +static inline u16 pi_swab16(char *b, int k) +{ + union { u16 u; char t[2]; } r; + + r.t[0] = b[2 * k + 1]; r.t[1] = b[2 * k]; + return r.u; +} + +static inline u32 pi_swab32(char *b, int k) +{ + union { u32 u; char f[4]; } r; + + r.f[0] = b[4 * k + 1]; r.f[1] = b[4 * k]; + r.f[2] = b[4 * k + 3]; r.f[3] = b[4 * k + 2]; + return r.u; +} + +struct pi_protocol { + char name[8]; + + int max_mode; + int epp_first; /* modes >= this use 8 ports */ + + int default_delay; + int max_units; /* max chained units probed for */ + + void (*write_regr)(struct pi_adapter *pi, int cont, int regr, int val); + int (*read_regr)(struct pi_adapter *pi, int cont, int regr); + void (*write_block)(struct pi_adapter *pi, char *buf, int count); + void (*read_block)(struct pi_adapter *pi, char *buf, int count); + + void (*connect)(struct pi_adapter *pi); + void (*disconnect)(struct pi_adapter *pi); + + int (*test_port)(struct pi_adapter *pi); + int (*probe_unit)(struct pi_adapter *pi); + int (*test_proto)(struct pi_adapter *pi, char *scratch, int verbose); + void (*log_adapter)(struct pi_adapter *pi, char *scratch, int verbose); + + int (*init_proto)(struct pi_adapter *pi); + void (*release_proto)(struct pi_adapter *pi); + struct module *owner; + struct device_driver driver; + struct scsi_host_template sht; +}; + +#define PATA_PARPORT_SHT ATA_PIO_SHT + +int pata_parport_register_driver(struct pi_protocol *pr); +void pata_parport_unregister_driver(struct pi_protocol *pr); +/* defines for old paride protocol modules */ +#define paride_register pata_parport_register_driver +#define paride_unregister pata_parport_unregister_driver + +#endif /* LINUX_PATA_PARPORT_H */ -- cgit v1.2.3 From e1d5d71d189f290343fb1f18eecf77335c5d1ef3 Mon Sep 17 00:00:00 2001 From: Michael Grzeschik Date: Fri, 27 Jan 2023 00:14:53 +0100 Subject: usb: uvc: move media/v4l2-uvc.h to usb/uvc.h Since the headerfile is only used in usb devices it is better placed with the other usb files. Reviewed-by: Laurent Pinchart Reviewed-by: Daniel Scally Tested-by: Daniel Scally Signed-off-by: Michael Grzeschik Link: https://lore.kernel.org/r/20230126231456.3402323-3-m.grzeschik@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/media/usb/uvc/uvc_ctrl.c | 2 +- drivers/media/usb/uvc/uvc_driver.c | 2 +- drivers/usb/gadget/function/uvc_v4l2.c | 2 +- include/linux/usb/uvc.h | 367 +++++++++++++++++++++++++++++++++ include/media/v4l2-uvc.h | 367 --------------------------------- 5 files changed, 370 insertions(+), 370 deletions(-) create mode 100644 include/linux/usb/uvc.h delete mode 100644 include/media/v4l2-uvc.h (limited to 'include/linux') diff --git a/drivers/media/usb/uvc/uvc_ctrl.c b/drivers/media/usb/uvc/uvc_ctrl.c index c3aeba3fe31b..5e9d3da862dd 100644 --- a/drivers/media/usb/uvc/uvc_ctrl.c +++ b/drivers/media/usb/uvc/uvc_ctrl.c @@ -14,13 +14,13 @@ #include #include #include +#include #include #include #include #include #include #include -#include #include "uvcvideo.h" diff --git a/drivers/media/usb/uvc/uvc_driver.c b/drivers/media/usb/uvc/uvc_driver.c index 11f3d716b5bf..edf8c4a201a8 100644 --- a/drivers/media/usb/uvc/uvc_driver.c +++ b/drivers/media/usb/uvc/uvc_driver.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include @@ -21,7 +22,6 @@ #include #include -#include #include "uvcvideo.h" diff --git a/drivers/usb/gadget/function/uvc_v4l2.c b/drivers/usb/gadget/function/uvc_v4l2.c index a189b08bba80..7435df0cf2a8 100644 --- a/drivers/usb/gadget/function/uvc_v4l2.c +++ b/drivers/usb/gadget/function/uvc_v4l2.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include @@ -18,7 +19,6 @@ #include #include #include -#include #include "f_uvc.h" #include "uvc.h" diff --git a/include/linux/usb/uvc.h b/include/linux/usb/uvc.h new file mode 100644 index 000000000000..b010a36fc1d9 --- /dev/null +++ b/include/linux/usb/uvc.h @@ -0,0 +1,367 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * v4l2 uvc internal API header + * + * Some commonly needed functions for uvc drivers + */ + +#ifndef __LINUX_V4L2_UVC_H +#define __LINUX_V4L2_UVC_H + +/* ------------------------------------------------------------------------ + * GUIDs + */ +#define UVC_GUID_UVC_CAMERA \ + {0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, \ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01} +#define UVC_GUID_UVC_OUTPUT \ + {0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, \ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x02} +#define UVC_GUID_UVC_MEDIA_TRANSPORT_INPUT \ + {0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, \ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x03} +#define UVC_GUID_UVC_PROCESSING \ + {0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, \ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01, 0x01} +#define UVC_GUID_UVC_SELECTOR \ + {0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, \ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01, 0x02} +#define UVC_GUID_EXT_GPIO_CONTROLLER \ + {0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, \ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01, 0x03} + +#define UVC_GUID_FORMAT_MJPEG \ + { 'M', 'J', 'P', 'G', 0x00, 0x00, 0x10, 0x00, \ + 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} +#define UVC_GUID_FORMAT_YUY2 \ + { 'Y', 'U', 'Y', '2', 0x00, 0x00, 0x10, 0x00, \ + 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} +#define UVC_GUID_FORMAT_YUY2_ISIGHT \ + { 'Y', 'U', 'Y', '2', 0x00, 0x00, 0x10, 0x00, \ + 0x80, 0x00, 0x00, 0x00, 0x00, 0x38, 0x9b, 0x71} +#define UVC_GUID_FORMAT_NV12 \ + { 'N', 'V', '1', '2', 0x00, 0x00, 0x10, 0x00, \ + 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} +#define UVC_GUID_FORMAT_YV12 \ + { 'Y', 'V', '1', '2', 0x00, 0x00, 0x10, 0x00, \ + 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} +#define UVC_GUID_FORMAT_I420 \ + { 'I', '4', '2', '0', 0x00, 0x00, 0x10, 0x00, \ + 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} +#define UVC_GUID_FORMAT_UYVY \ + { 'U', 'Y', 'V', 'Y', 0x00, 0x00, 0x10, 0x00, \ + 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} +#define UVC_GUID_FORMAT_Y800 \ + { 'Y', '8', '0', '0', 0x00, 0x00, 0x10, 0x00, \ + 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} +#define UVC_GUID_FORMAT_Y8 \ + { 'Y', '8', ' ', ' ', 0x00, 0x00, 0x10, 0x00, \ + 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} +#define UVC_GUID_FORMAT_Y10 \ + { 'Y', '1', '0', ' ', 0x00, 0x00, 0x10, 0x00, \ + 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} +#define UVC_GUID_FORMAT_Y12 \ + { 'Y', '1', '2', ' ', 0x00, 0x00, 0x10, 0x00, \ + 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} +#define UVC_GUID_FORMAT_Y16 \ + { 'Y', '1', '6', ' ', 0x00, 0x00, 0x10, 0x00, \ + 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} +#define UVC_GUID_FORMAT_BY8 \ + { 'B', 'Y', '8', ' ', 0x00, 0x00, 0x10, 0x00, \ + 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} +#define UVC_GUID_FORMAT_BA81 \ + { 'B', 'A', '8', '1', 0x00, 0x00, 0x10, 0x00, \ + 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} +#define UVC_GUID_FORMAT_GBRG \ + { 'G', 'B', 'R', 'G', 0x00, 0x00, 0x10, 0x00, \ + 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} +#define UVC_GUID_FORMAT_GRBG \ + { 'G', 'R', 'B', 'G', 0x00, 0x00, 0x10, 0x00, \ + 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} +#define UVC_GUID_FORMAT_RGGB \ + { 'R', 'G', 'G', 'B', 0x00, 0x00, 0x10, 0x00, \ + 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} +#define UVC_GUID_FORMAT_BG16 \ + { 'B', 'G', '1', '6', 0x00, 0x00, 0x10, 0x00, \ + 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} +#define UVC_GUID_FORMAT_GB16 \ + { 'G', 'B', '1', '6', 0x00, 0x00, 0x10, 0x00, \ + 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} +#define UVC_GUID_FORMAT_RG16 \ + { 'R', 'G', '1', '6', 0x00, 0x00, 0x10, 0x00, \ + 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} +#define UVC_GUID_FORMAT_GR16 \ + { 'G', 'R', '1', '6', 0x00, 0x00, 0x10, 0x00, \ + 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} +#define UVC_GUID_FORMAT_RGBP \ + { 'R', 'G', 'B', 'P', 0x00, 0x00, 0x10, 0x00, \ + 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} +#define UVC_GUID_FORMAT_BGR3 \ + { 0x7d, 0xeb, 0x36, 0xe4, 0x4f, 0x52, 0xce, 0x11, \ + 0x9f, 0x53, 0x00, 0x20, 0xaf, 0x0b, 0xa7, 0x70} +#define UVC_GUID_FORMAT_BGR4 \ + { 0x7e, 0xeb, 0x36, 0xe4, 0x4f, 0x52, 0xce, 0x11, \ + 0x9f, 0x53, 0x00, 0x20, 0xaf, 0x0b, 0xa7, 0x70} +#define UVC_GUID_FORMAT_M420 \ + { 'M', '4', '2', '0', 0x00, 0x00, 0x10, 0x00, \ + 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} + +#define UVC_GUID_FORMAT_H264 \ + { 'H', '2', '6', '4', 0x00, 0x00, 0x10, 0x00, \ + 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} +#define UVC_GUID_FORMAT_H265 \ + { 'H', '2', '6', '5', 0x00, 0x00, 0x10, 0x00, \ + 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} +#define UVC_GUID_FORMAT_Y8I \ + { 'Y', '8', 'I', ' ', 0x00, 0x00, 0x10, 0x00, \ + 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} +#define UVC_GUID_FORMAT_Y12I \ + { 'Y', '1', '2', 'I', 0x00, 0x00, 0x10, 0x00, \ + 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} +#define UVC_GUID_FORMAT_Z16 \ + { 'Z', '1', '6', ' ', 0x00, 0x00, 0x10, 0x00, \ + 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} +#define UVC_GUID_FORMAT_RW10 \ + { 'R', 'W', '1', '0', 0x00, 0x00, 0x10, 0x00, \ + 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} +#define UVC_GUID_FORMAT_INVZ \ + { 'I', 'N', 'V', 'Z', 0x90, 0x2d, 0x58, 0x4a, \ + 0x92, 0x0b, 0x77, 0x3f, 0x1f, 0x2c, 0x55, 0x6b} +#define UVC_GUID_FORMAT_INZI \ + { 'I', 'N', 'Z', 'I', 0x66, 0x1a, 0x42, 0xa2, \ + 0x90, 0x65, 0xd0, 0x18, 0x14, 0xa8, 0xef, 0x8a} +#define UVC_GUID_FORMAT_INVI \ + { 'I', 'N', 'V', 'I', 0xdb, 0x57, 0x49, 0x5e, \ + 0x8e, 0x3f, 0xf4, 0x79, 0x53, 0x2b, 0x94, 0x6f} +#define UVC_GUID_FORMAT_CNF4 \ + { 'C', ' ', ' ', ' ', 0x00, 0x00, 0x10, 0x00, \ + 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} + +#define UVC_GUID_FORMAT_D3DFMT_L8 \ + {0x32, 0x00, 0x00, 0x00, 0x00, 0x00, 0x10, 0x00, \ + 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} +#define UVC_GUID_FORMAT_KSMEDIA_L8_IR \ + {0x32, 0x00, 0x00, 0x00, 0x02, 0x00, 0x10, 0x00, \ + 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} + +#define UVC_GUID_FORMAT_HEVC \ + { 'H', 'E', 'V', 'C', 0x00, 0x00, 0x10, 0x00, \ + 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} + +/* ------------------------------------------------------------------------ + * Video formats + */ + +struct uvc_format_desc { + char *name; + u8 guid[16]; + u32 fcc; +}; + +static struct uvc_format_desc uvc_fmts[] = { + { + .name = "YUV 4:2:2 (YUYV)", + .guid = UVC_GUID_FORMAT_YUY2, + .fcc = V4L2_PIX_FMT_YUYV, + }, + { + .name = "YUV 4:2:2 (YUYV)", + .guid = UVC_GUID_FORMAT_YUY2_ISIGHT, + .fcc = V4L2_PIX_FMT_YUYV, + }, + { + .name = "YUV 4:2:0 (NV12)", + .guid = UVC_GUID_FORMAT_NV12, + .fcc = V4L2_PIX_FMT_NV12, + }, + { + .name = "MJPEG", + .guid = UVC_GUID_FORMAT_MJPEG, + .fcc = V4L2_PIX_FMT_MJPEG, + }, + { + .name = "YVU 4:2:0 (YV12)", + .guid = UVC_GUID_FORMAT_YV12, + .fcc = V4L2_PIX_FMT_YVU420, + }, + { + .name = "YUV 4:2:0 (I420)", + .guid = UVC_GUID_FORMAT_I420, + .fcc = V4L2_PIX_FMT_YUV420, + }, + { + .name = "YUV 4:2:0 (M420)", + .guid = UVC_GUID_FORMAT_M420, + .fcc = V4L2_PIX_FMT_M420, + }, + { + .name = "YUV 4:2:2 (UYVY)", + .guid = UVC_GUID_FORMAT_UYVY, + .fcc = V4L2_PIX_FMT_UYVY, + }, + { + .name = "Greyscale 8-bit (Y800)", + .guid = UVC_GUID_FORMAT_Y800, + .fcc = V4L2_PIX_FMT_GREY, + }, + { + .name = "Greyscale 8-bit (Y8 )", + .guid = UVC_GUID_FORMAT_Y8, + .fcc = V4L2_PIX_FMT_GREY, + }, + { + .name = "Greyscale 8-bit (D3DFMT_L8)", + .guid = UVC_GUID_FORMAT_D3DFMT_L8, + .fcc = V4L2_PIX_FMT_GREY, + }, + { + .name = "IR 8-bit (L8_IR)", + .guid = UVC_GUID_FORMAT_KSMEDIA_L8_IR, + .fcc = V4L2_PIX_FMT_GREY, + }, + { + .name = "Greyscale 10-bit (Y10 )", + .guid = UVC_GUID_FORMAT_Y10, + .fcc = V4L2_PIX_FMT_Y10, + }, + { + .name = "Greyscale 12-bit (Y12 )", + .guid = UVC_GUID_FORMAT_Y12, + .fcc = V4L2_PIX_FMT_Y12, + }, + { + .name = "Greyscale 16-bit (Y16 )", + .guid = UVC_GUID_FORMAT_Y16, + .fcc = V4L2_PIX_FMT_Y16, + }, + { + .name = "BGGR Bayer (BY8 )", + .guid = UVC_GUID_FORMAT_BY8, + .fcc = V4L2_PIX_FMT_SBGGR8, + }, + { + .name = "BGGR Bayer (BA81)", + .guid = UVC_GUID_FORMAT_BA81, + .fcc = V4L2_PIX_FMT_SBGGR8, + }, + { + .name = "GBRG Bayer (GBRG)", + .guid = UVC_GUID_FORMAT_GBRG, + .fcc = V4L2_PIX_FMT_SGBRG8, + }, + { + .name = "GRBG Bayer (GRBG)", + .guid = UVC_GUID_FORMAT_GRBG, + .fcc = V4L2_PIX_FMT_SGRBG8, + }, + { + .name = "RGGB Bayer (RGGB)", + .guid = UVC_GUID_FORMAT_RGGB, + .fcc = V4L2_PIX_FMT_SRGGB8, + }, + { + .name = "RGB565", + .guid = UVC_GUID_FORMAT_RGBP, + .fcc = V4L2_PIX_FMT_RGB565, + }, + { + .name = "BGR 8:8:8 (BGR3)", + .guid = UVC_GUID_FORMAT_BGR3, + .fcc = V4L2_PIX_FMT_BGR24, + }, + { + .name = "BGRA/X 8:8:8:8 (BGR4)", + .guid = UVC_GUID_FORMAT_BGR4, + .fcc = V4L2_PIX_FMT_XBGR32, + }, + { + .name = "H.264", + .guid = UVC_GUID_FORMAT_H264, + .fcc = V4L2_PIX_FMT_H264, + }, + { + .name = "H.265", + .guid = UVC_GUID_FORMAT_H265, + .fcc = V4L2_PIX_FMT_HEVC, + }, + { + .name = "Greyscale 8 L/R (Y8I)", + .guid = UVC_GUID_FORMAT_Y8I, + .fcc = V4L2_PIX_FMT_Y8I, + }, + { + .name = "Greyscale 12 L/R (Y12I)", + .guid = UVC_GUID_FORMAT_Y12I, + .fcc = V4L2_PIX_FMT_Y12I, + }, + { + .name = "Depth data 16-bit (Z16)", + .guid = UVC_GUID_FORMAT_Z16, + .fcc = V4L2_PIX_FMT_Z16, + }, + { + .name = "Bayer 10-bit (SRGGB10P)", + .guid = UVC_GUID_FORMAT_RW10, + .fcc = V4L2_PIX_FMT_SRGGB10P, + }, + { + .name = "Bayer 16-bit (SBGGR16)", + .guid = UVC_GUID_FORMAT_BG16, + .fcc = V4L2_PIX_FMT_SBGGR16, + }, + { + .name = "Bayer 16-bit (SGBRG16)", + .guid = UVC_GUID_FORMAT_GB16, + .fcc = V4L2_PIX_FMT_SGBRG16, + }, + { + .name = "Bayer 16-bit (SRGGB16)", + .guid = UVC_GUID_FORMAT_RG16, + .fcc = V4L2_PIX_FMT_SRGGB16, + }, + { + .name = "Bayer 16-bit (SGRBG16)", + .guid = UVC_GUID_FORMAT_GR16, + .fcc = V4L2_PIX_FMT_SGRBG16, + }, + { + .name = "Depth data 16-bit (Z16)", + .guid = UVC_GUID_FORMAT_INVZ, + .fcc = V4L2_PIX_FMT_Z16, + }, + { + .name = "Greyscale 10-bit (Y10 )", + .guid = UVC_GUID_FORMAT_INVI, + .fcc = V4L2_PIX_FMT_Y10, + }, + { + .name = "IR:Depth 26-bit (INZI)", + .guid = UVC_GUID_FORMAT_INZI, + .fcc = V4L2_PIX_FMT_INZI, + }, + { + .name = "4-bit Depth Confidence (Packed)", + .guid = UVC_GUID_FORMAT_CNF4, + .fcc = V4L2_PIX_FMT_CNF4, + }, + { + .name = "HEVC", + .guid = UVC_GUID_FORMAT_HEVC, + .fcc = V4L2_PIX_FMT_HEVC, + }, +}; + +static inline struct uvc_format_desc *uvc_format_by_guid(const u8 guid[16]) +{ + unsigned int len = ARRAY_SIZE(uvc_fmts); + unsigned int i; + + for (i = 0; i < len; ++i) { + if (memcmp(guid, uvc_fmts[i].guid, 16) == 0) + return &uvc_fmts[i]; + } + + return NULL; +} + +#endif /* __LINUX_V4L2_UVC_H */ diff --git a/include/media/v4l2-uvc.h b/include/media/v4l2-uvc.h deleted file mode 100644 index b010a36fc1d9..000000000000 --- a/include/media/v4l2-uvc.h +++ /dev/null @@ -1,367 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * v4l2 uvc internal API header - * - * Some commonly needed functions for uvc drivers - */ - -#ifndef __LINUX_V4L2_UVC_H -#define __LINUX_V4L2_UVC_H - -/* ------------------------------------------------------------------------ - * GUIDs - */ -#define UVC_GUID_UVC_CAMERA \ - {0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, \ - 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01} -#define UVC_GUID_UVC_OUTPUT \ - {0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, \ - 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x02} -#define UVC_GUID_UVC_MEDIA_TRANSPORT_INPUT \ - {0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, \ - 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x03} -#define UVC_GUID_UVC_PROCESSING \ - {0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, \ - 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01, 0x01} -#define UVC_GUID_UVC_SELECTOR \ - {0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, \ - 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01, 0x02} -#define UVC_GUID_EXT_GPIO_CONTROLLER \ - {0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, \ - 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01, 0x03} - -#define UVC_GUID_FORMAT_MJPEG \ - { 'M', 'J', 'P', 'G', 0x00, 0x00, 0x10, 0x00, \ - 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} -#define UVC_GUID_FORMAT_YUY2 \ - { 'Y', 'U', 'Y', '2', 0x00, 0x00, 0x10, 0x00, \ - 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} -#define UVC_GUID_FORMAT_YUY2_ISIGHT \ - { 'Y', 'U', 'Y', '2', 0x00, 0x00, 0x10, 0x00, \ - 0x80, 0x00, 0x00, 0x00, 0x00, 0x38, 0x9b, 0x71} -#define UVC_GUID_FORMAT_NV12 \ - { 'N', 'V', '1', '2', 0x00, 0x00, 0x10, 0x00, \ - 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} -#define UVC_GUID_FORMAT_YV12 \ - { 'Y', 'V', '1', '2', 0x00, 0x00, 0x10, 0x00, \ - 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} -#define UVC_GUID_FORMAT_I420 \ - { 'I', '4', '2', '0', 0x00, 0x00, 0x10, 0x00, \ - 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} -#define UVC_GUID_FORMAT_UYVY \ - { 'U', 'Y', 'V', 'Y', 0x00, 0x00, 0x10, 0x00, \ - 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} -#define UVC_GUID_FORMAT_Y800 \ - { 'Y', '8', '0', '0', 0x00, 0x00, 0x10, 0x00, \ - 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} -#define UVC_GUID_FORMAT_Y8 \ - { 'Y', '8', ' ', ' ', 0x00, 0x00, 0x10, 0x00, \ - 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} -#define UVC_GUID_FORMAT_Y10 \ - { 'Y', '1', '0', ' ', 0x00, 0x00, 0x10, 0x00, \ - 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} -#define UVC_GUID_FORMAT_Y12 \ - { 'Y', '1', '2', ' ', 0x00, 0x00, 0x10, 0x00, \ - 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} -#define UVC_GUID_FORMAT_Y16 \ - { 'Y', '1', '6', ' ', 0x00, 0x00, 0x10, 0x00, \ - 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} -#define UVC_GUID_FORMAT_BY8 \ - { 'B', 'Y', '8', ' ', 0x00, 0x00, 0x10, 0x00, \ - 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} -#define UVC_GUID_FORMAT_BA81 \ - { 'B', 'A', '8', '1', 0x00, 0x00, 0x10, 0x00, \ - 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} -#define UVC_GUID_FORMAT_GBRG \ - { 'G', 'B', 'R', 'G', 0x00, 0x00, 0x10, 0x00, \ - 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} -#define UVC_GUID_FORMAT_GRBG \ - { 'G', 'R', 'B', 'G', 0x00, 0x00, 0x10, 0x00, \ - 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} -#define UVC_GUID_FORMAT_RGGB \ - { 'R', 'G', 'G', 'B', 0x00, 0x00, 0x10, 0x00, \ - 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} -#define UVC_GUID_FORMAT_BG16 \ - { 'B', 'G', '1', '6', 0x00, 0x00, 0x10, 0x00, \ - 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} -#define UVC_GUID_FORMAT_GB16 \ - { 'G', 'B', '1', '6', 0x00, 0x00, 0x10, 0x00, \ - 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} -#define UVC_GUID_FORMAT_RG16 \ - { 'R', 'G', '1', '6', 0x00, 0x00, 0x10, 0x00, \ - 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} -#define UVC_GUID_FORMAT_GR16 \ - { 'G', 'R', '1', '6', 0x00, 0x00, 0x10, 0x00, \ - 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} -#define UVC_GUID_FORMAT_RGBP \ - { 'R', 'G', 'B', 'P', 0x00, 0x00, 0x10, 0x00, \ - 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} -#define UVC_GUID_FORMAT_BGR3 \ - { 0x7d, 0xeb, 0x36, 0xe4, 0x4f, 0x52, 0xce, 0x11, \ - 0x9f, 0x53, 0x00, 0x20, 0xaf, 0x0b, 0xa7, 0x70} -#define UVC_GUID_FORMAT_BGR4 \ - { 0x7e, 0xeb, 0x36, 0xe4, 0x4f, 0x52, 0xce, 0x11, \ - 0x9f, 0x53, 0x00, 0x20, 0xaf, 0x0b, 0xa7, 0x70} -#define UVC_GUID_FORMAT_M420 \ - { 'M', '4', '2', '0', 0x00, 0x00, 0x10, 0x00, \ - 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} - -#define UVC_GUID_FORMAT_H264 \ - { 'H', '2', '6', '4', 0x00, 0x00, 0x10, 0x00, \ - 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} -#define UVC_GUID_FORMAT_H265 \ - { 'H', '2', '6', '5', 0x00, 0x00, 0x10, 0x00, \ - 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} -#define UVC_GUID_FORMAT_Y8I \ - { 'Y', '8', 'I', ' ', 0x00, 0x00, 0x10, 0x00, \ - 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} -#define UVC_GUID_FORMAT_Y12I \ - { 'Y', '1', '2', 'I', 0x00, 0x00, 0x10, 0x00, \ - 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} -#define UVC_GUID_FORMAT_Z16 \ - { 'Z', '1', '6', ' ', 0x00, 0x00, 0x10, 0x00, \ - 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} -#define UVC_GUID_FORMAT_RW10 \ - { 'R', 'W', '1', '0', 0x00, 0x00, 0x10, 0x00, \ - 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} -#define UVC_GUID_FORMAT_INVZ \ - { 'I', 'N', 'V', 'Z', 0x90, 0x2d, 0x58, 0x4a, \ - 0x92, 0x0b, 0x77, 0x3f, 0x1f, 0x2c, 0x55, 0x6b} -#define UVC_GUID_FORMAT_INZI \ - { 'I', 'N', 'Z', 'I', 0x66, 0x1a, 0x42, 0xa2, \ - 0x90, 0x65, 0xd0, 0x18, 0x14, 0xa8, 0xef, 0x8a} -#define UVC_GUID_FORMAT_INVI \ - { 'I', 'N', 'V', 'I', 0xdb, 0x57, 0x49, 0x5e, \ - 0x8e, 0x3f, 0xf4, 0x79, 0x53, 0x2b, 0x94, 0x6f} -#define UVC_GUID_FORMAT_CNF4 \ - { 'C', ' ', ' ', ' ', 0x00, 0x00, 0x10, 0x00, \ - 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} - -#define UVC_GUID_FORMAT_D3DFMT_L8 \ - {0x32, 0x00, 0x00, 0x00, 0x00, 0x00, 0x10, 0x00, \ - 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} -#define UVC_GUID_FORMAT_KSMEDIA_L8_IR \ - {0x32, 0x00, 0x00, 0x00, 0x02, 0x00, 0x10, 0x00, \ - 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} - -#define UVC_GUID_FORMAT_HEVC \ - { 'H', 'E', 'V', 'C', 0x00, 0x00, 0x10, 0x00, \ - 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} - -/* ------------------------------------------------------------------------ - * Video formats - */ - -struct uvc_format_desc { - char *name; - u8 guid[16]; - u32 fcc; -}; - -static struct uvc_format_desc uvc_fmts[] = { - { - .name = "YUV 4:2:2 (YUYV)", - .guid = UVC_GUID_FORMAT_YUY2, - .fcc = V4L2_PIX_FMT_YUYV, - }, - { - .name = "YUV 4:2:2 (YUYV)", - .guid = UVC_GUID_FORMAT_YUY2_ISIGHT, - .fcc = V4L2_PIX_FMT_YUYV, - }, - { - .name = "YUV 4:2:0 (NV12)", - .guid = UVC_GUID_FORMAT_NV12, - .fcc = V4L2_PIX_FMT_NV12, - }, - { - .name = "MJPEG", - .guid = UVC_GUID_FORMAT_MJPEG, - .fcc = V4L2_PIX_FMT_MJPEG, - }, - { - .name = "YVU 4:2:0 (YV12)", - .guid = UVC_GUID_FORMAT_YV12, - .fcc = V4L2_PIX_FMT_YVU420, - }, - { - .name = "YUV 4:2:0 (I420)", - .guid = UVC_GUID_FORMAT_I420, - .fcc = V4L2_PIX_FMT_YUV420, - }, - { - .name = "YUV 4:2:0 (M420)", - .guid = UVC_GUID_FORMAT_M420, - .fcc = V4L2_PIX_FMT_M420, - }, - { - .name = "YUV 4:2:2 (UYVY)", - .guid = UVC_GUID_FORMAT_UYVY, - .fcc = V4L2_PIX_FMT_UYVY, - }, - { - .name = "Greyscale 8-bit (Y800)", - .guid = UVC_GUID_FORMAT_Y800, - .fcc = V4L2_PIX_FMT_GREY, - }, - { - .name = "Greyscale 8-bit (Y8 )", - .guid = UVC_GUID_FORMAT_Y8, - .fcc = V4L2_PIX_FMT_GREY, - }, - { - .name = "Greyscale 8-bit (D3DFMT_L8)", - .guid = UVC_GUID_FORMAT_D3DFMT_L8, - .fcc = V4L2_PIX_FMT_GREY, - }, - { - .name = "IR 8-bit (L8_IR)", - .guid = UVC_GUID_FORMAT_KSMEDIA_L8_IR, - .fcc = V4L2_PIX_FMT_GREY, - }, - { - .name = "Greyscale 10-bit (Y10 )", - .guid = UVC_GUID_FORMAT_Y10, - .fcc = V4L2_PIX_FMT_Y10, - }, - { - .name = "Greyscale 12-bit (Y12 )", - .guid = UVC_GUID_FORMAT_Y12, - .fcc = V4L2_PIX_FMT_Y12, - }, - { - .name = "Greyscale 16-bit (Y16 )", - .guid = UVC_GUID_FORMAT_Y16, - .fcc = V4L2_PIX_FMT_Y16, - }, - { - .name = "BGGR Bayer (BY8 )", - .guid = UVC_GUID_FORMAT_BY8, - .fcc = V4L2_PIX_FMT_SBGGR8, - }, - { - .name = "BGGR Bayer (BA81)", - .guid = UVC_GUID_FORMAT_BA81, - .fcc = V4L2_PIX_FMT_SBGGR8, - }, - { - .name = "GBRG Bayer (GBRG)", - .guid = UVC_GUID_FORMAT_GBRG, - .fcc = V4L2_PIX_FMT_SGBRG8, - }, - { - .name = "GRBG Bayer (GRBG)", - .guid = UVC_GUID_FORMAT_GRBG, - .fcc = V4L2_PIX_FMT_SGRBG8, - }, - { - .name = "RGGB Bayer (RGGB)", - .guid = UVC_GUID_FORMAT_RGGB, - .fcc = V4L2_PIX_FMT_SRGGB8, - }, - { - .name = "RGB565", - .guid = UVC_GUID_FORMAT_RGBP, - .fcc = V4L2_PIX_FMT_RGB565, - }, - { - .name = "BGR 8:8:8 (BGR3)", - .guid = UVC_GUID_FORMAT_BGR3, - .fcc = V4L2_PIX_FMT_BGR24, - }, - { - .name = "BGRA/X 8:8:8:8 (BGR4)", - .guid = UVC_GUID_FORMAT_BGR4, - .fcc = V4L2_PIX_FMT_XBGR32, - }, - { - .name = "H.264", - .guid = UVC_GUID_FORMAT_H264, - .fcc = V4L2_PIX_FMT_H264, - }, - { - .name = "H.265", - .guid = UVC_GUID_FORMAT_H265, - .fcc = V4L2_PIX_FMT_HEVC, - }, - { - .name = "Greyscale 8 L/R (Y8I)", - .guid = UVC_GUID_FORMAT_Y8I, - .fcc = V4L2_PIX_FMT_Y8I, - }, - { - .name = "Greyscale 12 L/R (Y12I)", - .guid = UVC_GUID_FORMAT_Y12I, - .fcc = V4L2_PIX_FMT_Y12I, - }, - { - .name = "Depth data 16-bit (Z16)", - .guid = UVC_GUID_FORMAT_Z16, - .fcc = V4L2_PIX_FMT_Z16, - }, - { - .name = "Bayer 10-bit (SRGGB10P)", - .guid = UVC_GUID_FORMAT_RW10, - .fcc = V4L2_PIX_FMT_SRGGB10P, - }, - { - .name = "Bayer 16-bit (SBGGR16)", - .guid = UVC_GUID_FORMAT_BG16, - .fcc = V4L2_PIX_FMT_SBGGR16, - }, - { - .name = "Bayer 16-bit (SGBRG16)", - .guid = UVC_GUID_FORMAT_GB16, - .fcc = V4L2_PIX_FMT_SGBRG16, - }, - { - .name = "Bayer 16-bit (SRGGB16)", - .guid = UVC_GUID_FORMAT_RG16, - .fcc = V4L2_PIX_FMT_SRGGB16, - }, - { - .name = "Bayer 16-bit (SGRBG16)", - .guid = UVC_GUID_FORMAT_GR16, - .fcc = V4L2_PIX_FMT_SGRBG16, - }, - { - .name = "Depth data 16-bit (Z16)", - .guid = UVC_GUID_FORMAT_INVZ, - .fcc = V4L2_PIX_FMT_Z16, - }, - { - .name = "Greyscale 10-bit (Y10 )", - .guid = UVC_GUID_FORMAT_INVI, - .fcc = V4L2_PIX_FMT_Y10, - }, - { - .name = "IR:Depth 26-bit (INZI)", - .guid = UVC_GUID_FORMAT_INZI, - .fcc = V4L2_PIX_FMT_INZI, - }, - { - .name = "4-bit Depth Confidence (Packed)", - .guid = UVC_GUID_FORMAT_CNF4, - .fcc = V4L2_PIX_FMT_CNF4, - }, - { - .name = "HEVC", - .guid = UVC_GUID_FORMAT_HEVC, - .fcc = V4L2_PIX_FMT_HEVC, - }, -}; - -static inline struct uvc_format_desc *uvc_format_by_guid(const u8 guid[16]) -{ - unsigned int len = ARRAY_SIZE(uvc_fmts); - unsigned int i; - - for (i = 0; i < len; ++i) { - if (memcmp(guid, uvc_fmts[i].guid, 16) == 0) - return &uvc_fmts[i]; - } - - return NULL; -} - -#endif /* __LINUX_V4L2_UVC_H */ -- cgit v1.2.3 From 466be4c9a6f0b7810991b4ac6c3e55345ea63954 Mon Sep 17 00:00:00 2001 From: Michael Grzeschik Date: Fri, 27 Jan 2023 00:14:54 +0100 Subject: usb: uvc: move uvc_fmts and uvc_format_by_guid to own compile unit The media driver USB_VIDEO_CLASS and USB_F_UVC are using the same function uvc_format_by_guid. Since the function is inline, every user will get a copy of the used uvc_fmts array and the function. This patch moves the code to an own compile unit and add this dependency as UVC_COMMON to both users. Reviewed-by: Laurent Pinchart Reviewed-by: Daniel Scally Tested-by: Daniel Scally Signed-off-by: Michael Grzeschik Link: https://lore.kernel.org/r/20230126231456.3402323-4-m.grzeschik@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/media/common/Kconfig | 3 + drivers/media/common/Makefile | 1 + drivers/media/common/uvc.c | 221 ++++++++++++++++++++++++++++++++++++++++++ drivers/media/usb/uvc/Kconfig | 1 + drivers/usb/gadget/Kconfig | 1 + include/linux/usb/uvc.h | 210 +-------------------------------------- 6 files changed, 228 insertions(+), 209 deletions(-) create mode 100644 drivers/media/common/uvc.c (limited to 'include/linux') diff --git a/drivers/media/common/Kconfig b/drivers/media/common/Kconfig index 852b7d92fbdd..b1bc58da27fc 100644 --- a/drivers/media/common/Kconfig +++ b/drivers/media/common/Kconfig @@ -14,6 +14,9 @@ config TTPCI_EEPROM tristate depends on I2C +config UVC_COMMON + tristate + config VIDEO_CX2341X tristate diff --git a/drivers/media/common/Makefile b/drivers/media/common/Makefile index d78a0df15478..3f17d696feb2 100644 --- a/drivers/media/common/Makefile +++ b/drivers/media/common/Makefile @@ -5,5 +5,6 @@ obj-y += b2c2/ siano/ v4l2-tpg/ videobuf2/ # (e. g. LC_ALL=C sort Makefile) obj-$(CONFIG_CYPRESS_FIRMWARE) += cypress_firmware.o obj-$(CONFIG_TTPCI_EEPROM) += ttpci-eeprom.o +obj-$(CONFIG_UVC_COMMON) += uvc.o obj-$(CONFIG_VIDEO_CX2341X) += cx2341x.o obj-$(CONFIG_VIDEO_TVEEPROM) += tveeprom.o diff --git a/drivers/media/common/uvc.c b/drivers/media/common/uvc.c new file mode 100644 index 000000000000..bb96d9e26d80 --- /dev/null +++ b/drivers/media/common/uvc.c @@ -0,0 +1,221 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#include +#include +#include +#include +#include +#include + +/* ------------------------------------------------------------------------ + * Video formats + */ + +static struct uvc_format_desc uvc_fmts[] = { + { + .name = "YUV 4:2:2 (YUYV)", + .guid = UVC_GUID_FORMAT_YUY2, + .fcc = V4L2_PIX_FMT_YUYV, + }, + { + .name = "YUV 4:2:2 (YUYV)", + .guid = UVC_GUID_FORMAT_YUY2_ISIGHT, + .fcc = V4L2_PIX_FMT_YUYV, + }, + { + .name = "YUV 4:2:0 (NV12)", + .guid = UVC_GUID_FORMAT_NV12, + .fcc = V4L2_PIX_FMT_NV12, + }, + { + .name = "MJPEG", + .guid = UVC_GUID_FORMAT_MJPEG, + .fcc = V4L2_PIX_FMT_MJPEG, + }, + { + .name = "YVU 4:2:0 (YV12)", + .guid = UVC_GUID_FORMAT_YV12, + .fcc = V4L2_PIX_FMT_YVU420, + }, + { + .name = "YUV 4:2:0 (I420)", + .guid = UVC_GUID_FORMAT_I420, + .fcc = V4L2_PIX_FMT_YUV420, + }, + { + .name = "YUV 4:2:0 (M420)", + .guid = UVC_GUID_FORMAT_M420, + .fcc = V4L2_PIX_FMT_M420, + }, + { + .name = "YUV 4:2:2 (UYVY)", + .guid = UVC_GUID_FORMAT_UYVY, + .fcc = V4L2_PIX_FMT_UYVY, + }, + { + .name = "Greyscale 8-bit (Y800)", + .guid = UVC_GUID_FORMAT_Y800, + .fcc = V4L2_PIX_FMT_GREY, + }, + { + .name = "Greyscale 8-bit (Y8 )", + .guid = UVC_GUID_FORMAT_Y8, + .fcc = V4L2_PIX_FMT_GREY, + }, + { + .name = "Greyscale 8-bit (D3DFMT_L8)", + .guid = UVC_GUID_FORMAT_D3DFMT_L8, + .fcc = V4L2_PIX_FMT_GREY, + }, + { + .name = "IR 8-bit (L8_IR)", + .guid = UVC_GUID_FORMAT_KSMEDIA_L8_IR, + .fcc = V4L2_PIX_FMT_GREY, + }, + { + .name = "Greyscale 10-bit (Y10 )", + .guid = UVC_GUID_FORMAT_Y10, + .fcc = V4L2_PIX_FMT_Y10, + }, + { + .name = "Greyscale 12-bit (Y12 )", + .guid = UVC_GUID_FORMAT_Y12, + .fcc = V4L2_PIX_FMT_Y12, + }, + { + .name = "Greyscale 16-bit (Y16 )", + .guid = UVC_GUID_FORMAT_Y16, + .fcc = V4L2_PIX_FMT_Y16, + }, + { + .name = "BGGR Bayer (BY8 )", + .guid = UVC_GUID_FORMAT_BY8, + .fcc = V4L2_PIX_FMT_SBGGR8, + }, + { + .name = "BGGR Bayer (BA81)", + .guid = UVC_GUID_FORMAT_BA81, + .fcc = V4L2_PIX_FMT_SBGGR8, + }, + { + .name = "GBRG Bayer (GBRG)", + .guid = UVC_GUID_FORMAT_GBRG, + .fcc = V4L2_PIX_FMT_SGBRG8, + }, + { + .name = "GRBG Bayer (GRBG)", + .guid = UVC_GUID_FORMAT_GRBG, + .fcc = V4L2_PIX_FMT_SGRBG8, + }, + { + .name = "RGGB Bayer (RGGB)", + .guid = UVC_GUID_FORMAT_RGGB, + .fcc = V4L2_PIX_FMT_SRGGB8, + }, + { + .name = "RGB565", + .guid = UVC_GUID_FORMAT_RGBP, + .fcc = V4L2_PIX_FMT_RGB565, + }, + { + .name = "BGR 8:8:8 (BGR3)", + .guid = UVC_GUID_FORMAT_BGR3, + .fcc = V4L2_PIX_FMT_BGR24, + }, + { + .name = "BGRA/X 8:8:8:8 (BGR4)", + .guid = UVC_GUID_FORMAT_BGR4, + .fcc = V4L2_PIX_FMT_XBGR32, + }, + { + .name = "H.264", + .guid = UVC_GUID_FORMAT_H264, + .fcc = V4L2_PIX_FMT_H264, + }, + { + .name = "H.265", + .guid = UVC_GUID_FORMAT_H265, + .fcc = V4L2_PIX_FMT_HEVC, + }, + { + .name = "Greyscale 8 L/R (Y8I)", + .guid = UVC_GUID_FORMAT_Y8I, + .fcc = V4L2_PIX_FMT_Y8I, + }, + { + .name = "Greyscale 12 L/R (Y12I)", + .guid = UVC_GUID_FORMAT_Y12I, + .fcc = V4L2_PIX_FMT_Y12I, + }, + { + .name = "Depth data 16-bit (Z16)", + .guid = UVC_GUID_FORMAT_Z16, + .fcc = V4L2_PIX_FMT_Z16, + }, + { + .name = "Bayer 10-bit (SRGGB10P)", + .guid = UVC_GUID_FORMAT_RW10, + .fcc = V4L2_PIX_FMT_SRGGB10P, + }, + { + .name = "Bayer 16-bit (SBGGR16)", + .guid = UVC_GUID_FORMAT_BG16, + .fcc = V4L2_PIX_FMT_SBGGR16, + }, + { + .name = "Bayer 16-bit (SGBRG16)", + .guid = UVC_GUID_FORMAT_GB16, + .fcc = V4L2_PIX_FMT_SGBRG16, + }, + { + .name = "Bayer 16-bit (SRGGB16)", + .guid = UVC_GUID_FORMAT_RG16, + .fcc = V4L2_PIX_FMT_SRGGB16, + }, + { + .name = "Bayer 16-bit (SGRBG16)", + .guid = UVC_GUID_FORMAT_GR16, + .fcc = V4L2_PIX_FMT_SGRBG16, + }, + { + .name = "Depth data 16-bit (Z16)", + .guid = UVC_GUID_FORMAT_INVZ, + .fcc = V4L2_PIX_FMT_Z16, + }, + { + .name = "Greyscale 10-bit (Y10 )", + .guid = UVC_GUID_FORMAT_INVI, + .fcc = V4L2_PIX_FMT_Y10, + }, + { + .name = "IR:Depth 26-bit (INZI)", + .guid = UVC_GUID_FORMAT_INZI, + .fcc = V4L2_PIX_FMT_INZI, + }, + { + .name = "4-bit Depth Confidence (Packed)", + .guid = UVC_GUID_FORMAT_CNF4, + .fcc = V4L2_PIX_FMT_CNF4, + }, + { + .name = "HEVC", + .guid = UVC_GUID_FORMAT_HEVC, + .fcc = V4L2_PIX_FMT_HEVC, + }, +}; + +struct uvc_format_desc *uvc_format_by_guid(const u8 guid[16]) +{ + unsigned int len = ARRAY_SIZE(uvc_fmts); + unsigned int i; + + for (i = 0; i < len; ++i) { + if (memcmp(guid, uvc_fmts[i].guid, 16) == 0) + return &uvc_fmts[i]; + } + + return NULL; +} +EXPORT_SYMBOL_GPL(uvc_format_by_guid); + +MODULE_LICENSE("GPL"); diff --git a/drivers/media/usb/uvc/Kconfig b/drivers/media/usb/uvc/Kconfig index ca51ee8e45f3..579532272fd6 100644 --- a/drivers/media/usb/uvc/Kconfig +++ b/drivers/media/usb/uvc/Kconfig @@ -3,6 +3,7 @@ config USB_VIDEO_CLASS tristate "USB Video Class (UVC)" depends on VIDEO_DEV select VIDEOBUF2_VMALLOC + select UVC_COMMON help Support for the USB Video Class (UVC). Currently only video input devices, such as webcams, are supported. diff --git a/drivers/usb/gadget/Kconfig b/drivers/usb/gadget/Kconfig index 4fa2ddf322b4..336db8f92afa 100644 --- a/drivers/usb/gadget/Kconfig +++ b/drivers/usb/gadget/Kconfig @@ -203,6 +203,7 @@ config USB_F_UAC2 config USB_F_UVC tristate + select UVC_COMMON config USB_F_MIDI tristate diff --git a/include/linux/usb/uvc.h b/include/linux/usb/uvc.h index b010a36fc1d9..8cebb46602a1 100644 --- a/include/linux/usb/uvc.h +++ b/include/linux/usb/uvc.h @@ -148,220 +148,12 @@ { 'H', 'E', 'V', 'C', 0x00, 0x00, 0x10, 0x00, \ 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} -/* ------------------------------------------------------------------------ - * Video formats - */ - struct uvc_format_desc { char *name; u8 guid[16]; u32 fcc; }; -static struct uvc_format_desc uvc_fmts[] = { - { - .name = "YUV 4:2:2 (YUYV)", - .guid = UVC_GUID_FORMAT_YUY2, - .fcc = V4L2_PIX_FMT_YUYV, - }, - { - .name = "YUV 4:2:2 (YUYV)", - .guid = UVC_GUID_FORMAT_YUY2_ISIGHT, - .fcc = V4L2_PIX_FMT_YUYV, - }, - { - .name = "YUV 4:2:0 (NV12)", - .guid = UVC_GUID_FORMAT_NV12, - .fcc = V4L2_PIX_FMT_NV12, - }, - { - .name = "MJPEG", - .guid = UVC_GUID_FORMAT_MJPEG, - .fcc = V4L2_PIX_FMT_MJPEG, - }, - { - .name = "YVU 4:2:0 (YV12)", - .guid = UVC_GUID_FORMAT_YV12, - .fcc = V4L2_PIX_FMT_YVU420, - }, - { - .name = "YUV 4:2:0 (I420)", - .guid = UVC_GUID_FORMAT_I420, - .fcc = V4L2_PIX_FMT_YUV420, - }, - { - .name = "YUV 4:2:0 (M420)", - .guid = UVC_GUID_FORMAT_M420, - .fcc = V4L2_PIX_FMT_M420, - }, - { - .name = "YUV 4:2:2 (UYVY)", - .guid = UVC_GUID_FORMAT_UYVY, - .fcc = V4L2_PIX_FMT_UYVY, - }, - { - .name = "Greyscale 8-bit (Y800)", - .guid = UVC_GUID_FORMAT_Y800, - .fcc = V4L2_PIX_FMT_GREY, - }, - { - .name = "Greyscale 8-bit (Y8 )", - .guid = UVC_GUID_FORMAT_Y8, - .fcc = V4L2_PIX_FMT_GREY, - }, - { - .name = "Greyscale 8-bit (D3DFMT_L8)", - .guid = UVC_GUID_FORMAT_D3DFMT_L8, - .fcc = V4L2_PIX_FMT_GREY, - }, - { - .name = "IR 8-bit (L8_IR)", - .guid = UVC_GUID_FORMAT_KSMEDIA_L8_IR, - .fcc = V4L2_PIX_FMT_GREY, - }, - { - .name = "Greyscale 10-bit (Y10 )", - .guid = UVC_GUID_FORMAT_Y10, - .fcc = V4L2_PIX_FMT_Y10, - }, - { - .name = "Greyscale 12-bit (Y12 )", - .guid = UVC_GUID_FORMAT_Y12, - .fcc = V4L2_PIX_FMT_Y12, - }, - { - .name = "Greyscale 16-bit (Y16 )", - .guid = UVC_GUID_FORMAT_Y16, - .fcc = V4L2_PIX_FMT_Y16, - }, - { - .name = "BGGR Bayer (BY8 )", - .guid = UVC_GUID_FORMAT_BY8, - .fcc = V4L2_PIX_FMT_SBGGR8, - }, - { - .name = "BGGR Bayer (BA81)", - .guid = UVC_GUID_FORMAT_BA81, - .fcc = V4L2_PIX_FMT_SBGGR8, - }, - { - .name = "GBRG Bayer (GBRG)", - .guid = UVC_GUID_FORMAT_GBRG, - .fcc = V4L2_PIX_FMT_SGBRG8, - }, - { - .name = "GRBG Bayer (GRBG)", - .guid = UVC_GUID_FORMAT_GRBG, - .fcc = V4L2_PIX_FMT_SGRBG8, - }, - { - .name = "RGGB Bayer (RGGB)", - .guid = UVC_GUID_FORMAT_RGGB, - .fcc = V4L2_PIX_FMT_SRGGB8, - }, - { - .name = "RGB565", - .guid = UVC_GUID_FORMAT_RGBP, - .fcc = V4L2_PIX_FMT_RGB565, - }, - { - .name = "BGR 8:8:8 (BGR3)", - .guid = UVC_GUID_FORMAT_BGR3, - .fcc = V4L2_PIX_FMT_BGR24, - }, - { - .name = "BGRA/X 8:8:8:8 (BGR4)", - .guid = UVC_GUID_FORMAT_BGR4, - .fcc = V4L2_PIX_FMT_XBGR32, - }, - { - .name = "H.264", - .guid = UVC_GUID_FORMAT_H264, - .fcc = V4L2_PIX_FMT_H264, - }, - { - .name = "H.265", - .guid = UVC_GUID_FORMAT_H265, - .fcc = V4L2_PIX_FMT_HEVC, - }, - { - .name = "Greyscale 8 L/R (Y8I)", - .guid = UVC_GUID_FORMAT_Y8I, - .fcc = V4L2_PIX_FMT_Y8I, - }, - { - .name = "Greyscale 12 L/R (Y12I)", - .guid = UVC_GUID_FORMAT_Y12I, - .fcc = V4L2_PIX_FMT_Y12I, - }, - { - .name = "Depth data 16-bit (Z16)", - .guid = UVC_GUID_FORMAT_Z16, - .fcc = V4L2_PIX_FMT_Z16, - }, - { - .name = "Bayer 10-bit (SRGGB10P)", - .guid = UVC_GUID_FORMAT_RW10, - .fcc = V4L2_PIX_FMT_SRGGB10P, - }, - { - .name = "Bayer 16-bit (SBGGR16)", - .guid = UVC_GUID_FORMAT_BG16, - .fcc = V4L2_PIX_FMT_SBGGR16, - }, - { - .name = "Bayer 16-bit (SGBRG16)", - .guid = UVC_GUID_FORMAT_GB16, - .fcc = V4L2_PIX_FMT_SGBRG16, - }, - { - .name = "Bayer 16-bit (SRGGB16)", - .guid = UVC_GUID_FORMAT_RG16, - .fcc = V4L2_PIX_FMT_SRGGB16, - }, - { - .name = "Bayer 16-bit (SGRBG16)", - .guid = UVC_GUID_FORMAT_GR16, - .fcc = V4L2_PIX_FMT_SGRBG16, - }, - { - .name = "Depth data 16-bit (Z16)", - .guid = UVC_GUID_FORMAT_INVZ, - .fcc = V4L2_PIX_FMT_Z16, - }, - { - .name = "Greyscale 10-bit (Y10 )", - .guid = UVC_GUID_FORMAT_INVI, - .fcc = V4L2_PIX_FMT_Y10, - }, - { - .name = "IR:Depth 26-bit (INZI)", - .guid = UVC_GUID_FORMAT_INZI, - .fcc = V4L2_PIX_FMT_INZI, - }, - { - .name = "4-bit Depth Confidence (Packed)", - .guid = UVC_GUID_FORMAT_CNF4, - .fcc = V4L2_PIX_FMT_CNF4, - }, - { - .name = "HEVC", - .guid = UVC_GUID_FORMAT_HEVC, - .fcc = V4L2_PIX_FMT_HEVC, - }, -}; - -static inline struct uvc_format_desc *uvc_format_by_guid(const u8 guid[16]) -{ - unsigned int len = ARRAY_SIZE(uvc_fmts); - unsigned int i; - - for (i = 0; i < len; ++i) { - if (memcmp(guid, uvc_fmts[i].guid, 16) == 0) - return &uvc_fmts[i]; - } - - return NULL; -} +struct uvc_format_desc *uvc_format_by_guid(const u8 guid[16]); #endif /* __LINUX_V4L2_UVC_H */ -- cgit v1.2.3 From 8ecb17a86c0fbb86ea9fb4fa26e742600e945794 Mon Sep 17 00:00:00 2001 From: Michael Grzeschik Date: Fri, 27 Jan 2023 00:14:55 +0100 Subject: usb: uvc: make uvc_format_desc table const Since the uvc_fmts array can not be modified we declare it const and change every user of the uvc_format_by_guid function aswell. Reviewed-by: Laurent Pinchart Reviewed-by: Daniel Scally Tested-by: Daniel Scally Signed-off-by: Michael Grzeschik Link: https://lore.kernel.org/r/20230126231456.3402323-5-m.grzeschik@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/media/common/uvc.c | 4 ++-- drivers/media/usb/uvc/uvc_driver.c | 2 +- drivers/usb/gadget/function/uvc_v4l2.c | 8 ++++---- include/linux/usb/uvc.h | 2 +- 4 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/media/common/uvc.c b/drivers/media/common/uvc.c index bb96d9e26d80..2b4df3e8f48a 100644 --- a/drivers/media/common/uvc.c +++ b/drivers/media/common/uvc.c @@ -11,7 +11,7 @@ * Video formats */ -static struct uvc_format_desc uvc_fmts[] = { +static const struct uvc_format_desc uvc_fmts[] = { { .name = "YUV 4:2:2 (YUYV)", .guid = UVC_GUID_FORMAT_YUY2, @@ -204,7 +204,7 @@ static struct uvc_format_desc uvc_fmts[] = { }, }; -struct uvc_format_desc *uvc_format_by_guid(const u8 guid[16]) +const struct uvc_format_desc *uvc_format_by_guid(const u8 guid[16]) { unsigned int len = ARRAY_SIZE(uvc_fmts); unsigned int i; diff --git a/drivers/media/usb/uvc/uvc_driver.c b/drivers/media/usb/uvc/uvc_driver.c index edf8c4a201a8..7aefa76a42b3 100644 --- a/drivers/media/usb/uvc/uvc_driver.c +++ b/drivers/media/usb/uvc/uvc_driver.c @@ -225,7 +225,7 @@ static int uvc_parse_format(struct uvc_device *dev, { struct usb_interface *intf = streaming->intf; struct usb_host_interface *alts = intf->cur_altsetting; - struct uvc_format_desc *fmtdesc; + const struct uvc_format_desc *fmtdesc; struct uvc_frame *frame; const unsigned char *start = buffer; unsigned int width_multiplier = 1; diff --git a/drivers/usb/gadget/function/uvc_v4l2.c b/drivers/usb/gadget/function/uvc_v4l2.c index 7435df0cf2a8..21e573e628f4 100644 --- a/drivers/usb/gadget/function/uvc_v4l2.c +++ b/drivers/usb/gadget/function/uvc_v4l2.c @@ -27,10 +27,10 @@ #include "uvc_v4l2.h" #include "uvc_configfs.h" -static struct uvc_format_desc *to_uvc_format(struct uvcg_format *uformat) +static const struct uvc_format_desc *to_uvc_format(struct uvcg_format *uformat) { char guid[16] = UVC_GUID_FORMAT_MJPEG; - struct uvc_format_desc *format; + const struct uvc_format_desc *format; struct uvcg_uncompressed *unc; if (uformat->type == UVCG_UNCOMPRESSED) { @@ -119,7 +119,7 @@ static struct uvcg_format *find_format_by_pix(struct uvc_device *uvc, struct uvcg_format *uformat = NULL; list_for_each_entry(format, &uvc->header->formats, entry) { - struct uvc_format_desc *fmtdesc = to_uvc_format(format->fmt); + const struct uvc_format_desc *fmtdesc = to_uvc_format(format->fmt); if (fmtdesc->fcc == pixelformat) { uformat = format->fmt; @@ -364,7 +364,7 @@ uvc_v4l2_enum_format(struct file *file, void *fh, struct v4l2_fmtdesc *f) { struct video_device *vdev = video_devdata(file); struct uvc_device *uvc = video_get_drvdata(vdev); - struct uvc_format_desc *fmtdesc; + const struct uvc_format_desc *fmtdesc; struct uvcg_format *uformat; if (f->index >= uvc->header->num_fmt) diff --git a/include/linux/usb/uvc.h b/include/linux/usb/uvc.h index 8cebb46602a1..b0210c5c5406 100644 --- a/include/linux/usb/uvc.h +++ b/include/linux/usb/uvc.h @@ -154,6 +154,6 @@ struct uvc_format_desc { u32 fcc; }; -struct uvc_format_desc *uvc_format_by_guid(const u8 guid[16]); +const struct uvc_format_desc *uvc_format_by_guid(const u8 guid[16]); #endif /* __LINUX_V4L2_UVC_H */ -- cgit v1.2.3 From 2d83eb5d24e1c8dba386928fcbf76d3b581a632d Mon Sep 17 00:00:00 2001 From: Michael Grzeschik Date: Fri, 27 Jan 2023 00:14:56 +0100 Subject: usb: uvc: use v4l2_fill_fmtdesc instead of open coded format name Since v4l2_fill_fmtdesc will be called in the ioctl v4l_enum_fmt anyway. We can set the format description and compressed flag from v4l_fill_fmtdesc and can remove the extra name field in uvc_format_desc. Reviewed-by: Daniel Scally Tested-by: Daniel Scally Signed-off-by: Michael Grzeschik Reviewed-by: Laurent Pinchart Link: https://lore.kernel.org/r/20230126231456.3402323-6-m.grzeschik@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/media/common/uvc.c | 38 ---------------------------------- drivers/usb/gadget/function/uvc_v4l2.c | 6 ------ include/linux/usb/uvc.h | 1 - 3 files changed, 45 deletions(-) (limited to 'include/linux') diff --git a/drivers/media/common/uvc.c b/drivers/media/common/uvc.c index 2b4df3e8f48a..9c0ba7a6c185 100644 --- a/drivers/media/common/uvc.c +++ b/drivers/media/common/uvc.c @@ -13,192 +13,154 @@ static const struct uvc_format_desc uvc_fmts[] = { { - .name = "YUV 4:2:2 (YUYV)", .guid = UVC_GUID_FORMAT_YUY2, .fcc = V4L2_PIX_FMT_YUYV, }, { - .name = "YUV 4:2:2 (YUYV)", .guid = UVC_GUID_FORMAT_YUY2_ISIGHT, .fcc = V4L2_PIX_FMT_YUYV, }, { - .name = "YUV 4:2:0 (NV12)", .guid = UVC_GUID_FORMAT_NV12, .fcc = V4L2_PIX_FMT_NV12, }, { - .name = "MJPEG", .guid = UVC_GUID_FORMAT_MJPEG, .fcc = V4L2_PIX_FMT_MJPEG, }, { - .name = "YVU 4:2:0 (YV12)", .guid = UVC_GUID_FORMAT_YV12, .fcc = V4L2_PIX_FMT_YVU420, }, { - .name = "YUV 4:2:0 (I420)", .guid = UVC_GUID_FORMAT_I420, .fcc = V4L2_PIX_FMT_YUV420, }, { - .name = "YUV 4:2:0 (M420)", .guid = UVC_GUID_FORMAT_M420, .fcc = V4L2_PIX_FMT_M420, }, { - .name = "YUV 4:2:2 (UYVY)", .guid = UVC_GUID_FORMAT_UYVY, .fcc = V4L2_PIX_FMT_UYVY, }, { - .name = "Greyscale 8-bit (Y800)", .guid = UVC_GUID_FORMAT_Y800, .fcc = V4L2_PIX_FMT_GREY, }, { - .name = "Greyscale 8-bit (Y8 )", .guid = UVC_GUID_FORMAT_Y8, .fcc = V4L2_PIX_FMT_GREY, }, { - .name = "Greyscale 8-bit (D3DFMT_L8)", .guid = UVC_GUID_FORMAT_D3DFMT_L8, .fcc = V4L2_PIX_FMT_GREY, }, { - .name = "IR 8-bit (L8_IR)", .guid = UVC_GUID_FORMAT_KSMEDIA_L8_IR, .fcc = V4L2_PIX_FMT_GREY, }, { - .name = "Greyscale 10-bit (Y10 )", .guid = UVC_GUID_FORMAT_Y10, .fcc = V4L2_PIX_FMT_Y10, }, { - .name = "Greyscale 12-bit (Y12 )", .guid = UVC_GUID_FORMAT_Y12, .fcc = V4L2_PIX_FMT_Y12, }, { - .name = "Greyscale 16-bit (Y16 )", .guid = UVC_GUID_FORMAT_Y16, .fcc = V4L2_PIX_FMT_Y16, }, { - .name = "BGGR Bayer (BY8 )", .guid = UVC_GUID_FORMAT_BY8, .fcc = V4L2_PIX_FMT_SBGGR8, }, { - .name = "BGGR Bayer (BA81)", .guid = UVC_GUID_FORMAT_BA81, .fcc = V4L2_PIX_FMT_SBGGR8, }, { - .name = "GBRG Bayer (GBRG)", .guid = UVC_GUID_FORMAT_GBRG, .fcc = V4L2_PIX_FMT_SGBRG8, }, { - .name = "GRBG Bayer (GRBG)", .guid = UVC_GUID_FORMAT_GRBG, .fcc = V4L2_PIX_FMT_SGRBG8, }, { - .name = "RGGB Bayer (RGGB)", .guid = UVC_GUID_FORMAT_RGGB, .fcc = V4L2_PIX_FMT_SRGGB8, }, { - .name = "RGB565", .guid = UVC_GUID_FORMAT_RGBP, .fcc = V4L2_PIX_FMT_RGB565, }, { - .name = "BGR 8:8:8 (BGR3)", .guid = UVC_GUID_FORMAT_BGR3, .fcc = V4L2_PIX_FMT_BGR24, }, { - .name = "BGRA/X 8:8:8:8 (BGR4)", .guid = UVC_GUID_FORMAT_BGR4, .fcc = V4L2_PIX_FMT_XBGR32, }, { - .name = "H.264", .guid = UVC_GUID_FORMAT_H264, .fcc = V4L2_PIX_FMT_H264, }, { - .name = "H.265", .guid = UVC_GUID_FORMAT_H265, .fcc = V4L2_PIX_FMT_HEVC, }, { - .name = "Greyscale 8 L/R (Y8I)", .guid = UVC_GUID_FORMAT_Y8I, .fcc = V4L2_PIX_FMT_Y8I, }, { - .name = "Greyscale 12 L/R (Y12I)", .guid = UVC_GUID_FORMAT_Y12I, .fcc = V4L2_PIX_FMT_Y12I, }, { - .name = "Depth data 16-bit (Z16)", .guid = UVC_GUID_FORMAT_Z16, .fcc = V4L2_PIX_FMT_Z16, }, { - .name = "Bayer 10-bit (SRGGB10P)", .guid = UVC_GUID_FORMAT_RW10, .fcc = V4L2_PIX_FMT_SRGGB10P, }, { - .name = "Bayer 16-bit (SBGGR16)", .guid = UVC_GUID_FORMAT_BG16, .fcc = V4L2_PIX_FMT_SBGGR16, }, { - .name = "Bayer 16-bit (SGBRG16)", .guid = UVC_GUID_FORMAT_GB16, .fcc = V4L2_PIX_FMT_SGBRG16, }, { - .name = "Bayer 16-bit (SRGGB16)", .guid = UVC_GUID_FORMAT_RG16, .fcc = V4L2_PIX_FMT_SRGGB16, }, { - .name = "Bayer 16-bit (SGRBG16)", .guid = UVC_GUID_FORMAT_GR16, .fcc = V4L2_PIX_FMT_SGRBG16, }, { - .name = "Depth data 16-bit (Z16)", .guid = UVC_GUID_FORMAT_INVZ, .fcc = V4L2_PIX_FMT_Z16, }, { - .name = "Greyscale 10-bit (Y10 )", .guid = UVC_GUID_FORMAT_INVI, .fcc = V4L2_PIX_FMT_Y10, }, { - .name = "IR:Depth 26-bit (INZI)", .guid = UVC_GUID_FORMAT_INZI, .fcc = V4L2_PIX_FMT_INZI, }, { - .name = "4-bit Depth Confidence (Packed)", .guid = UVC_GUID_FORMAT_CNF4, .fcc = V4L2_PIX_FMT_CNF4, }, { - .name = "HEVC", .guid = UVC_GUID_FORMAT_HEVC, .fcc = V4L2_PIX_FMT_HEVC, }, diff --git a/drivers/usb/gadget/function/uvc_v4l2.c b/drivers/usb/gadget/function/uvc_v4l2.c index 21e573e628f4..3f0a9795c0d4 100644 --- a/drivers/usb/gadget/function/uvc_v4l2.c +++ b/drivers/usb/gadget/function/uvc_v4l2.c @@ -374,15 +374,9 @@ uvc_v4l2_enum_format(struct file *file, void *fh, struct v4l2_fmtdesc *f) if (!uformat) return -EINVAL; - if (uformat->type != UVCG_UNCOMPRESSED) - f->flags |= V4L2_FMT_FLAG_COMPRESSED; - fmtdesc = to_uvc_format(uformat); f->pixelformat = fmtdesc->fcc; - strscpy(f->description, fmtdesc->name, sizeof(f->description)); - f->description[strlen(fmtdesc->name) - 1] = 0; - return 0; } diff --git a/include/linux/usb/uvc.h b/include/linux/usb/uvc.h index b0210c5c5406..88d96095bcb1 100644 --- a/include/linux/usb/uvc.h +++ b/include/linux/usb/uvc.h @@ -149,7 +149,6 @@ 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} struct uvc_format_desc { - char *name; u8 guid[16]; u32 fcc; }; -- cgit v1.2.3 From 2bf40502badf9bc15a487244dd23ce0b08c306c0 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 25 Jan 2023 16:34:25 +0200 Subject: usb: gadget: Use correct APIs and data types for UUID handling We have two types for UUIDs depending on the byte ordering. Instead of explaining how bytes should go over the wire, use dedicated APIs and data types. This removes a confusion over the byte ordering. Signed-off-by: Andy Shevchenko Tested-By: Jó Ágila Bitsch Link: https://lore.kernel.org/r/20230125143425.85268-1-andriy.shevchenko@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/composite.c | 4 ++-- include/linux/usb/webusb.h | 9 +++------ 2 files changed, 5 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c index 8e2603688016..fa7dd6cf014d 100644 --- a/drivers/usb/gadget/composite.c +++ b/drivers/usb/gadget/composite.c @@ -829,7 +829,7 @@ static int bos_desc(struct usb_composite_dev *cdev) if (cdev->use_webusb) { struct usb_plat_dev_cap_descriptor *webusb_cap; struct usb_webusb_cap_data *webusb_cap_data; - uuid_t webusb_uuid = WEBUSB_UUID; + guid_t webusb_uuid = WEBUSB_UUID; webusb_cap = cdev->req->buf + le16_to_cpu(bos->wTotalLength); webusb_cap_data = (struct usb_webusb_cap_data *) webusb_cap->CapabilityData; @@ -841,7 +841,7 @@ static int bos_desc(struct usb_composite_dev *cdev) webusb_cap->bDescriptorType = USB_DT_DEVICE_CAPABILITY; webusb_cap->bDevCapabilityType = USB_PLAT_DEV_CAP_TYPE; webusb_cap->bReserved = 0; - export_uuid(webusb_cap->UUID, &webusb_uuid); + export_guid(webusb_cap->UUID, &webusb_uuid); if (cdev->bcd_webusb_version != 0) webusb_cap_data->bcdVersion = cpu_to_le16(cdev->bcd_webusb_version); diff --git a/include/linux/usb/webusb.h b/include/linux/usb/webusb.h index b430d84357f3..fe43020b4a48 100644 --- a/include/linux/usb/webusb.h +++ b/include/linux/usb/webusb.h @@ -11,15 +11,12 @@ #include "uapi/linux/usb/ch9.h" /* - * little endian PlatformCapablityUUID for WebUSB + * Little Endian PlatformCapablityUUID for WebUSB * 3408b638-09a9-47a0-8bfd-a0768815b665 - * to identify Platform Device Capability descriptors as referring to WebUSB - * - * the UUID above MUST be sent over the wire as the byte sequence: - * {0x38, 0xB6, 0x08, 0x34, 0xA9, 0x09, 0xA0, 0x47, 0x8B, 0xFD, 0xA0, 0x76, 0x88, 0x15, 0xB6, 0x65}. + * to identify Platform Device Capability descriptors as referring to WebUSB. */ #define WEBUSB_UUID \ - UUID_INIT(0x38b60834, 0xa909, 0xa047, 0x8b, 0xfd, 0xa0, 0x76, 0x88, 0x15, 0xb6, 0x65) + GUID_INIT(0x3408b638, 0x09a9, 0x47a0, 0x8b, 0xfd, 0xa0, 0x76, 0x88, 0x15, 0xb6, 0x65) /* * WebUSB Platform Capability data -- cgit v1.2.3 From 40eaa8c0cbba4a27668c7e01373ccd5b38381e2f Mon Sep 17 00:00:00 2001 From: Hector Martin Date: Mon, 23 Jan 2023 15:53:54 +0900 Subject: soc: apple: rtkit: Add apple_rtkit_idle() function This is yet another low power mode, used by DCP. Reviewed-by: Eric Curtin Reviewed-by: Sven Peter Signed-off-by: Hector Martin --- drivers/soc/apple/rtkit.c | 21 +++++++++++++++++++++ include/linux/soc/apple/rtkit.h | 5 +++++ 2 files changed, 26 insertions(+) (limited to 'include/linux') diff --git a/drivers/soc/apple/rtkit.c b/drivers/soc/apple/rtkit.c index 8ec74d7539eb..efb1fa77dff2 100644 --- a/drivers/soc/apple/rtkit.c +++ b/drivers/soc/apple/rtkit.c @@ -9,6 +9,7 @@ enum { APPLE_RTKIT_PWR_STATE_OFF = 0x00, /* power off, cannot be restarted */ APPLE_RTKIT_PWR_STATE_SLEEP = 0x01, /* sleeping, can be restarted */ + APPLE_RTKIT_PWR_STATE_IDLE = 0x201, /* sleeping, retain state */ APPLE_RTKIT_PWR_STATE_QUIESCED = 0x10, /* running but no communication */ APPLE_RTKIT_PWR_STATE_ON = 0x20, /* normal operating state */ }; @@ -881,6 +882,26 @@ int apple_rtkit_shutdown(struct apple_rtkit *rtk) } EXPORT_SYMBOL_GPL(apple_rtkit_shutdown); +int apple_rtkit_idle(struct apple_rtkit *rtk) +{ + int ret; + + /* if OFF is used here the co-processor will not wake up again */ + ret = apple_rtkit_set_ap_power_state(rtk, + APPLE_RTKIT_PWR_STATE_IDLE); + if (ret) + return ret; + + ret = apple_rtkit_set_iop_power_state(rtk, APPLE_RTKIT_PWR_STATE_IDLE); + if (ret) + return ret; + + rtk->iop_power_state = APPLE_RTKIT_PWR_STATE_IDLE; + rtk->ap_power_state = APPLE_RTKIT_PWR_STATE_IDLE; + return 0; +} +EXPORT_SYMBOL_GPL(apple_rtkit_idle); + int apple_rtkit_quiesce(struct apple_rtkit *rtk) { int ret; diff --git a/include/linux/soc/apple/rtkit.h b/include/linux/soc/apple/rtkit.h index c9cabb679cd1..a2446b45ed7f 100644 --- a/include/linux/soc/apple/rtkit.h +++ b/include/linux/soc/apple/rtkit.h @@ -104,6 +104,11 @@ int apple_rtkit_wake(struct apple_rtkit *rtk); */ int apple_rtkit_shutdown(struct apple_rtkit *rtk); +/* + * Put the co-processor into idle mode + */ +int apple_rtkit_idle(struct apple_rtkit *rtk); + /* * Checks if RTKit is running and ready to handle messages. */ -- cgit v1.2.3 From 4435d63f172851b57a6a0943b73a6b8055a9356f Mon Sep 17 00:00:00 2001 From: Asahi Lina Date: Sat, 21 Jan 2023 16:42:53 +0900 Subject: soc: apple: rtkit: Add a private pointer to apple_rtkit_shmem This allows downstream consumers to keep track of private data for shmem mappings. In particular, the Rust abstraction will use this to safely drop data associated with a mapping when it is unmapped. Signed-off-by: Asahi Lina Reviewed-by: Sven Peter Reviewed-by: Eric Curtin Signed-off-by: Hector Martin --- include/linux/soc/apple/rtkit.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soc/apple/rtkit.h b/include/linux/soc/apple/rtkit.h index a2446b45ed7f..927b214ef1c6 100644 --- a/include/linux/soc/apple/rtkit.h +++ b/include/linux/soc/apple/rtkit.h @@ -22,6 +22,7 @@ * @size: Size of the shared memory buffer. * @iova: Device VA of shared memory buffer. * @is_mapped: Shared memory buffer is managed by the co-processor. + * @private: Private data pointer for the parent driver. */ struct apple_rtkit_shmem { @@ -30,6 +31,7 @@ struct apple_rtkit_shmem { size_t size; dma_addr_t iova; bool is_mapped; + void *private; }; /* -- cgit v1.2.3 From b3892860f50920ea46342d32bf51323877365082 Mon Sep 17 00:00:00 2001 From: Asahi Lina Date: Sat, 21 Jan 2023 16:41:35 +0900 Subject: soc: apple: rtkit: Export non-devm init/free functions While we normally encourage devm usage by drivers, some consumers (and in particular the upcoming Rust abstractions) might want to manually manage memory. Export the raw functions to make this possible. Signed-off-by: Asahi Lina Reviewed-by: Sven Peter Reviewed-by: Eric Curtin Signed-off-by: Hector Martin --- drivers/soc/apple/rtkit.c | 15 ++++++++++----- include/linux/soc/apple/rtkit.h | 19 +++++++++++++++++++ 2 files changed, 29 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/soc/apple/rtkit.c b/drivers/soc/apple/rtkit.c index efb1fa77dff2..35ec35aa500d 100644 --- a/drivers/soc/apple/rtkit.c +++ b/drivers/soc/apple/rtkit.c @@ -699,7 +699,7 @@ static int apple_rtkit_request_mbox_chan(struct apple_rtkit *rtk) return 0; } -static struct apple_rtkit *apple_rtkit_init(struct device *dev, void *cookie, +struct apple_rtkit *apple_rtkit_init(struct device *dev, void *cookie, const char *mbox_name, int mbox_idx, const struct apple_rtkit_ops *ops) { @@ -751,6 +751,7 @@ free_rtk: kfree(rtk); return ERR_PTR(ret); } +EXPORT_SYMBOL_GPL(apple_rtkit_init); static int apple_rtkit_wait_for_completion(struct completion *c) { @@ -947,10 +948,8 @@ int apple_rtkit_wake(struct apple_rtkit *rtk) } EXPORT_SYMBOL_GPL(apple_rtkit_wake); -static void apple_rtkit_free(void *data) +void apple_rtkit_free(struct apple_rtkit *rtk) { - struct apple_rtkit *rtk = data; - mbox_free_channel(rtk->mbox_chan); destroy_workqueue(rtk->wq); @@ -961,6 +960,12 @@ static void apple_rtkit_free(void *data) kfree(rtk->syslog_msg_buffer); kfree(rtk); } +EXPORT_SYMBOL_GPL(apple_rtkit_free); + +static void apple_rtkit_free_wrapper(void *data) +{ + apple_rtkit_free(data); +} struct apple_rtkit *devm_apple_rtkit_init(struct device *dev, void *cookie, const char *mbox_name, int mbox_idx, @@ -973,7 +978,7 @@ struct apple_rtkit *devm_apple_rtkit_init(struct device *dev, void *cookie, if (IS_ERR(rtk)) return rtk; - ret = devm_add_action_or_reset(dev, apple_rtkit_free, rtk); + ret = devm_add_action_or_reset(dev, apple_rtkit_free_wrapper, rtk); if (ret) return ERR_PTR(ret); diff --git a/include/linux/soc/apple/rtkit.h b/include/linux/soc/apple/rtkit.h index 927b214ef1c6..fc456f75c131 100644 --- a/include/linux/soc/apple/rtkit.h +++ b/include/linux/soc/apple/rtkit.h @@ -79,6 +79,25 @@ struct apple_rtkit *devm_apple_rtkit_init(struct device *dev, void *cookie, const char *mbox_name, int mbox_idx, const struct apple_rtkit_ops *ops); +/* + * Non-devm version of devm_apple_rtkit_init. Must be freed with + * apple_rtkit_free. + * + * @dev: Pointer to the device node this coprocessor is assocated with + * @cookie: opaque cookie passed to all functions defined in rtkit_ops + * @mbox_name: mailbox name used to communicate with the co-processor + * @mbox_idx: mailbox index to be used if mbox_name is NULL + * @ops: pointer to rtkit_ops to be used for this co-processor + */ +struct apple_rtkit *apple_rtkit_init(struct device *dev, void *cookie, + const char *mbox_name, int mbox_idx, + const struct apple_rtkit_ops *ops); + +/* + * Free an instance of apple_rtkit. + */ +void apple_rtkit_free(struct apple_rtkit *rtk); + /* * Reinitialize internal structures. Must only be called with the co-processor * is held in reset. -- cgit v1.2.3 From 2b8e35337605ca581f777cad73d7a6ac2ccbf6ec Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 30 Jan 2023 13:17:46 +0200 Subject: container_of: Update header inclusions The commit 848dba781f19 ("container_of: remove container_of_safe()") removed the code that uses err.h. Replace the inclusion by stddef.h which provides offsetof() definition which is still in use. Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20230130111746.59830-1-andriy.shevchenko@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/container_of.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/container_of.h b/include/linux/container_of.h index 1d898f9158b4..713890c867be 100644 --- a/include/linux/container_of.h +++ b/include/linux/container_of.h @@ -3,7 +3,7 @@ #define _LINUX_CONTAINER_OF_H #include -#include +#include #define typeof_member(T, m) typeof(((T*)0)->m) -- cgit v1.2.3 From 3bd3bc2ada84229e74f974d4dafcaca59ae8347f Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Mon, 23 Jan 2023 16:49:49 +0000 Subject: soundwire: bus: Remove unused reset_page_addr() callback A previous patch removed unnecessary zeroing of the page registers after a paged transaction, so now the reset_page_addr callback is unused and can be removed. Signed-off-by: Richard Fitzgerald Reviewed-by: Pierre-Louis Bossart Link: https://lore.kernel.org/r/20230123164949.245898-3-rf@opensource.cirrus.com Signed-off-by: Vinod Koul --- drivers/soundwire/cadence_master.c | 14 -------------- drivers/soundwire/cadence_master.h | 3 --- drivers/soundwire/intel_auxdevice.c | 1 - include/linux/soundwire/sdw.h | 3 --- 4 files changed, 21 deletions(-) (limited to 'include/linux') diff --git a/drivers/soundwire/cadence_master.c b/drivers/soundwire/cadence_master.c index 521387322145..f44e8f9a1c09 100644 --- a/drivers/soundwire/cadence_master.c +++ b/drivers/soundwire/cadence_master.c @@ -770,20 +770,6 @@ cdns_xfer_msg_defer(struct sdw_bus *bus, } EXPORT_SYMBOL(cdns_xfer_msg_defer); -enum sdw_command_response -cdns_reset_page_addr(struct sdw_bus *bus, unsigned int dev_num) -{ - struct sdw_cdns *cdns = bus_to_cdns(bus); - struct sdw_msg msg; - - /* Create dummy message with valid device number */ - memset(&msg, 0, sizeof(msg)); - msg.dev_num = dev_num; - - return cdns_program_scp_addr(cdns, &msg); -} -EXPORT_SYMBOL(cdns_reset_page_addr); - u32 cdns_read_ping_status(struct sdw_bus *bus) { struct sdw_cdns *cdns = bus_to_cdns(bus); diff --git a/drivers/soundwire/cadence_master.h b/drivers/soundwire/cadence_master.h index fa9dc38264a4..2efc857d21aa 100644 --- a/drivers/soundwire/cadence_master.h +++ b/drivers/soundwire/cadence_master.h @@ -182,9 +182,6 @@ struct sdw_cdns_pdi *sdw_cdns_alloc_pdi(struct sdw_cdns *cdns, void sdw_cdns_config_stream(struct sdw_cdns *cdns, u32 ch, u32 dir, struct sdw_cdns_pdi *pdi); -enum sdw_command_response -cdns_reset_page_addr(struct sdw_bus *bus, unsigned int dev_num); - enum sdw_command_response cdns_xfer_msg(struct sdw_bus *bus, struct sdw_msg *msg); diff --git a/drivers/soundwire/intel_auxdevice.c b/drivers/soundwire/intel_auxdevice.c index 96c6b2112feb..5021be0f4158 100644 --- a/drivers/soundwire/intel_auxdevice.c +++ b/drivers/soundwire/intel_auxdevice.c @@ -113,7 +113,6 @@ static struct sdw_master_ops sdw_intel_ops = { .override_adr = sdw_dmi_override_adr, .xfer_msg = cdns_xfer_msg, .xfer_msg_defer = cdns_xfer_msg_defer, - .reset_page_addr = cdns_reset_page_addr, .set_bus_conf = cdns_bus_conf, .pre_bank_switch = generic_pre_bank_switch, .post_bank_switch = generic_post_bank_switch, diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index 3cd2a761911f..a8d74635ea0d 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -838,7 +838,6 @@ struct sdw_defer { * @override_adr: Override value read from firmware (quirk for buggy firmware) * @xfer_msg: Transfer message callback * @xfer_msg_defer: Defer version of transfer message callback - * @reset_page_addr: Reset the SCP page address registers * @set_bus_conf: Set the bus configuration * @pre_bank_switch: Callback for pre bank switch * @post_bank_switch: Callback for post bank switch @@ -854,8 +853,6 @@ struct sdw_master_ops { enum sdw_command_response (*xfer_msg_defer) (struct sdw_bus *bus, struct sdw_msg *msg, struct sdw_defer *defer); - enum sdw_command_response (*reset_page_addr) - (struct sdw_bus *bus, unsigned int dev_num); int (*set_bus_conf)(struct sdw_bus *bus, struct sdw_bus_params *params); int (*pre_bank_switch)(struct sdw_bus *bus); -- cgit v1.2.3 From 4e197ee880c24ecb63f7fe17449b3653bc64b03c Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Tue, 31 Jan 2023 09:46:39 +0100 Subject: clk: imx6ul: add ethernet refclock mux support Add ethernet refclock mux support and set it to internal clock by default. This configuration will not affect existing boards. clock tree before this patch: fec1 <- enet1_ref_125m (gate) <- enet1_ref (divider) <-, |- pll6_enet fec2 <- enet2_ref_125m (gate) <- enet2_ref (divider) <-´ after this patch: fec1 <- enet1_ref_sel(mux) <- enet1_ref_125m (gate) <- ... `--<> enet1_ref_pad |- pll6_enet fec2 <- enet2_ref_sel(mux) <- enet2_ref_125m (gate) <- ... `--<> enet2_ref_pad Signed-off-by: Oleksij Rempel Acked-by: Lee Jones Reviewed-by: Abel Vesa Signed-off-by: Abel Vesa Link: https://lore.kernel.org/r/20230131084642.709385-17-o.rempel@pengutronix.de --- drivers/clk/imx/clk-imx6ul.c | 26 ++++++++++++++++++++++++++ include/dt-bindings/clock/imx6ul-clock.h | 6 +++++- include/linux/mfd/syscon/imx6q-iomuxc-gpr.h | 6 ++++-- 3 files changed, 35 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/clk/imx/clk-imx6ul.c b/drivers/clk/imx/clk-imx6ul.c index c3c465c1b0e7..2836adb817b7 100644 --- a/drivers/clk/imx/clk-imx6ul.c +++ b/drivers/clk/imx/clk-imx6ul.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -94,6 +95,17 @@ static const struct clk_div_table video_div_table[] = { { } }; +static const char * enet1_ref_sels[] = { "enet1_ref_125m", "enet1_ref_pad", }; +static const u32 enet1_ref_sels_table[] = { IMX6UL_GPR1_ENET1_TX_CLK_DIR, + IMX6UL_GPR1_ENET1_CLK_SEL }; +static const u32 enet1_ref_sels_table_mask = IMX6UL_GPR1_ENET1_TX_CLK_DIR | + IMX6UL_GPR1_ENET1_CLK_SEL; +static const char * enet2_ref_sels[] = { "enet2_ref_125m", "enet2_ref_pad", }; +static const u32 enet2_ref_sels_table[] = { IMX6UL_GPR1_ENET2_TX_CLK_DIR, + IMX6UL_GPR1_ENET2_CLK_SEL }; +static const u32 enet2_ref_sels_table_mask = IMX6UL_GPR1_ENET2_TX_CLK_DIR | + IMX6UL_GPR1_ENET2_CLK_SEL; + static u32 share_count_asrc; static u32 share_count_audio; static u32 share_count_sai1; @@ -472,6 +484,17 @@ static void __init imx6ul_clocks_init(struct device_node *ccm_node) /* mask handshake of mmdc */ imx_mmdc_mask_handshake(base, 0); + hws[IMX6UL_CLK_ENET1_REF_PAD] = imx_obtain_fixed_of_clock(ccm_node, "enet1_ref_pad", 0); + + hws[IMX6UL_CLK_ENET1_REF_SEL] = imx_clk_gpr_mux("enet1_ref_sel", "fsl,imx6ul-iomuxc-gpr", + IOMUXC_GPR1, enet1_ref_sels, ARRAY_SIZE(enet1_ref_sels), + enet1_ref_sels_table, enet1_ref_sels_table_mask); + hws[IMX6UL_CLK_ENET2_REF_PAD] = imx_obtain_fixed_of_clock(ccm_node, "enet2_ref_pad", 0); + + hws[IMX6UL_CLK_ENET2_REF_SEL] = imx_clk_gpr_mux("enet2_ref_sel", "fsl,imx6ul-iomuxc-gpr", + IOMUXC_GPR1, enet2_ref_sels, ARRAY_SIZE(enet2_ref_sels), + enet2_ref_sels_table, enet2_ref_sels_table_mask); + imx_check_clk_hws(hws, IMX6UL_CLK_END); of_clk_add_hw_provider(np, of_clk_hw_onecell_get, clk_hw_data); @@ -516,6 +539,9 @@ static void __init imx6ul_clocks_init(struct device_node *ccm_node) clk_set_parent(hws[IMX6ULL_CLK_EPDC_PRE_SEL]->clk, hws[IMX6UL_CLK_PLL3_PFD2]->clk); clk_set_parent(hws[IMX6UL_CLK_ENFC_SEL]->clk, hws[IMX6UL_CLK_PLL2_PFD2]->clk); + + clk_set_parent(hws[IMX6UL_CLK_ENET1_REF_SEL]->clk, hws[IMX6UL_CLK_ENET_REF]->clk); + clk_set_parent(hws[IMX6UL_CLK_ENET2_REF_SEL]->clk, hws[IMX6UL_CLK_ENET2_REF]->clk); } CLK_OF_DECLARE(imx6ul, "fsl,imx6ul-ccm", imx6ul_clocks_init); diff --git a/include/dt-bindings/clock/imx6ul-clock.h b/include/dt-bindings/clock/imx6ul-clock.h index b44920f1edb0..66239ebc0e23 100644 --- a/include/dt-bindings/clock/imx6ul-clock.h +++ b/include/dt-bindings/clock/imx6ul-clock.h @@ -257,7 +257,11 @@ #define IMX6UL_CLK_GPIO5 248 #define IMX6UL_CLK_MMDC_P1_IPG 249 #define IMX6UL_CLK_ENET1_REF_125M 250 +#define IMX6UL_CLK_ENET1_REF_SEL 251 +#define IMX6UL_CLK_ENET1_REF_PAD 252 +#define IMX6UL_CLK_ENET2_REF_SEL 253 +#define IMX6UL_CLK_ENET2_REF_PAD 254 -#define IMX6UL_CLK_END 251 +#define IMX6UL_CLK_END 255 #endif /* __DT_BINDINGS_CLOCK_IMX6UL_H */ diff --git a/include/linux/mfd/syscon/imx6q-iomuxc-gpr.h b/include/linux/mfd/syscon/imx6q-iomuxc-gpr.h index d4b5e527a7a3..09c6b3184bb0 100644 --- a/include/linux/mfd/syscon/imx6q-iomuxc-gpr.h +++ b/include/linux/mfd/syscon/imx6q-iomuxc-gpr.h @@ -451,8 +451,10 @@ #define IMX6SX_GPR12_PCIE_RX_EQ_2 (0x2 << 0) /* For imx6ul iomux gpr register field define */ -#define IMX6UL_GPR1_ENET1_CLK_DIR (0x1 << 17) -#define IMX6UL_GPR1_ENET2_CLK_DIR (0x1 << 18) +#define IMX6UL_GPR1_ENET2_TX_CLK_DIR BIT(18) +#define IMX6UL_GPR1_ENET1_TX_CLK_DIR BIT(17) +#define IMX6UL_GPR1_ENET2_CLK_SEL BIT(14) +#define IMX6UL_GPR1_ENET1_CLK_SEL BIT(13) #define IMX6UL_GPR1_ENET1_CLK_OUTPUT (0x1 << 17) #define IMX6UL_GPR1_ENET2_CLK_OUTPUT (0x1 << 18) #define IMX6UL_GPR1_ENET_CLK_DIR (0x3 << 17) -- cgit v1.2.3 From dd0b9619a21ef77127e6002f9cb2d254c03ceed1 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Thu, 19 Jan 2023 15:32:10 +0800 Subject: soundwire: cadence: use directly bus sdw_defer structure Copying the bus sdw_defer structure into the Cadence internals leads to using stale pointers and kernel oopses on errors. It's just simpler and safer to use the bus sdw_defer structure directly. Link: https://github.com/thesofproject/linux/issues/4056 Signed-off-by: Pierre-Louis Bossart Reviewed-by: Ranjani Sridharan Signed-off-by: Bard Liao Link: https://lore.kernel.org/r/20230119073211.85979-4-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- drivers/soundwire/bus.c | 2 +- drivers/soundwire/cadence_master.c | 17 ++++++++--------- drivers/soundwire/cadence_master.h | 5 +---- include/linux/soundwire/sdw.h | 3 +-- 4 files changed, 11 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c index 9eb54dcbe035..29d644bb4020 100644 --- a/drivers/soundwire/bus.c +++ b/drivers/soundwire/bus.c @@ -237,7 +237,7 @@ static inline int do_transfer_defer(struct sdw_bus *bus, init_completion(&defer->complete); for (i = 0; i <= retry; i++) { - resp = bus->ops->xfer_msg_defer(bus, msg, defer); + resp = bus->ops->xfer_msg_defer(bus, msg); ret = find_response_code(resp); /* if cmd is ok or ignored return */ if (ret == 0 || ret == -ENODATA) diff --git a/drivers/soundwire/cadence_master.c b/drivers/soundwire/cadence_master.c index f44e8f9a1c09..65fcb28c8f58 100644 --- a/drivers/soundwire/cadence_master.c +++ b/drivers/soundwire/cadence_master.c @@ -750,7 +750,7 @@ EXPORT_SYMBOL(cdns_xfer_msg); enum sdw_command_response cdns_xfer_msg_defer(struct sdw_bus *bus, - struct sdw_msg *msg, struct sdw_defer *defer) + struct sdw_msg *msg) { struct sdw_cdns *cdns = bus_to_cdns(bus); int cmd = 0, ret; @@ -763,9 +763,6 @@ cdns_xfer_msg_defer(struct sdw_bus *bus, if (ret) return SDW_CMD_FAIL_OTHER; - cdns->defer = defer; - cdns->defer->length = msg->len; - return _cdns_xfer_msg(cdns, msg, cmd, 0, msg->len, true); } EXPORT_SYMBOL(cdns_xfer_msg_defer); @@ -879,13 +876,15 @@ irqreturn_t sdw_cdns_irq(int irq, void *dev_id) return IRQ_NONE; if (int_status & CDNS_MCP_INT_RX_WL) { + struct sdw_bus *bus = &cdns->bus; + struct sdw_defer *defer = &bus->defer_msg; + cdns_read_response(cdns); - if (cdns->defer) { - cdns_fill_msg_resp(cdns, cdns->defer->msg, - cdns->defer->length, 0); - complete(&cdns->defer->complete); - cdns->defer = NULL; + if (defer && defer->msg) { + cdns_fill_msg_resp(cdns, defer->msg, + defer->length, 0); + complete(&defer->complete); } else { complete(&cdns->tx_complete); } diff --git a/drivers/soundwire/cadence_master.h b/drivers/soundwire/cadence_master.h index 2efc857d21aa..90289a3dd505 100644 --- a/drivers/soundwire/cadence_master.h +++ b/drivers/soundwire/cadence_master.h @@ -109,7 +109,6 @@ struct sdw_cdns_dai_runtime { * @instance: instance number * @response_buf: SoundWire response buffer * @tx_complete: Tx completion - * @defer: Defer pointer * @ports: Data ports * @num_ports: Total number of data ports * @pcm: PCM streams @@ -130,7 +129,6 @@ struct sdw_cdns { u32 response_buf[CDNS_MCP_IP_MAX_CMD_LEN + 2]; struct completion tx_complete; - struct sdw_defer *defer; struct sdw_cdns_port *ports; int num_ports; @@ -186,8 +184,7 @@ enum sdw_command_response cdns_xfer_msg(struct sdw_bus *bus, struct sdw_msg *msg); enum sdw_command_response -cdns_xfer_msg_defer(struct sdw_bus *bus, - struct sdw_msg *msg, struct sdw_defer *defer); +cdns_xfer_msg_defer(struct sdw_bus *bus, struct sdw_msg *msg); u32 cdns_read_ping_status(struct sdw_bus *bus); diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index a8d74635ea0d..9e5fc0307284 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -851,8 +851,7 @@ struct sdw_master_ops { enum sdw_command_response (*xfer_msg) (struct sdw_bus *bus, struct sdw_msg *msg); enum sdw_command_response (*xfer_msg_defer) - (struct sdw_bus *bus, struct sdw_msg *msg, - struct sdw_defer *defer); + (struct sdw_bus *bus, struct sdw_msg *msg); int (*set_bus_conf)(struct sdw_bus *bus, struct sdw_bus_params *params); int (*pre_bank_switch)(struct sdw_bus *bus); -- cgit v1.2.3 From 66f95de7c13be5e442d8ed4cf00e13f8dbdc1315 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Thu, 19 Jan 2023 15:32:11 +0800 Subject: soundwire: cadence: further simplify low-level xfer_msg_defer() callback The message pointer is already stored in the bus->defer structure, not need to pass it as an argument. Suggested-by: Ranjani Sridharan Signed-off-by: Pierre-Louis Bossart Reviewed-by: Ranjani Sridharan Signed-off-by: Bard Liao Link: https://lore.kernel.org/r/20230119073211.85979-5-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- drivers/soundwire/bus.c | 2 +- drivers/soundwire/cadence_master.c | 5 +++-- drivers/soundwire/cadence_master.h | 2 +- include/linux/soundwire/sdw.h | 5 +++-- 4 files changed, 8 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c index 29d644bb4020..b6aca59c3130 100644 --- a/drivers/soundwire/bus.c +++ b/drivers/soundwire/bus.c @@ -237,7 +237,7 @@ static inline int do_transfer_defer(struct sdw_bus *bus, init_completion(&defer->complete); for (i = 0; i <= retry; i++) { - resp = bus->ops->xfer_msg_defer(bus, msg); + resp = bus->ops->xfer_msg_defer(bus); ret = find_response_code(resp); /* if cmd is ok or ignored return */ if (ret == 0 || ret == -ENODATA) diff --git a/drivers/soundwire/cadence_master.c b/drivers/soundwire/cadence_master.c index 65fcb28c8f58..e835dabb516c 100644 --- a/drivers/soundwire/cadence_master.c +++ b/drivers/soundwire/cadence_master.c @@ -749,10 +749,11 @@ cdns_xfer_msg(struct sdw_bus *bus, struct sdw_msg *msg) EXPORT_SYMBOL(cdns_xfer_msg); enum sdw_command_response -cdns_xfer_msg_defer(struct sdw_bus *bus, - struct sdw_msg *msg) +cdns_xfer_msg_defer(struct sdw_bus *bus) { struct sdw_cdns *cdns = bus_to_cdns(bus); + struct sdw_defer *defer = &bus->defer_msg; + struct sdw_msg *msg = defer->msg; int cmd = 0, ret; /* for defer only 1 message is supported */ diff --git a/drivers/soundwire/cadence_master.h b/drivers/soundwire/cadence_master.h index 90289a3dd505..dec0b4f993c1 100644 --- a/drivers/soundwire/cadence_master.h +++ b/drivers/soundwire/cadence_master.h @@ -184,7 +184,7 @@ enum sdw_command_response cdns_xfer_msg(struct sdw_bus *bus, struct sdw_msg *msg); enum sdw_command_response -cdns_xfer_msg_defer(struct sdw_bus *bus, struct sdw_msg *msg); +cdns_xfer_msg_defer(struct sdw_bus *bus); u32 cdns_read_ping_status(struct sdw_bus *bus); diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index 9e5fc0307284..d09a9857e1de 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -837,7 +837,8 @@ struct sdw_defer { * @read_prop: Read Master properties * @override_adr: Override value read from firmware (quirk for buggy firmware) * @xfer_msg: Transfer message callback - * @xfer_msg_defer: Defer version of transfer message callback + * @xfer_msg_defer: Defer version of transfer message callback. The message is handled with the + * bus struct @sdw_defer * @set_bus_conf: Set the bus configuration * @pre_bank_switch: Callback for pre bank switch * @post_bank_switch: Callback for post bank switch @@ -851,7 +852,7 @@ struct sdw_master_ops { enum sdw_command_response (*xfer_msg) (struct sdw_bus *bus, struct sdw_msg *msg); enum sdw_command_response (*xfer_msg_defer) - (struct sdw_bus *bus, struct sdw_msg *msg); + (struct sdw_bus *bus); int (*set_bus_conf)(struct sdw_bus *bus, struct sdw_bus_params *params); int (*pre_bank_switch)(struct sdw_bus *bus); -- cgit v1.2.3 From 5e6a51787fef20b849682d8c49ec9c2beed5c373 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 24 Jan 2023 15:38:38 +0200 Subject: uuid: Decouple guid_t and uuid_le types and respective macros The guid_t type and respective macros are being used internally only. The uuid_le has its user outside the kernel. Decouple these types and macros, and make guid_t completely internal type to the kernel. Signed-off-by: Andy Shevchenko Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20230124133838.22645-1-andriy.shevchenko@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- MAINTAINERS | 2 +- include/linux/uuid.h | 20 ++++++++++++++++---- include/uapi/linux/uuid.h | 12 ++++-------- 3 files changed, 21 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/MAINTAINERS b/MAINTAINERS index 1397e8db4cf1..1f61dc5c7847 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -10566,6 +10566,7 @@ F: drivers/watchdog/mei_wdt.c F: include/linux/mei_aux.h F: include/linux/mei_cl_bus.h F: include/uapi/linux/mei.h +F: include/uapi/linux/uuid.h F: samples/mei/* INTEL MAX 10 BMC MFD DRIVER @@ -21829,7 +21830,6 @@ L: linux-kernel@vger.kernel.org S: Maintained T: git git://git.infradead.org/users/hch/uuid.git F: include/linux/uuid.h -F: include/uapi/linux/uuid.h F: lib/test_uuid.c F: lib/uuid.c diff --git a/include/linux/uuid.h b/include/linux/uuid.h index 8cdc0d3567cd..5be158a49e11 100644 --- a/include/linux/uuid.h +++ b/include/linux/uuid.h @@ -8,15 +8,25 @@ #ifndef _LINUX_UUID_H_ #define _LINUX_UUID_H_ -#include #include #define UUID_SIZE 16 +typedef struct { + __u8 b[UUID_SIZE]; +} guid_t; + typedef struct { __u8 b[UUID_SIZE]; } uuid_t; +#define GUID_INIT(a, b, c, d0, d1, d2, d3, d4, d5, d6, d7) \ +((guid_t) \ +{{ (a) & 0xff, ((a) >> 8) & 0xff, ((a) >> 16) & 0xff, ((a) >> 24) & 0xff, \ + (b) & 0xff, ((b) >> 8) & 0xff, \ + (c) & 0xff, ((c) >> 8) & 0xff, \ + (d0), (d1), (d2), (d3), (d4), (d5), (d6), (d7) }}) + #define UUID_INIT(a, b, c, d0, d1, d2, d3, d4, d5, d6, d7) \ ((uuid_t) \ {{ ((a) >> 24) & 0xff, ((a) >> 16) & 0xff, ((a) >> 8) & 0xff, (a) & 0xff, \ @@ -97,10 +107,12 @@ extern const u8 uuid_index[16]; int guid_parse(const char *uuid, guid_t *u); int uuid_parse(const char *uuid, uuid_t *u); -/* backwards compatibility, don't use in new code */ -static inline int uuid_le_cmp(const guid_t u1, const guid_t u2) +/* MEI UUID type, don't use anywhere else */ +#include + +static inline int uuid_le_cmp(const uuid_le u1, const uuid_le u2) { - return memcmp(&u1, &u2, sizeof(guid_t)); + return memcmp(&u1, &u2, sizeof(uuid_le)); } #endif diff --git a/include/uapi/linux/uuid.h b/include/uapi/linux/uuid.h index c0f4bd9b040e..96ac684a4b2f 100644 --- a/include/uapi/linux/uuid.h +++ b/include/uapi/linux/uuid.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* DO NOT USE in new code! This is solely for MEI due to legacy reasons */ /* - * UUID/GUID definition + * MEI UUID definition * * Copyright (C) 2010, Intel Corp. * Huang Ying @@ -14,19 +14,15 @@ typedef struct { __u8 b[16]; -} guid_t; +} uuid_le; -#define GUID_INIT(a, b, c, d0, d1, d2, d3, d4, d5, d6, d7) \ -((guid_t) \ +#define UUID_LE(a, b, c, d0, d1, d2, d3, d4, d5, d6, d7) \ +((uuid_le) \ {{ (a) & 0xff, ((a) >> 8) & 0xff, ((a) >> 16) & 0xff, ((a) >> 24) & 0xff, \ (b) & 0xff, ((b) >> 8) & 0xff, \ (c) & 0xff, ((c) >> 8) & 0xff, \ (d0), (d1), (d2), (d3), (d4), (d5), (d6), (d7) }}) -/* backwards compatibility, don't use in new code */ -typedef guid_t uuid_le; -#define UUID_LE(a, b, c, d0, d1, d2, d3, d4, d5, d6, d7) \ - GUID_INIT(a, b, c, d0, d1, d2, d3, d4, d5, d6, d7) #define NULL_UUID_LE \ UUID_LE(0x00000000, 0x0000, 0x0000, 0x00, 0x00, 0x00, 0x00, \ 0x00, 0x00, 0x00, 0x00) -- cgit v1.2.3 From d931b83e62b1dd352fc326c0b1cf3be3ef19e113 Mon Sep 17 00:00:00 2001 From: Pierre Gondois Date: Tue, 24 Jan 2023 16:40:47 +0100 Subject: cacheinfo: Make default acpi_get_cache_info() return an error commit bd500361a937 ("ACPI: PPTT: Update acpi_find_last_cache_level() to acpi_get_cache_info()") updates the prototype of acpi_get_cache_info(). The cache 'levels' is update through a pointer and not the return value of the function. If CONFIG_ACPI_PPTT is not defined, acpi_get_cache_info() doesn't update its *levels and *split_levels parameters and returns 0. This can lead to a faulty behaviour. Make acpi_get_cache_info() return an error code if CONFIG_ACPI_PPTT is not defined. Also, In init_cache_level(), if no PPTT is present or CONFIG_ACPI_PPTT is not defined, instead of aborting if acpi_get_cache_info() returns an error code, just continue. This allows to try fetching the cache information from clidr_el1. Signed-off-by: Pierre Gondois Link: https://lore.kernel.org/r/20230124154053.355376-3-pierre.gondois@arm.com Signed-off-by: Greg Kroah-Hartman --- arch/arm64/kernel/cacheinfo.c | 2 +- include/linux/cacheinfo.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/kernel/cacheinfo.c b/arch/arm64/kernel/cacheinfo.c index 36c3b07cdf2d..91677f4d3395 100644 --- a/arch/arm64/kernel/cacheinfo.c +++ b/arch/arm64/kernel/cacheinfo.c @@ -64,7 +64,7 @@ int init_cache_level(unsigned int cpu) } else { ret = acpi_get_cache_info(cpu, &fw_level, NULL); if (ret < 0) - return ret; + fw_level = 0; } if (fw_level < 0) diff --git a/include/linux/cacheinfo.h b/include/linux/cacheinfo.h index dfef57077cd0..908e19d17f49 100644 --- a/include/linux/cacheinfo.h +++ b/include/linux/cacheinfo.h @@ -100,7 +100,7 @@ static inline int acpi_get_cache_info(unsigned int cpu, unsigned int *levels, unsigned int *split_levels) { - return 0; + return -ENOENT; } #else int acpi_get_cache_info(unsigned int cpu, -- cgit v1.2.3 From 4971c268b85e1c7a734a61622fc0813c86e2362e Mon Sep 17 00:00:00 2001 From: Roberto Sassu Date: Tue, 31 Jan 2023 18:42:43 +0100 Subject: ima: Align ima_file_mmap() parameters with mmap_file LSM hook Commit 98de59bfe4b2f ("take calculation of final prot in security_mmap_file() into a helper") moved the code to update prot, to be the actual protections applied to the kernel, to a new helper called mmap_prot(). However, while without the helper ima_file_mmap() was getting the updated prot, with the helper ima_file_mmap() gets the original prot, which contains the protections requested by the application. A possible consequence of this change is that, if an application calls mmap() with only PROT_READ, and the kernel applies PROT_EXEC in addition, that application would have access to executable memory without having this event recorded in the IMA measurement list. This situation would occur for example if the application, before mmap(), calls the personality() system call with READ_IMPLIES_EXEC as the first argument. Align ima_file_mmap() parameters with those of the mmap_file LSM hook, so that IMA can receive both the requested prot and the final prot. Since the requested protections are stored in a new variable, and the final protections are stored in the existing variable, this effectively restores the original behavior of the MMAP_CHECK hook. Cc: stable@vger.kernel.org Fixes: 98de59bfe4b2 ("take calculation of final prot in security_mmap_file() into a helper") Signed-off-by: Roberto Sassu Reviewed-by: Stefan Berger Signed-off-by: Mimi Zohar --- include/linux/ima.h | 6 ++++-- security/integrity/ima/ima_main.c | 7 +++++-- security/security.c | 7 ++++--- 3 files changed, 13 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ima.h b/include/linux/ima.h index 5a0b2a285a18..d79fee67235e 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -21,7 +21,8 @@ extern int ima_file_check(struct file *file, int mask); extern void ima_post_create_tmpfile(struct user_namespace *mnt_userns, struct inode *inode); extern void ima_file_free(struct file *file); -extern int ima_file_mmap(struct file *file, unsigned long prot); +extern int ima_file_mmap(struct file *file, unsigned long reqprot, + unsigned long prot, unsigned long flags); extern int ima_file_mprotect(struct vm_area_struct *vma, unsigned long prot); extern int ima_load_data(enum kernel_load_data_id id, bool contents); extern int ima_post_load_data(char *buf, loff_t size, @@ -76,7 +77,8 @@ static inline void ima_file_free(struct file *file) return; } -static inline int ima_file_mmap(struct file *file, unsigned long prot) +static inline int ima_file_mmap(struct file *file, unsigned long reqprot, + unsigned long prot, unsigned long flags) { return 0; } diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c index 1d40cdfa23d5..3948e54421cf 100644 --- a/security/integrity/ima/ima_main.c +++ b/security/integrity/ima/ima_main.c @@ -397,7 +397,9 @@ out: /** * ima_file_mmap - based on policy, collect/store measurement. * @file: pointer to the file to be measured (May be NULL) - * @prot: contains the protection that will be applied by the kernel. + * @reqprot: protection requested by the application + * @prot: protection that will be applied by the kernel + * @flags: operational flags * * Measure files being mmapped executable based on the ima_must_measure() * policy decision. @@ -405,7 +407,8 @@ out: * On success return 0. On integrity appraisal error, assuming the file * is in policy and IMA-appraisal is in enforcing mode, return -EACCES. */ -int ima_file_mmap(struct file *file, unsigned long prot) +int ima_file_mmap(struct file *file, unsigned long reqprot, + unsigned long prot, unsigned long flags) { u32 secid; diff --git a/security/security.c b/security/security.c index d1571900a8c7..174afa4fad81 100644 --- a/security/security.c +++ b/security/security.c @@ -1661,12 +1661,13 @@ static inline unsigned long mmap_prot(struct file *file, unsigned long prot) int security_mmap_file(struct file *file, unsigned long prot, unsigned long flags) { + unsigned long prot_adj = mmap_prot(file, prot); int ret; - ret = call_int_hook(mmap_file, 0, file, prot, - mmap_prot(file, prot), flags); + + ret = call_int_hook(mmap_file, 0, file, prot, prot_adj, flags); if (ret) return ret; - return ima_file_mmap(file, prot); + return ima_file_mmap(file, prot, prot_adj, flags); } int security_mmap_addr(unsigned long addr) -- cgit v1.2.3 From c1085957dece02bda586cbffc1328f3bca09325f Mon Sep 17 00:00:00 2001 From: Yangtao Li Date: Thu, 12 Jan 2023 21:34:43 +0800 Subject: f2fs: clarify compress level bit offset commit 3fde13f817e2 ("f2fs: compress: support compress level") introduce compress level, which macro(COMPRESS_LEVEL_OFFSET) is 8, But use wrong comment about compress level. Let's fix it. Signed-off-by: Yangtao Li Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- include/linux/f2fs_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index ee0d75d9a302..1701f25117ea 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -315,7 +315,7 @@ struct f2fs_inode { __u8 i_log_cluster_size; /* log of cluster size */ __le16 i_compress_flag; /* compress flag */ /* 0 bit: chksum flag - * [10,15] bits: compress level + * [8,15] bits: compress level */ __le32 i_extra_end[0]; /* for attribute size calculation */ } __packed; -- cgit v1.2.3 From 8b3517f88ff2983f52698893519227c10aac90b2 Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Wed, 1 Feb 2023 12:30:18 +0800 Subject: PCI: loongson: Prevent LS7A MRRS increases Except for isochronous-configured devices, software may set Max_Read_Request_Size (MRRS) to any value up to 4096. If a device issues a read request with size greater than the completer's Max_Payload_Size (MPS), the completer is required to break the response into multiple completions. Instead of correctly responding with multiple completions to a large read request, some LS7A Root Ports respond with a Completer Abort. To prevent this, the MRRS must be limited to an implementation-specific value. The OS cannot detect that value, so rely on BIOS to configure MRRS before booting, and quirk the Root Ports so we never set an MRRS larger than that BIOS value for any downstream device. N.B. Hot-added devices are not configured by BIOS, and they power up with MRRS = 512 bytes, so these devices will be limited to 512 bytes. If the LS7A limit is smaller, those hot-added devices may not work correctly, but per [1], hotplug is not supported with this chipset revision. [1] https://lore.kernel.org/r/073638a7-ae68-2847-ac3d-29e5e760d6af@loongson.cn [bhelgaas: commit log] Link: https://bugzilla.kernel.org/show_bug.cgi?id=216884 Link: https://lore.kernel.org/r/20230201043018.778499-3-chenhuacai@loongson.cn Signed-off-by: Huacai Chen Signed-off-by: Bjorn Helgaas --- drivers/pci/controller/pci-loongson.c | 44 ++++++++++++----------------------- drivers/pci/pci.c | 10 ++++++++ include/linux/pci.h | 1 + 3 files changed, 26 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/controller/pci-loongson.c b/drivers/pci/controller/pci-loongson.c index 05c50408f13b..759ec211c17b 100644 --- a/drivers/pci/controller/pci-loongson.c +++ b/drivers/pci/controller/pci-loongson.c @@ -75,37 +75,23 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, DEV_LS7A_LPC, system_bus_quirk); -static void loongson_mrrs_quirk(struct pci_dev *dev) +static void loongson_mrrs_quirk(struct pci_dev *pdev) { - struct pci_bus *bus = dev->bus; - struct pci_dev *bridge; - static const struct pci_device_id bridge_devids[] = { - { PCI_VDEVICE(LOONGSON, DEV_PCIE_PORT_0) }, - { PCI_VDEVICE(LOONGSON, DEV_PCIE_PORT_1) }, - { PCI_VDEVICE(LOONGSON, DEV_PCIE_PORT_2) }, - { 0, }, - }; - - /* look for the matching bridge */ - while (!pci_is_root_bus(bus)) { - bridge = bus->self; - bus = bus->parent; - /* - * Some Loongson PCIe ports have a h/w limitation of - * 256 bytes maximum read request size. They can't handle - * anything larger than this. So force this limit on - * any devices attached under these ports. - */ - if (pci_match_id(bridge_devids, bridge)) { - if (pcie_get_readrq(dev) > 256) { - pci_info(dev, "limiting MRRS to 256\n"); - pcie_set_readrq(dev, 256); - } - break; - } - } + /* + * Some Loongson PCIe ports have h/w limitations of maximum read + * request size. They can't handle anything larger than this. So + * force this limit on any devices attached under these ports. + */ + struct pci_host_bridge *bridge = pci_find_host_bridge(pdev->bus); + + bridge->no_inc_mrrs = 1; } -DECLARE_PCI_FIXUP_ENABLE(PCI_ANY_ID, PCI_ANY_ID, loongson_mrrs_quirk); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, + DEV_PCIE_PORT_0, loongson_mrrs_quirk); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, + DEV_PCIE_PORT_1, loongson_mrrs_quirk); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, + DEV_PCIE_PORT_2, loongson_mrrs_quirk); static void loongson_pci_pin_quirk(struct pci_dev *pdev) { diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index fba95486caaf..9d98bba72af9 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -6033,6 +6033,7 @@ int pcie_set_readrq(struct pci_dev *dev, int rq) { u16 v; int ret; + struct pci_host_bridge *bridge = pci_find_host_bridge(dev->bus); if (rq < 128 || rq > 4096 || !is_power_of_2(rq)) return -EINVAL; @@ -6051,6 +6052,15 @@ int pcie_set_readrq(struct pci_dev *dev, int rq) v = (ffs(rq) - 8) << 12; + if (bridge->no_inc_mrrs) { + int max_mrrs = pcie_get_readrq(dev); + + if (rq > max_mrrs) { + pci_info(dev, "can't set Max_Read_Request_Size to %d; max is %d\n", rq, max_mrrs); + return -EINVAL; + } + } + ret = pcie_capability_clear_and_set_word(dev, PCI_EXP_DEVCTL, PCI_EXP_DEVCTL_READRQ, v); diff --git a/include/linux/pci.h b/include/linux/pci.h index adffd65e84b4..3df2049ec4a8 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -572,6 +572,7 @@ struct pci_host_bridge { void *release_data; unsigned int ignore_reset_delay:1; /* For entire hierarchy */ unsigned int no_ext_tags:1; /* No Extended Tags */ + unsigned int no_inc_mrrs:1; /* No Increase MRRS */ unsigned int native_aer:1; /* OS may use PCIe AER */ unsigned int native_pcie_hotplug:1; /* OS may use PCIe hotplug */ unsigned int native_shpc_hotplug:1; /* OS may use SHPC hotplug */ -- cgit v1.2.3 From 37e98d9bedb50644654fd196e38acad49903fadc Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 1 Feb 2023 09:33:49 +0100 Subject: driver core: bus: move lock_class_key into dynamic structure Move the lock_class_key structure out of struct bus_type and into the dynamic structure we create already for all bus_types registered with the kernel. This saves on static space and removes one more writable field in struct bus_type. In the future, the same field can be moved out of the struct class logic because it shares this same private structure. Most everyone will never notice this change, as lockdep is not enabled in real systems so no memory or logic changes are happening for them. Cc: "Rafael J. Wysocki" Acked-by: Rafael J. Wysocki Signed-off-by: Greg Kroah-Hartman Link: https://lore.kernel.org/r/20230201083349.4038660-1-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/base/base.h | 2 ++ drivers/base/bus.c | 5 ++++- include/linux/device/bus.h | 1 - 3 files changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/base.h b/drivers/base/base.h index 2208af509ce8..0e806f641079 100644 --- a/drivers/base/base.h +++ b/drivers/base/base.h @@ -52,6 +52,8 @@ struct subsys_private { struct kset glue_dirs; struct class *class; + + struct lock_class_key lock_key; }; #define to_subsys_private(obj) container_of_const(obj, struct subsys_private, subsys.kobj) diff --git a/drivers/base/bus.c b/drivers/base/bus.c index cf1b8f00b4c0..aa70b3a7d778 100644 --- a/drivers/base/bus.c +++ b/drivers/base/bus.c @@ -154,6 +154,7 @@ static void bus_release(struct kobject *kobj) struct subsys_private *priv = to_subsys_private(kobj); struct bus_type *bus = priv->bus; + lockdep_unregister_key(&priv->lock_key); kfree(priv); bus->p = NULL; } @@ -743,7 +744,7 @@ int bus_register(struct bus_type *bus) { int retval; struct subsys_private *priv; - struct lock_class_key *key = &bus->lock_key; + struct lock_class_key *key; priv = kzalloc(sizeof(struct subsys_private), GFP_KERNEL); if (!priv) @@ -785,6 +786,8 @@ int bus_register(struct bus_type *bus) } INIT_LIST_HEAD(&priv->interfaces); + key = &priv->lock_key; + lockdep_register_key(key); __mutex_init(&priv->mutex, "subsys mutex", key); klist_init(&priv->klist_devices, klist_devices_get, klist_devices_put); klist_init(&priv->klist_drivers, NULL, NULL); diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h index 87e4d029c915..e3094db1e9fa 100644 --- a/include/linux/device/bus.h +++ b/include/linux/device/bus.h @@ -112,7 +112,6 @@ struct bus_type { const struct iommu_ops *iommu_ops; struct subsys_private *p; - struct lock_class_key lock_key; bool need_parent_lock; }; -- cgit v1.2.3 From de82f60f9c86b72635ce49f7ab822e6a00a90dca Mon Sep 17 00:00:00 2001 From: Michael Bottini Date: Thu, 19 Jan 2023 19:15:19 -0800 Subject: PCI/ASPM: Add pci_enable_link_state() Add pci_enable_link_state() to allow devices to change the default BIOS configured states. Clears the BIOS default settings then sets the new states and reconfigures the link under the semaphore. Also add PCIE_LINK_STATE_ALL macro for convenience for callers that want to enable all link states. Link: https://lore.kernel.org/r/20230120031522.2304439-2-david.e.box@linux.intel.com Signed-off-by: Michael Bottini Signed-off-by: David E. Box Signed-off-by: Lorenzo Pieralisi Reviewed-by: Kuppuswamy Sathyanarayanan Acked-by: Bjorn Helgaas --- drivers/pci/pcie/aspm.c | 54 +++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/pci.h | 7 +++++++ 2 files changed, 61 insertions(+) (limited to 'include/linux') diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c index 53a1fa306e1e..339c686a5094 100644 --- a/drivers/pci/pcie/aspm.c +++ b/drivers/pci/pcie/aspm.c @@ -1181,6 +1181,60 @@ int pci_disable_link_state(struct pci_dev *pdev, int state) } EXPORT_SYMBOL(pci_disable_link_state); +/** + * pci_enable_link_state - Clear and set the default device link state so that + * the link may be allowed to enter the specified states. Note that if the + * BIOS didn't grant ASPM control to the OS, this does nothing because we can't + * touch the LNKCTL register. Also note that this does not enable states + * disabled by pci_disable_link_state(). Return 0 or a negative errno. + * + * @pdev: PCI device + * @state: Mask of ASPM link states to enable + */ +int pci_enable_link_state(struct pci_dev *pdev, int state) +{ + struct pcie_link_state *link = pcie_aspm_get_link(pdev); + + if (!link) + return -EINVAL; + /* + * A driver requested that ASPM be enabled on this device, but + * if we don't have permission to manage ASPM (e.g., on ACPI + * systems we have to observe the FADT ACPI_FADT_NO_ASPM bit and + * the _OSC method), we can't honor that request. + */ + if (aspm_disabled) { + pci_warn(pdev, "can't override BIOS ASPM; OS doesn't have ASPM control\n"); + return -EPERM; + } + + down_read(&pci_bus_sem); + mutex_lock(&aspm_lock); + link->aspm_default = 0; + if (state & PCIE_LINK_STATE_L0S) + link->aspm_default |= ASPM_STATE_L0S; + if (state & PCIE_LINK_STATE_L1) + /* L1 PM substates require L1 */ + link->aspm_default |= ASPM_STATE_L1 | ASPM_STATE_L1SS; + if (state & PCIE_LINK_STATE_L1_1) + link->aspm_default |= ASPM_STATE_L1_1; + if (state & PCIE_LINK_STATE_L1_2) + link->aspm_default |= ASPM_STATE_L1_2; + if (state & PCIE_LINK_STATE_L1_1_PCIPM) + link->aspm_default |= ASPM_STATE_L1_1_PCIPM; + if (state & PCIE_LINK_STATE_L1_2_PCIPM) + link->aspm_default |= ASPM_STATE_L1_2_PCIPM; + pcie_config_aspm_link(link, policy_to_aspm_state(link)); + + link->clkpm_default = (state & PCIE_LINK_STATE_CLKPM) ? 1 : 0; + pcie_set_clkpm(link, policy_to_clkpm_state(link)); + mutex_unlock(&aspm_lock); + up_read(&pci_bus_sem); + + return 0; +} +EXPORT_SYMBOL(pci_enable_link_state); + static int pcie_aspm_set_policy(const char *val, const struct kernel_param *kp) { diff --git a/include/linux/pci.h b/include/linux/pci.h index adffd65e84b4..ea601e6fbbda 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1685,10 +1685,15 @@ extern bool pcie_ports_native; #define PCIE_LINK_STATE_L1_2 BIT(4) #define PCIE_LINK_STATE_L1_1_PCIPM BIT(5) #define PCIE_LINK_STATE_L1_2_PCIPM BIT(6) +#define PCIE_LINK_STATE_ALL (PCIE_LINK_STATE_L0S | PCIE_LINK_STATE_L1 |\ + PCIE_LINK_STATE_CLKPM | PCIE_LINK_STATE_L1_1 |\ + PCIE_LINK_STATE_L1_2 | PCIE_LINK_STATE_L1_1_PCIPM |\ + PCIE_LINK_STATE_L1_2_PCIPM) #ifdef CONFIG_PCIEASPM int pci_disable_link_state(struct pci_dev *pdev, int state); int pci_disable_link_state_locked(struct pci_dev *pdev, int state); +int pci_enable_link_state(struct pci_dev *pdev, int state); void pcie_no_aspm(void); bool pcie_aspm_support_enabled(void); bool pcie_aspm_enabled(struct pci_dev *pdev); @@ -1697,6 +1702,8 @@ static inline int pci_disable_link_state(struct pci_dev *pdev, int state) { return 0; } static inline int pci_disable_link_state_locked(struct pci_dev *pdev, int state) { return 0; } +static inline int pci_enable_link_state(struct pci_dev *pdev, int state) +{ return 0; } static inline void pcie_no_aspm(void) { } static inline bool pcie_aspm_support_enabled(void) { return false; } static inline bool pcie_aspm_enabled(struct pci_dev *pdev) { return false; } -- cgit v1.2.3 From 1bd9a7b4afd5e0b938868a90b16d514c19808e6c Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Tue, 24 Jan 2023 19:37:20 +0100 Subject: phy: Remove unused phy_optional_get() There were never any upstream users of this function since its introduction almost 10 years ago. Besides, the dummy for phy_optional_get() should have returned NULL instead of an error code. Signed-off-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/df61992b1d66bccf4e6e1eafae94a7f7d7629f34.1674584626.git.geert+renesas@glider.be Signed-off-by: Vinod Koul --- Documentation/driver-api/phy/phy.rst | 11 +++++------ drivers/phy/phy-core.c | 21 --------------------- include/linux/phy/phy.h | 7 ------- 3 files changed, 5 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/Documentation/driver-api/phy/phy.rst b/Documentation/driver-api/phy/phy.rst index 8e8b3e8f9523..26467dd4f291 100644 --- a/Documentation/driver-api/phy/phy.rst +++ b/Documentation/driver-api/phy/phy.rst @@ -103,7 +103,6 @@ it. This framework provides the following APIs to get a reference to the PHY. :: struct phy *phy_get(struct device *dev, const char *string); - struct phy *phy_optional_get(struct device *dev, const char *string); struct phy *devm_phy_get(struct device *dev, const char *string); struct phy *devm_phy_optional_get(struct device *dev, const char *string); @@ -111,15 +110,15 @@ it. This framework provides the following APIs to get a reference to the PHY. struct device_node *np, int index); -phy_get, phy_optional_get, devm_phy_get and devm_phy_optional_get can -be used to get the PHY. In the case of dt boot, the string arguments +phy_get, devm_phy_get and devm_phy_optional_get can be used to get the PHY. +In the case of dt boot, the string arguments should contain the phy name as given in the dt data and in the case of non-dt boot, it should contain the label of the PHY. The two devm_phy_get associates the device with the PHY using devres on successful PHY get. On driver detach, release function is invoked on -the devres data and devres data is freed. phy_optional_get and -devm_phy_optional_get should be used when the phy is optional. These -two functions will never return -ENODEV, but instead returns NULL when +the devres data and devres data is freed. +devm_phy_optional_get should be used when the phy is optional. This +function will never return -ENODEV, but instead returns NULL when the phy cannot be found.Some generic drivers, such as ehci, may use multiple phys and for such drivers referencing phy(s) by name(s) does not make sense. In this case, devm_of_phy_get_by_index can be used to get a phy reference based on diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c index d93ddf1262c5..672f5c865886 100644 --- a/drivers/phy/phy-core.c +++ b/drivers/phy/phy-core.c @@ -766,27 +766,6 @@ struct phy *phy_get(struct device *dev, const char *string) } EXPORT_SYMBOL_GPL(phy_get); -/** - * phy_optional_get() - lookup and obtain a reference to an optional phy. - * @dev: device that requests this phy - * @string: the phy name as given in the dt data or the name of the controller - * port for non-dt case - * - * Returns the phy driver, after getting a refcount to it; or - * NULL if there is no such phy. The caller is responsible for - * calling phy_put() to release that count. - */ -struct phy *phy_optional_get(struct device *dev, const char *string) -{ - struct phy *phy = phy_get(dev, string); - - if (PTR_ERR(phy) == -ENODEV) - phy = NULL; - - return phy; -} -EXPORT_SYMBOL_GPL(phy_optional_get); - /** * devm_phy_get() - lookup and obtain a reference to a phy. * @dev: device that requests this phy diff --git a/include/linux/phy/phy.h b/include/linux/phy/phy.h index b1413757fcc3..1b4f9be21e01 100644 --- a/include/linux/phy/phy.h +++ b/include/linux/phy/phy.h @@ -250,7 +250,6 @@ static inline void phy_set_bus_width(struct phy *phy, int bus_width) phy->attrs.bus_width = bus_width; } struct phy *phy_get(struct device *dev, const char *string); -struct phy *phy_optional_get(struct device *dev, const char *string); struct phy *devm_phy_get(struct device *dev, const char *string); struct phy *devm_phy_optional_get(struct device *dev, const char *string); struct phy *devm_of_phy_get(struct device *dev, struct device_node *np, @@ -426,12 +425,6 @@ static inline struct phy *phy_get(struct device *dev, const char *string) return ERR_PTR(-ENOSYS); } -static inline struct phy *phy_optional_get(struct device *dev, - const char *string) -{ - return ERR_PTR(-ENOSYS); -} - static inline struct phy *devm_phy_get(struct device *dev, const char *string) { return ERR_PTR(-ENOSYS); -- cgit v1.2.3 From d02aa181ee595c81738b6bd7ebad6025fbee035a Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Tue, 24 Jan 2023 19:37:22 +0100 Subject: phy: Add devm_of_phy_optional_get() helper Add an optional variant of devm_of_phy_get() that also takes care of printing real errors, so drivers no longer have to open-code this operation. Signed-off-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/4cd0069bcff424ffc5c3a102397c02370b91985b.1674584626.git.geert+renesas@glider.be Signed-off-by: Vinod Koul --- Documentation/driver-api/phy/phy.rst | 7 +++++-- drivers/phy/phy-core.c | 30 ++++++++++++++++++++++++++++++ include/linux/phy/phy.h | 9 +++++++++ 3 files changed, 44 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/Documentation/driver-api/phy/phy.rst b/Documentation/driver-api/phy/phy.rst index 6cadc58f4ce0..81785c084f3e 100644 --- a/Documentation/driver-api/phy/phy.rst +++ b/Documentation/driver-api/phy/phy.rst @@ -108,6 +108,9 @@ it. This framework provides the following APIs to get a reference to the PHY. const char *string); struct phy *devm_of_phy_get(struct device *dev, struct device_node *np, const char *con_id); + struct phy *devm_of_phy_optional_get(struct device *dev, + struct device_node *np, + const char *con_id); struct phy *devm_of_phy_get_by_index(struct device *dev, struct device_node *np, int index); @@ -119,8 +122,8 @@ non-dt boot, it should contain the label of the PHY. The two devm_phy_get associates the device with the PHY using devres on successful PHY get. On driver detach, release function is invoked on the devres data and devres data is freed. -devm_phy_optional_get should be used when the phy is optional. This -function will never return -ENODEV, but instead returns NULL when +The _optional_get variants should be used when the phy is optional. These +functions will never return -ENODEV, but instead return NULL when the phy cannot be found. Some generic drivers, such as ehci, may use multiple phys. In this case, devm_of_phy_get or devm_of_phy_get_by_index can be used to get a phy diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c index 672f5c865886..9951efc03eaa 100644 --- a/drivers/phy/phy-core.c +++ b/drivers/phy/phy-core.c @@ -858,6 +858,36 @@ struct phy *devm_of_phy_get(struct device *dev, struct device_node *np, } EXPORT_SYMBOL_GPL(devm_of_phy_get); +/** + * devm_of_phy_optional_get() - lookup and obtain a reference to an optional + * phy. + * @dev: device that requests this phy + * @np: node containing the phy + * @con_id: name of the phy from device's point of view + * + * Gets the phy using of_phy_get(), and associates a device with it using + * devres. On driver detach, release function is invoked on the devres data, + * then, devres data is freed. This differs to devm_of_phy_get() in + * that if the phy does not exist, it is not considered an error and + * -ENODEV will not be returned. Instead the NULL phy is returned, + * which can be passed to all other phy consumer calls. + */ +struct phy *devm_of_phy_optional_get(struct device *dev, struct device_node *np, + const char *con_id) +{ + struct phy *phy = devm_of_phy_get(dev, np, con_id); + + if (PTR_ERR(phy) == -ENODEV) + phy = NULL; + + if (IS_ERR(phy)) + dev_err_probe(dev, PTR_ERR(phy), "failed to get PHY %pOF:%s", + np, con_id); + + return phy; +} +EXPORT_SYMBOL_GPL(devm_of_phy_optional_get); + /** * devm_of_phy_get_by_index() - lookup and obtain a reference to a phy by index. * @dev: device that requests this phy diff --git a/include/linux/phy/phy.h b/include/linux/phy/phy.h index 1b4f9be21e01..3a570bc59fc7 100644 --- a/include/linux/phy/phy.h +++ b/include/linux/phy/phy.h @@ -254,6 +254,8 @@ struct phy *devm_phy_get(struct device *dev, const char *string); struct phy *devm_phy_optional_get(struct device *dev, const char *string); struct phy *devm_of_phy_get(struct device *dev, struct device_node *np, const char *con_id); +struct phy *devm_of_phy_optional_get(struct device *dev, struct device_node *np, + const char *con_id); struct phy *devm_of_phy_get_by_index(struct device *dev, struct device_node *np, int index); void of_phy_put(struct phy *phy); @@ -443,6 +445,13 @@ static inline struct phy *devm_of_phy_get(struct device *dev, return ERR_PTR(-ENOSYS); } +static inline struct phy *devm_of_phy_optional_get(struct device *dev, + struct device_node *np, + const char *con_id) +{ + return NULL; +} + static inline struct phy *devm_of_phy_get_by_index(struct device *dev, struct device_node *np, int index) -- cgit v1.2.3 From f5b3c341a46ec55d93332ee5c254a278af902ffe Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 2 Feb 2023 16:54:12 +0200 Subject: mei: Move uuid_le_cmp() to its only user There is only a single user of uuid_le_cmp() API, let's make it private to that user. Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20230202145412.87569-1-andriy.shevchenko@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/misc/mei/mei_dev.h | 5 +++++ include/linux/uuid.h | 5 ----- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/misc/mei/mei_dev.h b/drivers/misc/mei/mei_dev.h index 996b70a988be..895011b7a0bf 100644 --- a/drivers/misc/mei/mei_dev.h +++ b/drivers/misc/mei/mei_dev.h @@ -13,6 +13,11 @@ #include #include +static inline int uuid_le_cmp(const uuid_le u1, const uuid_le u2) +{ + return memcmp(&u1, &u2, sizeof(uuid_le)); +} + #include "hw.h" #include "hbm.h" diff --git a/include/linux/uuid.h b/include/linux/uuid.h index 5be158a49e11..6b1a3efa1e0b 100644 --- a/include/linux/uuid.h +++ b/include/linux/uuid.h @@ -110,9 +110,4 @@ int uuid_parse(const char *uuid, uuid_t *u); /* MEI UUID type, don't use anywhere else */ #include -static inline int uuid_le_cmp(const uuid_le u1, const uuid_le u2) -{ - return memcmp(&u1, &u2, sizeof(uuid_le)); -} - #endif -- cgit v1.2.3 From fb6f026b833a71f4701e12b43800e46d7351f7a2 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Tue, 10 Jan 2023 19:03:53 +0000 Subject: mm/damon/core: update kernel-doc comments for DAMOS action supports of each DAMON operations set Patch series "mm/damon: trivial fixups". This patchset contains patches for trivial fixups of DAMON's documentation, MAINTAINERS section, and selftests. This patch (of 8): Supports of each DAMOS action are up to DAMON operations set implementation in use, but not well mentioned on the kernel-doc comments. Add the comment. Link: https://lkml.kernel.org/r/20230110190400.119388-1-sj@kernel.org Link: https://lkml.kernel.org/r/20230110190400.119388-2-sj@kernel.org Signed-off-by: SeongJae Park Cc: Jonathan Corbet Cc: Shuah Khan Signed-off-by: Andrew Morton --- include/linux/damon.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index 7907918ad2e0..3fa96d7c9fe4 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -91,6 +91,12 @@ struct damon_target { * @DAMOS_LRU_DEPRIO: Deprioritize the region on its LRU lists. * @DAMOS_STAT: Do nothing but count the stat. * @NR_DAMOS_ACTIONS: Total number of DAMOS actions + * + * The support of each action is up to running &struct damon_operations. + * &enum DAMON_OPS_VADDR and &enum DAMON_OPS_FVADDR supports all actions except + * &enum DAMOS_LRU_PRIO and &enum DAMOS_LRU_DEPRIO. &enum DAMON_OPS_PADDR + * supports only &enum DAMOS_PAGEOUT, &enum DAMOS_LRU_PRIO, &enum + * DAMOS_LRU_DEPRIO, and &DAMOS_STAT. */ enum damos_action { DAMOS_WILLNEED, -- cgit v1.2.3 From 55901e89d2864b5ef9961892470eedf29279d412 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Tue, 10 Jan 2023 19:03:54 +0000 Subject: mm/damon/core: update kernel-doc comments for DAMOS filters supports of each DAMON operations set Supports of each DAMOS filter type are up to DAMON operations set implementation in use, but not well mentioned on the kernel-doc comments. Add the comment. Link: https://lkml.kernel.org/r/20230110190400.119388-3-sj@kernel.org Signed-off-by: SeongJae Park Cc: Jonathan Corbet Cc: Shuah Khan Signed-off-by: Andrew Morton --- include/linux/damon.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index 3fa96d7c9fe4..dfb245bb3053 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -227,6 +227,11 @@ struct damos_stat { * @DAMOS_FILTER_TYPE_ANON: Anonymous pages. * @DAMOS_FILTER_TYPE_MEMCG: Specific memcg's pages. * @NR_DAMOS_FILTER_TYPES: Number of filter types. + * + * The support of each filter type is up to running &struct damon_operations. + * &enum DAMON_OPS_PADDR is supporting all filter types, while + * &enum DAMON_OPS_VADDR and &enum DAMON_OPS_FVADDR are not supporting any + * filter types. */ enum damos_filter_type { DAMOS_FILTER_TYPE_ANON, -- cgit v1.2.3 From c5d5546ea06512accc894cd19265c7041a6ac81a Mon Sep 17 00:00:00 2001 From: Vernon Yang Date: Tue, 10 Jan 2023 23:42:11 +0800 Subject: maple_tree: remove the parameter entry of mas_preallocate The parameter entry of mas_preallocate is not used, so drop it. Link: https://lkml.kernel.org/r/20230110154211.1758562-1-vernon2gm@gmail.com Signed-off-by: Vernon Yang Cc: Liam Howlett Cc: Matthew Wilcox Signed-off-by: Andrew Morton --- include/linux/maple_tree.h | 2 +- lib/maple_tree.c | 3 +-- mm/mmap.c | 16 ++++++++-------- mm/nommu.c | 8 ++++---- tools/testing/radix-tree/maple.c | 32 ++++++++++++++++---------------- 5 files changed, 30 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/include/linux/maple_tree.h b/include/linux/maple_tree.h index 815a27661517..a7bf58fd7cc6 100644 --- a/include/linux/maple_tree.h +++ b/include/linux/maple_tree.h @@ -455,7 +455,7 @@ int mas_store_gfp(struct ma_state *mas, void *entry, gfp_t gfp); void mas_store_prealloc(struct ma_state *mas, void *entry); void *mas_find(struct ma_state *mas, unsigned long max); void *mas_find_rev(struct ma_state *mas, unsigned long min); -int mas_preallocate(struct ma_state *mas, void *entry, gfp_t gfp); +int mas_preallocate(struct ma_state *mas, gfp_t gfp); bool mas_is_err(struct ma_state *mas); bool mas_nomem(struct ma_state *mas, gfp_t gfp); diff --git a/lib/maple_tree.c b/lib/maple_tree.c index baff62a012e1..5be99550e36d 100644 --- a/lib/maple_tree.c +++ b/lib/maple_tree.c @@ -5700,12 +5700,11 @@ EXPORT_SYMBOL_GPL(mas_store_prealloc); /** * mas_preallocate() - Preallocate enough nodes for a store operation * @mas: The maple state - * @entry: The entry that will be stored * @gfp: The GFP_FLAGS to use for allocations. * * Return: 0 on success, -ENOMEM if memory could not be allocated. */ -int mas_preallocate(struct ma_state *mas, void *entry, gfp_t gfp) +int mas_preallocate(struct ma_state *mas, gfp_t gfp) { int ret; diff --git a/mm/mmap.c b/mm/mmap.c index 425a9349e610..4fe29b8f99b0 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -472,7 +472,7 @@ static int vma_link(struct mm_struct *mm, struct vm_area_struct *vma) MA_STATE(mas, &mm->mm_mt, 0, 0); struct address_space *mapping = NULL; - if (mas_preallocate(&mas, vma, GFP_KERNEL)) + if (mas_preallocate(&mas, GFP_KERNEL)) return -ENOMEM; if (vma->vm_file) { @@ -538,7 +538,7 @@ inline int vma_expand(struct ma_state *mas, struct vm_area_struct *vma, /* Only handles expanding */ VM_BUG_ON(vma->vm_start < start || vma->vm_end > end); - if (mas_preallocate(mas, vma, GFP_KERNEL)) + if (mas_preallocate(mas, GFP_KERNEL)) goto nomem; vma_adjust_trans_huge(vma, start, end, 0); @@ -712,7 +712,7 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start, } } - if (mas_preallocate(&mas, vma, GFP_KERNEL)) + if (mas_preallocate(&mas, GFP_KERNEL)) return -ENOMEM; vma_adjust_trans_huge(orig_vma, start, end, adjust_next); @@ -1938,7 +1938,7 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address) /* Check that both stack segments have the same anon_vma? */ } - if (mas_preallocate(&mas, vma, GFP_KERNEL)) + if (mas_preallocate(&mas, GFP_KERNEL)) return -ENOMEM; /* We must make sure the anon_vma is allocated. */ @@ -2019,7 +2019,7 @@ int expand_downwards(struct vm_area_struct *vma, unsigned long address) return -ENOMEM; } - if (mas_preallocate(&mas, vma, GFP_KERNEL)) + if (mas_preallocate(&mas, GFP_KERNEL)) return -ENOMEM; /* We must make sure the anon_vma is allocated. */ @@ -2311,7 +2311,7 @@ do_mas_align_munmap(struct ma_state *mas, struct vm_area_struct *vma, mt_init_flags(&mt_detach, MT_FLAGS_LOCK_EXTERN); mt_set_external_lock(&mt_detach, &mm->mmap_lock); - if (mas_preallocate(mas, vma, GFP_KERNEL)) + if (mas_preallocate(mas, GFP_KERNEL)) return -ENOMEM; mas->last = end - 1; @@ -2680,7 +2680,7 @@ cannot_expand: goto free_vma; } - if (mas_preallocate(&mas, vma, GFP_KERNEL)) { + if (mas_preallocate(&mas, GFP_KERNEL)) { error = -ENOMEM; if (file) goto close_and_free_vma; @@ -2953,7 +2953,7 @@ static int do_brk_flags(struct ma_state *mas, struct vm_area_struct *vma, can_vma_merge_after(vma, flags, NULL, NULL, addr >> PAGE_SHIFT, NULL_VM_UFFD_CTX, NULL)) { mas_set_range(mas, vma->vm_start, addr + len - 1); - if (mas_preallocate(mas, vma, GFP_KERNEL)) + if (mas_preallocate(mas, GFP_KERNEL)) goto unacct_fail; vma_adjust_trans_huge(vma, vma->vm_start, addr + len, 0); diff --git a/mm/nommu.c b/mm/nommu.c index df1711acdf5b..0481922fe66e 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -602,7 +602,7 @@ static int add_vma_to_mm(struct mm_struct *mm, struct vm_area_struct *vma) { MA_STATE(mas, &mm->mm_mt, vma->vm_start, vma->vm_end); - if (mas_preallocate(&mas, vma, GFP_KERNEL)) { + if (mas_preallocate(&mas, GFP_KERNEL)) { pr_warn("Allocation of vma tree for process %d failed\n", current->pid); return -ENOMEM; @@ -633,7 +633,7 @@ static int delete_vma_from_mm(struct vm_area_struct *vma) { MA_STATE(mas, &vma->vm_mm->mm_mt, 0, 0); - if (mas_preallocate(&mas, vma, GFP_KERNEL)) { + if (mas_preallocate(&mas, GFP_KERNEL)) { pr_warn("Allocation of vma tree for process %d failed\n", current->pid); return -ENOMEM; @@ -1091,7 +1091,7 @@ unsigned long do_mmap(struct file *file, if (!vma) goto error_getting_vma; - if (mas_preallocate(&mas, vma, GFP_KERNEL)) + if (mas_preallocate(&mas, GFP_KERNEL)) goto error_maple_preallocate; region->vm_usage = 1; @@ -1369,7 +1369,7 @@ int split_vma(struct mm_struct *mm, struct vm_area_struct *vma, if (!new) goto err_vma_dup; - if (mas_preallocate(&mas, vma, GFP_KERNEL)) { + if (mas_preallocate(&mas, GFP_KERNEL)) { pr_warn("Allocation of vma tree for process %d failed\n", current->pid); goto err_mas_preallocate; diff --git a/tools/testing/radix-tree/maple.c b/tools/testing/radix-tree/maple.c index 1f36bc1c5d36..958ee9bdb316 100644 --- a/tools/testing/radix-tree/maple.c +++ b/tools/testing/radix-tree/maple.c @@ -35342,7 +35342,7 @@ static noinline void check_prealloc(struct maple_tree *mt) for (i = 0; i <= max; i++) mtree_test_store_range(mt, i * 10, i * 10 + 5, &i); - MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); + MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); allocated = mas_allocated(&mas); height = mas_mt_height(&mas); MT_BUG_ON(mt, allocated == 0); @@ -35351,18 +35351,18 @@ static noinline void check_prealloc(struct maple_tree *mt) allocated = mas_allocated(&mas); MT_BUG_ON(mt, allocated != 0); - MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); + MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); allocated = mas_allocated(&mas); height = mas_mt_height(&mas); MT_BUG_ON(mt, allocated == 0); MT_BUG_ON(mt, allocated != 1 + height * 3); - MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); + MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); mas_destroy(&mas); allocated = mas_allocated(&mas); MT_BUG_ON(mt, allocated != 0); - MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); + MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); allocated = mas_allocated(&mas); height = mas_mt_height(&mas); MT_BUG_ON(mt, allocated == 0); @@ -35370,25 +35370,25 @@ static noinline void check_prealloc(struct maple_tree *mt) mn = mas_pop_node(&mas); MT_BUG_ON(mt, mas_allocated(&mas) != allocated - 1); ma_free_rcu(mn); - MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); + MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); mas_destroy(&mas); allocated = mas_allocated(&mas); MT_BUG_ON(mt, allocated != 0); - MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); + MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); allocated = mas_allocated(&mas); height = mas_mt_height(&mas); MT_BUG_ON(mt, allocated == 0); MT_BUG_ON(mt, allocated != 1 + height * 3); mn = mas_pop_node(&mas); MT_BUG_ON(mt, mas_allocated(&mas) != allocated - 1); - MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); + MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); mas_destroy(&mas); allocated = mas_allocated(&mas); MT_BUG_ON(mt, allocated != 0); ma_free_rcu(mn); - MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); + MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); allocated = mas_allocated(&mas); height = mas_mt_height(&mas); MT_BUG_ON(mt, allocated == 0); @@ -35397,12 +35397,12 @@ static noinline void check_prealloc(struct maple_tree *mt) MT_BUG_ON(mt, mas_allocated(&mas) != allocated - 1); mas_push_node(&mas, mn); MT_BUG_ON(mt, mas_allocated(&mas) != allocated); - MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); + MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); mas_destroy(&mas); allocated = mas_allocated(&mas); MT_BUG_ON(mt, allocated != 0); - MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); + MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); allocated = mas_allocated(&mas); height = mas_mt_height(&mas); MT_BUG_ON(mt, allocated == 0); @@ -35410,21 +35410,21 @@ static noinline void check_prealloc(struct maple_tree *mt) mas_store_prealloc(&mas, ptr); MT_BUG_ON(mt, mas_allocated(&mas) != 0); - MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); + MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); allocated = mas_allocated(&mas); height = mas_mt_height(&mas); MT_BUG_ON(mt, allocated == 0); MT_BUG_ON(mt, allocated != 1 + height * 3); mas_store_prealloc(&mas, ptr); MT_BUG_ON(mt, mas_allocated(&mas) != 0); - MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); + MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); allocated = mas_allocated(&mas); height = mas_mt_height(&mas); MT_BUG_ON(mt, allocated == 0); MT_BUG_ON(mt, allocated != 1 + height * 3); mas_store_prealloc(&mas, ptr); - MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); + MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); allocated = mas_allocated(&mas); height = mas_mt_height(&mas); MT_BUG_ON(mt, allocated == 0); @@ -35432,14 +35432,14 @@ static noinline void check_prealloc(struct maple_tree *mt) mas_store_prealloc(&mas, ptr); MT_BUG_ON(mt, mas_allocated(&mas) != 0); mt_set_non_kernel(1); - MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL & GFP_NOWAIT) == 0); + MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL & GFP_NOWAIT) == 0); allocated = mas_allocated(&mas); height = mas_mt_height(&mas); MT_BUG_ON(mt, allocated != 0); mas_destroy(&mas); - MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); + MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); allocated = mas_allocated(&mas); height = mas_mt_height(&mas); MT_BUG_ON(mt, allocated == 0); @@ -35447,7 +35447,7 @@ static noinline void check_prealloc(struct maple_tree *mt) mas_store_prealloc(&mas, ptr); MT_BUG_ON(mt, mas_allocated(&mas) != 0); mt_set_non_kernel(1); - MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL & GFP_NOWAIT) == 0); + MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL & GFP_NOWAIT) == 0); allocated = mas_allocated(&mas); height = mas_mt_height(&mas); MT_BUG_ON(mt, allocated != 0); -- cgit v1.2.3 From 7d4a8be0c4b2b7ffb367929d2b352651f083806b Mon Sep 17 00:00:00 2001 From: Alistair Popple Date: Tue, 10 Jan 2023 13:57:22 +1100 Subject: mm/mmu_notifier: remove unused mmu_notifier_range_update_to_read_only export mmu_notifier_range_update_to_read_only() was originally introduced in commit c6d23413f81b ("mm/mmu_notifier: mmu_notifier_range_update_to_read_only() helper") as an optimisation for device drivers that know a range has only been mapped read-only. However there are no users of this feature so remove it. As it is the only user of the struct mmu_notifier_range.vma field remove that also. Link: https://lkml.kernel.org/r/20230110025722.600912-1-apopple@nvidia.com Signed-off-by: Alistair Popple Acked-by: Mike Rapoport (IBM) Reviewed-by: Jason Gunthorpe Reviewed-by: Christoph Hellwig Reviewed-by: Mike Kravetz Cc: Ira Weiny Cc: Jerome Glisse Cc: John Hubbard Cc: Ralph Campbell Signed-off-by: Andrew Morton --- fs/proc/task_mmu.c | 2 +- include/linux/mmu_notifier.h | 13 +++++-------- kernel/events/uprobes.c | 2 +- mm/huge_memory.c | 4 ++-- mm/hugetlb.c | 12 ++++++------ mm/khugepaged.c | 6 +++--- mm/ksm.c | 5 ++--- mm/madvise.c | 2 +- mm/mapping_dirty_helpers.c | 2 +- mm/memory.c | 10 +++++----- mm/migrate_device.c | 4 ++-- mm/mmu_notifier.c | 10 ---------- mm/mprotect.c | 2 +- mm/mremap.c | 2 +- mm/oom_kill.c | 2 +- mm/rmap.c | 11 +++++------ 16 files changed, 37 insertions(+), 52 deletions(-) (limited to 'include/linux') diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index af1c49ae11b1..a44339a77a75 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1306,7 +1306,7 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, inc_tlb_flush_pending(mm); mmu_notifier_range_init(&range, MMU_NOTIFY_SOFT_DIRTY, - 0, NULL, mm, 0, -1UL); + 0, mm, 0, -1UL); mmu_notifier_invalidate_range_start(&range); } walk_page_range(mm, 0, -1, &clear_refs_walk_ops, &cp); diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index d6c06e140277..64a3e051c3c4 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -269,7 +269,6 @@ extern struct lockdep_map __mmu_notifier_invalidate_range_start_map; #endif struct mmu_notifier_range { - struct vm_area_struct *vma; struct mm_struct *mm; unsigned long start; unsigned long end; @@ -514,12 +513,10 @@ static inline void mmu_notifier_subscriptions_destroy(struct mm_struct *mm) static inline void mmu_notifier_range_init(struct mmu_notifier_range *range, enum mmu_notifier_event event, unsigned flags, - struct vm_area_struct *vma, struct mm_struct *mm, unsigned long start, unsigned long end) { - range->vma = vma; range->event = event; range->mm = mm; range->start = start; @@ -530,10 +527,10 @@ static inline void mmu_notifier_range_init(struct mmu_notifier_range *range, static inline void mmu_notifier_range_init_owner( struct mmu_notifier_range *range, enum mmu_notifier_event event, unsigned int flags, - struct vm_area_struct *vma, struct mm_struct *mm, - unsigned long start, unsigned long end, void *owner) + struct mm_struct *mm, unsigned long start, + unsigned long end, void *owner) { - mmu_notifier_range_init(range, event, flags, vma, mm, start, end); + mmu_notifier_range_init(range, event, flags, mm, start, end); range->owner = owner; } @@ -659,9 +656,9 @@ static inline void _mmu_notifier_range_init(struct mmu_notifier_range *range, range->end = end; } -#define mmu_notifier_range_init(range,event,flags,vma,mm,start,end) \ +#define mmu_notifier_range_init(range,event,flags,mm,start,end) \ _mmu_notifier_range_init(range, start, end) -#define mmu_notifier_range_init_owner(range, event, flags, vma, mm, start, \ +#define mmu_notifier_range_init_owner(range, event, flags, mm, start, \ end, owner) \ _mmu_notifier_range_init(range, start, end) diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index d9e357b7e17c..29f36d2ae129 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -161,7 +161,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, int err; struct mmu_notifier_range range; - mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, mm, addr, + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, addr, addr + PAGE_SIZE); if (new_page) { diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 7e68a36b4f7d..c13b1f67d14e 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2020,7 +2020,7 @@ void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud, spinlock_t *ptl; struct mmu_notifier_range range; - mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm, + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm, address & HPAGE_PUD_MASK, (address & HPAGE_PUD_MASK) + HPAGE_PUD_SIZE); mmu_notifier_invalidate_range_start(&range); @@ -2282,7 +2282,7 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, spinlock_t *ptl; struct mmu_notifier_range range; - mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm, + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm, address & HPAGE_PMD_MASK, (address & HPAGE_PMD_MASK) + HPAGE_PMD_SIZE); mmu_notifier_invalidate_range_start(&range); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 6fe65f14d33b..273a6522aa4c 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4966,7 +4966,7 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, int ret = 0; if (cow) { - mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, src_vma, src, + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, src, src_vma->vm_start, src_vma->vm_end); mmu_notifier_invalidate_range_start(&range); @@ -5177,7 +5177,7 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma, struct mmu_notifier_range range; bool shared_pmd = false; - mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, mm, old_addr, + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, old_addr, old_end); adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); /* @@ -5391,7 +5391,7 @@ void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, struct mmu_notifier_range range; struct mmu_gather tlb; - mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm, + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm, start, end); adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); mmu_notifier_invalidate_range_start(&range); @@ -5597,7 +5597,7 @@ retry_avoidcopy: pages_per_huge_page(h)); __SetPageUptodate(new_page); - mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, mm, haddr, + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, haddr, haddr + huge_page_size(h)); mmu_notifier_invalidate_range_start(&range); @@ -6637,7 +6637,7 @@ long hugetlb_change_protection(struct vm_area_struct *vma, * range if PMD sharing is possible. */ mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_VMA, - 0, vma, mm, start, end); + 0, mm, start, end); adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); BUG_ON(address >= end); @@ -7368,7 +7368,7 @@ static void hugetlb_unshare_pmds(struct vm_area_struct *vma, * No need to call adjust_range_if_pmd_sharing_possible(), because * we have already done the PUD_SIZE alignment. */ - mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, mm, + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, start, end); mmu_notifier_invalidate_range_start(&range); hugetlb_vma_lock_write(vma); diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 90acfea40c13..57164c15e076 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1040,8 +1040,8 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address, anon_vma_lock_write(vma->anon_vma); - mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, NULL, mm, - address, address + HPAGE_PMD_SIZE); + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, address, + address + HPAGE_PMD_SIZE); mmu_notifier_invalidate_range_start(&range); pte = pte_offset_map(pmd, address); @@ -1412,7 +1412,7 @@ static void collapse_and_free_pmd(struct mm_struct *mm, struct vm_area_struct *v if (vma->anon_vma) lockdep_assert_held_write(&vma->anon_vma->root->rwsem); - mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, NULL, mm, addr, + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, addr, addr + HPAGE_PMD_SIZE); mmu_notifier_invalidate_range_start(&range); pmd = pmdp_collapse_flush(vma, addr, pmdp); diff --git a/mm/ksm.c b/mm/ksm.c index dd02780c387f..cea0c4478220 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -1057,8 +1057,7 @@ static int write_protect_page(struct vm_area_struct *vma, struct page *page, BUG_ON(PageTransCompound(page)); - mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, mm, - pvmw.address, + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, pvmw.address, pvmw.address + PAGE_SIZE); mmu_notifier_invalidate_range_start(&range); @@ -1164,7 +1163,7 @@ static int replace_page(struct vm_area_struct *vma, struct page *page, if (!pmd_present(pmde) || pmd_trans_huge(pmde)) goto out; - mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, mm, addr, + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, addr, addr + PAGE_SIZE); mmu_notifier_invalidate_range_start(&range); diff --git a/mm/madvise.c b/mm/madvise.c index e407d335e614..5296e78dccda 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -765,7 +765,7 @@ static int madvise_free_single_vma(struct vm_area_struct *vma, range.end = min(vma->vm_end, end_addr); if (range.end <= vma->vm_start) return -EINVAL; - mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, mm, + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, range.start, range.end); lru_add_drain(); diff --git a/mm/mapping_dirty_helpers.c b/mm/mapping_dirty_helpers.c index 175e424b9ab1..e1eb33f49059 100644 --- a/mm/mapping_dirty_helpers.c +++ b/mm/mapping_dirty_helpers.c @@ -191,7 +191,7 @@ static int wp_clean_pre_vma(unsigned long start, unsigned long end, wpwalk->tlbflush_end = start; mmu_notifier_range_init(&wpwalk->range, MMU_NOTIFY_PROTECTION_PAGE, 0, - walk->vma, walk->mm, start, end); + walk->mm, start, end); mmu_notifier_invalidate_range_start(&wpwalk->range); flush_cache_range(walk->vma, start, end); diff --git a/mm/memory.c b/mm/memory.c index 90f8f72777c7..c6bacd58d032 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1266,7 +1266,7 @@ copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) if (is_cow) { mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE, - 0, src_vma, src_mm, addr, end); + 0, src_mm, addr, end); mmu_notifier_invalidate_range_start(&range); /* * Disabling preemption is not needed for the write side, as @@ -1683,7 +1683,7 @@ void unmap_vmas(struct mmu_gather *tlb, struct maple_tree *mt, }; MA_STATE(mas, mt, vma->vm_end, vma->vm_end); - mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma, vma->vm_mm, + mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma->vm_mm, start_addr, end_addr); mmu_notifier_invalidate_range_start(&range); do { @@ -1709,7 +1709,7 @@ void zap_page_range_single(struct vm_area_struct *vma, unsigned long address, struct mmu_gather tlb; lru_add_drain(); - mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm, + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm, address, end); if (is_vm_hugetlb_page(vma)) adjust_range_if_pmd_sharing_possible(vma, &range.start, @@ -3091,7 +3091,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) __SetPageUptodate(new_page); - mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, mm, + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, vmf->address & PAGE_MASK, (vmf->address & PAGE_MASK) + PAGE_SIZE); mmu_notifier_invalidate_range_start(&range); @@ -3561,7 +3561,7 @@ static vm_fault_t remove_device_exclusive_entry(struct vm_fault *vmf) if (!folio_lock_or_retry(folio, vma->vm_mm, vmf->flags)) return VM_FAULT_RETRY; - mmu_notifier_range_init_owner(&range, MMU_NOTIFY_EXCLUSIVE, 0, vma, + mmu_notifier_range_init_owner(&range, MMU_NOTIFY_EXCLUSIVE, 0, vma->vm_mm, vmf->address & PAGE_MASK, (vmf->address & PAGE_MASK) + PAGE_SIZE, NULL); mmu_notifier_invalidate_range_start(&range); diff --git a/mm/migrate_device.c b/mm/migrate_device.c index 721b2365dbca..6c3740318a98 100644 --- a/mm/migrate_device.c +++ b/mm/migrate_device.c @@ -306,7 +306,7 @@ static void migrate_vma_collect(struct migrate_vma *migrate) * private page mappings that won't be migrated. */ mmu_notifier_range_init_owner(&range, MMU_NOTIFY_MIGRATE, 0, - migrate->vma, migrate->vma->vm_mm, migrate->start, migrate->end, + migrate->vma->vm_mm, migrate->start, migrate->end, migrate->pgmap_owner); mmu_notifier_invalidate_range_start(&range); @@ -733,7 +733,7 @@ static void __migrate_device_pages(unsigned long *src_pfns, notified = true; mmu_notifier_range_init_owner(&range, - MMU_NOTIFY_MIGRATE, 0, migrate->vma, + MMU_NOTIFY_MIGRATE, 0, migrate->vma->vm_mm, addr, migrate->end, migrate->pgmap_owner); mmu_notifier_invalidate_range_start(&range); diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c index f45ff1b7626a..50c0dde1354f 100644 --- a/mm/mmu_notifier.c +++ b/mm/mmu_notifier.c @@ -1120,13 +1120,3 @@ void mmu_notifier_synchronize(void) synchronize_srcu(&srcu); } EXPORT_SYMBOL_GPL(mmu_notifier_synchronize); - -bool -mmu_notifier_range_update_to_read_only(const struct mmu_notifier_range *range) -{ - if (!range->vma || range->event != MMU_NOTIFY_PROTECTION_VMA) - return false; - /* Return true if the vma still have the read flag set. */ - return range->vma->vm_flags & VM_READ; -} -EXPORT_SYMBOL_GPL(mmu_notifier_range_update_to_read_only); diff --git a/mm/mprotect.c b/mm/mprotect.c index 92fc6f3fa512..6ecdf0671b81 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -398,7 +398,7 @@ static inline long change_pmd_range(struct mmu_gather *tlb, if (!range.start) { mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_VMA, 0, - vma, vma->vm_mm, addr, end); + vma->vm_mm, addr, end); mmu_notifier_invalidate_range_start(&range); } diff --git a/mm/mremap.c b/mm/mremap.c index 930f65c315c0..05f90f47e149 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -498,7 +498,7 @@ unsigned long move_page_tables(struct vm_area_struct *vma, new_addr, len); flush_cache_range(vma, old_addr, old_end); - mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma, vma->vm_mm, + mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma->vm_mm, old_addr, old_end); mmu_notifier_invalidate_range_start(&range); diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 1276e49b31b0..044e1eed720e 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -542,7 +542,7 @@ static bool __oom_reap_task_mm(struct mm_struct *mm) struct mmu_gather tlb; mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, - vma, mm, vma->vm_start, + mm, vma->vm_start, vma->vm_end); tlb_gather_mmu(&tlb, mm); if (mmu_notifier_invalidate_range_start_nonblock(&range)) { diff --git a/mm/rmap.c b/mm/rmap.c index ab74e0547a52..6ccd42bbae93 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -944,9 +944,8 @@ static int page_vma_mkclean_one(struct page_vma_mapped_walk *pvmw) * We have to assume the worse case ie pmd for invalidation. Note that * the folio can not be freed from this function. */ - mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE, - 0, vma, vma->vm_mm, address, - vma_address_end(pvmw)); + mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE, 0, + vma->vm_mm, address, vma_address_end(pvmw)); mmu_notifier_invalidate_range_start(&range); while (page_vma_mapped_walk(pvmw)) { @@ -1475,7 +1474,7 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, * try_to_unmap() must hold a reference on the folio. */ range.end = vma_address_end(&pvmw); - mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm, + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm, address, range.end); if (folio_test_hugetlb(folio)) { /* @@ -1850,7 +1849,7 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, * try_to_unmap() must hold a reference on the page. */ range.end = vma_address_end(&pvmw); - mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm, + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm, address, range.end); if (folio_test_hugetlb(folio)) { /* @@ -2180,7 +2179,7 @@ static bool page_make_device_exclusive_one(struct folio *folio, swp_entry_t entry; pte_t swp_pte; - mmu_notifier_range_init_owner(&range, MMU_NOTIFY_EXCLUSIVE, 0, vma, + mmu_notifier_range_init_owner(&range, MMU_NOTIFY_EXCLUSIVE, 0, vma->vm_mm, address, min(vma->vm_end, address + folio_size(folio)), args->owner); -- cgit v1.2.3 From 94688e8eb453e616098cb930e5f6fed4a6ea2dfa Mon Sep 17 00:00:00 2001 From: Matthew Wilcox (Oracle) Date: Wed, 11 Jan 2023 14:28:47 +0000 Subject: mm: remove folio_pincount_ptr() and head_compound_pincount() We can use folio->_pincount directly, since all users are guarded by tests of compound/large. Link: https://lkml.kernel.org/r/20230111142915.1001531-2-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: John Hubbard Signed-off-by: Andrew Morton --- Documentation/core-api/pin_user_pages.rst | 29 ++++++++++++++--------------- include/linux/mm.h | 14 ++------------ include/linux/mm_types.h | 5 ----- mm/debug.c | 4 ++-- mm/gup.c | 8 ++++---- mm/huge_memory.c | 4 ++-- mm/hugetlb.c | 4 ++-- mm/page_alloc.c | 9 ++++++--- 8 files changed, 32 insertions(+), 45 deletions(-) (limited to 'include/linux') diff --git a/Documentation/core-api/pin_user_pages.rst b/Documentation/core-api/pin_user_pages.rst index facafbdecb95..9fb0b1080d3b 100644 --- a/Documentation/core-api/pin_user_pages.rst +++ b/Documentation/core-api/pin_user_pages.rst @@ -55,18 +55,17 @@ flags the caller provides. The caller is required to pass in a non-null struct pages* array, and the function then pins pages by incrementing each by a special value: GUP_PIN_COUNTING_BIAS. -For compound pages, the GUP_PIN_COUNTING_BIAS scheme is not used. Instead, -an exact form of pin counting is achieved, by using the 2nd struct page -in the compound page. A new struct page field, compound_pincount, has -been added in order to support this. - -This approach for compound pages avoids the counting upper limit problems that -are discussed below. Those limitations would have been aggravated severely by -huge pages, because each tail page adds a refcount to the head page. And in -fact, testing revealed that, without a separate compound_pincount field, -page overflows were seen in some huge page stress tests. - -This also means that huge pages and compound pages do not suffer +For large folios, the GUP_PIN_COUNTING_BIAS scheme is not used. Instead, +the extra space available in the struct folio is used to store the +pincount directly. + +This approach for large folios avoids the counting upper limit problems +that are discussed below. Those limitations would have been aggravated +severely by huge pages, because each tail page adds a refcount to the +head page. And in fact, testing revealed that, without a separate pincount +field, refcount overflows were seen in some huge page stress tests. + +This also means that huge pages and large folios do not suffer from the false positives problem that is mentioned below.:: Function @@ -264,9 +263,9 @@ place.) Other diagnostics ================= -dump_page() has been enhanced slightly, to handle these new counting -fields, and to better report on compound pages in general. Specifically, -for compound pages, the exact (compound_pincount) pincount is reported. +dump_page() has been enhanced slightly to handle these new counting +fields, and to better report on large folios in general. Specifically, +for large folios, the exact pincount is reported. References ========== diff --git a/include/linux/mm.h b/include/linux/mm.h index 76c97cb8ee9a..6d3945207067 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1011,11 +1011,6 @@ static inline void folio_set_compound_dtor(struct folio *folio, void destroy_large_folio(struct folio *folio); -static inline int head_compound_pincount(struct page *head) -{ - return atomic_read(compound_pincount_ptr(head)); -} - static inline void set_compound_order(struct page *page, unsigned int order) { page[1].compound_order = order; @@ -1641,11 +1636,6 @@ static inline struct folio *pfn_folio(unsigned long pfn) return page_folio(pfn_to_page(pfn)); } -static inline atomic_t *folio_pincount_ptr(struct folio *folio) -{ - return &folio_page(folio, 1)->compound_pincount; -} - /** * folio_maybe_dma_pinned - Report if a folio may be pinned for DMA. * @folio: The folio. @@ -1663,7 +1653,7 @@ static inline atomic_t *folio_pincount_ptr(struct folio *folio) * expected to be able to deal gracefully with a false positive. * * For large folios, the result will be exactly correct. That's because - * we have more tracking data available: the compound_pincount is used + * we have more tracking data available: the _pincount field is used * instead of the GUP_PIN_COUNTING_BIAS scheme. * * For more information, please see Documentation/core-api/pin_user_pages.rst. @@ -1674,7 +1664,7 @@ static inline atomic_t *folio_pincount_ptr(struct folio *folio) static inline bool folio_maybe_dma_pinned(struct folio *folio) { if (folio_test_large(folio)) - return atomic_read(folio_pincount_ptr(folio)) > 0; + return atomic_read(&folio->_pincount) > 0; /* * folio_ref_count() is signed. If that refcount overflows, then diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 10b6eb311ede..6ff1d7db00a7 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -443,11 +443,6 @@ static inline atomic_t *subpages_mapcount_ptr(struct page *page) return &page[1].subpages_mapcount; } -static inline atomic_t *compound_pincount_ptr(struct page *page) -{ - return &page[1].compound_pincount; -} - /* * Used for sizing the vmemmap region on some architectures */ diff --git a/mm/debug.c b/mm/debug.c index 7f8e5f744e42..893c9dbf76ca 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -94,11 +94,11 @@ static void __dump_page(struct page *page) page, page_ref_count(head), mapcount, mapping, page_to_pgoff(page), page_to_pfn(page)); if (compound) { - pr_warn("head:%p order:%u compound_mapcount:%d subpages_mapcount:%d compound_pincount:%d\n", + pr_warn("head:%p order:%u compound_mapcount:%d subpages_mapcount:%d pincount:%d\n", head, compound_order(head), head_compound_mapcount(head), head_subpages_mapcount(head), - head_compound_pincount(head)); + atomic_read(&folio->_pincount)); } #ifdef CONFIG_MEMCG diff --git a/mm/gup.c b/mm/gup.c index f45a3a5be53a..38ba1697dd61 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -111,7 +111,7 @@ retry: * FOLL_GET: folio's refcount will be incremented by @refs. * * FOLL_PIN on large folios: folio's refcount will be incremented by - * @refs, and its compound_pincount will be incremented by @refs. + * @refs, and its pincount will be incremented by @refs. * * FOLL_PIN on single-page folios: folio's refcount will be incremented by * @refs * GUP_PIN_COUNTING_BIAS. @@ -157,7 +157,7 @@ struct folio *try_grab_folio(struct page *page, int refs, unsigned int flags) * try_get_folio() is left intact. */ if (folio_test_large(folio)) - atomic_add(refs, folio_pincount_ptr(folio)); + atomic_add(refs, &folio->_pincount); else folio_ref_add(folio, refs * (GUP_PIN_COUNTING_BIAS - 1)); @@ -182,7 +182,7 @@ static void gup_put_folio(struct folio *folio, int refs, unsigned int flags) if (flags & FOLL_PIN) { node_stat_mod_folio(folio, NR_FOLL_PIN_RELEASED, refs); if (folio_test_large(folio)) - atomic_sub(refs, folio_pincount_ptr(folio)); + atomic_sub(refs, &folio->_pincount); else refs *= GUP_PIN_COUNTING_BIAS; } @@ -232,7 +232,7 @@ int __must_check try_grab_page(struct page *page, unsigned int flags) */ if (folio_test_large(folio)) { folio_ref_add(folio, 1); - atomic_add(1, folio_pincount_ptr(folio)); + atomic_add(1, &folio->_pincount); } else { folio_ref_add(folio, GUP_PIN_COUNTING_BIAS); } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index c13b1f67d14e..9570f03cdee4 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2477,9 +2477,9 @@ static void __split_huge_page_tail(struct page *head, int tail, * of swap cache pages that store the swp_entry_t in tail pages. * Fix up and warn once if private is unexpectedly set. * - * What of 32-bit systems, on which head[1].compound_pincount overlays + * What of 32-bit systems, on which folio->_pincount overlays * head[1].private? No problem: THP_SWAP is not enabled on 32-bit, and - * compound_pincount must be 0 for folio_ref_freeze() to have succeeded. + * pincount must be 0 for folio_ref_freeze() to have succeeded. */ if (!folio_test_swapcache(page_folio(head))) { VM_WARN_ON_ONCE_PAGE(page_tail->private != 0, page_tail); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 273a6522aa4c..15b2707c1600 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1476,7 +1476,7 @@ static void __destroy_compound_gigantic_folio(struct folio *folio, atomic_set(folio_mapcount_ptr(folio), 0); atomic_set(folio_subpages_mapcount_ptr(folio), 0); - atomic_set(folio_pincount_ptr(folio), 0); + atomic_set(&folio->_pincount, 0); for (i = 1; i < nr_pages; i++) { p = folio_page(folio, i); @@ -1998,7 +1998,7 @@ static bool __prep_compound_gigantic_folio(struct folio *folio, } atomic_set(folio_mapcount_ptr(folio), -1); atomic_set(folio_subpages_mapcount_ptr(folio), 0); - atomic_set(folio_pincount_ptr(folio), 0); + atomic_set(&folio->_pincount, 0); return true; out_error: diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 5514d84cc712..b224c2132ed1 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -775,11 +775,13 @@ void free_compound_page(struct page *page) static void prep_compound_head(struct page *page, unsigned int order) { + struct folio *folio = (struct folio *)page; + set_compound_page_dtor(page, COMPOUND_PAGE_DTOR); set_compound_order(page, order); atomic_set(compound_mapcount_ptr(page), -1); atomic_set(subpages_mapcount_ptr(page), 0); - atomic_set(compound_pincount_ptr(page), 0); + atomic_set(&folio->_pincount, 0); } static void prep_compound_tail(struct page *head, int tail_idx) @@ -1291,6 +1293,7 @@ static inline bool free_page_is_bad(struct page *page) static int free_tail_pages_check(struct page *head_page, struct page *page) { + struct folio *folio = (struct folio *)head_page; int ret = 1; /* @@ -1314,8 +1317,8 @@ static int free_tail_pages_check(struct page *head_page, struct page *page) bad_page(page, "nonzero subpages_mapcount"); goto out; } - if (unlikely(head_compound_pincount(head_page))) { - bad_page(page, "nonzero compound_pincount"); + if (unlikely(atomic_read(&folio->_pincount))) { + bad_page(page, "nonzero pincount"); goto out; } break; -- cgit v1.2.3 From eec20426d48bd7b63c69969a793943ed1a99b731 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox (Oracle) Date: Wed, 11 Jan 2023 14:28:48 +0000 Subject: mm: convert head_subpages_mapcount() into folio_nr_pages_mapped() Calling this 'mapcount' is confusing since mapcount is usually the number of times something is mapped; instead this is the number of mapped pages. It's also better to enforce that this is a folio rather than a head page. Move folio_nr_pages_mapped() into mm/internal.h since this is not something we want device drivers or filesystems poking at. Get rid of folio_subpages_mapcount_ptr() and use folio->_nr_pages_mapped directly. Link: https://lkml.kernel.org/r/20230111142915.1001531-3-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- include/linux/mm.h | 22 ++-------------------- include/linux/mm_types.h | 12 +++--------- mm/debug.c | 4 ++-- mm/hugetlb.c | 4 ++-- mm/internal.h | 18 ++++++++++++++++++ mm/rmap.c | 9 +++++---- 6 files changed, 32 insertions(+), 37 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 6d3945207067..2bdd08a5b8b4 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -843,24 +843,6 @@ static inline int head_compound_mapcount(struct page *head) return atomic_read(compound_mapcount_ptr(head)) + 1; } -/* - * If a 16GB hugetlb page were mapped by PTEs of all of its 4kB sub-pages, - * its subpages_mapcount would be 0x400000: choose the COMPOUND_MAPPED bit - * above that range, instead of 2*(PMD_SIZE/PAGE_SIZE). Hugetlb currently - * leaves subpages_mapcount at 0, but avoid surprise if it participates later. - */ -#define COMPOUND_MAPPED 0x800000 -#define SUBPAGES_MAPPED (COMPOUND_MAPPED - 1) - -/* - * Number of sub-pages mapped by PTE, does not include compound mapcount. - * Must be called only on head of compound page. - */ -static inline int head_subpages_mapcount(struct page *head) -{ - return atomic_read(subpages_mapcount_ptr(head)) & SUBPAGES_MAPPED; -} - /* * The atomic page->_mapcount, starts from -1: so that transitions * both from it and to it can be tracked, using atomic_inc_and_test @@ -920,9 +902,9 @@ static inline bool folio_large_is_mapped(struct folio *folio) { /* * Reading folio_mapcount_ptr() below could be omitted if hugetlb - * participated in incrementing subpages_mapcount when compound mapped. + * participated in incrementing nr_pages_mapped when compound mapped. */ - return atomic_read(folio_subpages_mapcount_ptr(folio)) > 0 || + return atomic_read(&folio->_nr_pages_mapped) > 0 || atomic_read(folio_mapcount_ptr(folio)) >= 0; } diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 6ff1d7db00a7..4751c67b98a6 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -307,7 +307,7 @@ static inline struct page *encoded_page_ptr(struct encoded_page *page) * @_folio_dtor: Which destructor to use for this folio. * @_folio_order: Do not use directly, call folio_order(). * @_compound_mapcount: Do not use directly, call folio_entire_mapcount(). - * @_subpages_mapcount: Do not use directly, call folio_mapcount(). + * @_nr_pages_mapped: Do not use directly, call folio_mapcount(). * @_pincount: Do not use directly, call folio_maybe_dma_pinned(). * @_folio_nr_pages: Do not use directly, call folio_nr_pages(). * @_flags_2: For alignment. Do not use. @@ -361,7 +361,7 @@ struct folio { unsigned char _folio_dtor; unsigned char _folio_order; atomic_t _compound_mapcount; - atomic_t _subpages_mapcount; + atomic_t _nr_pages_mapped; atomic_t _pincount; #ifdef CONFIG_64BIT unsigned int _folio_nr_pages; @@ -404,7 +404,7 @@ FOLIO_MATCH(compound_head, _head_1); FOLIO_MATCH(compound_dtor, _folio_dtor); FOLIO_MATCH(compound_order, _folio_order); FOLIO_MATCH(compound_mapcount, _compound_mapcount); -FOLIO_MATCH(subpages_mapcount, _subpages_mapcount); +FOLIO_MATCH(subpages_mapcount, _nr_pages_mapped); FOLIO_MATCH(compound_pincount, _pincount); #ifdef CONFIG_64BIT FOLIO_MATCH(compound_nr, _folio_nr_pages); @@ -427,12 +427,6 @@ static inline atomic_t *folio_mapcount_ptr(struct folio *folio) return &tail->compound_mapcount; } -static inline atomic_t *folio_subpages_mapcount_ptr(struct folio *folio) -{ - struct page *tail = &folio->page + 1; - return &tail->subpages_mapcount; -} - static inline atomic_t *compound_mapcount_ptr(struct page *page) { return &page[1].compound_mapcount; diff --git a/mm/debug.c b/mm/debug.c index 893c9dbf76ca..8e58e8dab0b2 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -94,10 +94,10 @@ static void __dump_page(struct page *page) page, page_ref_count(head), mapcount, mapping, page_to_pgoff(page), page_to_pfn(page)); if (compound) { - pr_warn("head:%p order:%u compound_mapcount:%d subpages_mapcount:%d pincount:%d\n", + pr_warn("head:%p order:%u compound_mapcount:%d nr_pages_mapped:%d pincount:%d\n", head, compound_order(head), head_compound_mapcount(head), - head_subpages_mapcount(head), + folio_nr_pages_mapped(folio), atomic_read(&folio->_pincount)); } diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 15b2707c1600..c9702224931c 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1475,7 +1475,7 @@ static void __destroy_compound_gigantic_folio(struct folio *folio, struct page *p; atomic_set(folio_mapcount_ptr(folio), 0); - atomic_set(folio_subpages_mapcount_ptr(folio), 0); + atomic_set(&folio->_nr_pages_mapped, 0); atomic_set(&folio->_pincount, 0); for (i = 1; i < nr_pages; i++) { @@ -1997,7 +1997,7 @@ static bool __prep_compound_gigantic_folio(struct folio *folio, set_compound_head(p, &folio->page); } atomic_set(folio_mapcount_ptr(folio), -1); - atomic_set(folio_subpages_mapcount_ptr(folio), 0); + atomic_set(&folio->_nr_pages_mapped, 0); atomic_set(&folio->_pincount, 0); return true; diff --git a/mm/internal.h b/mm/internal.h index 1d6f4e168510..583e15357e09 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -52,6 +52,24 @@ struct folio_batch; void page_writeback_init(void); +/* + * If a 16GB hugetlb folio were mapped by PTEs of all of its 4kB pages, + * its nr_pages_mapped would be 0x400000: choose the COMPOUND_MAPPED bit + * above that range, instead of 2*(PMD_SIZE/PAGE_SIZE). Hugetlb currently + * leaves nr_pages_mapped at 0, but avoid surprise if it participates later. + */ +#define COMPOUND_MAPPED 0x800000 +#define FOLIO_PAGES_MAPPED (COMPOUND_MAPPED - 1) + +/* + * How many individual pages have an elevated _mapcount. Excludes + * the folio's entire_mapcount. + */ +static inline int folio_nr_pages_mapped(struct folio *folio) +{ + return atomic_read(&folio->_nr_pages_mapped) & FOLIO_PAGES_MAPPED; +} + static inline void *folio_raw_mapping(struct folio *folio) { unsigned long mapping = (unsigned long)folio->mapping; diff --git a/mm/rmap.c b/mm/rmap.c index 6ccd42bbae93..b573472b4ac3 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1080,12 +1080,13 @@ int pfn_mkclean_range(unsigned long pfn, unsigned long nr_pages, pgoff_t pgoff, int total_compound_mapcount(struct page *head) { + struct folio *folio = (struct folio *)head; int mapcount = head_compound_mapcount(head); int nr_subpages; int i; /* In the common case, avoid the loop when no subpages mapped by PTE */ - if (head_subpages_mapcount(head) == 0) + if (folio_nr_pages_mapped(folio) == 0) return mapcount; /* * Add all the PTE mappings of those subpages mapped by PTE. @@ -1233,7 +1234,7 @@ void page_add_anon_rmap(struct page *page, nr = atomic_add_return_relaxed(COMPOUND_MAPPED, mapped); if (likely(nr < COMPOUND_MAPPED + COMPOUND_MAPPED)) { nr_pmdmapped = thp_nr_pages(page); - nr = nr_pmdmapped - (nr & SUBPAGES_MAPPED); + nr = nr_pmdmapped - (nr & FOLIO_PAGES_MAPPED); /* Raced ahead of a remove and another add? */ if (unlikely(nr < 0)) nr = 0; @@ -1337,7 +1338,7 @@ void page_add_file_rmap(struct page *page, nr = atomic_add_return_relaxed(COMPOUND_MAPPED, mapped); if (likely(nr < COMPOUND_MAPPED + COMPOUND_MAPPED)) { nr_pmdmapped = thp_nr_pages(page); - nr = nr_pmdmapped - (nr & SUBPAGES_MAPPED); + nr = nr_pmdmapped - (nr & FOLIO_PAGES_MAPPED); /* Raced ahead of a remove and another add? */ if (unlikely(nr < 0)) nr = 0; @@ -1399,7 +1400,7 @@ void page_remove_rmap(struct page *page, nr = atomic_sub_return_relaxed(COMPOUND_MAPPED, mapped); if (likely(nr < COMPOUND_MAPPED)) { nr_pmdmapped = thp_nr_pages(page); - nr = nr_pmdmapped - (nr & SUBPAGES_MAPPED); + nr = nr_pmdmapped - (nr & FOLIO_PAGES_MAPPED); /* Raced ahead of another remove and an add? */ if (unlikely(nr < 0)) nr = 0; -- cgit v1.2.3 From b14224fbea62e5bffd680613376fe1268f4103ba Mon Sep 17 00:00:00 2001 From: Matthew Wilcox (Oracle) Date: Wed, 11 Jan 2023 14:28:50 +0000 Subject: mm: convert total_compound_mapcount() to folio_total_mapcount() Instead of enforcing that the argument must be a head page by naming, enforce it with the compiler by making it a folio. Also rename the counter in struct folio from _compound_mapcount to _entire_mapcount. Link: https://lkml.kernel.org/r/20230111142915.1001531-5-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- include/linux/mm.h | 6 +++--- include/linux/mm_types.h | 6 +++--- mm/rmap.c | 21 ++++++++++----------- 3 files changed, 16 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 2bdd08a5b8b4..bdf83e75bcd6 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -871,7 +871,7 @@ static inline int page_mapcount(struct page *page) return head_compound_mapcount(page) + mapcount; } -int total_compound_mapcount(struct page *head); +int folio_total_mapcount(struct folio *folio); /** * folio_mapcount() - Calculate the number of mappings of this folio. @@ -888,14 +888,14 @@ static inline int folio_mapcount(struct folio *folio) { if (likely(!folio_test_large(folio))) return atomic_read(&folio->_mapcount) + 1; - return total_compound_mapcount(&folio->page); + return folio_total_mapcount(folio); } static inline int total_mapcount(struct page *page) { if (likely(!PageCompound(page))) return atomic_read(&page->_mapcount) + 1; - return total_compound_mapcount(compound_head(page)); + return folio_total_mapcount(page_folio(page)); } static inline bool folio_large_is_mapped(struct folio *folio) diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 4751c67b98a6..70cbda768308 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -306,7 +306,7 @@ static inline struct page *encoded_page_ptr(struct encoded_page *page) * @_head_1: Points to the folio. Do not use. * @_folio_dtor: Which destructor to use for this folio. * @_folio_order: Do not use directly, call folio_order(). - * @_compound_mapcount: Do not use directly, call folio_entire_mapcount(). + * @_entire_mapcount: Do not use directly, call folio_entire_mapcount(). * @_nr_pages_mapped: Do not use directly, call folio_mapcount(). * @_pincount: Do not use directly, call folio_maybe_dma_pinned(). * @_folio_nr_pages: Do not use directly, call folio_nr_pages(). @@ -360,7 +360,7 @@ struct folio { unsigned long _head_1; unsigned char _folio_dtor; unsigned char _folio_order; - atomic_t _compound_mapcount; + atomic_t _entire_mapcount; atomic_t _nr_pages_mapped; atomic_t _pincount; #ifdef CONFIG_64BIT @@ -403,7 +403,7 @@ FOLIO_MATCH(flags, _flags_1); FOLIO_MATCH(compound_head, _head_1); FOLIO_MATCH(compound_dtor, _folio_dtor); FOLIO_MATCH(compound_order, _folio_order); -FOLIO_MATCH(compound_mapcount, _compound_mapcount); +FOLIO_MATCH(compound_mapcount, _entire_mapcount); FOLIO_MATCH(subpages_mapcount, _nr_pages_mapped); FOLIO_MATCH(compound_pincount, _pincount); #ifdef CONFIG_64BIT diff --git a/mm/rmap.c b/mm/rmap.c index b573472b4ac3..1418efc80027 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1078,27 +1078,26 @@ int pfn_mkclean_range(unsigned long pfn, unsigned long nr_pages, pgoff_t pgoff, return page_vma_mkclean_one(&pvmw); } -int total_compound_mapcount(struct page *head) +int folio_total_mapcount(struct folio *folio) { - struct folio *folio = (struct folio *)head; - int mapcount = head_compound_mapcount(head); - int nr_subpages; + int mapcount = folio_entire_mapcount(folio); + int nr_pages; int i; - /* In the common case, avoid the loop when no subpages mapped by PTE */ + /* In the common case, avoid the loop when no pages mapped by PTE */ if (folio_nr_pages_mapped(folio) == 0) return mapcount; /* - * Add all the PTE mappings of those subpages mapped by PTE. - * Limit the loop, knowing that only subpages_mapcount are mapped? + * Add all the PTE mappings of those pages mapped by PTE. + * Limit the loop to folio_nr_pages_mapped()? * Perhaps: given all the raciness, that may be a good or a bad idea. */ - nr_subpages = thp_nr_pages(head); - for (i = 0; i < nr_subpages; i++) - mapcount += atomic_read(&head[i]._mapcount); + nr_pages = folio_nr_pages(folio); + for (i = 0; i < nr_pages; i++) + mapcount += atomic_read(&folio_page(folio, i)->_mapcount); /* But each of those _mapcounts was based on -1 */ - mapcount += nr_subpages; + mapcount += nr_pages; return mapcount; } -- cgit v1.2.3 From 4d510f3da4c216d4c2695395f67aec38e2aa6cc7 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox (Oracle) Date: Wed, 11 Jan 2023 14:28:54 +0000 Subject: mm: add folio_add_new_anon_rmap() In contrast to other rmap functions, page_add_new_anon_rmap() is always called with a freshly allocated page. That means it can't be called with a tail page. Turn page_add_new_anon_rmap() into folio_add_new_anon_rmap() and add a page_add_new_anon_rmap() wrapper. Callers can be converted individually. [akpm@linux-foundation.org: fix NOMMU build. page_add_new_anon_rmap() requires CONFIG_MMU] [willy@infradead.org: folio-compat.c needs rmap.h] Link: https://lkml.kernel.org/r/20230111142915.1001531-9-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- include/linux/rmap.h | 2 ++ mm/folio-compat.c | 11 +++++++++++ mm/rmap.c | 37 ++++++++++++++++++------------------- 3 files changed, 31 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index bd3504d11b15..aa682a2a93ce 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -194,6 +194,8 @@ void page_add_anon_rmap(struct page *, struct vm_area_struct *, unsigned long address, rmap_t flags); void page_add_new_anon_rmap(struct page *, struct vm_area_struct *, unsigned long address); +void folio_add_new_anon_rmap(struct folio *, struct vm_area_struct *, + unsigned long address); void page_add_file_rmap(struct page *, struct vm_area_struct *, bool compound); void page_remove_rmap(struct page *, struct vm_area_struct *, diff --git a/mm/folio-compat.c b/mm/folio-compat.c index 69ed25790c68..18c48b557926 100644 --- a/mm/folio-compat.c +++ b/mm/folio-compat.c @@ -6,6 +6,7 @@ #include #include +#include #include #include "internal.h" @@ -123,3 +124,13 @@ void putback_lru_page(struct page *page) { folio_putback_lru(page_folio(page)); } + +#ifdef CONFIG_MMU +void page_add_new_anon_rmap(struct page *page, struct vm_area_struct *vma, + unsigned long address) +{ + VM_BUG_ON_PAGE(PageTail(page), page); + + return folio_add_new_anon_rmap((struct folio *)page, vma, address); +} +#endif diff --git a/mm/rmap.c b/mm/rmap.c index 430c066c2295..513e23e5a158 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1264,41 +1264,40 @@ void page_add_anon_rmap(struct page *page, struct vm_area_struct *vma, } /** - * page_add_new_anon_rmap - add mapping to a new anonymous page - * @page: the page to add the mapping to + * folio_add_new_anon_rmap - Add mapping to a new anonymous folio. + * @folio: The folio to add the mapping to. * @vma: the vm area in which the mapping is added * @address: the user virtual address mapped * - * If it's a compound page, it is accounted as a compound page. As the page - * is new, it's assume to get mapped exclusively by a single process. - * - * Same as page_add_anon_rmap but must only be called on *new* pages. + * Like page_add_anon_rmap() but must only be called on *new* folios. * This means the inc-and-test can be bypassed. - * Page does not have to be locked. + * The folio does not have to be locked. + * + * If the folio is large, it is accounted as a THP. As the folio + * is new, it's assumed to be mapped exclusively by a single process. */ -void page_add_new_anon_rmap(struct page *page, - struct vm_area_struct *vma, unsigned long address) +void folio_add_new_anon_rmap(struct folio *folio, struct vm_area_struct *vma, + unsigned long address) { int nr; VM_BUG_ON_VMA(address < vma->vm_start || address >= vma->vm_end, vma); - __SetPageSwapBacked(page); + __folio_set_swapbacked(folio); - if (likely(!PageCompound(page))) { + if (likely(!folio_test_pmd_mappable(folio))) { /* increment count (starts at -1) */ - atomic_set(&page->_mapcount, 0); + atomic_set(&folio->_mapcount, 0); nr = 1; } else { - VM_BUG_ON_PAGE(!PageTransHuge(page), page); /* increment count (starts at -1) */ - atomic_set(compound_mapcount_ptr(page), 0); - atomic_set(subpages_mapcount_ptr(page), COMPOUND_MAPPED); - nr = thp_nr_pages(page); - __mod_lruvec_page_state(page, NR_ANON_THPS, nr); + atomic_set(&folio->_entire_mapcount, 0); + atomic_set(&folio->_nr_pages_mapped, COMPOUND_MAPPED); + nr = folio_nr_pages(folio); + __lruvec_stat_mod_folio(folio, NR_ANON_THPS, nr); } - __mod_lruvec_page_state(page, NR_ANON_MAPPED, nr); - __page_set_anon_rmap(page, vma, address, 1); + __lruvec_stat_mod_folio(folio, NR_ANON_MAPPED, nr); + __page_set_anon_rmap(&folio->page, vma, address, 1); } /** -- cgit v1.2.3 From c7f84b5723f1a60becd79d895ab214a7d5ee93c1 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox (Oracle) Date: Wed, 11 Jan 2023 14:28:57 +0000 Subject: mm: use entire_mapcount in __page_dup_rmap() Remove the use of the compound_mapcount_ptr() wrapper, and add an assertion that we're not passing a tail page if we're duplicating a PMD. Link: https://lkml.kernel.org/r/20230111142915.1001531-12-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- include/linux/rmap.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index aa682a2a93ce..a6bd1f0a183d 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -208,7 +208,14 @@ void hugepage_add_new_anon_rmap(struct page *, struct vm_area_struct *, static inline void __page_dup_rmap(struct page *page, bool compound) { - atomic_inc(compound ? compound_mapcount_ptr(page) : &page->_mapcount); + if (compound) { + struct folio *folio = (struct folio *)page; + + VM_BUG_ON_PAGE(compound && !PageHead(page), page); + atomic_inc(&folio->_entire_mapcount); + } else { + atomic_inc(&page->_mapcount); + } } static inline void page_dup_file_rmap(struct page *page, bool compound) -- cgit v1.2.3 From c97eeb8f260dba098ba775e37d216f81f28559a9 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox (Oracle) Date: Wed, 11 Jan 2023 14:29:00 +0000 Subject: mm: convert page_mapcount() to use folio_entire_mapcount() Remove a use of head_compound_mapcount(). Link: https://lkml.kernel.org/r/20230111142915.1001531-15-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- include/linux/mm.h | 22 +++++++++++++--------- 1 file changed, 13 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index bdf83e75bcd6..a6afa6c51a4d 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -853,22 +853,26 @@ static inline void page_mapcount_reset(struct page *page) atomic_set(&(page)->_mapcount, -1); } -/* - * Mapcount of 0-order page; when compound sub-page, includes - * compound_mapcount of compound_head of page. +/** + * page_mapcount() - Number of times this precise page is mapped. + * @page: The page. + * + * The number of times this page is mapped. If this page is part of + * a large folio, it includes the number of times this page is mapped + * as part of that folio. * - * Result is undefined for pages which cannot be mapped into userspace. + * The result is undefined for pages which cannot be mapped into userspace. * For example SLAB or special types of pages. See function page_has_type(). - * They use this place in struct page differently. + * They use this field in struct page differently. */ static inline int page_mapcount(struct page *page) { int mapcount = atomic_read(&page->_mapcount) + 1; - if (likely(!PageCompound(page))) - return mapcount; - page = compound_head(page); - return head_compound_mapcount(page) + mapcount; + if (unlikely(PageCompound(page))) + mapcount += folio_entire_mapcount(page_folio(page)); + + return mapcount; } int folio_total_mapcount(struct folio *folio); -- cgit v1.2.3 From 1aa4d03b60c0f61a8d96d5d633bf7968dbf6841f Mon Sep 17 00:00:00 2001 From: Matthew Wilcox (Oracle) Date: Wed, 11 Jan 2023 14:29:01 +0000 Subject: mm: remove head_compound_mapcount() and _ptr functions folio_mapcount_ptr(), compound_mapcount_ptr() and subpages_mapcount_ptr() are all now unused. Link: https://lkml.kernel.org/r/20230111142915.1001531-16-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- include/linux/mm.h | 15 +++------------ include/linux/mm_types.h | 16 ---------------- 2 files changed, 3 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index a6afa6c51a4d..7ff6e2410aa3 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -831,16 +831,7 @@ static inline int is_vmalloc_or_module_addr(const void *x) static inline int folio_entire_mapcount(struct folio *folio) { VM_BUG_ON_FOLIO(!folio_test_large(folio), folio); - return atomic_read(folio_mapcount_ptr(folio)) + 1; -} - -/* - * Mapcount of compound page as a whole, does not include mapped sub-pages. - * Must be called only on head of compound page. - */ -static inline int head_compound_mapcount(struct page *head) -{ - return atomic_read(compound_mapcount_ptr(head)) + 1; + return atomic_read(&folio->_entire_mapcount) + 1; } /* @@ -905,11 +896,11 @@ static inline int total_mapcount(struct page *page) static inline bool folio_large_is_mapped(struct folio *folio) { /* - * Reading folio_mapcount_ptr() below could be omitted if hugetlb + * Reading _entire_mapcount below could be omitted if hugetlb * participated in incrementing nr_pages_mapped when compound mapped. */ return atomic_read(&folio->_nr_pages_mapped) > 0 || - atomic_read(folio_mapcount_ptr(folio)) >= 0; + atomic_read(&folio->_entire_mapcount) >= 0; } /** diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 70cbda768308..ffcf21fbaaf0 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -421,22 +421,6 @@ FOLIO_MATCH(hugetlb_cgroup_rsvd, _hugetlb_cgroup_rsvd); FOLIO_MATCH(hugetlb_hwpoison, _hugetlb_hwpoison); #undef FOLIO_MATCH -static inline atomic_t *folio_mapcount_ptr(struct folio *folio) -{ - struct page *tail = &folio->page + 1; - return &tail->compound_mapcount; -} - -static inline atomic_t *compound_mapcount_ptr(struct page *page) -{ - return &page[1].compound_mapcount; -} - -static inline atomic_t *subpages_mapcount_ptr(struct page *page) -{ - return &page[1].subpages_mapcount; -} - /* * Used for sizing the vmemmap region on some architectures */ -- cgit v1.2.3 From 5eb5cea11dcbafaa37685bc4e89e1d4ae9c434ea Mon Sep 17 00:00:00 2001 From: Matthew Wilcox (Oracle) Date: Wed, 11 Jan 2023 14:29:02 +0000 Subject: mm: reimplement compound_order() Make compound_order() use struct folio. It can't be turned into a wrapper around folio_order() as a page can be turned into a tail page between a check in compound_order() and the assertion in folio_test_large(). Link: https://lkml.kernel.org/r/20230111142915.1001531-17-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- include/linux/mm.h | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 7ff6e2410aa3..3adc37cebe6f 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -719,11 +719,20 @@ int vma_is_stack_for_current(struct vm_area_struct *vma); struct mmu_gather; struct inode; +/* + * compound_order() can be called without holding a reference, which means + * that niceties like page_folio() don't work. These callers should be + * prepared to handle wild return values. For example, PG_head may be + * set before _folio_order is initialised, or this may be a tail page. + * See compaction.c for some good examples. + */ static inline unsigned int compound_order(struct page *page) { - if (!PageHead(page)) + struct folio *folio = (struct folio *)page; + + if (!test_bit(PG_head, &folio->flags)) return 0; - return page[1].compound_order; + return folio->_folio_order; } /** -- cgit v1.2.3 From 21a000fe97a018c6d25be63892afb4fd8210ab57 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox (Oracle) Date: Wed, 11 Jan 2023 14:29:03 +0000 Subject: mm: reimplement compound_nr() Turn compound_nr() into a wrapper around folio_nr_pages(). Similarly to compound_order(), casting the struct page directly to struct folio preserves the existing behaviour, while calling page_folio() would change the behaviour. Move thp_nr_pages() down in the file so that compound_nr() can be after folio_nr_pages(). [willy@infradead.org: fix assertion triggering] Link: https://lkml.kernel.org/r/Y8AFgZEEjnUIaCbf@casper.infradead.org Link: https://lkml.kernel.org/r/20230111142915.1001531-18-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Cc: Hugh Dickins Signed-off-by: Andrew Morton --- include/linux/mm.h | 49 +++++++++++++++++++++++++++---------------------- 1 file changed, 27 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 3adc37cebe6f..3acf09d5b0bd 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1005,18 +1005,6 @@ static inline void set_compound_order(struct page *page, unsigned int order) #endif } -/* Returns the number of pages in this potentially compound page. */ -static inline unsigned long compound_nr(struct page *page) -{ - if (!PageHead(page)) - return 1; -#ifdef CONFIG_64BIT - return page[1].compound_nr; -#else - return 1UL << compound_order(page); -#endif -} - /* Returns the number of bytes in this potentially compound page. */ static inline unsigned long page_size(struct page *page) { @@ -1039,16 +1027,6 @@ static inline unsigned int thp_order(struct page *page) return compound_order(page); } -/** - * thp_nr_pages - The number of regular pages in this huge page. - * @page: The head page of a huge page. - */ -static inline int thp_nr_pages(struct page *page) -{ - VM_BUG_ON_PGFLAGS(PageTail(page), page); - return compound_nr(page); -} - /** * thp_size - Size of a transparent huge page. * @page: Head page of a transparent huge page. @@ -1758,6 +1736,33 @@ static inline long folio_nr_pages(struct folio *folio) #endif } +/* + * compound_nr() returns the number of pages in this potentially compound + * page. compound_nr() can be called on a tail page, and is defined to + * return 1 in that case. + */ +static inline unsigned long compound_nr(struct page *page) +{ + struct folio *folio = (struct folio *)page; + + if (!test_bit(PG_head, &folio->flags)) + return 1; +#ifdef CONFIG_64BIT + return folio->_folio_nr_pages; +#else + return 1L << folio->_folio_order; +#endif +} + +/** + * thp_nr_pages - The number of regular pages in this huge page. + * @page: The head page of a huge page. + */ +static inline int thp_nr_pages(struct page *page) +{ + return folio_nr_pages((struct folio *)page); +} + /** * folio_next - Move to the next physical folio. * @folio: The folio we're currently operating on. -- cgit v1.2.3 From bad6da64565846ef5ba85b0b685cfde9db0085dc Mon Sep 17 00:00:00 2001 From: Matthew Wilcox (Oracle) Date: Wed, 11 Jan 2023 14:29:04 +0000 Subject: mm: convert set_compound_page_dtor() and set_compound_order() to folios Replace uses of compound_dtor, compound_order and compound_nr by their folio equivalents. Link: https://lkml.kernel.org/r/20230111142915.1001531-19-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- include/linux/mm.h | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 3acf09d5b0bd..836b96e08a14 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -984,8 +984,11 @@ extern compound_page_dtor * const compound_page_dtors[NR_COMPOUND_DTORS]; static inline void set_compound_page_dtor(struct page *page, enum compound_dtor_id compound_dtor) { + struct folio *folio = (struct folio *)page; + VM_BUG_ON_PAGE(compound_dtor >= NR_COMPOUND_DTORS, page); - page[1].compound_dtor = compound_dtor; + VM_BUG_ON_PAGE(!PageHead(page), page); + folio->_folio_dtor = compound_dtor; } static inline void folio_set_compound_dtor(struct folio *folio, @@ -999,9 +1002,11 @@ void destroy_large_folio(struct folio *folio); static inline void set_compound_order(struct page *page, unsigned int order) { - page[1].compound_order = order; + struct folio *folio = (struct folio *)page; + + folio->_folio_order = order; #ifdef CONFIG_64BIT - page[1].compound_nr = 1U << order; + folio->_folio_nr_pages = 1U << order; #endif } -- cgit v1.2.3 From 1c5509be58f636afabbdaf66e7436da8ec0a1828 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox (Oracle) Date: Wed, 11 Jan 2023 14:29:08 +0000 Subject: mm: remove 'First tail page' members from struct page All former users now use the folio equivalents, so remove them from the definition of struct page. Link: https://lkml.kernel.org/r/20230111142915.1001531-23-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- include/linux/mm_types.h | 18 ------------------ kernel/crash_core.c | 4 ++-- 2 files changed, 2 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index ffcf21fbaaf0..94b1707f5d33 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -140,16 +140,6 @@ struct page { }; struct { /* Tail pages of compound page */ unsigned long compound_head; /* Bit zero is set */ - - /* First tail page only */ - unsigned char compound_dtor; - unsigned char compound_order; - atomic_t compound_mapcount; - atomic_t subpages_mapcount; - atomic_t compound_pincount; -#ifdef CONFIG_64BIT - unsigned int compound_nr; /* 1 << compound_order */ -#endif }; struct { /* Second tail page of transparent huge page */ unsigned long _compound_pad_1; /* compound_head */ @@ -401,14 +391,6 @@ FOLIO_MATCH(memcg_data, memcg_data); offsetof(struct page, pg) + sizeof(struct page)) FOLIO_MATCH(flags, _flags_1); FOLIO_MATCH(compound_head, _head_1); -FOLIO_MATCH(compound_dtor, _folio_dtor); -FOLIO_MATCH(compound_order, _folio_order); -FOLIO_MATCH(compound_mapcount, _entire_mapcount); -FOLIO_MATCH(subpages_mapcount, _nr_pages_mapped); -FOLIO_MATCH(compound_pincount, _pincount); -#ifdef CONFIG_64BIT -FOLIO_MATCH(compound_nr, _folio_nr_pages); -#endif #undef FOLIO_MATCH #define FOLIO_MATCH(pg, fl) \ static_assert(offsetof(struct folio, fl) == \ diff --git a/kernel/crash_core.c b/kernel/crash_core.c index 87ef6096823f..755f5f08ab38 100644 --- a/kernel/crash_core.c +++ b/kernel/crash_core.c @@ -455,8 +455,8 @@ static int __init crash_save_vmcoreinfo_init(void) VMCOREINFO_OFFSET(page, lru); VMCOREINFO_OFFSET(page, _mapcount); VMCOREINFO_OFFSET(page, private); - VMCOREINFO_OFFSET(page, compound_dtor); - VMCOREINFO_OFFSET(page, compound_order); + VMCOREINFO_OFFSET(folio, _folio_dtor); + VMCOREINFO_OFFSET(folio, _folio_order); VMCOREINFO_OFFSET(page, compound_head); VMCOREINFO_OFFSET(pglist_data, node_zones); VMCOREINFO_OFFSET(pglist_data, nr_zones); -- cgit v1.2.3 From a8d55327ccc1f999a5fba4eee67ed08bd36493ad Mon Sep 17 00:00:00 2001 From: Matthew Wilcox (Oracle) Date: Wed, 11 Jan 2023 14:29:09 +0000 Subject: doc: correct struct folio kernel-doc Insert appropriate public: and private: markers to make the generated kernel-doc look right. Link: https://lkml.kernel.org/r/20230111142915.1001531-24-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- include/linux/mm_types.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 94b1707f5d33..d458e9b8496c 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -292,16 +292,12 @@ static inline struct page *encoded_page_ptr(struct encoded_page *page) * @_refcount: Do not access this member directly. Use folio_ref_count() * to find how many references there are to this folio. * @memcg_data: Memory Control Group data. - * @_flags_1: For large folios, additional page flags. - * @_head_1: Points to the folio. Do not use. * @_folio_dtor: Which destructor to use for this folio. * @_folio_order: Do not use directly, call folio_order(). * @_entire_mapcount: Do not use directly, call folio_entire_mapcount(). * @_nr_pages_mapped: Do not use directly, call folio_mapcount(). * @_pincount: Do not use directly, call folio_maybe_dma_pinned(). * @_folio_nr_pages: Do not use directly, call folio_nr_pages(). - * @_flags_2: For alignment. Do not use. - * @_head_2: Points to the folio. Do not use. * @_hugetlb_subpool: Do not use directly, use accessor in hugetlb.h. * @_hugetlb_cgroup: Do not use directly, use accessor in hugetlb_cgroup.h. * @_hugetlb_cgroup_rsvd: Do not use directly, use accessor in hugetlb_cgroup.h. @@ -348,6 +344,7 @@ struct folio { struct { unsigned long _flags_1; unsigned long _head_1; + /* public: */ unsigned char _folio_dtor; unsigned char _folio_order; atomic_t _entire_mapcount; @@ -356,6 +353,7 @@ struct folio { #ifdef CONFIG_64BIT unsigned int _folio_nr_pages; #endif + /* private: the union with struct page is transitional */ }; struct page __page_1; }; @@ -363,10 +361,12 @@ struct folio { struct { unsigned long _flags_2; unsigned long _head_2; + /* public: */ void *_hugetlb_subpool; void *_hugetlb_cgroup; void *_hugetlb_cgroup_rsvd; void *_hugetlb_hwpoison; + /* private: the union with struct page is transitional */ }; struct page __page_2; }; -- cgit v1.2.3 From 4375a553f46c6cb66d1711d8f514dfdf34ce74b0 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox (Oracle) Date: Wed, 11 Jan 2023 14:29:10 +0000 Subject: mm: move page->deferred_list to folio->_deferred_list Remove the entire block of definitions for the second tail page, and add the deferred list to the struct folio. This actually moves _deferred_list to a different offset in struct folio because I don't see a need to include the padding. This lets us use list_for_each_entry_safe() in deferred_split_scan() and avoid a number of calls to compound_head(). Link: https://lkml.kernel.org/r/20230111142915.1001531-25-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- include/linux/huge_mm.h | 9 ++++----- include/linux/mm_types.h | 14 ++++++++------ mm/huge_memory.c | 32 +++++++++++++++----------------- 3 files changed, 27 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index a1341fdcf666..aacfcb02606f 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -295,11 +295,10 @@ static inline bool thp_migration_supported(void) static inline struct list_head *page_deferred_list(struct page *page) { - /* - * See organization of tail pages of compound page in - * "struct page" definition. - */ - return &page[2].deferred_list; + struct folio *folio = (struct folio *)page; + + VM_BUG_ON_FOLIO(folio_order(folio) < 2, folio); + return &folio->_deferred_list; } #else /* CONFIG_TRANSPARENT_HUGEPAGE */ diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index d458e9b8496c..7eb4d0815a78 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -141,12 +141,6 @@ struct page { struct { /* Tail pages of compound page */ unsigned long compound_head; /* Bit zero is set */ }; - struct { /* Second tail page of transparent huge page */ - unsigned long _compound_pad_1; /* compound_head */ - unsigned long _compound_pad_2; - /* For both global and memcg */ - struct list_head deferred_list; - }; struct { /* Second tail page of hugetlb page */ unsigned long _hugetlb_pad_1; /* compound_head */ void *hugetlb_subpool; @@ -302,6 +296,7 @@ static inline struct page *encoded_page_ptr(struct encoded_page *page) * @_hugetlb_cgroup: Do not use directly, use accessor in hugetlb_cgroup.h. * @_hugetlb_cgroup_rsvd: Do not use directly, use accessor in hugetlb_cgroup.h. * @_hugetlb_hwpoison: Do not use directly, call raw_hwp_list_head(). + * @_deferred_list: Folios to be split under memory pressure. * * A folio is a physically, virtually and logically contiguous set * of bytes. It is a power-of-two in size, and it is aligned to that @@ -366,6 +361,13 @@ struct folio { void *_hugetlb_cgroup; void *_hugetlb_cgroup_rsvd; void *_hugetlb_hwpoison; + /* private: the union with struct page is transitional */ + }; + struct { + unsigned long _flags_2a; + unsigned long _head_2a; + /* public: */ + struct list_head _deferred_list; /* private: the union with struct page is transitional */ }; struct page __page_2; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index bfa960f012fa..a4138daaa0b8 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2756,9 +2756,9 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) /* Prevent deferred_split_scan() touching ->_refcount */ spin_lock(&ds_queue->split_queue_lock); if (folio_ref_freeze(folio, 1 + extra_pins)) { - if (!list_empty(page_deferred_list(&folio->page))) { + if (!list_empty(&folio->_deferred_list)) { ds_queue->split_queue_len--; - list_del(page_deferred_list(&folio->page)); + list_del(&folio->_deferred_list); } spin_unlock(&ds_queue->split_queue_lock); if (mapping) { @@ -2873,8 +2873,8 @@ static unsigned long deferred_split_scan(struct shrinker *shrink, struct pglist_data *pgdata = NODE_DATA(sc->nid); struct deferred_split *ds_queue = &pgdata->deferred_split_queue; unsigned long flags; - LIST_HEAD(list), *pos, *next; - struct page *page; + LIST_HEAD(list); + struct folio *folio, *next; int split = 0; #ifdef CONFIG_MEMCG @@ -2884,14 +2884,13 @@ static unsigned long deferred_split_scan(struct shrinker *shrink, spin_lock_irqsave(&ds_queue->split_queue_lock, flags); /* Take pin on all head pages to avoid freeing them under us */ - list_for_each_safe(pos, next, &ds_queue->split_queue) { - page = list_entry((void *)pos, struct page, deferred_list); - page = compound_head(page); - if (get_page_unless_zero(page)) { - list_move(page_deferred_list(page), &list); + list_for_each_entry_safe(folio, next, &ds_queue->split_queue, + _deferred_list) { + if (folio_try_get(folio)) { + list_move(&folio->_deferred_list, &list); } else { - /* We lost race with put_compound_page() */ - list_del_init(page_deferred_list(page)); + /* We lost race with folio_put() */ + list_del_init(&folio->_deferred_list); ds_queue->split_queue_len--; } if (!--sc->nr_to_scan) @@ -2899,16 +2898,15 @@ static unsigned long deferred_split_scan(struct shrinker *shrink, } spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags); - list_for_each_safe(pos, next, &list) { - page = list_entry((void *)pos, struct page, deferred_list); - if (!trylock_page(page)) + list_for_each_entry_safe(folio, next, &list, _deferred_list) { + if (!folio_trylock(folio)) goto next; /* split_huge_page() removes page from list on success */ - if (!split_huge_page(page)) + if (!split_folio(folio)) split++; - unlock_page(page); + folio_unlock(folio); next: - put_page(page); + folio_put(folio); } spin_lock_irqsave(&ds_queue->split_queue_lock, flags); -- cgit v1.2.3 From 8991de90e99755b13026b1db32d1fa52e94c6a96 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox (Oracle) Date: Wed, 11 Jan 2023 14:29:11 +0000 Subject: mm/huge_memory: remove page_deferred_list() Use folio->_deferred_list directly. Link: https://lkml.kernel.org/r/20230111142915.1001531-26-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- include/linux/huge_mm.h | 8 -------- mm/huge_memory.c | 34 +++++++++++++++++----------------- 2 files changed, 17 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index aacfcb02606f..b9978978a160 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -293,14 +293,6 @@ static inline bool thp_migration_supported(void) return IS_ENABLED(CONFIG_ARCH_ENABLE_THP_MIGRATION); } -static inline struct list_head *page_deferred_list(struct page *page) -{ - struct folio *folio = (struct folio *)page; - - VM_BUG_ON_FOLIO(folio_order(folio) < 2, folio); - return &folio->_deferred_list; -} - #else /* CONFIG_TRANSPARENT_HUGEPAGE */ #define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; }) #define HPAGE_PMD_MASK ({ BUILD_BUG(); 0; }) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index a4138daaa0b8..7aedfe7cf5df 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -580,12 +580,10 @@ static inline struct deferred_split *get_deferred_split_queue(struct page *page) void prep_transhuge_page(struct page *page) { - /* - * we use page->mapping and page->index in second tail page - * as list_head: assuming THP order >= 2 - */ + struct folio *folio = (struct folio *)page; - INIT_LIST_HEAD(page_deferred_list(page)); + VM_BUG_ON_FOLIO(folio_order(folio) < 2, folio); + INIT_LIST_HEAD(&folio->_deferred_list); set_compound_page_dtor(page, TRANSHUGE_PAGE_DTOR); } @@ -2802,13 +2800,14 @@ out: void free_transhuge_page(struct page *page) { + struct folio *folio = (struct folio *)page; struct deferred_split *ds_queue = get_deferred_split_queue(page); unsigned long flags; spin_lock_irqsave(&ds_queue->split_queue_lock, flags); - if (!list_empty(page_deferred_list(page))) { + if (!list_empty(&folio->_deferred_list)) { ds_queue->split_queue_len--; - list_del(page_deferred_list(page)); + list_del(&folio->_deferred_list); } spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags); free_compound_page(page); @@ -2816,38 +2815,39 @@ void free_transhuge_page(struct page *page) void deferred_split_huge_page(struct page *page) { + struct folio *folio = page_folio(page); struct deferred_split *ds_queue = get_deferred_split_queue(page); #ifdef CONFIG_MEMCG - struct mem_cgroup *memcg = page_memcg(compound_head(page)); + struct mem_cgroup *memcg = folio_memcg(folio); #endif unsigned long flags; - VM_BUG_ON_PAGE(!PageTransHuge(page), page); + VM_BUG_ON_FOLIO(folio_order(folio) < 2, folio); /* * The try_to_unmap() in page reclaim path might reach here too, * this may cause a race condition to corrupt deferred split queue. - * And, if page reclaim is already handling the same page, it is + * And, if page reclaim is already handling the same folio, it is * unnecessary to handle it again in shrinker. * - * Check PageSwapCache to determine if the page is being - * handled by page reclaim since THP swap would add the page into + * Check the swapcache flag to determine if the folio is being + * handled by page reclaim since THP swap would add the folio into * swap cache before calling try_to_unmap(). */ - if (PageSwapCache(page)) + if (folio_test_swapcache(folio)) return; - if (!list_empty(page_deferred_list(page))) + if (!list_empty(&folio->_deferred_list)) return; spin_lock_irqsave(&ds_queue->split_queue_lock, flags); - if (list_empty(page_deferred_list(page))) { + if (list_empty(&folio->_deferred_list)) { count_vm_event(THP_DEFERRED_SPLIT_PAGE); - list_add_tail(page_deferred_list(page), &ds_queue->split_queue); + list_add_tail(&folio->_deferred_list, &ds_queue->split_queue); ds_queue->split_queue_len++; #ifdef CONFIG_MEMCG if (memcg) - set_shrinker_bit(memcg, page_to_nid(page), + set_shrinker_bit(memcg, folio_nid(folio), deferred_split_shrinker.id); #endif } -- cgit v1.2.3 From f158ed6195ef949060811fd85086928470651944 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox (Oracle) Date: Wed, 11 Jan 2023 14:29:13 +0000 Subject: mm: convert deferred_split_huge_page() to deferred_split_folio() Now that both callers use a folio, pass the folio in and save a call to compound_head(). Link: https://lkml.kernel.org/r/20230111142915.1001531-28-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- Documentation/mm/transhuge.rst | 6 +++--- include/linux/huge_mm.h | 4 ++-- mm/huge_memory.c | 3 +-- mm/rmap.c | 2 +- 4 files changed, 7 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/Documentation/mm/transhuge.rst b/Documentation/mm/transhuge.rst index 03bbd0a19041..a9608fe51649 100644 --- a/Documentation/mm/transhuge.rst +++ b/Documentation/mm/transhuge.rst @@ -153,8 +153,8 @@ clear where references should go after split: it will stay on the head page. Note that split_huge_pmd() doesn't have any limitations on refcounting: pmd can be split at any point and never fails. -Partial unmap and deferred_split_huge_page() -============================================ +Partial unmap and deferred_split_folio() +======================================== Unmapping part of THP (with munmap() or other way) is not going to free memory immediately. Instead, we detect that a subpage of THP is not in use @@ -166,6 +166,6 @@ the place where we can detect partial unmap. It also might be counterproductive since in many cases partial unmap happens during exit(2) if a THP crosses a VMA boundary. -The function deferred_split_huge_page() is used to queue a page for splitting. +The function deferred_split_folio() is used to queue a folio for splitting. The splitting itself will happen when we get memory pressure via shrinker interface. diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index b9978978a160..70bd867eba94 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -187,7 +187,7 @@ static inline int split_huge_page(struct page *page) { return split_huge_page_to_list(page, NULL); } -void deferred_split_huge_page(struct page *page); +void deferred_split_folio(struct folio *folio); void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long address, bool freeze, struct folio *folio); @@ -340,7 +340,7 @@ static inline int split_huge_page(struct page *page) { return 0; } -static inline void deferred_split_huge_page(struct page *page) {} +static inline void deferred_split_folio(struct folio *folio) {} #define split_huge_pmd(__vma, __pmd, __address) \ do { } while (0) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index c23b0e01734b..868fcccdff72 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2815,9 +2815,8 @@ void free_transhuge_page(struct page *page) free_compound_page(page); } -void deferred_split_huge_page(struct page *page) +void deferred_split_folio(struct folio *folio) { - struct folio *folio = page_folio(page); struct deferred_split *ds_queue = get_deferred_split_queue(folio); #ifdef CONFIG_MEMCG struct mem_cgroup *memcg = folio_memcg(folio); diff --git a/mm/rmap.c b/mm/rmap.c index 0020474f46c1..a079d9964b9c 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1427,7 +1427,7 @@ void page_remove_rmap(struct page *page, struct vm_area_struct *vma, */ if (folio_test_pmd_mappable(folio) && folio_test_anon(folio)) if (!compound || nr < nr_pmdmapped) - deferred_split_huge_page(&folio->page); + deferred_split_folio(folio); } /* -- cgit v1.2.3 From 6a171c16e62f854e6a7e0f837dbe8f3ace0f00ce Mon Sep 17 00:00:00 2001 From: Sidhartha Kumar Date: Wed, 11 Jan 2023 14:29:14 +0000 Subject: mm: remove the hugetlb field from struct page Patch series "Get rid of tail page fields". Continue the shrinkage of the struct page definition by getting rid of the 'first tail page' and 'second tail page' fields. I originally did this patch set before Hugh's rewrite of the subpages_mapcount, so it needed substantial updates; hope I didn't miss anything. This patch (of 28): commit dad6a5eb5556(mm,hugetlb: use folio fields in second tail page) added a transitional hugetlb field to struct page and struct folio to make room for another int in the first tail of a compound page. Hugetlb folio conversions have changed all page users of this field to use the fields within the folio so struct page no longer needs this hugetlb specific field. Link: https://lkml.kernel.org/r/20230111142915.1001531-1-willy@infradead.org Link: https://lkml.kernel.org/r/20230111142915.1001531-29-willy@infradead.org Signed-off-by: Sidhartha Kumar Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- include/linux/mm_types.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 7eb4d0815a78..452920467223 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -141,14 +141,6 @@ struct page { struct { /* Tail pages of compound page */ unsigned long compound_head; /* Bit zero is set */ }; - struct { /* Second tail page of hugetlb page */ - unsigned long _hugetlb_pad_1; /* compound_head */ - void *hugetlb_subpool; - void *hugetlb_cgroup; - void *hugetlb_cgroup_rsvd; - void *hugetlb_hwpoison; - /* No more space on 32-bit: use third tail if more */ - }; struct { /* Page table pages */ unsigned long _pt_pad_1; /* compound_head */ pgtable_t pmd_huge_pte; /* protected by page->ptl */ @@ -399,10 +391,6 @@ FOLIO_MATCH(compound_head, _head_1); offsetof(struct page, pg) + 2 * sizeof(struct page)) FOLIO_MATCH(flags, _flags_2); FOLIO_MATCH(compound_head, _head_2); -FOLIO_MATCH(hugetlb_subpool, _hugetlb_subpool); -FOLIO_MATCH(hugetlb_cgroup, _hugetlb_cgroup); -FOLIO_MATCH(hugetlb_cgroup_rsvd, _hugetlb_cgroup_rsvd); -FOLIO_MATCH(hugetlb_hwpoison, _hugetlb_hwpoison); #undef FOLIO_MATCH /* -- cgit v1.2.3 From 2ff6cecee669bf0fc63eadebac8cfc81f74b9a4c Mon Sep 17 00:00:00 2001 From: Sidhartha Kumar Date: Thu, 12 Jan 2023 14:46:03 -0600 Subject: mm/memory-failure: convert hugetlb_clear_page_hwpoison to folios Change hugetlb_clear_page_hwpoison() to folio_clear_hugetlb_hwpoison() by changing the function to take in a folio. This converts one use of ClearPageHWPoison and HPageRawHwpUnreliable to their folio equivalents. Link: https://lkml.kernel.org/r/20230112204608.80136-4-sidhartha.kumar@oracle.com Signed-off-by: Sidhartha Kumar Acked-by: Naoya Horiguchi Cc: Matthew Wilcox Cc: Miaohe Lin Signed-off-by: Andrew Morton --- include/linux/hugetlb.h | 4 ++-- mm/hugetlb.c | 2 +- mm/memory-failure.c | 10 +++++----- 3 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 7d6413c3b8f5..cf60fe741c1d 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -878,9 +878,9 @@ extern int dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn); #ifdef CONFIG_MEMORY_FAILURE -extern void hugetlb_clear_page_hwpoison(struct page *hpage); +extern void folio_clear_hugetlb_hwpoison(struct folio *folio); #else -static inline void hugetlb_clear_page_hwpoison(struct page *hpage) +static inline void folio_clear_hugetlb_hwpoison(struct folio *folio) { } #endif diff --git a/mm/hugetlb.c b/mm/hugetlb.c index ca9e177b9c54..291ad4cb02f9 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1731,7 +1731,7 @@ static void __update_and_free_page(struct hstate *h, struct page *page) * which makes any healthy subpages reusable. */ if (unlikely(folio_test_hwpoison(folio))) - hugetlb_clear_page_hwpoison(&folio->page); + folio_clear_hugetlb_hwpoison(folio); for (i = 0; i < pages_per_huge_page(h); i++) { subpage = folio_page(folio, i); diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 19f6035608d5..d4aaed2756af 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1785,12 +1785,12 @@ static unsigned long free_raw_hwp_pages(struct page *hpage, bool move_flag) return __free_raw_hwp_pages(hpage, move_flag); } -void hugetlb_clear_page_hwpoison(struct page *hpage) +void folio_clear_hugetlb_hwpoison(struct folio *folio) { - if (HPageRawHwpUnreliable(hpage)) + if (folio_test_hugetlb_raw_hwp_unreliable(folio)) return; - ClearPageHWPoison(hpage); - free_raw_hwp_pages(hpage, true); + folio_clear_hwpoison(folio); + free_raw_hwp_pages(&folio->page, true); } /* @@ -1889,7 +1889,7 @@ retry: folio_lock(folio); if (hwpoison_filter(p)) { - hugetlb_clear_page_hwpoison(&folio->page); + folio_clear_hugetlb_hwpoison(folio); if (migratable_cleared) folio_set_hugetlb_migratable(folio); folio_unlock(folio); -- cgit v1.2.3 From 8115612883978069fee8793f873a627ff5868718 Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Thu, 12 Jan 2023 12:39:28 +0000 Subject: mm: pagevec: add folio_batch_reinit() Patch series "update mlock to use folios", v4. This series updates mlock to use folios, converting the internal interface to using folios exclusively and exposing the folio interface externally. As a product of this we move to using a folio batch rather than a pagevec for mlock folios, which brings it in line with the core folio batches contained in mm/swap.c. This patch (of 5): This performs the same task as pagevec_reinit(), only modifying a folio batch rather than a pagevec. Link: https://lkml.kernel.org/r/cover.1673526881.git.lstoakes@gmail.com Link: https://lkml.kernel.org/r/9018cecacb39e34c883540f997f9be8281153613.1673526881.git.lstoakes@gmail.com Signed-off-by: Lorenzo Stoakes Acked-by: Vlastimil Babka Cc: Christian Brauner Cc: Geert Uytterhoeven Cc: Hugh Dickins Cc: Joel Fernandes (Google) Cc: Jonathan Corbet Cc: Liam R. Howlett Cc: Matthew Wilcox Cc: Mike Rapoport (IBM) Cc: William Kucharski Signed-off-by: Andrew Morton --- include/linux/pagevec.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h index 215eb6c3bdc9..2a6f61a0c10a 100644 --- a/include/linux/pagevec.h +++ b/include/linux/pagevec.h @@ -103,6 +103,11 @@ static inline void folio_batch_init(struct folio_batch *fbatch) fbatch->percpu_pvec_drained = false; } +static inline void folio_batch_reinit(struct folio_batch *fbatch) +{ + fbatch->nr = 0; +} + static inline unsigned int folio_batch_count(struct folio_batch *fbatch) { return fbatch->nr; -- cgit v1.2.3 From 950fe885a89770619e315f9b46301eebf0aab7b3 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 13 Jan 2023 18:10:26 +0100 Subject: mm: remove __HAVE_ARCH_PTE_SWP_EXCLUSIVE __HAVE_ARCH_PTE_SWP_EXCLUSIVE is now supported by all architectures that support swp PTEs, so let's drop it. Link: https://lkml.kernel.org/r/20230113171026.582290-27-david@redhat.com Signed-off-by: David Hildenbrand Signed-off-by: Andrew Morton --- arch/alpha/include/asm/pgtable.h | 1 - arch/arc/include/asm/pgtable-bits-arcv2.h | 1 - arch/arm/include/asm/pgtable.h | 1 - arch/arm64/include/asm/pgtable.h | 1 - arch/csky/include/asm/pgtable.h | 1 - arch/hexagon/include/asm/pgtable.h | 1 - arch/ia64/include/asm/pgtable.h | 1 - arch/loongarch/include/asm/pgtable.h | 1 - arch/m68k/include/asm/mcf_pgtable.h | 1 - arch/m68k/include/asm/motorola_pgtable.h | 1 - arch/m68k/include/asm/sun3_pgtable.h | 1 - arch/microblaze/include/asm/pgtable.h | 1 - arch/mips/include/asm/pgtable.h | 1 - arch/nios2/include/asm/pgtable.h | 1 - arch/openrisc/include/asm/pgtable.h | 1 - arch/parisc/include/asm/pgtable.h | 1 - arch/powerpc/include/asm/book3s/32/pgtable.h | 1 - arch/powerpc/include/asm/book3s/64/pgtable.h | 1 - arch/powerpc/include/asm/nohash/pgtable.h | 1 - arch/riscv/include/asm/pgtable.h | 1 - arch/s390/include/asm/pgtable.h | 1 - arch/sh/include/asm/pgtable_32.h | 1 - arch/sparc/include/asm/pgtable_32.h | 1 - arch/sparc/include/asm/pgtable_64.h | 1 - arch/um/include/asm/pgtable.h | 1 - arch/x86/include/asm/pgtable.h | 1 - arch/xtensa/include/asm/pgtable.h | 1 - include/linux/pgtable.h | 29 ---------------------------- mm/debug_vm_pgtable.c | 2 -- mm/memory.c | 4 ---- mm/rmap.c | 11 ----------- 31 files changed, 73 deletions(-) (limited to 'include/linux') diff --git a/arch/alpha/include/asm/pgtable.h b/arch/alpha/include/asm/pgtable.h index 970abf511b13..ba43cb841d19 100644 --- a/arch/alpha/include/asm/pgtable.h +++ b/arch/alpha/include/asm/pgtable.h @@ -328,7 +328,6 @@ extern inline pte_t mk_swap_pte(unsigned long type, unsigned long offset) #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) #define __swp_entry_to_pte(x) ((pte_t) { (x).val }) -#define __HAVE_ARCH_PTE_SWP_EXCLUSIVE static inline int pte_swp_exclusive(pte_t pte) { return pte_val(pte) & _PAGE_SWP_EXCLUSIVE; diff --git a/arch/arc/include/asm/pgtable-bits-arcv2.h b/arch/arc/include/asm/pgtable-bits-arcv2.h index 611f412713b9..6e9f8ca6d6a1 100644 --- a/arch/arc/include/asm/pgtable-bits-arcv2.h +++ b/arch/arc/include/asm/pgtable-bits-arcv2.h @@ -132,7 +132,6 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) #define __swp_entry_to_pte(x) ((pte_t) { (x).val }) -#define __HAVE_ARCH_PTE_SWP_EXCLUSIVE static inline int pte_swp_exclusive(pte_t pte) { return pte_val(pte) & _PAGE_SWP_EXCLUSIVE; diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h index 886c275995a2..2e626e6da9a3 100644 --- a/arch/arm/include/asm/pgtable.h +++ b/arch/arm/include/asm/pgtable.h @@ -298,7 +298,6 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) #define __swp_entry_to_pte(swp) __pte((swp).val) -#define __HAVE_ARCH_PTE_SWP_EXCLUSIVE static inline int pte_swp_exclusive(pte_t pte) { return pte_isset(pte, L_PTE_SWP_EXCLUSIVE); diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 65e78999c75d..575c63de894f 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -417,7 +417,6 @@ static inline pgprot_t mk_pmd_sect_prot(pgprot_t prot) return __pgprot((pgprot_val(prot) & ~PMD_TABLE_BIT) | PMD_TYPE_SECT); } -#define __HAVE_ARCH_PTE_SWP_EXCLUSIVE static inline pte_t pte_swp_mkexclusive(pte_t pte) { return set_pte_bit(pte, __pgprot(PTE_SWP_EXCLUSIVE)); diff --git a/arch/csky/include/asm/pgtable.h b/arch/csky/include/asm/pgtable.h index 574c97b9ecca..d4042495febc 100644 --- a/arch/csky/include/asm/pgtable.h +++ b/arch/csky/include/asm/pgtable.h @@ -200,7 +200,6 @@ static inline pte_t pte_mkyoung(pte_t pte) return pte; } -#define __HAVE_ARCH_PTE_SWP_EXCLUSIVE static inline int pte_swp_exclusive(pte_t pte) { return pte_val(pte) & _PAGE_SWP_EXCLUSIVE; diff --git a/arch/hexagon/include/asm/pgtable.h b/arch/hexagon/include/asm/pgtable.h index 7eb008e477c8..59393613d086 100644 --- a/arch/hexagon/include/asm/pgtable.h +++ b/arch/hexagon/include/asm/pgtable.h @@ -397,7 +397,6 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd) (((type & 0x1f) << 1) | \ ((offset & 0x3ffff8) << 10) | ((offset & 0x7) << 7)) }) -#define __HAVE_ARCH_PTE_SWP_EXCLUSIVE static inline int pte_swp_exclusive(pte_t pte) { return pte_val(pte) & _PAGE_SWP_EXCLUSIVE; diff --git a/arch/ia64/include/asm/pgtable.h b/arch/ia64/include/asm/pgtable.h index e4b8ab931399..21c97e31a28a 100644 --- a/arch/ia64/include/asm/pgtable.h +++ b/arch/ia64/include/asm/pgtable.h @@ -424,7 +424,6 @@ extern void paging_init (void); #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) #define __swp_entry_to_pte(x) ((pte_t) { (x).val }) -#define __HAVE_ARCH_PTE_SWP_EXCLUSIVE static inline int pte_swp_exclusive(pte_t pte) { return pte_val(pte) & _PAGE_SWP_EXCLUSIVE; diff --git a/arch/loongarch/include/asm/pgtable.h b/arch/loongarch/include/asm/pgtable.h index c6b8fe7ac43c..d28fb9dbec59 100644 --- a/arch/loongarch/include/asm/pgtable.h +++ b/arch/loongarch/include/asm/pgtable.h @@ -276,7 +276,6 @@ static inline pte_t mk_swap_pte(unsigned long type, unsigned long offset) #define __pmd_to_swp_entry(pmd) ((swp_entry_t) { pmd_val(pmd) }) #define __swp_entry_to_pmd(x) ((pmd_t) { (x).val | _PAGE_HUGE }) -#define __HAVE_ARCH_PTE_SWP_EXCLUSIVE static inline int pte_swp_exclusive(pte_t pte) { return pte_val(pte) & _PAGE_SWP_EXCLUSIVE; diff --git a/arch/m68k/include/asm/mcf_pgtable.h b/arch/m68k/include/asm/mcf_pgtable.h index e573d7b649f7..13741c1245e1 100644 --- a/arch/m68k/include/asm/mcf_pgtable.h +++ b/arch/m68k/include/asm/mcf_pgtable.h @@ -275,7 +275,6 @@ extern pgd_t kernel_pg_dir[PTRS_PER_PGD]; #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) #define __swp_entry_to_pte(x) (__pte((x).val)) -#define __HAVE_ARCH_PTE_SWP_EXCLUSIVE static inline int pte_swp_exclusive(pte_t pte) { return pte_val(pte) & _PAGE_SWP_EXCLUSIVE; diff --git a/arch/m68k/include/asm/motorola_pgtable.h b/arch/m68k/include/asm/motorola_pgtable.h index c1782563e793..ec0dc19ab834 100644 --- a/arch/m68k/include/asm/motorola_pgtable.h +++ b/arch/m68k/include/asm/motorola_pgtable.h @@ -190,7 +190,6 @@ extern pgd_t kernel_pg_dir[128]; #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) #define __swp_entry_to_pte(x) ((pte_t) { (x).val }) -#define __HAVE_ARCH_PTE_SWP_EXCLUSIVE static inline int pte_swp_exclusive(pte_t pte) { return pte_val(pte) & _PAGE_SWP_EXCLUSIVE; diff --git a/arch/m68k/include/asm/sun3_pgtable.h b/arch/m68k/include/asm/sun3_pgtable.h index dbfc9703b15d..e582b0484a55 100644 --- a/arch/m68k/include/asm/sun3_pgtable.h +++ b/arch/m68k/include/asm/sun3_pgtable.h @@ -174,7 +174,6 @@ extern pgd_t kernel_pg_dir[PTRS_PER_PGD]; #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) #define __swp_entry_to_pte(x) ((pte_t) { (x).val }) -#define __HAVE_ARCH_PTE_SWP_EXCLUSIVE static inline int pte_swp_exclusive(pte_t pte) { return pte_val(pte) & _PAGE_SWP_EXCLUSIVE; diff --git a/arch/microblaze/include/asm/pgtable.h b/arch/microblaze/include/asm/pgtable.h index 7e3de54bf426..d1b8272abcd9 100644 --- a/arch/microblaze/include/asm/pgtable.h +++ b/arch/microblaze/include/asm/pgtable.h @@ -412,7 +412,6 @@ extern pgd_t swapper_pg_dir[PTRS_PER_PGD]; #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) >> 2 }) #define __swp_entry_to_pte(x) ((pte_t) { (x).val << 2 }) -#define __HAVE_ARCH_PTE_SWP_EXCLUSIVE static inline int pte_swp_exclusive(pte_t pte) { return pte_val(pte) & _PAGE_SWP_EXCLUSIVE; diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h index 711874cee8e4..791389bf3c12 100644 --- a/arch/mips/include/asm/pgtable.h +++ b/arch/mips/include/asm/pgtable.h @@ -528,7 +528,6 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) } #endif -#define __HAVE_ARCH_PTE_SWP_EXCLUSIVE #if defined(CONFIG_PHYS_ADDR_T_64BIT) && defined(CONFIG_CPU_MIPS32) static inline int pte_swp_exclusive(pte_t pte) { diff --git a/arch/nios2/include/asm/pgtable.h b/arch/nios2/include/asm/pgtable.h index 05999da01731..0f5c2564e9f5 100644 --- a/arch/nios2/include/asm/pgtable.h +++ b/arch/nios2/include/asm/pgtable.h @@ -253,7 +253,6 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd) #define __swp_entry_to_pte(swp) ((pte_t) { (swp).val }) #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) -#define __HAVE_ARCH_PTE_SWP_EXCLUSIVE static inline int pte_swp_exclusive(pte_t pte) { return pte_val(pte) & _PAGE_SWP_EXCLUSIVE; diff --git a/arch/openrisc/include/asm/pgtable.h b/arch/openrisc/include/asm/pgtable.h index 903b32d662ab..3eb9b9555d0d 100644 --- a/arch/openrisc/include/asm/pgtable.h +++ b/arch/openrisc/include/asm/pgtable.h @@ -408,7 +408,6 @@ static inline void update_mmu_cache(struct vm_area_struct *vma, #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) #define __swp_entry_to_pte(x) ((pte_t) { (x).val }) -#define __HAVE_ARCH_PTE_SWP_EXCLUSIVE static inline int pte_swp_exclusive(pte_t pte) { return pte_val(pte) & _PAGE_SWP_EXCLUSIVE; diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h index 3033bb88df34..e2950f5db7c9 100644 --- a/arch/parisc/include/asm/pgtable.h +++ b/arch/parisc/include/asm/pgtable.h @@ -422,7 +422,6 @@ extern void paging_init (void); #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) #define __swp_entry_to_pte(x) ((pte_t) { (x).val }) -#define __HAVE_ARCH_PTE_SWP_EXCLUSIVE static inline int pte_swp_exclusive(pte_t pte) { return pte_val(pte) & _PAGE_SWP_EXCLUSIVE; diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h index 0ecb3a58f23f..7bf1fe7297c6 100644 --- a/arch/powerpc/include/asm/book3s/32/pgtable.h +++ b/arch/powerpc/include/asm/book3s/32/pgtable.h @@ -386,7 +386,6 @@ static inline void __ptep_set_access_flags(struct vm_area_struct *vma, #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) >> 3 }) #define __swp_entry_to_pte(x) ((pte_t) { (x).val << 3 }) -#define __HAVE_ARCH_PTE_SWP_EXCLUSIVE static inline int pte_swp_exclusive(pte_t pte) { return pte_val(pte) & _PAGE_SWP_EXCLUSIVE; diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index cb4c67bf45d7..4acc9690f599 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -717,7 +717,6 @@ static inline pte_t pte_swp_clear_soft_dirty(pte_t pte) } #endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */ -#define __HAVE_ARCH_PTE_SWP_EXCLUSIVE static inline pte_t pte_swp_mkexclusive(pte_t pte) { return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_SWP_EXCLUSIVE)); diff --git a/arch/powerpc/include/asm/nohash/pgtable.h b/arch/powerpc/include/asm/nohash/pgtable.h index 5f4620940c2c..a6caaaab6f92 100644 --- a/arch/powerpc/include/asm/nohash/pgtable.h +++ b/arch/powerpc/include/asm/nohash/pgtable.h @@ -151,7 +151,6 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) return __pte((pte_val(pte) & _PAGE_CHG_MASK) | pgprot_val(newprot)); } -#define __HAVE_ARCH_PTE_SWP_EXCLUSIVE static inline int pte_swp_exclusive(pte_t pte) { return pte_val(pte) & _PAGE_SWP_EXCLUSIVE; diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 03a4728db039..5b9f409a940d 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -752,7 +752,6 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma, #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) #define __swp_entry_to_pte(x) ((pte_t) { (x).val }) -#define __HAVE_ARCH_PTE_SWP_EXCLUSIVE static inline int pte_swp_exclusive(pte_t pte) { return pte_val(pte) & _PAGE_SWP_EXCLUSIVE; diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index b26cbf1c533c..2b5db99e31dd 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -812,7 +812,6 @@ static inline int pmd_protnone(pmd_t pmd) } #endif -#define __HAVE_ARCH_PTE_SWP_EXCLUSIVE static inline int pte_swp_exclusive(pte_t pte) { return pte_val(pte) & _PAGE_SWP_EXCLUSIVE; diff --git a/arch/sh/include/asm/pgtable_32.h b/arch/sh/include/asm/pgtable_32.h index c34aa795a9d2..21952b094650 100644 --- a/arch/sh/include/asm/pgtable_32.h +++ b/arch/sh/include/asm/pgtable_32.h @@ -479,7 +479,6 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd) /* In both cases, we borrow bit 6 to store the exclusive marker in swap PTEs. */ #define _PAGE_SWP_EXCLUSIVE _PAGE_USER -#define __HAVE_ARCH_PTE_SWP_EXCLUSIVE static inline int pte_swp_exclusive(pte_t pte) { return pte.pte_low & _PAGE_SWP_EXCLUSIVE; diff --git a/arch/sparc/include/asm/pgtable_32.h b/arch/sparc/include/asm/pgtable_32.h index abf7a2601209..d4330e3c57a6 100644 --- a/arch/sparc/include/asm/pgtable_32.h +++ b/arch/sparc/include/asm/pgtable_32.h @@ -353,7 +353,6 @@ static inline swp_entry_t __swp_entry(unsigned long type, unsigned long offset) #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) #define __swp_entry_to_pte(x) ((pte_t) { (x).val }) -#define __HAVE_ARCH_PTE_SWP_EXCLUSIVE static inline int pte_swp_exclusive(pte_t pte) { return pte_val(pte) & SRMMU_SWP_EXCLUSIVE; diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h index a1658eebd036..2dc8d4641734 100644 --- a/arch/sparc/include/asm/pgtable_64.h +++ b/arch/sparc/include/asm/pgtable_64.h @@ -989,7 +989,6 @@ pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp); #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) #define __swp_entry_to_pte(x) ((pte_t) { (x).val }) -#define __HAVE_ARCH_PTE_SWP_EXCLUSIVE static inline int pte_swp_exclusive(pte_t pte) { return pte_val(pte) & _PAGE_SWP_EXCLUSIVE; diff --git a/arch/um/include/asm/pgtable.h b/arch/um/include/asm/pgtable.h index cedc5fd451ce..a70d1618eb35 100644 --- a/arch/um/include/asm/pgtable.h +++ b/arch/um/include/asm/pgtable.h @@ -313,7 +313,6 @@ extern pte_t *virt_to_pte(struct mm_struct *mm, unsigned long addr); ((swp_entry_t) { pte_val(pte_mkuptodate(pte)) }) #define __swp_entry_to_pte(x) ((pte_t) { (x).val }) -#define __HAVE_ARCH_PTE_SWP_EXCLUSIVE static inline int pte_swp_exclusive(pte_t pte) { return pte_get_bits(pte, _PAGE_SWP_EXCLUSIVE); diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index d25195726b78..7425f32e5293 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -1299,7 +1299,6 @@ static inline void update_mmu_cache_pud(struct vm_area_struct *vma, unsigned long addr, pud_t *pud) { } -#define __HAVE_ARCH_PTE_SWP_EXCLUSIVE static inline pte_t pte_swp_mkexclusive(pte_t pte) { return pte_set_flags(pte, _PAGE_SWP_EXCLUSIVE); diff --git a/arch/xtensa/include/asm/pgtable.h b/arch/xtensa/include/asm/pgtable.h index 1025e2dc292b..fc7a14884c6c 100644 --- a/arch/xtensa/include/asm/pgtable.h +++ b/arch/xtensa/include/asm/pgtable.h @@ -360,7 +360,6 @@ ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) #define __swp_entry_to_pte(x) ((pte_t) { (x).val }) -#define __HAVE_ARCH_PTE_SWP_EXCLUSIVE static inline int pte_swp_exclusive(pte_t pte) { return pte_val(pte) & _PAGE_SWP_EXCLUSIVE; diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 1159b25b0542..5fd45454c073 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -1064,35 +1064,6 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot) #define arch_start_context_switch(prev) do {} while (0) #endif -/* - * When replacing an anonymous page by a real (!non) swap entry, we clear - * PG_anon_exclusive from the page and instead remember whether the flag was - * set in the swp pte. During fork(), we have to mark the entry as !exclusive - * (possibly shared). On swapin, we use that information to restore - * PG_anon_exclusive, which is very helpful in cases where we might have - * additional (e.g., FOLL_GET) references on a page and wouldn't be able to - * detect exclusivity. - * - * These functions don't apply to non-swap entries (e.g., migration, hwpoison, - * ...). - */ -#ifndef __HAVE_ARCH_PTE_SWP_EXCLUSIVE -static inline pte_t pte_swp_mkexclusive(pte_t pte) -{ - return pte; -} - -static inline int pte_swp_exclusive(pte_t pte) -{ - return false; -} - -static inline pte_t pte_swp_clear_exclusive(pte_t pte) -{ - return pte; -} -#endif - #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY #ifndef CONFIG_ARCH_ENABLE_THP_MIGRATION static inline pmd_t pmd_swp_mksoft_dirty(pmd_t pmd) diff --git a/mm/debug_vm_pgtable.c b/mm/debug_vm_pgtable.c index ff8d6f6af896..af59cc7bd307 100644 --- a/mm/debug_vm_pgtable.c +++ b/mm/debug_vm_pgtable.c @@ -810,7 +810,6 @@ static void __init pmd_swap_soft_dirty_tests(struct pgtable_debug_args *args) { static void __init pte_swap_exclusive_tests(struct pgtable_debug_args *args) { -#ifdef __HAVE_ARCH_PTE_SWP_EXCLUSIVE unsigned long max_swap_offset; swp_entry_t entry, entry2; pte_t pte; @@ -841,7 +840,6 @@ static void __init pte_swap_exclusive_tests(struct pgtable_debug_args *args) WARN_ON(!is_swap_pte(pte)); entry2 = pte_to_swp_entry(pte); WARN_ON(memcmp(&entry, &entry2, sizeof(entry))); -#endif /* __HAVE_ARCH_PTE_SWP_EXCLUSIVE */ } static void __init pte_swap_tests(struct pgtable_debug_args *args) diff --git a/mm/memory.c b/mm/memory.c index c6bacd58d032..87b33b4967c2 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3864,10 +3864,6 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) * the swap entry concurrently) for certainly exclusive pages. */ if (!folio_test_ksm(folio)) { - /* - * Note that pte_swp_exclusive() == false for architectures - * without __HAVE_ARCH_PTE_SWP_EXCLUSIVE. - */ exclusive = pte_swp_exclusive(vmf->orig_pte); if (folio != swapcache) { /* diff --git a/mm/rmap.c b/mm/rmap.c index 073999f78adf..0d07c500fc86 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1710,17 +1710,6 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, page_vma_mapped_walk_done(&pvmw); break; } - /* - * Note: We *don't* remember if the page was mapped - * exclusively in the swap pte if the architecture - * doesn't support __HAVE_ARCH_PTE_SWP_EXCLUSIVE. In - * that case, swapin code has to re-determine that - * manually and might detect the page as possibly - * shared, for example, if there are other references on - * the page or if the page is under writeback. We made - * sure that there are no GUP pins on the page that - * would rely on it, so for GUP pins this is fine. - */ if (list_empty(&mm->mmlist)) { spin_lock(&mmlist_lock); if (list_empty(&mm->mmlist)) -- cgit v1.2.3 From 6189eb82f0aec8a877190bf52e629c687ed02773 Mon Sep 17 00:00:00 2001 From: Pasha Tatashin Date: Fri, 13 Jan 2023 15:42:53 +0000 Subject: mm/page_ext: do not allocate space for page_ext->flags if not needed There is 8 byte page_ext->flags field allocated per page whenever CONFIG_PAGE_EXTENSION is enabled. However, not every user of page_ext uses flags. Therefore, check whether flags is needed at least by one user and if so allocate space for it. For example when page_table_check is enabled, on a machine with 128G of memory before the fix: [ 2.244288] allocated 536870912 bytes of page_ext after the fix: [ 2.160154] allocated 268435456 bytes of page_ext Also, add a kernel-doc comment before page_ext_operations that describes the fields, and remove check if need() is set, as that is now a required field. [pasha.tatashin@soleen.com: address comments from Mike Rapoport] Link: https://lkml.kernel.org/r/20230117202103.1412449-1-pasha.tatashin@soleen.com Link: https://lkml.kernel.org/r/20230113154253.92480-1-pasha.tatashin@soleen.com Signed-off-by: Pasha Tatashin Acked-by: David Hildenbrand Acked-by: Vlastimil Babka Acked-by: David Rientjes Reviewed-by: Mike Rapoport (IBM) Cc: Charan Teja Kalla Cc: Li Zhe Cc: Michal Hocko Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- include/linux/page_ext.h | 18 ++++++++++++++++++ mm/page_ext.c | 14 ++++++++++++-- mm/page_owner.c | 1 + mm/page_table_check.c | 1 + 4 files changed, 32 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h index 22be4582faae..67314f648aeb 100644 --- a/include/linux/page_ext.h +++ b/include/linux/page_ext.h @@ -7,15 +7,33 @@ #include struct pglist_data; + +/** + * struct page_ext_operations - per page_ext client operations + * @offset: Offset to the client's data within page_ext. Offset is returned to + * the client by page_ext_init. + * @size: The size of the client data within page_ext. + * @need: Function that returns true if client requires page_ext. + * @init: (optional) Called to initialize client once page_exts are allocated. + * @need_shared_flags: True when client is using shared page_ext->flags + * field. + * + * Each Page Extension client must define page_ext_operations in + * page_ext_ops array. + */ struct page_ext_operations { size_t offset; size_t size; bool (*need)(void); void (*init)(void); + bool need_shared_flags; }; #ifdef CONFIG_PAGE_EXTENSION +/* + * The page_ext_flags users must set need_shared_flags to true. + */ enum page_ext_flags { PAGE_EXT_OWNER, PAGE_EXT_OWNER_ALLOCATED, diff --git a/mm/page_ext.c b/mm/page_ext.c index 4ee522fd381c..e2c22ffdbb81 100644 --- a/mm/page_ext.c +++ b/mm/page_ext.c @@ -71,6 +71,7 @@ static bool need_page_idle(void) } static struct page_ext_operations page_idle_ops __initdata = { .need = need_page_idle, + .need_shared_flags = true, }; #endif @@ -86,7 +87,7 @@ static struct page_ext_operations *page_ext_ops[] __initdata = { #endif }; -unsigned long page_ext_size = sizeof(struct page_ext); +unsigned long page_ext_size; static unsigned long total_usage; static struct page_ext *lookup_page_ext(const struct page *page); @@ -106,7 +107,16 @@ static bool __init invoke_need_callbacks(void) bool need = false; for (i = 0; i < entries; i++) { - if (page_ext_ops[i]->need && page_ext_ops[i]->need()) { + if (page_ext_ops[i]->need()) { + if (page_ext_ops[i]->need_shared_flags) { + page_ext_size = sizeof(struct page_ext); + break; + } + } + } + + for (i = 0; i < entries; i++) { + if (page_ext_ops[i]->need()) { page_ext_ops[i]->offset = page_ext_size; page_ext_size += page_ext_ops[i]->size; need = true; diff --git a/mm/page_owner.c b/mm/page_owner.c index 2d27f532df4c..f0553bedb39d 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -99,6 +99,7 @@ struct page_ext_operations page_owner_ops = { .size = sizeof(struct page_owner), .need = need_page_owner, .init = init_page_owner, + .need_shared_flags = true, }; static inline struct page_owner *get_page_owner(struct page_ext *page_ext) diff --git a/mm/page_table_check.c b/mm/page_table_check.c index 93e633c1d587..25d8610c0042 100644 --- a/mm/page_table_check.c +++ b/mm/page_table_check.c @@ -45,6 +45,7 @@ struct page_ext_operations page_table_check_ops = { .size = sizeof(struct page_table_check), .need = need_page_table_check, .init = init_page_table_check, + .need_shared_flags = false, }; static struct page_table_check *get_page_table_check(struct page_ext *page_ext) -- cgit v1.2.3 From 2973d8229b78d3f148e0c45916a1e8b237dc6167 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Fri, 13 Jan 2023 11:12:17 +0000 Subject: mm: discard __GFP_ATOMIC __GFP_ATOMIC serves little purpose. Its main effect is to set ALLOC_HARDER which adds a few little boosts to increase the chance of an allocation succeeding, one of which is to lower the water-mark at which it will succeed. It is *always* paired with __GFP_HIGH which sets ALLOC_HIGH which also adjusts this watermark. It is probable that other users of __GFP_HIGH should benefit from the other little bonuses that __GFP_ATOMIC gets. __GFP_ATOMIC also gives a warning if used with __GFP_DIRECT_RECLAIM. There is little point to this. We already get a might_sleep() warning if __GFP_DIRECT_RECLAIM is set. __GFP_ATOMIC allows the "watermark_boost" to be side-stepped. It is probable that testing ALLOC_HARDER is a better fit here. __GFP_ATOMIC is used by tegra-smmu.c to check if the allocation might sleep. This should test __GFP_DIRECT_RECLAIM instead. This patch: - removes __GFP_ATOMIC - allows __GFP_HIGH allocations to ignore watermark boosting as well as GFP_ATOMIC requests. - makes other adjustments as suggested by the above. The net result is not change to GFP_ATOMIC allocations. Other allocations that use __GFP_HIGH will benefit from a few different extra privileges. This affects: xen, dm, md, ntfs3 the vermillion frame buffer hibernation ksm swap all of which likely produce more benefit than cost if these selected allocation are more likely to succeed quickly. [mgorman: Minor adjustments to rework on top of a series] Link: https://lkml.kernel.org/r/163712397076.13692.4727608274002939094@noble.neil.brown.name Link: https://lkml.kernel.org/r/20230113111217.14134-7-mgorman@techsingularity.net Signed-off-by: NeilBrown Signed-off-by: Mel Gorman Acked-by: Vlastimil Babka Acked-by: Michal Hocko Cc: Matthew Wilcox Cc: Thierry Reding Signed-off-by: Andrew Morton --- Documentation/mm/balance.rst | 2 +- drivers/iommu/tegra-smmu.c | 4 ++-- include/linux/gfp_types.h | 12 ++++-------- include/trace/events/mmflags.h | 1 - lib/test_printf.c | 8 ++++---- mm/internal.h | 2 +- mm/page_alloc.c | 13 +++---------- tools/perf/builtin-kmem.c | 1 - 8 files changed, 15 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/Documentation/mm/balance.rst b/Documentation/mm/balance.rst index 6a1fadf3e173..e38e9d83c1c7 100644 --- a/Documentation/mm/balance.rst +++ b/Documentation/mm/balance.rst @@ -6,7 +6,7 @@ Memory Balancing Started Jan 2000 by Kanoj Sarcar -Memory balancing is needed for !__GFP_ATOMIC and !__GFP_KSWAPD_RECLAIM as +Memory balancing is needed for !__GFP_HIGH and !__GFP_KSWAPD_RECLAIM as well as for non __GFP_IO allocations. The first reason why a caller may avoid reclaim is that the caller can not diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c index 5b1af40221ec..af8d0e685260 100644 --- a/drivers/iommu/tegra-smmu.c +++ b/drivers/iommu/tegra-smmu.c @@ -671,12 +671,12 @@ static struct page *as_get_pde_page(struct tegra_smmu_as *as, * allocate page in a sleeping context if GFP flags permit. Hence * spinlock needs to be unlocked and re-locked after allocation. */ - if (!(gfp & __GFP_ATOMIC)) + if (gfpflags_allow_blocking(gfp)) spin_unlock_irqrestore(&as->lock, *flags); page = alloc_page(gfp | __GFP_DMA | __GFP_ZERO); - if (!(gfp & __GFP_ATOMIC)) + if (gfpflags_allow_blocking(gfp)) spin_lock_irqsave(&as->lock, *flags); /* diff --git a/include/linux/gfp_types.h b/include/linux/gfp_types.h index d88c46ca82e1..5088637fe5c2 100644 --- a/include/linux/gfp_types.h +++ b/include/linux/gfp_types.h @@ -31,7 +31,7 @@ typedef unsigned int __bitwise gfp_t; #define ___GFP_IO 0x40u #define ___GFP_FS 0x80u #define ___GFP_ZERO 0x100u -#define ___GFP_ATOMIC 0x200u +/* 0x200u unused */ #define ___GFP_DIRECT_RECLAIM 0x400u #define ___GFP_KSWAPD_RECLAIM 0x800u #define ___GFP_WRITE 0x1000u @@ -116,11 +116,8 @@ typedef unsigned int __bitwise gfp_t; * * %__GFP_HIGH indicates that the caller is high-priority and that granting * the request is necessary before the system can make forward progress. - * For example, creating an IO context to clean pages. - * - * %__GFP_ATOMIC indicates that the caller cannot reclaim or sleep and is - * high priority. Users are typically interrupt handlers. This may be - * used in conjunction with %__GFP_HIGH + * For example creating an IO context to clean pages and requests + * from atomic context. * * %__GFP_MEMALLOC allows access to all memory. This should only be used when * the caller guarantees the allocation will allow more memory to be freed @@ -135,7 +132,6 @@ typedef unsigned int __bitwise gfp_t; * %__GFP_NOMEMALLOC is used to explicitly forbid access to emergency reserves. * This takes precedence over the %__GFP_MEMALLOC flag if both are set. */ -#define __GFP_ATOMIC ((__force gfp_t)___GFP_ATOMIC) #define __GFP_HIGH ((__force gfp_t)___GFP_HIGH) #define __GFP_MEMALLOC ((__force gfp_t)___GFP_MEMALLOC) #define __GFP_NOMEMALLOC ((__force gfp_t)___GFP_NOMEMALLOC) @@ -329,7 +325,7 @@ typedef unsigned int __bitwise gfp_t; * version does not attempt reclaim/compaction at all and is by default used * in page fault path, while the non-light is used by khugepaged. */ -#define GFP_ATOMIC (__GFP_HIGH|__GFP_ATOMIC|__GFP_KSWAPD_RECLAIM) +#define GFP_ATOMIC (__GFP_HIGH|__GFP_KSWAPD_RECLAIM) #define GFP_KERNEL (__GFP_RECLAIM | __GFP_IO | __GFP_FS) #define GFP_KERNEL_ACCOUNT (GFP_KERNEL | __GFP_ACCOUNT) #define GFP_NOWAIT (__GFP_KSWAPD_RECLAIM) diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h index 412b5a46374c..9db52bc4ce19 100644 --- a/include/trace/events/mmflags.h +++ b/include/trace/events/mmflags.h @@ -31,7 +31,6 @@ gfpflag_string(__GFP_HIGHMEM), \ gfpflag_string(GFP_DMA32), \ gfpflag_string(__GFP_HIGH), \ - gfpflag_string(__GFP_ATOMIC), \ gfpflag_string(__GFP_IO), \ gfpflag_string(__GFP_FS), \ gfpflag_string(__GFP_NOWARN), \ diff --git a/lib/test_printf.c b/lib/test_printf.c index d34dc636b81c..46b4e6c414a3 100644 --- a/lib/test_printf.c +++ b/lib/test_printf.c @@ -674,17 +674,17 @@ flags(void) gfp = GFP_ATOMIC|__GFP_DMA; test("GFP_ATOMIC|GFP_DMA", "%pGg", &gfp); - gfp = __GFP_ATOMIC; - test("__GFP_ATOMIC", "%pGg", &gfp); + gfp = __GFP_HIGH; + test("__GFP_HIGH", "%pGg", &gfp); /* Any flags not translated by the table should remain numeric */ gfp = ~__GFP_BITS_MASK; snprintf(cmp_buffer, BUF_SIZE, "%#lx", (unsigned long) gfp); test(cmp_buffer, "%pGg", &gfp); - snprintf(cmp_buffer, BUF_SIZE, "__GFP_ATOMIC|%#lx", + snprintf(cmp_buffer, BUF_SIZE, "__GFP_HIGH|%#lx", (unsigned long) gfp); - gfp |= __GFP_ATOMIC; + gfp |= __GFP_HIGH; test(cmp_buffer, "%pGg", &gfp); kfree(cmp_buffer); diff --git a/mm/internal.h b/mm/internal.h index b0b88a95347f..2d09a7a0600a 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -24,7 +24,7 @@ struct folio_batch; #define GFP_RECLAIM_MASK (__GFP_RECLAIM|__GFP_HIGH|__GFP_IO|__GFP_FS|\ __GFP_NOWARN|__GFP_RETRY_MAYFAIL|__GFP_NOFAIL|\ __GFP_NORETRY|__GFP_MEMALLOC|__GFP_NOMEMALLOC|\ - __GFP_ATOMIC|__GFP_NOLOCKDEP) + __GFP_NOLOCKDEP) /* The GFP flags allowed during early boot */ #define GFP_BOOT_MASK (__GFP_BITS_MASK & ~(__GFP_RECLAIM|__GFP_IO|__GFP_FS)) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 18ca33a1945d..0cfad30fb44c 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4105,13 +4105,14 @@ static inline bool zone_watermark_fast(struct zone *z, unsigned int order, if (__zone_watermark_ok(z, order, mark, highest_zoneidx, alloc_flags, free_pages)) return true; + /* - * Ignore watermark boosting for GFP_ATOMIC order-0 allocations + * Ignore watermark boosting for __GFP_HIGH order-0 allocations * when checking the min watermark. The min watermark is the * point where boosting is ignored so that kswapd is woken up * when below the low watermark. */ - if (unlikely(!order && (gfp_mask & __GFP_ATOMIC) && z->watermark_boost + if (unlikely(!order && (alloc_flags & ALLOC_MIN_RESERVE) && z->watermark_boost && ((alloc_flags & ALLOC_WMARK_MASK) == WMARK_MIN))) { mark = z->_watermark[WMARK_MIN]; return __zone_watermark_ok(z, order, mark, highest_zoneidx, @@ -5076,14 +5077,6 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, unsigned int zonelist_iter_cookie; int reserve_flags; - /* - * We also sanity check to catch abuse of atomic reserves being used by - * callers that are not in atomic context. - */ - if (WARN_ON_ONCE((gfp_mask & (__GFP_ATOMIC|__GFP_DIRECT_RECLAIM)) == - (__GFP_ATOMIC|__GFP_DIRECT_RECLAIM))) - gfp_mask &= ~__GFP_ATOMIC; - restart: compaction_retries = 0; no_progress_loops = 0; diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index 8ae0a1535293..f3029742b800 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -653,7 +653,6 @@ static const struct { { "__GFP_HIGHMEM", "HM" }, { "GFP_DMA32", "D32" }, { "__GFP_HIGH", "H" }, - { "__GFP_ATOMIC", "_A" }, { "__GFP_IO", "I" }, { "__GFP_FS", "F" }, { "__GFP_NOWARN", "NWR" }, -- cgit v1.2.3 From 2cf1338454a8a9a0b3c1271ccb521afa2d6ae241 Mon Sep 17 00:00:00 2001 From: David Stevens Date: Fri, 13 Jan 2023 11:30:11 +0900 Subject: mm: fix khugepaged with shmem_enabled=advise Pass vm_flags as a parameter to shmem_is_huge, rather than reading the flags from the vm_area_struct in question. This allows the updated flags from hugepage_madvise to be passed to the check, which is necessary because madvise does not update the vm_area_struct's flags until after hugepage_madvise returns. This fixes an issue when shmem_enabled=madvise, where MADV_HUGEPAGE on shmem was not able to register the mm_struct with khugepaged. Prior to cd89fb065099, the mm_struct was registered by MADV_HUGEPAGE regardless of the value of shmem_enabled (which was only checked when scanning vmas). Link: https://lkml.kernel.org/r/20230113023011.1784015-1-stevensd@google.com Fixes: cd89fb065099 ("mm,thp,shmem: make khugepaged obey tmpfs mount flags") Signed-off-by: David Stevens Cc: David Stevens Cc: Hugh Dickins Cc: Rik van Riel Signed-off-by: Andrew Morton --- include/linux/shmem_fs.h | 10 ++-------- mm/huge_memory.c | 3 ++- mm/shmem.c | 18 +++++++++--------- 3 files changed, 13 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index d500ea967dc7..d09d54be4ffd 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -92,14 +92,8 @@ extern struct page *shmem_read_mapping_page_gfp(struct address_space *mapping, extern void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end); int shmem_unuse(unsigned int type); -extern bool shmem_is_huge(struct vm_area_struct *vma, struct inode *inode, - pgoff_t index, bool shmem_huge_force); -static inline bool shmem_huge_enabled(struct vm_area_struct *vma, - bool shmem_huge_force) -{ - return shmem_is_huge(vma, file_inode(vma->vm_file), vma->vm_pgoff, - shmem_huge_force); -} +extern bool shmem_is_huge(struct inode *inode, pgoff_t index, bool shmem_huge_force, + struct mm_struct *mm, unsigned long vm_flags); extern unsigned long shmem_swap_usage(struct vm_area_struct *vma); extern unsigned long shmem_partial_swap_usage(struct address_space *mapping, pgoff_t start, pgoff_t end); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 868fcccdff72..1d6977dc6b31 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -119,7 +119,8 @@ bool hugepage_vma_check(struct vm_area_struct *vma, unsigned long vm_flags, * own flags. */ if (!in_pf && shmem_file(vma->vm_file)) - return shmem_huge_enabled(vma, !enforce_sysfs); + return shmem_is_huge(file_inode(vma->vm_file), vma->vm_pgoff, + !enforce_sysfs, vma->vm_mm, vm_flags); /* Enforce sysfs THP requirements as necessary */ if (enforce_sysfs && diff --git a/mm/shmem.c b/mm/shmem.c index c5048c6c83dd..9e1015cbad29 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -468,15 +468,14 @@ static bool shmem_confirm_swap(struct address_space *mapping, static int shmem_huge __read_mostly = SHMEM_HUGE_NEVER; -bool shmem_is_huge(struct vm_area_struct *vma, struct inode *inode, - pgoff_t index, bool shmem_huge_force) +bool shmem_is_huge(struct inode *inode, pgoff_t index, bool shmem_huge_force, + struct mm_struct *mm, unsigned long vm_flags) { loff_t i_size; if (!S_ISREG(inode->i_mode)) return false; - if (vma && ((vma->vm_flags & VM_NOHUGEPAGE) || - test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags))) + if (mm && ((vm_flags & VM_NOHUGEPAGE) || test_bit(MMF_DISABLE_THP, &mm->flags))) return false; if (shmem_huge == SHMEM_HUGE_DENY) return false; @@ -493,7 +492,7 @@ bool shmem_is_huge(struct vm_area_struct *vma, struct inode *inode, return true; fallthrough; case SHMEM_HUGE_ADVISE: - if (vma && (vma->vm_flags & VM_HUGEPAGE)) + if (mm && (vm_flags & VM_HUGEPAGE)) return true; fallthrough; default: @@ -676,8 +675,8 @@ static long shmem_unused_huge_count(struct super_block *sb, #define shmem_huge SHMEM_HUGE_DENY -bool shmem_is_huge(struct vm_area_struct *vma, struct inode *inode, - pgoff_t index, bool shmem_huge_force) +bool shmem_is_huge(struct inode *inode, pgoff_t index, bool shmem_huge_force, + struct mm_struct *mm, unsigned long vm_flags) { return false; } @@ -1068,7 +1067,7 @@ static int shmem_getattr(struct user_namespace *mnt_userns, STATX_ATTR_NODUMP); generic_fillattr(&init_user_ns, inode, stat); - if (shmem_is_huge(NULL, inode, 0, false)) + if (shmem_is_huge(inode, 0, false, NULL, 0)) stat->blksize = HPAGE_PMD_SIZE; if (request_mask & STATX_BTIME) { @@ -1926,7 +1925,8 @@ repeat: return 0; } - if (!shmem_is_huge(vma, inode, index, false)) + if (!shmem_is_huge(inode, index, false, + vma ? vma->vm_mm : NULL, vma ? vma->vm_flags : 0)) goto alloc_nohuge; huge_gfp = vma_thp_gfp_mask(vma); -- cgit v1.2.3 From ee7a5906ff08e435ed95ec9fe7c7eed2c11015d2 Mon Sep 17 00:00:00 2001 From: Vishal Moola (Oracle) Date: Wed, 4 Jan 2023 13:14:26 -0800 Subject: pagemap: add filemap_grab_folio() Patch series "Convert to filemap_get_folios_tag()", v5. This patch series replaces find_get_pages_range_tag() with filemap_get_folios_tag(). This also allows the removal of multiple calls to compound_head() throughout. It also makes a good chunk of the straightforward conversions to folios, and takes the opportunity to introduce a function that grabs a folio from the pagecache. This patch (of 23): Add function filemap_grab_folio() to grab a folio from the page cache. This function is meant to serve as a folio replacement for grab_cache_page, and is used to facilitate the removal of find_get_pages_range_tag(). Link: https://lkml.kernel.org/r/20230104211448.4804-1-vishal.moola@gmail.com Link: https://lkml.kernel.org/r/20230104211448.4804-2-vishal.moola@gmail.com Signed-off-by: Vishal Moola (Oracle) Reviewed-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- include/linux/pagemap.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 29e1f9e76eb6..468183be67be 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -546,6 +546,26 @@ static inline struct folio *filemap_lock_folio(struct address_space *mapping, return __filemap_get_folio(mapping, index, FGP_LOCK, 0); } +/** + * filemap_grab_folio - grab a folio from the page cache + * @mapping: The address space to search + * @index: The page index + * + * Looks up the page cache entry at @mapping & @index. If no folio is found, + * a new folio is created. The folio is locked, marked as accessed, and + * returned. + * + * Return: A found or created folio. NULL if no folio is found and failed to + * create a folio. + */ +static inline struct folio *filemap_grab_folio(struct address_space *mapping, + pgoff_t index) +{ + return __filemap_get_folio(mapping, index, + FGP_LOCK | FGP_ACCESSED | FGP_CREAT, + mapping_gfp_mask(mapping)); +} + /** * find_get_page - find and get a page reference * @mapping: the address_space to search -- cgit v1.2.3 From 247f9e1feef4e57911510c8f82348efb4491ea0e Mon Sep 17 00:00:00 2001 From: Vishal Moola (Oracle) Date: Wed, 4 Jan 2023 13:14:27 -0800 Subject: filemap: add filemap_get_folios_tag() This is the equivalent of find_get_pages_range_tag(), except for folios instead of pages. One noteable difference is filemap_get_folios_tag() does not take in a maximum pages argument. It instead tries to fill a folio batch and stops either once full (15 folios) or reaching the end of the search range. The new function supports large folios, the initial function did not since all callers don't use large folios. Link: https://lkml.kernel.org/r/20230104211448.4804-3-vishal.moola@gmail.com Signed-off-by: Vishal Moola (Oracle) Reviewed-by: Matthew Wilcow (Oracle) Signed-off-by: Andrew Morton --- include/linux/pagemap.h | 2 ++ mm/filemap.c | 54 +++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 56 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 468183be67be..bb3c1d51b1cb 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -739,6 +739,8 @@ unsigned filemap_get_folios(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch); unsigned filemap_get_folios_contig(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch); +unsigned filemap_get_folios_tag(struct address_space *mapping, pgoff_t *start, + pgoff_t end, xa_mark_t tag, struct folio_batch *fbatch); unsigned find_get_pages_range_tag(struct address_space *mapping, pgoff_t *index, pgoff_t end, xa_mark_t tag, unsigned int nr_pages, struct page **pages); diff --git a/mm/filemap.c b/mm/filemap.c index c4d4ace9cc70..291bb3e0957a 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2281,6 +2281,60 @@ out: } EXPORT_SYMBOL(filemap_get_folios_contig); +/** + * filemap_get_folios_tag - Get a batch of folios matching @tag + * @mapping: The address_space to search + * @start: The starting page index + * @end: The final page index (inclusive) + * @tag: The tag index + * @fbatch: The batch to fill + * + * Same as filemap_get_folios(), but only returning folios tagged with @tag. + * + * Return: The number of folios found. + * Also update @start to index the next folio for traversal. + */ +unsigned filemap_get_folios_tag(struct address_space *mapping, pgoff_t *start, + pgoff_t end, xa_mark_t tag, struct folio_batch *fbatch) +{ + XA_STATE(xas, &mapping->i_pages, *start); + struct folio *folio; + + rcu_read_lock(); + while ((folio = find_get_entry(&xas, end, tag)) != NULL) { + /* + * Shadow entries should never be tagged, but this iteration + * is lockless so there is a window for page reclaim to evict + * a page we saw tagged. Skip over it. + */ + if (xa_is_value(folio)) + continue; + if (!folio_batch_add(fbatch, folio)) { + unsigned long nr = folio_nr_pages(folio); + + if (folio_test_hugetlb(folio)) + nr = 1; + *start = folio->index + nr; + goto out; + } + } + /* + * We come here when there is no page beyond @end. We take care to not + * overflow the index @start as it confuses some of the callers. This + * breaks the iteration when there is a page at index -1 but that is + * already broke anyway. + */ + if (end == (pgoff_t)-1) + *start = (pgoff_t)-1; + else + *start = end + 1; +out: + rcu_read_unlock(); + + return folio_batch_count(fbatch); +} +EXPORT_SYMBOL(filemap_get_folios_tag); + /** * find_get_pages_range_tag - Find and return head pages matching @tag. * @mapping: the address_space to search -- cgit v1.2.3 From c5792d9384113de4085dfbce6940e2a853debb67 Mon Sep 17 00:00:00 2001 From: Vishal Moola (Oracle) Date: Wed, 4 Jan 2023 13:14:48 -0800 Subject: filemap: remove find_get_pages_range_tag() All callers to find_get_pages_range_tag(), find_get_pages_tag(), pagevec_lookup_range_tag(), and pagevec_lookup_tag() have been removed. Link: https://lkml.kernel.org/r/20230104211448.4804-24-vishal.moola@gmail.com Signed-off-by: Vishal Moola (Oracle) Signed-off-by: Andrew Morton --- include/linux/pagemap.h | 10 --------- include/linux/pagevec.h | 8 ------- mm/filemap.c | 60 ------------------------------------------------- mm/swap.c | 10 --------- 4 files changed, 88 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index bb3c1d51b1cb..9f1081683771 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -741,16 +741,6 @@ unsigned filemap_get_folios_contig(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch); unsigned filemap_get_folios_tag(struct address_space *mapping, pgoff_t *start, pgoff_t end, xa_mark_t tag, struct folio_batch *fbatch); -unsigned find_get_pages_range_tag(struct address_space *mapping, pgoff_t *index, - pgoff_t end, xa_mark_t tag, unsigned int nr_pages, - struct page **pages); -static inline unsigned find_get_pages_tag(struct address_space *mapping, - pgoff_t *index, xa_mark_t tag, unsigned int nr_pages, - struct page **pages) -{ - return find_get_pages_range_tag(mapping, index, (pgoff_t)-1, tag, - nr_pages, pages); -} struct page *grab_cache_page_write_begin(struct address_space *mapping, pgoff_t index); diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h index 2a6f61a0c10a..f582f7213ea5 100644 --- a/include/linux/pagevec.h +++ b/include/linux/pagevec.h @@ -26,14 +26,6 @@ struct pagevec { }; void __pagevec_release(struct pagevec *pvec); -unsigned pagevec_lookup_range_tag(struct pagevec *pvec, - struct address_space *mapping, pgoff_t *index, pgoff_t end, - xa_mark_t tag); -static inline unsigned pagevec_lookup_tag(struct pagevec *pvec, - struct address_space *mapping, pgoff_t *index, xa_mark_t tag) -{ - return pagevec_lookup_range_tag(pvec, mapping, index, (pgoff_t)-1, tag); -} static inline void pagevec_init(struct pagevec *pvec) { diff --git a/mm/filemap.c b/mm/filemap.c index 85adbcf2d9a7..31bf18ec6d01 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2337,66 +2337,6 @@ out: } EXPORT_SYMBOL(filemap_get_folios_tag); -/** - * find_get_pages_range_tag - Find and return head pages matching @tag. - * @mapping: the address_space to search - * @index: the starting page index - * @end: The final page index (inclusive) - * @tag: the tag index - * @nr_pages: the maximum number of pages - * @pages: where the resulting pages are placed - * - * Like find_get_pages_range(), except we only return head pages which are - * tagged with @tag. @index is updated to the index immediately after the - * last page we return, ready for the next iteration. - * - * Return: the number of pages which were found. - */ -unsigned find_get_pages_range_tag(struct address_space *mapping, pgoff_t *index, - pgoff_t end, xa_mark_t tag, unsigned int nr_pages, - struct page **pages) -{ - XA_STATE(xas, &mapping->i_pages, *index); - struct folio *folio; - unsigned ret = 0; - - if (unlikely(!nr_pages)) - return 0; - - rcu_read_lock(); - while ((folio = find_get_entry(&xas, end, tag))) { - /* - * Shadow entries should never be tagged, but this iteration - * is lockless so there is a window for page reclaim to evict - * a page we saw tagged. Skip over it. - */ - if (xa_is_value(folio)) - continue; - - pages[ret] = &folio->page; - if (++ret == nr_pages) { - *index = folio->index + folio_nr_pages(folio); - goto out; - } - } - - /* - * We come here when we got to @end. We take care to not overflow the - * index @index as it confuses some of the callers. This breaks the - * iteration when there is a page at index -1 but that is already - * broken anyway. - */ - if (end == (pgoff_t)-1) - *index = (pgoff_t)-1; - else - *index = end + 1; -out: - rcu_read_unlock(); - - return ret; -} -EXPORT_SYMBOL(find_get_pages_range_tag); - /* * CD/DVDs are error prone. When a medium error occurs, the driver may fail * a _large_ part of the i/o request. Imagine the worst scenario: diff --git a/mm/swap.c b/mm/swap.c index 42d67f9baa8c..5e4f92700c16 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -1115,16 +1115,6 @@ void folio_batch_remove_exceptionals(struct folio_batch *fbatch) fbatch->nr = j; } -unsigned pagevec_lookup_range_tag(struct pagevec *pvec, - struct address_space *mapping, pgoff_t *index, pgoff_t end, - xa_mark_t tag) -{ - pvec->nr = find_get_pages_range_tag(mapping, index, end, tag, - PAGEVEC_SIZE, pvec->pages); - return pagevec_count(pvec); -} -EXPORT_SYMBOL(pagevec_lookup_range_tag); - /* * Perform any setup for the swap system */ -- cgit v1.2.3 From 6bc56a4d855303705802c5ede4625973637484c7 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox (Oracle) Date: Mon, 16 Jan 2023 19:18:09 +0000 Subject: mm: add vma_alloc_zeroed_movable_folio() Replace alloc_zeroed_user_highpage_movable(). The main difference is returning a folio containing a single page instead of returning the page, but take the opportunity to rename the function to match other allocation functions a little better and rewrite the documentation to place more emphasis on the zeroing rather than the highmem aspect. Link: https://lkml.kernel.org/r/20230116191813.2145215-2-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Zi Yan Signed-off-by: Andrew Morton --- arch/alpha/include/asm/page.h | 5 ++--- arch/arm64/include/asm/page.h | 4 ++-- arch/arm64/mm/fault.c | 4 ++-- arch/ia64/include/asm/page.h | 14 ++++++-------- arch/m68k/include/asm/page_no.h | 5 ++--- arch/s390/include/asm/page.h | 5 ++--- arch/x86/include/asm/page.h | 5 ++--- include/linux/highmem.h | 33 ++++++++++++++++----------------- mm/memory.c | 16 ++++++++++------ 9 files changed, 44 insertions(+), 47 deletions(-) (limited to 'include/linux') diff --git a/arch/alpha/include/asm/page.h b/arch/alpha/include/asm/page.h index 8f3f5eecba28..bc5256fba8f0 100644 --- a/arch/alpha/include/asm/page.h +++ b/arch/alpha/include/asm/page.h @@ -17,9 +17,8 @@ extern void clear_page(void *page); #define clear_user_page(page, vaddr, pg) clear_page(page) -#define alloc_zeroed_user_highpage_movable(vma, vaddr) \ - alloc_page_vma(GFP_HIGHUSER_MOVABLE | __GFP_ZERO, vma, vaddr) -#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE_MOVABLE +#define vma_alloc_zeroed_movable_folio(vma, vaddr) \ + vma_alloc_folio(GFP_HIGHUSER_MOVABLE | __GFP_ZERO, 0, vma, vaddr, false) extern void copy_page(void * _to, void * _from); #define copy_user_page(to, from, vaddr, pg) copy_page(to, from) diff --git a/arch/arm64/include/asm/page.h b/arch/arm64/include/asm/page.h index 993a27ea6f54..2312e6ee595f 100644 --- a/arch/arm64/include/asm/page.h +++ b/arch/arm64/include/asm/page.h @@ -29,9 +29,9 @@ void copy_user_highpage(struct page *to, struct page *from, void copy_highpage(struct page *to, struct page *from); #define __HAVE_ARCH_COPY_HIGHPAGE -struct page *alloc_zeroed_user_highpage_movable(struct vm_area_struct *vma, +struct folio *vma_alloc_zeroed_movable_folio(struct vm_area_struct *vma, unsigned long vaddr); -#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE_MOVABLE +#define vma_alloc_zeroed_movable_folio vma_alloc_zeroed_movable_folio void tag_clear_highpage(struct page *to); #define __HAVE_ARCH_TAG_CLEAR_HIGHPAGE diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 596f46dabe4e..f4cb0f85ccf4 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -925,7 +925,7 @@ NOKPROBE_SYMBOL(do_debug_exception); /* * Used during anonymous page fault handling. */ -struct page *alloc_zeroed_user_highpage_movable(struct vm_area_struct *vma, +struct folio *vma_alloc_zeroed_movable_folio(struct vm_area_struct *vma, unsigned long vaddr) { gfp_t flags = GFP_HIGHUSER_MOVABLE | __GFP_ZERO; @@ -938,7 +938,7 @@ struct page *alloc_zeroed_user_highpage_movable(struct vm_area_struct *vma, if (vma->vm_flags & VM_MTE) flags |= __GFP_ZEROTAGS; - return alloc_page_vma(flags, vma, vaddr); + return vma_alloc_folio(flags, 0, vma, vaddr, false); } void tag_clear_highpage(struct page *page) diff --git a/arch/ia64/include/asm/page.h b/arch/ia64/include/asm/page.h index 1b990466d540..ba0b365cf2b2 100644 --- a/arch/ia64/include/asm/page.h +++ b/arch/ia64/include/asm/page.h @@ -82,17 +82,15 @@ do { \ } while (0) -#define alloc_zeroed_user_highpage_movable(vma, vaddr) \ +#define vma_alloc_zeroed_movable_folio(vma, vaddr) \ ({ \ - struct page *page = alloc_page_vma( \ - GFP_HIGHUSER_MOVABLE | __GFP_ZERO, vma, vaddr); \ - if (page) \ - flush_dcache_page(page); \ - page; \ + struct folio *folio = vma_alloc_folio( \ + GFP_HIGHUSER_MOVABLE | __GFP_ZERO, 0, vma, vaddr, false); \ + if (folio) \ + flush_dcache_folio(folio); \ + folio; \ }) -#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE_MOVABLE - #define virt_addr_valid(kaddr) pfn_valid(__pa(kaddr) >> PAGE_SHIFT) #include diff --git a/arch/m68k/include/asm/page_no.h b/arch/m68k/include/asm/page_no.h index c9d0d84158a4..abd2c3aeb015 100644 --- a/arch/m68k/include/asm/page_no.h +++ b/arch/m68k/include/asm/page_no.h @@ -13,9 +13,8 @@ extern unsigned long memory_end; #define clear_user_page(page, vaddr, pg) clear_page(page) #define copy_user_page(to, from, vaddr, pg) copy_page(to, from) -#define alloc_zeroed_user_highpage_movable(vma, vaddr) \ - alloc_page_vma(GFP_HIGHUSER_MOVABLE | __GFP_ZERO, vma, vaddr) -#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE_MOVABLE +#define vma_alloc_zeroed_movable_folio(vma, vaddr) \ + vma_alloc_folio(GFP_HIGHUSER_MOVABLE | __GFP_ZERO, 0, vma, vaddr, false) #define __pa(vaddr) ((unsigned long)(vaddr)) #define __va(paddr) ((void *)((unsigned long)(paddr))) diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h index 61dea67bb9c7..8a2a3b5d1e29 100644 --- a/arch/s390/include/asm/page.h +++ b/arch/s390/include/asm/page.h @@ -73,9 +73,8 @@ static inline void copy_page(void *to, void *from) #define clear_user_page(page, vaddr, pg) clear_page(page) #define copy_user_page(to, from, vaddr, pg) copy_page(to, from) -#define alloc_zeroed_user_highpage_movable(vma, vaddr) \ - alloc_page_vma(GFP_HIGHUSER_MOVABLE | __GFP_ZERO, vma, vaddr) -#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE_MOVABLE +#define vma_alloc_zeroed_movable_folio(vma, vaddr) \ + vma_alloc_folio(GFP_HIGHUSER_MOVABLE | __GFP_ZERO, 0, vma, vaddr, false) /* * These are used to make use of C type-checking.. diff --git a/arch/x86/include/asm/page.h b/arch/x86/include/asm/page.h index 9cc82f305f4b..d18e5c332cb9 100644 --- a/arch/x86/include/asm/page.h +++ b/arch/x86/include/asm/page.h @@ -34,9 +34,8 @@ static inline void copy_user_page(void *to, void *from, unsigned long vaddr, copy_page(to, from); } -#define alloc_zeroed_user_highpage_movable(vma, vaddr) \ - alloc_page_vma(GFP_HIGHUSER_MOVABLE | __GFP_ZERO, vma, vaddr) -#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE_MOVABLE +#define vma_alloc_zeroed_movable_folio(vma, vaddr) \ + vma_alloc_folio(GFP_HIGHUSER_MOVABLE | __GFP_ZERO, 0, vma, vaddr, false) #ifndef __pa #define __pa(x) __phys_addr((unsigned long)(x)) diff --git a/include/linux/highmem.h b/include/linux/highmem.h index d7097b8158f2..e22509420ac6 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -207,31 +207,30 @@ static inline void clear_user_highpage(struct page *page, unsigned long vaddr) } #endif -#ifndef __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE_MOVABLE +#ifndef vma_alloc_zeroed_movable_folio /** - * alloc_zeroed_user_highpage_movable - Allocate a zeroed HIGHMEM page for a VMA that the caller knows can move - * @vma: The VMA the page is to be allocated for - * @vaddr: The virtual address the page will be inserted into + * vma_alloc_zeroed_movable_folio - Allocate a zeroed page for a VMA. + * @vma: The VMA the page is to be allocated for. + * @vaddr: The virtual address the page will be inserted into. * - * Returns: The allocated and zeroed HIGHMEM page + * This function will allocate a page suitable for inserting into this + * VMA at this virtual address. It may be allocated from highmem or + * the movable zone. An architecture may provide its own implementation. * - * This function will allocate a page for a VMA that the caller knows will - * be able to migrate in the future using move_pages() or reclaimed - * - * An architecture may override this function by defining - * __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE_MOVABLE and providing their own - * implementation. + * Return: A folio containing one allocated and zeroed page or NULL if + * we are out of memory. */ -static inline struct page * -alloc_zeroed_user_highpage_movable(struct vm_area_struct *vma, +static inline +struct folio *vma_alloc_zeroed_movable_folio(struct vm_area_struct *vma, unsigned long vaddr) { - struct page *page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vaddr); + struct folio *folio; - if (page) - clear_user_highpage(page, vaddr); + folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, vaddr, false); + if (folio) + clear_user_highpage(&folio->page, vaddr); - return page; + return folio; } #endif diff --git a/mm/memory.c b/mm/memory.c index 87b33b4967c2..b6358ffbccaa 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3056,10 +3056,12 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) goto oom; if (is_zero_pfn(pte_pfn(vmf->orig_pte))) { - new_page = alloc_zeroed_user_highpage_movable(vma, - vmf->address); - if (!new_page) + struct folio *new_folio; + + new_folio = vma_alloc_zeroed_movable_folio(vma, vmf->address); + if (!new_folio) goto oom; + new_page = &new_folio->page; } else { new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vmf->address); @@ -3995,6 +3997,7 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct page *page; + struct folio *folio; vm_fault_t ret = 0; pte_t entry; @@ -4044,11 +4047,12 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) /* Allocate our own private page. */ if (unlikely(anon_vma_prepare(vma))) goto oom; - page = alloc_zeroed_user_highpage_movable(vma, vmf->address); - if (!page) + folio = vma_alloc_zeroed_movable_folio(vma, vmf->address); + if (!folio) goto oom; - if (mem_cgroup_charge(page_folio(page), vma->vm_mm, GFP_KERNEL)) + page = &folio->page; + if (mem_cgroup_charge(folio, vma->vm_mm, GFP_KERNEL)) goto oom_free_page; cgroup_throttle_swaprate(page, GFP_KERNEL); -- cgit v1.2.3 From 9cfb816b1c6c99f4b3c1d4a0fb096162cd17ec71 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox (Oracle) Date: Mon, 16 Jan 2023 19:25:06 +0000 Subject: mm/fs: convert inode_attach_wb() to take a folio Patch series "Writeback folio conversions". Remove more calls to compound_head() by passing folios around instead of pages. This patch (of 2): The only caller of inode_attach_wb() which doesn't pass NULL already has a folio, so convert the whole call-chain to take folios. Link: https://lkml.kernel.org/r/20230116192507.2146150-1-willy@infradead.org Link: https://lkml.kernel.org/r/20230116192507.2146150-2-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- fs/fs-writeback.c | 6 +++--- include/linux/writeback.h | 12 ++++++------ mm/page-writeback.c | 2 +- 3 files changed, 10 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 6fba5a52127b..12f60f1ed2a0 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -237,7 +237,7 @@ void wb_wait_for_completion(struct wb_completion *done) static atomic_t isw_nr_in_flight = ATOMIC_INIT(0); static struct workqueue_struct *isw_wq; -void __inode_attach_wb(struct inode *inode, struct page *page) +void __inode_attach_wb(struct inode *inode, struct folio *folio) { struct backing_dev_info *bdi = inode_to_bdi(inode); struct bdi_writeback *wb = NULL; @@ -245,8 +245,8 @@ void __inode_attach_wb(struct inode *inode, struct page *page) if (inode_cgwb_enabled(inode)) { struct cgroup_subsys_state *memcg_css; - if (page) { - memcg_css = mem_cgroup_css_from_page(page); + if (folio) { + memcg_css = mem_cgroup_css_from_page(&folio->page); wb = wb_get_create(bdi, memcg_css, GFP_ATOMIC); } else { /* must pin memcg_css, see wb_get_create() */ diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 2554b71765e9..3f1491b07474 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -207,7 +207,7 @@ static inline void wait_on_inode(struct inode *inode) #include #include -void __inode_attach_wb(struct inode *inode, struct page *page); +void __inode_attach_wb(struct inode *inode, struct folio *folio); void wbc_attach_and_unlock_inode(struct writeback_control *wbc, struct inode *inode) __releases(&inode->i_lock); @@ -222,16 +222,16 @@ bool cleanup_offline_cgwb(struct bdi_writeback *wb); /** * inode_attach_wb - associate an inode with its wb * @inode: inode of interest - * @page: page being dirtied (may be NULL) + * @folio: folio being dirtied (may be NULL) * * If @inode doesn't have its wb, associate it with the wb matching the - * memcg of @page or, if @page is NULL, %current. May be called w/ or w/o + * memcg of @folio or, if @folio is NULL, %current. May be called w/ or w/o * @inode->i_lock. */ -static inline void inode_attach_wb(struct inode *inode, struct page *page) +static inline void inode_attach_wb(struct inode *inode, struct folio *folio) { if (!inode->i_wb) - __inode_attach_wb(inode, page); + __inode_attach_wb(inode, folio); } /** @@ -290,7 +290,7 @@ static inline void wbc_init_bio(struct writeback_control *wbc, struct bio *bio) #else /* CONFIG_CGROUP_WRITEBACK */ -static inline void inode_attach_wb(struct inode *inode, struct page *page) +static inline void inode_attach_wb(struct inode *inode, struct folio *folio) { } diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 5e892f20bed7..92b90d2ab513 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2652,7 +2652,7 @@ static void folio_account_dirtied(struct folio *folio, struct bdi_writeback *wb; long nr = folio_nr_pages(folio); - inode_attach_wb(inode, &folio->page); + inode_attach_wb(inode, folio); wb = inode_to_wb(inode); __lruvec_stat_mod_folio(folio, NR_FILE_DIRTY, nr); -- cgit v1.2.3 From 75376c6fb93b99e94192cfff48222d11819ee917 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox (Oracle) Date: Mon, 16 Jan 2023 19:25:07 +0000 Subject: mm: convert mem_cgroup_css_from_page() to mem_cgroup_css_from_folio() Only one caller doesn't have a folio, so move the page_folio() call to that one caller from mem_cgroup_css_from_folio(). Link: https://lkml.kernel.org/r/20230116192507.2146150-3-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- fs/fs-writeback.c | 6 ++++-- include/linux/memcontrol.h | 2 +- mm/memcontrol.c | 12 +++++------- 3 files changed, 10 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 12f60f1ed2a0..195dc23e0d83 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -246,7 +246,7 @@ void __inode_attach_wb(struct inode *inode, struct folio *folio) struct cgroup_subsys_state *memcg_css; if (folio) { - memcg_css = mem_cgroup_css_from_page(&folio->page); + memcg_css = mem_cgroup_css_from_folio(folio); wb = wb_get_create(bdi, memcg_css, GFP_ATOMIC); } else { /* must pin memcg_css, see wb_get_create() */ @@ -859,6 +859,7 @@ EXPORT_SYMBOL_GPL(wbc_detach_inode); void wbc_account_cgroup_owner(struct writeback_control *wbc, struct page *page, size_t bytes) { + struct folio *folio; struct cgroup_subsys_state *css; int id; @@ -871,7 +872,8 @@ void wbc_account_cgroup_owner(struct writeback_control *wbc, struct page *page, if (!wbc->wb || wbc->no_cgroup_owner) return; - css = mem_cgroup_css_from_page(page); + folio = page_folio(page); + css = mem_cgroup_css_from_folio(folio); /* dead cgroups shouldn't contribute to inode ownership arbitration */ if (!(css->flags & CSS_ONLINE)) return; diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index e605fc885f08..35478695cabf 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -890,7 +890,7 @@ static inline bool mm_match_cgroup(struct mm_struct *mm, return match; } -struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page); +struct cgroup_subsys_state *mem_cgroup_css_from_folio(struct folio *folio); ino_t page_cgroup_ino(struct page *page); static inline bool mem_cgroup_online(struct mem_cgroup *memcg) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index faeea84964aa..893427aded01 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -350,21 +350,19 @@ EXPORT_SYMBOL(memcg_kmem_enabled_key); #endif /** - * mem_cgroup_css_from_page - css of the memcg associated with a page - * @page: page of interest + * mem_cgroup_css_from_folio - css of the memcg associated with a folio + * @folio: folio of interest * * If memcg is bound to the default hierarchy, css of the memcg associated - * with @page is returned. The returned css remains associated with @page + * with @folio is returned. The returned css remains associated with @folio * until it is released. * * If memcg is bound to a traditional hierarchy, the css of root_mem_cgroup * is returned. */ -struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page) +struct cgroup_subsys_state *mem_cgroup_css_from_folio(struct folio *folio) { - struct mem_cgroup *memcg; - - memcg = page_memcg(page); + struct mem_cgroup *memcg = folio_memcg(folio); if (!memcg || !cgroup_subsys_on_dfl(memory_cgrp_subsys)) memcg = root_mem_cgroup; -- cgit v1.2.3 From 7ec7096b8577d3b899c1dae456a414f2d08c7ddb Mon Sep 17 00:00:00 2001 From: Pasha Tatashin Date: Tue, 17 Jan 2023 20:46:17 +0000 Subject: mm/page_ext: init page_ext early if there are no deferred struct pages page_ext must be initialized after all struct pages are initialized. Therefore, page_ext is initialized after page_alloc_init_late(), and can optionally be initialized earlier via early_page_ext kernel parameter which as a side effect also disables deferred struct pages. Allow to automatically init page_ext early when there are no deferred struct pages in order to be able to use page_ext during kernel boot and track for example page allocations early. [pasha.tatashin@soleen.com: fix build with CONFIG_PAGE_EXTENSION=n] Link: https://lkml.kernel.org/r/20230118155251.2522985-1-pasha.tatashin@soleen.com Link: https://lkml.kernel.org/r/20230117204617.1553748-1-pasha.tatashin@soleen.com Signed-off-by: Pasha Tatashin Acked-by: Mike Rapoport (IBM) Acked-by: Vlastimil Babka Cc: Charan Teja Kalla Cc: David Hildenbrand Cc: Li Zhe Cc: Michal Hocko Signed-off-by: Andrew Morton --- include/linux/page_ext.h | 2 ++ init/main.c | 6 +++--- mm/page_alloc.c | 6 +++++- mm/page_ext.c | 2 +- 4 files changed, 11 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h index 67314f648aeb..bc2e39090a1f 100644 --- a/include/linux/page_ext.h +++ b/include/linux/page_ext.h @@ -29,6 +29,8 @@ struct page_ext_operations { bool need_shared_flags; }; +extern bool deferred_struct_pages; + #ifdef CONFIG_PAGE_EXTENSION /* diff --git a/init/main.c b/init/main.c index e1c3911d7c70..64cd2ff051c4 100644 --- a/init/main.c +++ b/init/main.c @@ -855,8 +855,8 @@ static void __init mm_init(void) pgtable_init(); debug_objects_mem_init(); vmalloc_init(); - /* Should be run after vmap initialization */ - if (early_page_ext_enabled()) + /* If no deferred init page_ext now, as vmap is fully initialized */ + if (!deferred_struct_pages) page_ext_init(); /* Should be run before the first non-init thread is created */ init_espfix_bsp(); @@ -1628,7 +1628,7 @@ static noinline void __init kernel_init_freeable(void) padata_init(); page_alloc_init_late(); /* Initialize page ext after all struct pages are initialized. */ - if (!early_page_ext_enabled()) + if (deferred_struct_pages) page_ext_init(); do_basic_setup(); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 0cfad30fb44c..ecb9e9acfe7f 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -430,6 +430,8 @@ EXPORT_SYMBOL(nr_online_nodes); int page_group_by_mobility_disabled __read_mostly; +bool deferred_struct_pages __meminitdata; + #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT /* * During boot we initialize deferred pages on-demand, as needed, but once @@ -6803,8 +6805,10 @@ void __meminit memmap_init_range(unsigned long size, int nid, unsigned long zone if (context == MEMINIT_EARLY) { if (overlap_memmap_init(zone, &pfn)) continue; - if (defer_init(nid, pfn, zone_end_pfn)) + if (defer_init(nid, pfn, zone_end_pfn)) { + deferred_struct_pages = true; break; + } } page = pfn_to_page(pfn); diff --git a/mm/page_ext.c b/mm/page_ext.c index e2c22ffdbb81..dc1626be458b 100644 --- a/mm/page_ext.c +++ b/mm/page_ext.c @@ -92,7 +92,7 @@ unsigned long page_ext_size; static unsigned long total_usage; static struct page_ext *lookup_page_ext(const struct page *page); -bool early_page_ext; +bool early_page_ext __meminitdata; static int __init setup_early_page_ext(char *str) { early_page_ext = true; -- cgit v1.2.3 From 04bac040bc71b4b37550eed5854f34ca161756f9 Mon Sep 17 00:00:00 2001 From: Sidhartha Kumar Date: Wed, 18 Jan 2023 09:40:39 -0800 Subject: mm/hugetlb: convert get_hwpoison_huge_page() to folios Straightforward conversion of get_hwpoison_huge_page() to get_hwpoison_hugetlb_folio(). Reduces two references to a head page in memory-failure.c [arnd@arndb.de: fix get_hwpoison_hugetlb_folio() stub] Link: https://lkml.kernel.org/r/20230119111920.635260-1-arnd@kernel.org Link: https://lkml.kernel.org/r/20230118174039.14247-1-sidhartha.kumar@oracle.com Signed-off-by: Sidhartha Kumar Signed-off-by: Arnd Bergmann Acked-by: Naoya Horiguchi Reviewed-by: Matthew Wilcox (Oracle) Cc: Mike Kravetz Cc: Muchun Song Signed-off-by: Andrew Morton --- include/linux/hugetlb.h | 4 ++-- mm/hugetlb.c | 10 +++++----- mm/memory-failure.c | 22 +++++++++++----------- 3 files changed, 18 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index cf60fe741c1d..a51e6daacac6 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -172,7 +172,7 @@ bool hugetlb_reserve_pages(struct inode *inode, long from, long to, long hugetlb_unreserve_pages(struct inode *inode, long start, long end, long freed); int isolate_hugetlb(struct page *page, struct list_head *list); -int get_hwpoison_huge_page(struct page *page, bool *hugetlb, bool unpoison); +int get_hwpoison_hugetlb_folio(struct folio *folio, bool *hugetlb, bool unpoison); int get_huge_page_for_hwpoison(unsigned long pfn, int flags, bool *migratable_cleared); void putback_active_hugepage(struct page *page); @@ -418,7 +418,7 @@ static inline int isolate_hugetlb(struct page *page, struct list_head *list) return -EBUSY; } -static inline int get_hwpoison_huge_page(struct page *page, bool *hugetlb, bool unpoison) +static inline int get_hwpoison_hugetlb_folio(struct folio *folio, bool *hugetlb, bool unpoison) { return 0; } diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 291ad4cb02f9..0f9df0143772 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -7268,18 +7268,18 @@ unlock: return ret; } -int get_hwpoison_huge_page(struct page *page, bool *hugetlb, bool unpoison) +int get_hwpoison_hugetlb_folio(struct folio *folio, bool *hugetlb, bool unpoison) { int ret = 0; *hugetlb = false; spin_lock_irq(&hugetlb_lock); - if (PageHeadHuge(page)) { + if (folio_test_hugetlb(folio)) { *hugetlb = true; - if (HPageFreed(page)) + if (folio_test_hugetlb_freed(folio)) ret = 0; - else if (HPageMigratable(page) || unpoison) - ret = get_page_unless_zero(page); + else if (folio_test_hugetlb_migratable(folio) || unpoison) + ret = folio_try_get(folio); else ret = -EBUSY; } diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 38f84bff8bdf..0a382191737f 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1257,28 +1257,28 @@ static inline bool HWPoisonHandlable(struct page *page, unsigned long flags) static int __get_hwpoison_page(struct page *page, unsigned long flags) { - struct page *head = compound_head(page); + struct folio *folio = page_folio(page); int ret = 0; bool hugetlb = false; - ret = get_hwpoison_huge_page(head, &hugetlb, false); + ret = get_hwpoison_hugetlb_folio(folio, &hugetlb, false); if (hugetlb) return ret; /* - * This check prevents from calling get_page_unless_zero() for any - * unsupported type of page in order to reduce the risk of unexpected - * races caused by taking a page refcount. + * This check prevents from calling folio_try_get() for any + * unsupported type of folio in order to reduce the risk of unexpected + * races caused by taking a folio refcount. */ - if (!HWPoisonHandlable(head, flags)) + if (!HWPoisonHandlable(&folio->page, flags)) return -EBUSY; - if (get_page_unless_zero(head)) { - if (head == compound_head(page)) + if (folio_try_get(folio)) { + if (folio == page_folio(page)) return 1; pr_info("%#lx cannot catch tail\n", page_to_pfn(page)); - put_page(head); + folio_put(folio); } return 0; @@ -1347,11 +1347,11 @@ out: static int __get_unpoison_page(struct page *page) { - struct page *head = compound_head(page); + struct folio *folio = page_folio(page); int ret = 0; bool hugetlb = false; - ret = get_hwpoison_huge_page(head, &hugetlb, true); + ret = get_hwpoison_hugetlb_folio(folio, &hugetlb, true); if (hugetlb) return ret; -- cgit v1.2.3 From 5649d113ffce9f532a9ecc5ab96a93e02efbf283 Mon Sep 17 00:00:00 2001 From: Yang Yang Date: Wed, 18 Jan 2023 20:13:03 +0800 Subject: swap_state: update shadow_nodes for anonymous page Shadow_nodes is for shadow nodes reclaiming of workingset handling, it is updated when page cache add or delete since long time ago workingset only supported page cache. But when workingset supports anonymous page detection, we missied updating shadow nodes for it. This caused that shadow nodes of anonymous page will never be reclaimd by scan_shadow_nodes() even they use much memory and system memory is tense. So update shadow_nodes of anonymous page when swap cache is add or delete by calling xas_set_update(..workingset_update_node). Link: https://lkml.kernel.org/r/202301182013032211005@zte.com.cn Fixes: aae466b0052e ("mm/swap: implement workingset detection for anonymous LRU") Signed-off-by: Yang Yang Reviewed-by: Ran Xiaokai Cc: Bagas Sanjaya Cc: Johannes Weiner Cc: Joonsoo Kim Cc: Matthew Wilcox Signed-off-by: Andrew Morton --- include/linux/xarray.h | 3 ++- mm/swap_state.c | 6 ++++++ mm/workingset.c | 21 +++++++++++++-------- 3 files changed, 21 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 44dd6d6e01bc..741703b45f61 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -1643,7 +1643,8 @@ static inline void xas_set_order(struct xa_state *xas, unsigned long index, * @update: Function to call when updating a node. * * The XArray can notify a caller after it has updated an xa_node. - * This is advanced functionality and is only needed by the page cache. + * This is advanced functionality and is only needed by the page + * cache and swap cache. */ static inline void xas_set_update(struct xa_state *xas, xa_update_node_t update) { diff --git a/mm/swap_state.c b/mm/swap_state.c index cb9aaa00951d..7a003d8abb37 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -94,6 +94,8 @@ int add_to_swap_cache(struct folio *folio, swp_entry_t entry, unsigned long i, nr = folio_nr_pages(folio); void *old; + xas_set_update(&xas, workingset_update_node); + VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_FOLIO(folio_test_swapcache(folio), folio); VM_BUG_ON_FOLIO(!folio_test_swapbacked(folio), folio); @@ -145,6 +147,8 @@ void __delete_from_swap_cache(struct folio *folio, pgoff_t idx = swp_offset(entry); XA_STATE(xas, &address_space->i_pages, idx); + xas_set_update(&xas, workingset_update_node); + VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_FOLIO(!folio_test_swapcache(folio), folio); VM_BUG_ON_FOLIO(folio_test_writeback(folio), folio); @@ -252,6 +256,8 @@ void clear_shadow_from_swap_cache(int type, unsigned long begin, struct address_space *address_space = swap_address_space(entry); XA_STATE(xas, &address_space->i_pages, curr); + xas_set_update(&xas, workingset_update_node); + xa_lock_irq(&address_space->i_pages); xas_for_each(&xas, old, end) { if (!xa_is_value(old)) diff --git a/mm/workingset.c b/mm/workingset.c index f194d13beabb..00c6f4d9d9be 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -657,11 +657,14 @@ static enum lru_status shadow_lru_isolate(struct list_head *item, goto out; } - if (!spin_trylock(&mapping->host->i_lock)) { - xa_unlock(&mapping->i_pages); - spin_unlock_irq(lru_lock); - ret = LRU_RETRY; - goto out; + /* For page cache we need to hold i_lock */ + if (mapping->host != NULL) { + if (!spin_trylock(&mapping->host->i_lock)) { + xa_unlock(&mapping->i_pages); + spin_unlock_irq(lru_lock); + ret = LRU_RETRY; + goto out; + } } list_lru_isolate(lru, item); @@ -683,9 +686,11 @@ static enum lru_status shadow_lru_isolate(struct list_head *item, out_invalid: xa_unlock_irq(&mapping->i_pages); - if (mapping_shrinkable(mapping)) - inode_add_lru(mapping->host); - spin_unlock(&mapping->host->i_lock); + if (mapping->host != NULL) { + if (mapping_shrinkable(mapping)) + inode_add_lru(mapping->host); + spin_unlock(&mapping->host->i_lock); + } ret = LRU_REMOVED_RETRY; out: cond_resched(); -- cgit v1.2.3 From b507808ebce23561d4ff8c2aa1fb949fe402bc61 Mon Sep 17 00:00:00 2001 From: Joey Gouly Date: Thu, 19 Jan 2023 16:03:43 +0000 Subject: mm: implement memory-deny-write-execute as a prctl Patch series "mm: In-kernel support for memory-deny-write-execute (MDWE)", v2. The background to this is that systemd has a configuration option called MemoryDenyWriteExecute [2], implemented as a SECCOMP BPF filter. Its aim is to prevent a user task from inadvertently creating an executable mapping that is (or was) writeable. Since such BPF filter is stateless, it cannot detect mappings that were previously writeable but subsequently changed to read-only. Therefore the filter simply rejects any mprotect(PROT_EXEC). The side-effect is that on arm64 with BTI support (Branch Target Identification), the dynamic loader cannot change an ELF section from PROT_EXEC to PROT_EXEC|PROT_BTI using mprotect(). For libraries, it can resort to unmapping and re-mapping but for the main executable it does not have a file descriptor. The original bug report in the Red Hat bugzilla - [3] - and subsequent glibc workaround for libraries - [4]. This series adds in-kernel support for this feature as a prctl PR_SET_MDWE, that is inherited on fork(). The prctl denies PROT_WRITE | PROT_EXEC mappings. Like the systemd BPF filter it also denies adding PROT_EXEC to mappings. However unlike the BPF filter it only denies it if the mapping didn't previous have PROT_EXEC. This allows to PROT_EXEC -> PROT_EXEC | PROT_BTI with mprotect(), which is a problem with the BPF filter. This patch (of 2): The aim of such policy is to prevent a user task from creating an executable mapping that is also writeable. An example of mmap() returning -EACCESS if the policy is enabled: mmap(0, size, PROT_READ | PROT_WRITE | PROT_EXEC, flags, 0, 0); Similarly, mprotect() would return -EACCESS below: addr = mmap(0, size, PROT_READ | PROT_EXEC, flags, 0, 0); mprotect(addr, size, PROT_READ | PROT_WRITE | PROT_EXEC); The BPF filter that systemd MDWE uses is stateless, and disallows mprotect() with PROT_EXEC completely. This new prctl allows PROT_EXEC to be enabled if it was already PROT_EXEC, which allows the following case: addr = mmap(0, size, PROT_READ | PROT_EXEC, flags, 0, 0); mprotect(addr, size, PROT_READ | PROT_EXEC | PROT_BTI); where PROT_BTI enables branch tracking identification on arm64. Link: https://lkml.kernel.org/r/20230119160344.54358-1-joey.gouly@arm.com Link: https://lkml.kernel.org/r/20230119160344.54358-2-joey.gouly@arm.com Signed-off-by: Joey Gouly Co-developed-by: Catalin Marinas Signed-off-by: Catalin Marinas Cc: Alexander Viro Cc: Jeremy Linton Cc: Kees Cook Cc: Lennart Poettering Cc: Mark Brown Cc: nd Cc: Shuah Khan Cc: Szabolcs Nagy Cc: Topi Miettinen Cc: Zbigniew Jędrzejewski-Szmek Cc: David Hildenbrand Signed-off-by: Andrew Morton --- include/linux/mman.h | 34 ++++++++++++++++++++++++++++++++++ include/linux/sched/coredump.h | 6 +++++- include/uapi/linux/prctl.h | 6 ++++++ kernel/sys.c | 33 +++++++++++++++++++++++++++++++++ mm/mmap.c | 10 ++++++++++ mm/mprotect.c | 5 +++++ 6 files changed, 93 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mman.h b/include/linux/mman.h index 58b3abd457a3..cee1e4b566d8 100644 --- a/include/linux/mman.h +++ b/include/linux/mman.h @@ -156,4 +156,38 @@ calc_vm_flag_bits(unsigned long flags) } unsigned long vm_commit_limit(void); + +/* + * Denies creating a writable executable mapping or gaining executable permissions. + * + * This denies the following: + * + * a) mmap(PROT_WRITE | PROT_EXEC) + * + * b) mmap(PROT_WRITE) + * mprotect(PROT_EXEC) + * + * c) mmap(PROT_WRITE) + * mprotect(PROT_READ) + * mprotect(PROT_EXEC) + * + * But allows the following: + * + * d) mmap(PROT_READ | PROT_EXEC) + * mmap(PROT_READ | PROT_EXEC | PROT_BTI) + */ +static inline bool map_deny_write_exec(struct vm_area_struct *vma, unsigned long vm_flags) +{ + if (!test_bit(MMF_HAS_MDWE, ¤t->mm->flags)) + return false; + + if ((vm_flags & VM_EXEC) && (vm_flags & VM_WRITE)) + return true; + + if (!(vma->vm_flags & VM_EXEC) && (vm_flags & VM_EXEC)) + return true; + + return false; +} + #endif /* _LINUX_MMAN_H */ diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h index 8270ad7ae14c..0e17ae7fbfd3 100644 --- a/include/linux/sched/coredump.h +++ b/include/linux/sched/coredump.h @@ -81,9 +81,13 @@ static inline int get_dumpable(struct mm_struct *mm) * lifecycle of this mm, just for simplicity. */ #define MMF_HAS_PINNED 27 /* FOLL_PIN has run, never cleared */ + +#define MMF_HAS_MDWE 28 +#define MMF_HAS_MDWE_MASK (1 << MMF_HAS_MDWE) + #define MMF_DISABLE_THP_MASK (1 << MMF_DISABLE_THP) #define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\ - MMF_DISABLE_THP_MASK) + MMF_DISABLE_THP_MASK | MMF_HAS_MDWE_MASK) #endif /* _LINUX_SCHED_COREDUMP_H */ diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index a5e06dcbba13..1312a137f7fb 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -281,6 +281,12 @@ struct prctl_mm_map { # define PR_SME_VL_LEN_MASK 0xffff # define PR_SME_VL_INHERIT (1 << 17) /* inherit across exec */ +/* Memory deny write / execute */ +#define PR_SET_MDWE 65 +# define PR_MDWE_REFUSE_EXEC_GAIN 1 + +#define PR_GET_MDWE 66 + #define PR_SET_VMA 0x53564d41 # define PR_SET_VMA_ANON_NAME 0 diff --git a/kernel/sys.c b/kernel/sys.c index 5fd54bf0e886..b3cab94545ed 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -2348,6 +2348,33 @@ static int prctl_set_vma(unsigned long opt, unsigned long start, } #endif /* CONFIG_ANON_VMA_NAME */ +static inline int prctl_set_mdwe(unsigned long bits, unsigned long arg3, + unsigned long arg4, unsigned long arg5) +{ + if (arg3 || arg4 || arg5) + return -EINVAL; + + if (bits & ~(PR_MDWE_REFUSE_EXEC_GAIN)) + return -EINVAL; + + if (bits & PR_MDWE_REFUSE_EXEC_GAIN) + set_bit(MMF_HAS_MDWE, ¤t->mm->flags); + else if (test_bit(MMF_HAS_MDWE, ¤t->mm->flags)) + return -EPERM; /* Cannot unset the flag */ + + return 0; +} + +static inline int prctl_get_mdwe(unsigned long arg2, unsigned long arg3, + unsigned long arg4, unsigned long arg5) +{ + if (arg2 || arg3 || arg4 || arg5) + return -EINVAL; + + return test_bit(MMF_HAS_MDWE, ¤t->mm->flags) ? + PR_MDWE_REFUSE_EXEC_GAIN : 0; +} + SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, unsigned long, arg4, unsigned long, arg5) { @@ -2623,6 +2650,12 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, error = sched_core_share_pid(arg2, arg3, arg4, arg5); break; #endif + case PR_SET_MDWE: + error = prctl_set_mdwe(arg2, arg3, arg4, arg5); + break; + case PR_GET_MDWE: + error = prctl_get_mdwe(arg2, arg3, arg4, arg5); + break; case PR_SET_VMA: error = prctl_set_vma(arg2, arg3, arg4, arg5); break; diff --git a/mm/mmap.c b/mm/mmap.c index 335ba3df9898..ffc0815cd7fb 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2669,6 +2669,16 @@ cannot_expand: vma_set_anonymous(vma); } + if (map_deny_write_exec(vma, vma->vm_flags)) { + error = -EACCES; + if (file) + goto close_and_free_vma; + else if (vma->vm_file) + goto unmap_and_free_vma; + else + goto free_vma; + } + /* Allow architectures to sanity-check the vm_flags */ if (!arch_validate_flags(vma->vm_flags)) { error = -EINVAL; diff --git a/mm/mprotect.c b/mm/mprotect.c index 6ecdf0671b81..6a22f3ad9b84 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -799,6 +799,11 @@ static int do_mprotect_pkey(unsigned long start, size_t len, break; } + if (map_deny_write_exec(vma, newflags)) { + error = -EACCES; + goto out; + } + /* Allow architectures to sanity-check the new flags */ if (!arch_validate_flags(newflags)) { error = -EINVAL; -- cgit v1.2.3 From 6b3f013bb90e737b06c7955571407190b4c760ce Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Thu, 19 Jan 2023 01:38:29 +0000 Subject: mm/damon: update comments in damon.h for damon_attrs Patch series "mm/damon: misc fixes". This patchset contains three miscellaneous simple fixes for DAMON online tuning. This patch (of 3): Commit cbeaa77b0449 ("mm/damon/core: use a dedicated struct for monitoring attributes") moved monitoring intervals from damon_ctx to a new struct, damon_attrs, but a comment in the header file has not updated for the change. Update it. Link: https://lkml.kernel.org/r/20230119013831.1911-1-sj@kernel.org Link: https://lkml.kernel.org/r/20230119013831.1911-2-sj@kernel.org Fixes: cbeaa77b0449 ("mm/damon/core: use a dedicated struct for monitoring attributes") Signed-off-by: SeongJae Park Cc: Brendan Higgins Signed-off-by: Andrew Morton --- include/linux/damon.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index dfb245bb3053..d5d4d19928e0 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -354,10 +354,10 @@ struct damon_ctx; * users should register the low level operations for their target address * space and usecase via the &damon_ctx.ops. Then, the monitoring thread * (&damon_ctx.kdamond) calls @init and @prepare_access_checks before starting - * the monitoring, @update after each &damon_ctx.ops_update_interval, and + * the monitoring, @update after each &damon_attrs.ops_update_interval, and * @check_accesses, @target_valid and @prepare_access_checks after each - * &damon_ctx.sample_interval. Finally, @reset_aggregated is called after each - * &damon_ctx.aggr_interval. + * &damon_attrs.sample_interval. Finally, @reset_aggregated is called after + * each &damon_attrs.aggr_interval. * * Each &struct damon_operations instance having valid @id can be registered * via damon_register_ops() and selected by damon_select_ops() later. -- cgit v1.2.3 From 36c7b4db7c942ae9e1b111f0c6b468c8b2e33842 Mon Sep 17 00:00:00 2001 From: T.J. Alumbaugh Date: Wed, 18 Jan 2023 00:18:24 +0000 Subject: mm: multi-gen LRU: section for memcg LRU Move memcg LRU code into a dedicated section. Improve the design doc to outline its architecture. Link: https://lkml.kernel.org/r/20230118001827.1040870-5-talumbau@google.com Signed-off-by: T.J. Alumbaugh Cc: Yu Zhao Signed-off-by: Andrew Morton --- Documentation/mm/multigen_lru.rst | 33 ++++- include/linux/mm_inline.h | 17 --- include/linux/mmzone.h | 13 +- mm/memcontrol.c | 8 +- mm/vmscan.c | 250 ++++++++++++++++++++++---------------- 5 files changed, 178 insertions(+), 143 deletions(-) (limited to 'include/linux') diff --git a/Documentation/mm/multigen_lru.rst b/Documentation/mm/multigen_lru.rst index 770b5d539856..5f1f6ecbb79b 100644 --- a/Documentation/mm/multigen_lru.rst +++ b/Documentation/mm/multigen_lru.rst @@ -186,9 +186,40 @@ is false positive, the cost is an additional scan of a range of PTEs, which may yield hot pages anyway. Parameters of the filter itself can control the false positive rate in the limit. +Memcg LRU +--------- +An memcg LRU is a per-node LRU of memcgs. It is also an LRU of LRUs, +since each node and memcg combination has an LRU of folios (see +``mem_cgroup_lruvec()``). Its goal is to improve the scalability of +global reclaim, which is critical to system-wide memory overcommit in +data centers. Note that memcg LRU only applies to global reclaim. + +The basic structure of an memcg LRU can be understood by an analogy to +the active/inactive LRU (of folios): + +1. It has the young and the old (generations), i.e., the counterparts + to the active and the inactive; +2. The increment of ``max_seq`` triggers promotion, i.e., the + counterpart to activation; +3. Other events trigger similar operations, e.g., offlining an memcg + triggers demotion, i.e., the counterpart to deactivation. + +In terms of global reclaim, it has two distinct features: + +1. Sharding, which allows each thread to start at a random memcg (in + the old generation) and improves parallelism; +2. Eventual fairness, which allows direct reclaim to bail out at will + and reduces latency without affecting fairness over some time. + +In terms of traversing memcgs during global reclaim, it improves the +best-case complexity from O(n) to O(1) and does not affect the +worst-case complexity O(n). Therefore, on average, it has a sublinear +complexity. + Summary ------- -The multi-gen LRU can be disassembled into the following parts: +The multi-gen LRU (of folios) can be disassembled into the following +parts: * Generations * Rmap walks diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index 26dcbda07e92..de1e622dd366 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -122,18 +122,6 @@ static inline bool lru_gen_in_fault(void) return current->in_lru_fault; } -#ifdef CONFIG_MEMCG -static inline int lru_gen_memcg_seg(struct lruvec *lruvec) -{ - return READ_ONCE(lruvec->lrugen.seg); -} -#else -static inline int lru_gen_memcg_seg(struct lruvec *lruvec) -{ - return 0; -} -#endif - static inline int lru_gen_from_seq(unsigned long seq) { return seq % MAX_NR_GENS; @@ -309,11 +297,6 @@ static inline bool lru_gen_in_fault(void) return false; } -static inline int lru_gen_memcg_seg(struct lruvec *lruvec) -{ - return 0; -} - static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) { return false; diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 815c7c2edf45..977be526c939 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -368,15 +368,6 @@ struct page_vma_mapped_walk; #define LRU_GEN_MASK ((BIT(LRU_GEN_WIDTH) - 1) << LRU_GEN_PGOFF) #define LRU_REFS_MASK ((BIT(LRU_REFS_WIDTH) - 1) << LRU_REFS_PGOFF) -/* see the comment on MEMCG_NR_GENS */ -enum { - MEMCG_LRU_NOP, - MEMCG_LRU_HEAD, - MEMCG_LRU_TAIL, - MEMCG_LRU_OLD, - MEMCG_LRU_YOUNG, -}; - #ifdef CONFIG_LRU_GEN enum { @@ -557,7 +548,7 @@ void lru_gen_exit_memcg(struct mem_cgroup *memcg); void lru_gen_online_memcg(struct mem_cgroup *memcg); void lru_gen_offline_memcg(struct mem_cgroup *memcg); void lru_gen_release_memcg(struct mem_cgroup *memcg); -void lru_gen_rotate_memcg(struct lruvec *lruvec, int op); +void lru_gen_soft_reclaim(struct lruvec *lruvec); #else /* !CONFIG_MEMCG */ @@ -608,7 +599,7 @@ static inline void lru_gen_release_memcg(struct mem_cgroup *memcg) { } -static inline void lru_gen_rotate_memcg(struct lruvec *lruvec, int op) +static inline void lru_gen_soft_reclaim(struct lruvec *lruvec) { } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 893427aded01..17335459d8dc 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -476,12 +476,8 @@ static void mem_cgroup_update_tree(struct mem_cgroup *memcg, int nid) struct mem_cgroup_tree_per_node *mctz; if (lru_gen_enabled()) { - struct lruvec *lruvec = &memcg->nodeinfo[nid]->lruvec; - - /* see the comment on MEMCG_NR_GENS */ - if (soft_limit_excess(memcg) && lru_gen_memcg_seg(lruvec) != MEMCG_LRU_HEAD) - lru_gen_rotate_memcg(lruvec, MEMCG_LRU_HEAD); - + if (soft_limit_excess(memcg)) + lru_gen_soft_reclaim(&memcg->nodeinfo[nid]->lruvec); return; } diff --git a/mm/vmscan.c b/mm/vmscan.c index 1be9120349f8..796d4ca65e97 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -4705,6 +4705,148 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw) mem_cgroup_unlock_pages(); } +/****************************************************************************** + * memcg LRU + ******************************************************************************/ + +/* see the comment on MEMCG_NR_GENS */ +enum { + MEMCG_LRU_NOP, + MEMCG_LRU_HEAD, + MEMCG_LRU_TAIL, + MEMCG_LRU_OLD, + MEMCG_LRU_YOUNG, +}; + +#ifdef CONFIG_MEMCG + +static int lru_gen_memcg_seg(struct lruvec *lruvec) +{ + return READ_ONCE(lruvec->lrugen.seg); +} + +static void lru_gen_rotate_memcg(struct lruvec *lruvec, int op) +{ + int seg; + int old, new; + int bin = get_random_u32_below(MEMCG_NR_BINS); + struct pglist_data *pgdat = lruvec_pgdat(lruvec); + + spin_lock(&pgdat->memcg_lru.lock); + + VM_WARN_ON_ONCE(hlist_nulls_unhashed(&lruvec->lrugen.list)); + + seg = 0; + new = old = lruvec->lrugen.gen; + + /* see the comment on MEMCG_NR_GENS */ + if (op == MEMCG_LRU_HEAD) + seg = MEMCG_LRU_HEAD; + else if (op == MEMCG_LRU_TAIL) + seg = MEMCG_LRU_TAIL; + else if (op == MEMCG_LRU_OLD) + new = get_memcg_gen(pgdat->memcg_lru.seq); + else if (op == MEMCG_LRU_YOUNG) + new = get_memcg_gen(pgdat->memcg_lru.seq + 1); + else + VM_WARN_ON_ONCE(true); + + hlist_nulls_del_rcu(&lruvec->lrugen.list); + + if (op == MEMCG_LRU_HEAD || op == MEMCG_LRU_OLD) + hlist_nulls_add_head_rcu(&lruvec->lrugen.list, &pgdat->memcg_lru.fifo[new][bin]); + else + hlist_nulls_add_tail_rcu(&lruvec->lrugen.list, &pgdat->memcg_lru.fifo[new][bin]); + + pgdat->memcg_lru.nr_memcgs[old]--; + pgdat->memcg_lru.nr_memcgs[new]++; + + lruvec->lrugen.gen = new; + WRITE_ONCE(lruvec->lrugen.seg, seg); + + if (!pgdat->memcg_lru.nr_memcgs[old] && old == get_memcg_gen(pgdat->memcg_lru.seq)) + WRITE_ONCE(pgdat->memcg_lru.seq, pgdat->memcg_lru.seq + 1); + + spin_unlock(&pgdat->memcg_lru.lock); +} + +void lru_gen_online_memcg(struct mem_cgroup *memcg) +{ + int gen; + int nid; + int bin = get_random_u32_below(MEMCG_NR_BINS); + + for_each_node(nid) { + struct pglist_data *pgdat = NODE_DATA(nid); + struct lruvec *lruvec = get_lruvec(memcg, nid); + + spin_lock(&pgdat->memcg_lru.lock); + + VM_WARN_ON_ONCE(!hlist_nulls_unhashed(&lruvec->lrugen.list)); + + gen = get_memcg_gen(pgdat->memcg_lru.seq); + + hlist_nulls_add_tail_rcu(&lruvec->lrugen.list, &pgdat->memcg_lru.fifo[gen][bin]); + pgdat->memcg_lru.nr_memcgs[gen]++; + + lruvec->lrugen.gen = gen; + + spin_unlock(&pgdat->memcg_lru.lock); + } +} + +void lru_gen_offline_memcg(struct mem_cgroup *memcg) +{ + int nid; + + for_each_node(nid) { + struct lruvec *lruvec = get_lruvec(memcg, nid); + + lru_gen_rotate_memcg(lruvec, MEMCG_LRU_OLD); + } +} + +void lru_gen_release_memcg(struct mem_cgroup *memcg) +{ + int gen; + int nid; + + for_each_node(nid) { + struct pglist_data *pgdat = NODE_DATA(nid); + struct lruvec *lruvec = get_lruvec(memcg, nid); + + spin_lock(&pgdat->memcg_lru.lock); + + VM_WARN_ON_ONCE(hlist_nulls_unhashed(&lruvec->lrugen.list)); + + gen = lruvec->lrugen.gen; + + hlist_nulls_del_rcu(&lruvec->lrugen.list); + pgdat->memcg_lru.nr_memcgs[gen]--; + + if (!pgdat->memcg_lru.nr_memcgs[gen] && gen == get_memcg_gen(pgdat->memcg_lru.seq)) + WRITE_ONCE(pgdat->memcg_lru.seq, pgdat->memcg_lru.seq + 1); + + spin_unlock(&pgdat->memcg_lru.lock); + } +} + +void lru_gen_soft_reclaim(struct lruvec *lruvec) +{ + /* see the comment on MEMCG_NR_GENS */ + if (lru_gen_memcg_seg(lruvec) != MEMCG_LRU_HEAD) + lru_gen_rotate_memcg(lruvec, MEMCG_LRU_HEAD); +} + +#else /* !CONFIG_MEMCG */ + +static int lru_gen_memcg_seg(struct lruvec *lruvec) +{ + return 0; +} + +#endif + /****************************************************************************** * the eviction ******************************************************************************/ @@ -5397,53 +5539,6 @@ done: pgdat->kswapd_failures = 0; } -#ifdef CONFIG_MEMCG -void lru_gen_rotate_memcg(struct lruvec *lruvec, int op) -{ - int seg; - int old, new; - int bin = get_random_u32_below(MEMCG_NR_BINS); - struct pglist_data *pgdat = lruvec_pgdat(lruvec); - - spin_lock(&pgdat->memcg_lru.lock); - - VM_WARN_ON_ONCE(hlist_nulls_unhashed(&lruvec->lrugen.list)); - - seg = 0; - new = old = lruvec->lrugen.gen; - - /* see the comment on MEMCG_NR_GENS */ - if (op == MEMCG_LRU_HEAD) - seg = MEMCG_LRU_HEAD; - else if (op == MEMCG_LRU_TAIL) - seg = MEMCG_LRU_TAIL; - else if (op == MEMCG_LRU_OLD) - new = get_memcg_gen(pgdat->memcg_lru.seq); - else if (op == MEMCG_LRU_YOUNG) - new = get_memcg_gen(pgdat->memcg_lru.seq + 1); - else - VM_WARN_ON_ONCE(true); - - hlist_nulls_del_rcu(&lruvec->lrugen.list); - - if (op == MEMCG_LRU_HEAD || op == MEMCG_LRU_OLD) - hlist_nulls_add_head_rcu(&lruvec->lrugen.list, &pgdat->memcg_lru.fifo[new][bin]); - else - hlist_nulls_add_tail_rcu(&lruvec->lrugen.list, &pgdat->memcg_lru.fifo[new][bin]); - - pgdat->memcg_lru.nr_memcgs[old]--; - pgdat->memcg_lru.nr_memcgs[new]++; - - lruvec->lrugen.gen = new; - WRITE_ONCE(lruvec->lrugen.seg, seg); - - if (!pgdat->memcg_lru.nr_memcgs[old] && old == get_memcg_gen(pgdat->memcg_lru.seq)) - WRITE_ONCE(pgdat->memcg_lru.seq, pgdat->memcg_lru.seq + 1); - - spin_unlock(&pgdat->memcg_lru.lock); -} -#endif - /****************************************************************************** * state change ******************************************************************************/ @@ -6086,67 +6181,6 @@ void lru_gen_exit_memcg(struct mem_cgroup *memcg) } } -void lru_gen_online_memcg(struct mem_cgroup *memcg) -{ - int gen; - int nid; - int bin = get_random_u32_below(MEMCG_NR_BINS); - - for_each_node(nid) { - struct pglist_data *pgdat = NODE_DATA(nid); - struct lruvec *lruvec = get_lruvec(memcg, nid); - - spin_lock(&pgdat->memcg_lru.lock); - - VM_WARN_ON_ONCE(!hlist_nulls_unhashed(&lruvec->lrugen.list)); - - gen = get_memcg_gen(pgdat->memcg_lru.seq); - - hlist_nulls_add_tail_rcu(&lruvec->lrugen.list, &pgdat->memcg_lru.fifo[gen][bin]); - pgdat->memcg_lru.nr_memcgs[gen]++; - - lruvec->lrugen.gen = gen; - - spin_unlock(&pgdat->memcg_lru.lock); - } -} - -void lru_gen_offline_memcg(struct mem_cgroup *memcg) -{ - int nid; - - for_each_node(nid) { - struct lruvec *lruvec = get_lruvec(memcg, nid); - - lru_gen_rotate_memcg(lruvec, MEMCG_LRU_OLD); - } -} - -void lru_gen_release_memcg(struct mem_cgroup *memcg) -{ - int gen; - int nid; - - for_each_node(nid) { - struct pglist_data *pgdat = NODE_DATA(nid); - struct lruvec *lruvec = get_lruvec(memcg, nid); - - spin_lock(&pgdat->memcg_lru.lock); - - VM_WARN_ON_ONCE(hlist_nulls_unhashed(&lruvec->lrugen.list)); - - gen = lruvec->lrugen.gen; - - hlist_nulls_del_rcu(&lruvec->lrugen.list); - pgdat->memcg_lru.nr_memcgs[gen]--; - - if (!pgdat->memcg_lru.nr_memcgs[gen] && gen == get_memcg_gen(pgdat->memcg_lru.seq)) - WRITE_ONCE(pgdat->memcg_lru.seq, pgdat->memcg_lru.seq + 1); - - spin_unlock(&pgdat->memcg_lru.lock); - } -} - #endif /* CONFIG_MEMCG */ static int __init init_lru_gen(void) -- cgit v1.2.3 From 44b8f8bf2438bfee3aceae4d647a7460213ff340 Mon Sep 17 00:00:00 2001 From: Jiaqi Yan Date: Fri, 20 Jan 2023 03:46:20 +0000 Subject: mm: memory-failure: add memory failure stats to sysfs Patch series "Introduce per NUMA node memory error statistics", v2. Background ========== In the RFC for Kernel Support of Memory Error Detection [1], one advantage of software-based scanning over hardware patrol scrubber is the ability to make statistics visible to system administrators. The statistics include 2 categories: * Memory error statistics, for example, how many memory error are encountered, how many of them are recovered by the kernel. Note these memory errors are non-fatal to kernel: during the machine check exception (MCE) handling kernel already classified MCE's severity to be unnecessary to panic (but either action required or optional). * Scanner statistics, for example how many times the scanner have fully scanned a NUMA node, how many errors are first detected by the scanner. The memory error statistics are useful to userspace and actually not specific to scanner detected memory errors, and are the focus of this patchset. Motivation ========== Memory error stats are important to userspace but insufficient in kernel today. Datacenter administrators can better monitor a machine's memory health with the visible stats. For example, while memory errors are inevitable on servers with 10+ TB memory, starting server maintenance when there are only 1~2 recovered memory errors could be overreacting; in cloud production environment maintenance usually means live migrate all the workload running on the server and this usually causes nontrivial disruption to the customer. Providing insight into the scope of memory errors on a system helps to determine the appropriate follow-up action. In addition, the kernel's existing memory error stats need to be standardized so that userspace can reliably count on their usefulness. Today kernel provides following memory error info to userspace, but they are not sufficient or have disadvantages: * HardwareCorrupted in /proc/meminfo: number of bytes poisoned in total, not per NUMA node stats though * ras:memory_failure_event: only available after explicitly enabled * /dev/mcelog provides many useful info about the MCEs, but doesn't capture how memory_failure recovered memory MCEs * kernel logs: userspace needs to process log text Exposing memory error stats is also a good start for the in-kernel memory error detector. Today the data source of memory error stats are either direct memory error consumption, or hardware patrol scrubber detection (either signaled as UCNA or SRAO). Once in-kernel memory scanner is implemented, it will be the main source as it is usually configured to scan memory DIMMs constantly and faster than hardware patrol scrubber. How Implemented =============== As Naoya pointed out [2], exposing memory error statistics to userspace is useful independent of software or hardware scanner. Therefore we implement the memory error statistics independent of the in-kernel memory error detector. It exposes the following per NUMA node memory error counters: /sys/devices/system/node/node${X}/memory_failure/total /sys/devices/system/node/node${X}/memory_failure/recovered /sys/devices/system/node/node${X}/memory_failure/ignored /sys/devices/system/node/node${X}/memory_failure/failed /sys/devices/system/node/node${X}/memory_failure/delayed These counters describe how many raw pages are poisoned and after the attempted recoveries by the kernel, their resolutions: how many are recovered, ignored, failed, or delayed respectively. This approach can be easier to extend for future use cases than /proc/meminfo, trace event, and log. The following math holds for the statistics: * total = recovered + ignored + failed + delayed These memory error stats are reset during machine boot. The 1st commit introduces these sysfs entries. The 2nd commit populates memory error stats every time memory_failure attempts memory error recovery. The 3rd commit adds documentations for introduced stats. [1] https://lore.kernel.org/linux-mm/7E670362-C29E-4626-B546-26530D54F937@gmail.com/T/#mc22959244f5388891c523882e61163c6e4d703af [2] https://lore.kernel.org/linux-mm/7E670362-C29E-4626-B546-26530D54F937@gmail.com/T/#m52d8d7a333d8536bd7ce74253298858b1c0c0ac6 This patch (of 3): Today kernel provides following memory error info to userspace, but each has its own disadvantage * HardwareCorrupted in /proc/meminfo: number of bytes poisoned in total, not per NUMA node stats though * ras:memory_failure_event: only available after explicitly enabled * /dev/mcelog provides many useful info about the MCEs, but doesn't capture how memory_failure recovered memory MCEs * kernel logs: userspace needs to process log text Exposes per NUMA node memory error stats as sysfs entries: /sys/devices/system/node/node${X}/memory_failure/total /sys/devices/system/node/node${X}/memory_failure/recovered /sys/devices/system/node/node${X}/memory_failure/ignored /sys/devices/system/node/node${X}/memory_failure/failed /sys/devices/system/node/node${X}/memory_failure/delayed These counters describe how many raw pages are poisoned and after the attempted recoveries by the kernel, their resolutions: how many are recovered, ignored, failed, or delayed respectively. The following math holds for the statistics: * total = recovered + ignored + failed + delayed Link: https://lkml.kernel.org/r/20230120034622.2698268-1-jiaqiyan@google.com Link: https://lkml.kernel.org/r/20230120034622.2698268-2-jiaqiyan@google.com Signed-off-by: Jiaqi Yan Acked-by: David Rientjes Acked-by: Naoya Horiguchi Cc: Kefeng Wang Cc: Tony Luck Cc: Yang Shi Signed-off-by: Andrew Morton --- drivers/base/node.c | 3 +++ include/linux/mm.h | 5 +++++ include/linux/mmzone.h | 28 ++++++++++++++++++++++++++++ mm/memory-failure.c | 35 +++++++++++++++++++++++++++++++++++ 4 files changed, 71 insertions(+) (limited to 'include/linux') diff --git a/drivers/base/node.c b/drivers/base/node.c index faf3597a96da..b46db17124f3 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -586,6 +586,9 @@ static const struct attribute_group *node_dev_groups[] = { &node_dev_group, #ifdef CONFIG_HAVE_ARCH_NODE_DEV_GROUP &arch_node_dev_group, +#endif +#ifdef CONFIG_MEMORY_FAILURE + &memory_failure_attr_group, #endif NULL }; diff --git a/include/linux/mm.h b/include/linux/mm.h index 836b96e08a14..c9db257f09b3 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3455,6 +3455,11 @@ enum mf_action_page_type { MF_MSG_UNKNOWN, }; +/* + * Sysfs entries for memory failure handling statistics. + */ +extern const struct attribute_group memory_failure_attr_group; + #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS) extern void clear_huge_page(struct page *page, unsigned long addr_hint, diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 977be526c939..9fb1b03b83b2 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1212,6 +1212,31 @@ struct deferred_split { }; #endif +#ifdef CONFIG_MEMORY_FAILURE +/* + * Per NUMA node memory failure handling statistics. + */ +struct memory_failure_stats { + /* + * Number of raw pages poisoned. + * Cases not accounted: memory outside kernel control, offline page, + * arch-specific memory_failure (SGX), hwpoison_filter() filtered + * error events, and unpoison actions from hwpoison_unpoison. + */ + unsigned long total; + /* + * Recovery results of poisoned raw pages handled by memory_failure, + * in sync with mf_result. + * total = ignored + failed + delayed + recovered. + * total * PAGE_SIZE * #nodes = /proc/meminfo/HardwareCorrupted. + */ + unsigned long ignored; + unsigned long failed; + unsigned long delayed; + unsigned long recovered; +}; +#endif + /* * On NUMA machines, each NUMA node would have a pg_data_t to describe * it's memory layout. On UMA machines there is a single pglist_data which @@ -1357,6 +1382,9 @@ typedef struct pglist_data { #ifdef CONFIG_NUMA struct memory_tier __rcu *memtier; #endif +#ifdef CONFIG_MEMORY_FAILURE + struct memory_failure_stats mf_stats; +#endif } pg_data_t; #define node_present_pages(nid) (NODE_DATA(nid)->node_present_pages) diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 0a382191737f..44eec2e93a0b 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -87,6 +87,41 @@ inline void num_poisoned_pages_sub(unsigned long pfn, long i) memblk_nr_poison_sub(pfn, i); } +/** + * MF_ATTR_RO - Create sysfs entry for each memory failure statistics. + * @_name: name of the file in the per NUMA sysfs directory. + */ +#define MF_ATTR_RO(_name) \ +static ssize_t _name##_show(struct device *dev, \ + struct device_attribute *attr, \ + char *buf) \ +{ \ + struct memory_failure_stats *mf_stats = \ + &NODE_DATA(dev->id)->mf_stats; \ + return sprintf(buf, "%lu\n", mf_stats->_name); \ +} \ +static DEVICE_ATTR_RO(_name) + +MF_ATTR_RO(total); +MF_ATTR_RO(ignored); +MF_ATTR_RO(failed); +MF_ATTR_RO(delayed); +MF_ATTR_RO(recovered); + +static struct attribute *memory_failure_attr[] = { + &dev_attr_total.attr, + &dev_attr_ignored.attr, + &dev_attr_failed.attr, + &dev_attr_delayed.attr, + &dev_attr_recovered.attr, + NULL, +}; + +const struct attribute_group memory_failure_attr_group = { + .name = "memory_failure", + .attrs = memory_failure_attr, +}; + /* * Return values: * 1: the page is dissolved (if needed) and taken off from buddy, -- cgit v1.2.3 From 3222d8c2a7f888bf38b845b125e9470b12108a4d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 25 Jan 2023 14:34:36 +0100 Subject: block: remove ->rw_page The ->rw_page method is a special purpose bypass of the usual bio handling path that is limited to single-page reads and writes and synchronous which causes a lot of extra code in the drivers, callers and the block layer. The only remaining user is the MM swap code. Switch that swap code to simply submit a single-vec on-stack bio an synchronously wait on it based on a newly added QUEUE_FLAG_SYNCHRONOUS flag set by the drivers that currently implement ->rw_page instead. While this touches one extra cache line and executes extra code, it simplifies the block layer and drivers and ensures that all feastures are properly supported by all drivers, e.g. right now ->rw_page bypassed cgroup writeback entirely. [akpm@linux-foundation.org: fix comment typo, per Dan] Link: https://lkml.kernel.org/r/20230125133436.447864-8-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Dan Williams Cc: Dave Jiang Cc: Ira Weiny Cc: Jens Axboe Cc: Keith Busch Cc: Minchan Kim Cc: Sergey Senozhatsky Cc: Vishal Verma Signed-off-by: Andrew Morton --- block/bdev.c | 78 ------------------------------------------- drivers/block/brd.c | 15 +-------- drivers/block/zram/zram_drv.c | 61 +-------------------------------- drivers/nvdimm/btt.c | 16 +-------- drivers/nvdimm/pmem.c | 24 +------------ include/linux/blkdev.h | 12 ++++--- mm/page_io.c | 53 +++++++++++++++++------------ mm/swapfile.c | 2 +- 8 files changed, 44 insertions(+), 217 deletions(-) (limited to 'include/linux') diff --git a/block/bdev.c b/block/bdev.c index edc110d90df4..1795c7d4b99e 100644 --- a/block/bdev.c +++ b/block/bdev.c @@ -304,84 +304,6 @@ out: } EXPORT_SYMBOL(thaw_bdev); -/** - * bdev_read_page() - Start reading a page from a block device - * @bdev: The device to read the page from - * @sector: The offset on the device to read the page to (need not be aligned) - * @page: The page to read - * - * On entry, the page should be locked. It will be unlocked when the page - * has been read. If the block driver implements rw_page synchronously, - * that will be true on exit from this function, but it need not be. - * - * Errors returned by this function are usually "soft", eg out of memory, or - * queue full; callers should try a different route to read this page rather - * than propagate an error back up the stack. - * - * Return: negative errno if an error occurs, 0 if submission was successful. - */ -int bdev_read_page(struct block_device *bdev, sector_t sector, - struct page *page) -{ - const struct block_device_operations *ops = bdev->bd_disk->fops; - int result = -EOPNOTSUPP; - - if (!ops->rw_page || bdev_get_integrity(bdev)) - return result; - - result = blk_queue_enter(bdev_get_queue(bdev), 0); - if (result) - return result; - result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, - REQ_OP_READ); - blk_queue_exit(bdev_get_queue(bdev)); - return result; -} - -/** - * bdev_write_page() - Start writing a page to a block device - * @bdev: The device to write the page to - * @sector: The offset on the device to write the page to (need not be aligned) - * @page: The page to write - * @wbc: The writeback_control for the write - * - * On entry, the page should be locked and not currently under writeback. - * On exit, if the write started successfully, the page will be unlocked and - * under writeback. If the write failed already (eg the driver failed to - * queue the page to the device), the page will still be locked. If the - * caller is a ->writepage implementation, it will need to unlock the page. - * - * Errors returned by this function are usually "soft", eg out of memory, or - * queue full; callers should try a different route to write this page rather - * than propagate an error back up the stack. - * - * Return: negative errno if an error occurs, 0 if submission was successful. - */ -int bdev_write_page(struct block_device *bdev, sector_t sector, - struct page *page, struct writeback_control *wbc) -{ - int result; - const struct block_device_operations *ops = bdev->bd_disk->fops; - - if (!ops->rw_page || bdev_get_integrity(bdev)) - return -EOPNOTSUPP; - result = blk_queue_enter(bdev_get_queue(bdev), 0); - if (result) - return result; - - set_page_writeback(page); - result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, - REQ_OP_WRITE); - if (result) { - end_page_writeback(page); - } else { - clean_page_buffers(page); - unlock_page(page); - } - blk_queue_exit(bdev_get_queue(bdev)); - return result; -} - /* * pseudo-fs */ diff --git a/drivers/block/brd.c b/drivers/block/brd.c index 20acc4a1fd6d..37dce184eb56 100644 --- a/drivers/block/brd.c +++ b/drivers/block/brd.c @@ -309,23 +309,9 @@ static void brd_submit_bio(struct bio *bio) bio_endio(bio); } -static int brd_rw_page(struct block_device *bdev, sector_t sector, - struct page *page, enum req_op op) -{ - struct brd_device *brd = bdev->bd_disk->private_data; - int err; - - if (PageTransHuge(page)) - return -ENOTSUPP; - err = brd_do_bvec(brd, page, PAGE_SIZE, 0, op, sector); - page_endio(page, op_is_write(op), err); - return err; -} - static const struct block_device_operations brd_fops = { .owner = THIS_MODULE, .submit_bio = brd_submit_bio, - .rw_page = brd_rw_page, }; /* @@ -411,6 +397,7 @@ static int brd_alloc(int i) /* Tell the block layer that this is not a rotational device */ blk_queue_flag_set(QUEUE_FLAG_NONROT, disk->queue); + blk_queue_flag_set(QUEUE_FLAG_SYNCHRONOUS, disk->queue); blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, disk->queue); err = add_disk(disk); if (err) diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 5d1088a645e3..25526707f607 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -1453,10 +1453,6 @@ static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index, /* Slot should be unlocked before the function call */ zram_slot_unlock(zram, index); - /* A null bio means rw_page was used, we must fallback to bio */ - if (!bio) - return -EOPNOTSUPP; - ret = zram_bvec_read_from_bdev(zram, page, index, bio, partial_io); } @@ -2081,61 +2077,6 @@ static void zram_slot_free_notify(struct block_device *bdev, zram_slot_unlock(zram, index); } -static int zram_rw_page(struct block_device *bdev, sector_t sector, - struct page *page, enum req_op op) -{ - int offset, ret; - u32 index; - struct zram *zram; - struct bio_vec bv; - unsigned long start_time; - - if (PageTransHuge(page)) - return -ENOTSUPP; - zram = bdev->bd_disk->private_data; - - if (!valid_io_request(zram, sector, PAGE_SIZE)) { - atomic64_inc(&zram->stats.invalid_io); - ret = -EINVAL; - goto out; - } - - index = sector >> SECTORS_PER_PAGE_SHIFT; - offset = (sector & (SECTORS_PER_PAGE - 1)) << SECTOR_SHIFT; - - bv.bv_page = page; - bv.bv_len = PAGE_SIZE; - bv.bv_offset = 0; - - start_time = bdev_start_io_acct(bdev->bd_disk->part0, - SECTORS_PER_PAGE, op, jiffies); - ret = zram_bvec_rw(zram, &bv, index, offset, op, NULL); - bdev_end_io_acct(bdev->bd_disk->part0, op, start_time); -out: - /* - * If I/O fails, just return error(ie, non-zero) without - * calling page_endio. - * It causes resubmit the I/O with bio request by upper functions - * of rw_page(e.g., swap_readpage, __swap_writepage) and - * bio->bi_end_io does things to handle the error - * (e.g., SetPageError, set_page_dirty and extra works). - */ - if (unlikely(ret < 0)) - return ret; - - switch (ret) { - case 0: - page_endio(page, op_is_write(op), 0); - break; - case 1: - ret = 0; - break; - default: - WARN_ON(1); - } - return ret; -} - static void zram_destroy_comps(struct zram *zram) { u32 prio; @@ -2290,7 +2231,6 @@ static const struct block_device_operations zram_devops = { .open = zram_open, .submit_bio = zram_submit_bio, .swap_slot_free_notify = zram_slot_free_notify, - .rw_page = zram_rw_page, .owner = THIS_MODULE }; @@ -2389,6 +2329,7 @@ static int zram_add(void) set_capacity(zram->disk, 0); /* zram devices sort of resembles non-rotational disks */ blk_queue_flag_set(QUEUE_FLAG_NONROT, zram->disk->queue); + blk_queue_flag_set(QUEUE_FLAG_SYNCHRONOUS, zram->disk->queue); blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, zram->disk->queue); /* diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c index 0297b7882e33..d5593b0dc700 100644 --- a/drivers/nvdimm/btt.c +++ b/drivers/nvdimm/btt.c @@ -1482,20 +1482,6 @@ static void btt_submit_bio(struct bio *bio) bio_endio(bio); } -static int btt_rw_page(struct block_device *bdev, sector_t sector, - struct page *page, enum req_op op) -{ - struct btt *btt = bdev->bd_disk->private_data; - int rc; - - rc = btt_do_bvec(btt, NULL, page, thp_size(page), 0, op, sector); - if (rc == 0) - page_endio(page, op_is_write(op), 0); - - return rc; -} - - static int btt_getgeo(struct block_device *bd, struct hd_geometry *geo) { /* some standard values */ @@ -1508,7 +1494,6 @@ static int btt_getgeo(struct block_device *bd, struct hd_geometry *geo) static const struct block_device_operations btt_fops = { .owner = THIS_MODULE, .submit_bio = btt_submit_bio, - .rw_page = btt_rw_page, .getgeo = btt_getgeo, }; @@ -1530,6 +1515,7 @@ static int btt_blk_init(struct btt *btt) blk_queue_logical_block_size(btt->btt_disk->queue, btt->sector_size); blk_queue_max_hw_sectors(btt->btt_disk->queue, UINT_MAX); blk_queue_flag_set(QUEUE_FLAG_NONROT, btt->btt_disk->queue); + blk_queue_flag_set(QUEUE_FLAG_SYNCHRONOUS, btt->btt_disk->queue); if (btt_meta_size(btt)) { rc = nd_integrity_init(btt->btt_disk, btt_meta_size(btt)); diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index 96e6e9a5f235..ceea55f621cc 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -238,28 +238,6 @@ static void pmem_submit_bio(struct bio *bio) bio_endio(bio); } -static int pmem_rw_page(struct block_device *bdev, sector_t sector, - struct page *page, enum req_op op) -{ - struct pmem_device *pmem = bdev->bd_disk->private_data; - blk_status_t rc; - - if (op_is_write(op)) - rc = pmem_do_write(pmem, page, 0, sector, thp_size(page)); - else - rc = pmem_do_read(pmem, page, 0, sector, thp_size(page)); - /* - * The ->rw_page interface is subtle and tricky. The core - * retries on any error, so we can only invoke page_endio() in - * the successful completion case. Otherwise, we'll see crashes - * caused by double completion. - */ - if (rc == 0) - page_endio(page, op_is_write(op), 0); - - return blk_status_to_errno(rc); -} - /* see "strong" declaration in tools/testing/nvdimm/pmem-dax.c */ __weak long __pmem_direct_access(struct pmem_device *pmem, pgoff_t pgoff, long nr_pages, enum dax_access_mode mode, void **kaddr, @@ -310,7 +288,6 @@ __weak long __pmem_direct_access(struct pmem_device *pmem, pgoff_t pgoff, static const struct block_device_operations pmem_fops = { .owner = THIS_MODULE, .submit_bio = pmem_submit_bio, - .rw_page = pmem_rw_page, }; static int pmem_dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff, @@ -565,6 +542,7 @@ static int pmem_attach_disk(struct device *dev, blk_queue_logical_block_size(q, pmem_sector_size(ndns)); blk_queue_max_hw_sectors(q, UINT_MAX); blk_queue_flag_set(QUEUE_FLAG_NONROT, q); + blk_queue_flag_set(QUEUE_FLAG_SYNCHRONOUS, q); if (pmem->pfn_flags & PFN_MAP) blk_queue_flag_set(QUEUE_FLAG_DAX, q); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 43d4e073b111..c5e59965b145 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -554,6 +554,7 @@ struct request_queue { #define QUEUE_FLAG_IO_STAT 7 /* do disk/partitions IO accounting */ #define QUEUE_FLAG_NOXMERGES 9 /* No extended merges */ #define QUEUE_FLAG_ADD_RANDOM 10 /* Contributes to random pool */ +#define QUEUE_FLAG_SYNCHRONOUS 11 /* always completes in submit context */ #define QUEUE_FLAG_SAME_FORCE 12 /* force complete on same CPU */ #define QUEUE_FLAG_INIT_DONE 14 /* queue is initialized */ #define QUEUE_FLAG_STABLE_WRITES 15 /* don't modify blks until WB is done */ @@ -1250,6 +1251,12 @@ static inline bool bdev_nonrot(struct block_device *bdev) return blk_queue_nonrot(bdev_get_queue(bdev)); } +static inline bool bdev_synchronous(struct block_device *bdev) +{ + return test_bit(QUEUE_FLAG_SYNCHRONOUS, + &bdev_get_queue(bdev)->queue_flags); +} + static inline bool bdev_stable_writes(struct block_device *bdev) { return test_bit(QUEUE_FLAG_STABLE_WRITES, @@ -1382,7 +1389,6 @@ struct block_device_operations { unsigned int flags); int (*open) (struct block_device *, fmode_t); void (*release) (struct gendisk *, fmode_t); - int (*rw_page)(struct block_device *, sector_t, struct page *, enum req_op); int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); unsigned int (*check_events) (struct gendisk *disk, @@ -1417,10 +1423,6 @@ extern int blkdev_compat_ptr_ioctl(struct block_device *, fmode_t, #define blkdev_compat_ptr_ioctl NULL #endif -extern int bdev_read_page(struct block_device *, sector_t, struct page *); -extern int bdev_write_page(struct block_device *, sector_t, struct page *, - struct writeback_control *); - static inline void blk_wake_io_task(struct task_struct *waiter) { /* diff --git a/mm/page_io.c b/mm/page_io.c index 0a1a3b831344..a805117f7fd7 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -27,7 +27,7 @@ #include #include "swap.h" -static void end_swap_bio_write(struct bio *bio) +static void __end_swap_bio_write(struct bio *bio) { struct page *page = bio_first_page_all(bio); @@ -48,6 +48,11 @@ static void end_swap_bio_write(struct bio *bio) ClearPageReclaim(page); } end_page_writeback(page); +} + +static void end_swap_bio_write(struct bio *bio) +{ + __end_swap_bio_write(bio); bio_put(bio); } @@ -326,15 +331,31 @@ static void swap_writepage_fs(struct page *page, struct writeback_control *wbc) *wbc->swap_plug = sio; } -static void swap_writepage_bdev(struct page *page, +static void swap_writepage_bdev_sync(struct page *page, struct writeback_control *wbc, struct swap_info_struct *sis) { - struct bio *bio; + struct bio_vec bv; + struct bio bio; - if (!bdev_write_page(sis->bdev, swap_page_sector(page), page, wbc)) { - count_swpout_vm_event(page); - return; - } + bio_init(&bio, sis->bdev, &bv, 1, + REQ_OP_WRITE | REQ_SWAP | wbc_to_write_flags(wbc)); + bio.bi_iter.bi_sector = swap_page_sector(page); + bio_add_page(&bio, page, thp_size(page), 0); + + bio_associate_blkg_from_page(&bio, page); + count_swpout_vm_event(page); + + set_page_writeback(page); + unlock_page(page); + + submit_bio_wait(&bio); + __end_swap_bio_write(&bio); +} + +static void swap_writepage_bdev_async(struct page *page, + struct writeback_control *wbc, struct swap_info_struct *sis) +{ + struct bio *bio; bio = bio_alloc(sis->bdev, 1, REQ_OP_WRITE | REQ_SWAP | wbc_to_write_flags(wbc), @@ -362,8 +383,10 @@ void __swap_writepage(struct page *page, struct writeback_control *wbc) */ if (data_race(sis->flags & SWP_FS_OPS)) swap_writepage_fs(page, wbc); + else if (sis->flags & SWP_SYNCHRONOUS_IO) + swap_writepage_bdev_sync(page, wbc, sis); else - swap_writepage_bdev(page, wbc, sis); + swap_writepage_bdev_async(page, wbc, sis); } void swap_write_unplug(struct swap_iocb *sio) @@ -447,12 +470,6 @@ static void swap_readpage_bdev_sync(struct page *page, struct bio_vec bv; struct bio bio; - if ((sis->flags & SWP_SYNCHRONOUS_IO) && - !bdev_read_page(sis->bdev, swap_page_sector(page), page)) { - count_vm_event(PSWPIN); - return; - } - bio_init(&bio, sis->bdev, &bv, 1, REQ_OP_READ); bio.bi_iter.bi_sector = swap_page_sector(page); bio_add_page(&bio, page, thp_size(page), 0); @@ -472,12 +489,6 @@ static void swap_readpage_bdev_async(struct page *page, { struct bio *bio; - if ((sis->flags & SWP_SYNCHRONOUS_IO) && - !bdev_read_page(sis->bdev, swap_page_sector(page), page)) { - count_vm_event(PSWPIN); - return; - } - bio = bio_alloc(sis->bdev, 1, REQ_OP_READ, GFP_KERNEL); bio->bi_iter.bi_sector = swap_page_sector(page); bio->bi_end_io = end_swap_bio_read; @@ -513,7 +524,7 @@ void swap_readpage(struct page *page, bool synchronous, struct swap_iocb **plug) unlock_page(page); } else if (data_race(sis->flags & SWP_FS_OPS)) { swap_readpage_fs(page, plug); - } else if (synchronous) { + } else if (synchronous || (sis->flags & SWP_SYNCHRONOUS_IO)) { swap_readpage_bdev_sync(page, sis); } else { swap_readpage_bdev_async(page, sis); diff --git a/mm/swapfile.c b/mm/swapfile.c index af151679d13a..888aed774fb6 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -3071,7 +3071,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) if (p->bdev && bdev_stable_writes(p->bdev)) p->flags |= SWP_STABLE_WRITES; - if (p->bdev && p->bdev->bd_disk->fops->rw_page) + if (p->bdev && bdev_synchronous(p->bdev)) p->flags |= SWP_SYNCHRONOUS_IO; if (p->bdev && bdev_nonrot(p->bdev)) { -- cgit v1.2.3 From 00cdf76012ab78b225345e8cf77d5391b4680b45 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox (Oracle) Date: Thu, 26 Jan 2023 20:15:52 +0000 Subject: mm: add memcpy_from_file_folio() This is the equivalent of memcpy_from_page(). It differs in that it takes the position in a file instead of offset in a folio, it accepts the total number of bytes to be copied (instead of the number of bytes to be copied from this folio) and it returns how many bytes were copied from the folio, rather than making the caller calculate that and then checking if the caller got it right. [akpm@linux-foundation.org: fix typo in comment] Link: https://lkml.kernel.org/r/20230126201552.1681588-1-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Cc: "Fabio M. De Francesco" Cc: Ira Weiny Signed-off-by: Andrew Morton --- include/linux/highmem.h | 29 +++++++++++++++++++++++++++++ include/linux/page-flags.h | 1 + 2 files changed, 30 insertions(+) (limited to 'include/linux') diff --git a/include/linux/highmem.h b/include/linux/highmem.h index e22509420ac6..348701dae77f 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -413,6 +413,35 @@ static inline void memzero_page(struct page *page, size_t offset, size_t len) kunmap_local(addr); } +/** + * memcpy_from_file_folio - Copy some bytes from a file folio. + * @to: The destination buffer. + * @folio: The folio to copy from. + * @pos: The position in the file. + * @len: The maximum number of bytes to copy. + * + * Copy up to @len bytes from this folio. This may be limited by PAGE_SIZE + * if the folio comes from HIGHMEM, and by the size of the folio. + * + * Return: The number of bytes copied from the folio. + */ +static inline size_t memcpy_from_file_folio(char *to, struct folio *folio, + loff_t pos, size_t len) +{ + size_t offset = offset_in_folio(folio, pos); + char *from = kmap_local_folio(folio, offset); + + if (folio_test_highmem(folio)) + len = min_t(size_t, len, PAGE_SIZE - offset); + else + len = min(len, folio_size(folio) - offset); + + memcpy(to, from, len); + kunmap_local(from); + + return len; +} + /** * folio_zero_segments() - Zero two byte ranges in a folio. * @folio: The folio to write to. diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 69e93a0c1277..a7e3a3405520 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -531,6 +531,7 @@ PAGEFLAG(Readahead, readahead, PF_NO_COMPOUND) * available at this point. */ #define PageHighMem(__p) is_highmem_idx(page_zonenum(__p)) +#define folio_test_highmem(__f) is_highmem_idx(folio_zonenum(__f)) #else PAGEFLAG_FALSE(HighMem, highmem) #endif -- cgit v1.2.3 From d585bdbeb79aa13b8a9bbe952d90f5252f7fe909 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox (Oracle) Date: Thu, 26 Jan 2023 20:12:54 +0000 Subject: fs: convert writepage_t callback to pass a folio Patch series "Convert writepage_t to use a folio". More folioisation. I split out the mpage work from everything else because it completely dominated the patch, but some implementations I just converted outright. This patch (of 2): We always write back an entire folio, but that's currently passed as the head page. Convert all filesystems that use write_cache_pages() to expect a folio instead of a page. Link: https://lkml.kernel.org/r/20230126201255.1681189-1-willy@infradead.org Link: https://lkml.kernel.org/r/20230126201255.1681189-2-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Cc: Christoph Hellwig Signed-off-by: Andrew Morton --- fs/cifs/file.c | 8 ++++---- fs/ext4/inode.c | 4 ++-- fs/ext4/super.c | 6 +++--- fs/fuse/file.c | 18 +++++++++--------- fs/iomap/buffered-io.c | 5 ++--- fs/mpage.c | 3 ++- fs/nfs/write.c | 7 ++++--- fs/ntfs3/inode.c | 6 +++--- fs/orangefs/inode.c | 23 +++++++++++------------ include/linux/writeback.h | 2 +- mm/page-writeback.c | 6 +++--- 11 files changed, 44 insertions(+), 44 deletions(-) (limited to 'include/linux') diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 8cdd2f67af24..162fab5a4583 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -2675,14 +2675,14 @@ wdata_send_pages(struct cifs_writedata *wdata, unsigned int nr_pages, static int cifs_writepage_locked(struct page *page, struct writeback_control *wbc); -static int cifs_write_one_page(struct page *page, struct writeback_control *wbc, - void *data) +static int cifs_write_one_page(struct folio *folio, + struct writeback_control *wbc, void *data) { struct address_space *mapping = data; int ret; - ret = cifs_writepage_locked(page, wbc); - unlock_page(page); + ret = cifs_writepage_locked(&folio->page, wbc); + folio_unlock(folio); mapping_set_error(mapping, ret); return ret; } diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index fb6cd994e59a..98c018dcd3fd 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2711,10 +2711,10 @@ out: return err; } -static int ext4_writepage_cb(struct page *page, struct writeback_control *wbc, +static int ext4_writepage_cb(struct folio *folio, struct writeback_control *wbc, void *data) { - return ext4_writepage(page, wbc); + return ext4_writepage(&folio->page, wbc); } static int ext4_do_writepages(struct mpage_da_data *mpd) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 260c1b3e3ef2..49a8942b1e51 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -482,7 +482,7 @@ static void ext4_journal_commit_callback(journal_t *journal, transaction_t *txn) * * However, we may have to redirty a page (see below.) */ -static int ext4_journalled_writepage_callback(struct page *page, +static int ext4_journalled_writepage_callback(struct folio *folio, struct writeback_control *wbc, void *data) { @@ -490,7 +490,7 @@ static int ext4_journalled_writepage_callback(struct page *page, struct buffer_head *bh, *head; struct journal_head *jh; - bh = head = page_buffers(page); + bh = head = folio_buffers(folio); do { /* * We have to redirty a page in these cases: @@ -509,7 +509,7 @@ static int ext4_journalled_writepage_callback(struct page *page, if (buffer_dirty(bh) || (jh && (jh->b_transaction != transaction || jh->b_next_transaction))) { - redirty_page_for_writepage(wbc, page); + folio_redirty_for_writepage(wbc, folio); goto out; } } while ((bh = bh->b_this_page) != head); diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 875314ee6f59..3648747fb64d 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -2184,7 +2184,7 @@ static bool fuse_writepage_need_send(struct fuse_conn *fc, struct page *page, return false; } -static int fuse_writepages_fill(struct page *page, +static int fuse_writepages_fill(struct folio *folio, struct writeback_control *wbc, void *_data) { struct fuse_fill_wb_data *data = _data; @@ -2203,7 +2203,7 @@ static int fuse_writepages_fill(struct page *page, goto out_unlock; } - if (wpa && fuse_writepage_need_send(fc, page, ap, data)) { + if (wpa && fuse_writepage_need_send(fc, &folio->page, ap, data)) { fuse_writepages_send(data); data->wpa = NULL; } @@ -2238,7 +2238,7 @@ static int fuse_writepages_fill(struct page *page, data->max_pages = 1; ap = &wpa->ia.ap; - fuse_write_args_fill(&wpa->ia, data->ff, page_offset(page), 0); + fuse_write_args_fill(&wpa->ia, data->ff, folio_pos(folio), 0); wpa->ia.write.in.write_flags |= FUSE_WRITE_CACHE; wpa->next = NULL; ap->args.in_pages = true; @@ -2246,13 +2246,13 @@ static int fuse_writepages_fill(struct page *page, ap->num_pages = 0; wpa->inode = inode; } - set_page_writeback(page); + folio_start_writeback(folio); - copy_highpage(tmp_page, page); + copy_highpage(tmp_page, &folio->page); ap->pages[ap->num_pages] = tmp_page; ap->descs[ap->num_pages].offset = 0; ap->descs[ap->num_pages].length = PAGE_SIZE; - data->orig_pages[ap->num_pages] = page; + data->orig_pages[ap->num_pages] = &folio->page; inc_wb_stat(&inode_to_bdi(inode)->wb, WB_WRITEBACK); inc_node_page_state(tmp_page, NR_WRITEBACK_TEMP); @@ -2266,13 +2266,13 @@ static int fuse_writepages_fill(struct page *page, spin_lock(&fi->lock); ap->num_pages++; spin_unlock(&fi->lock); - } else if (fuse_writepage_add(wpa, page)) { + } else if (fuse_writepage_add(wpa, &folio->page)) { data->wpa = wpa; } else { - end_page_writeback(page); + folio_end_writeback(folio); } out_unlock: - unlock_page(page); + folio_unlock(folio); return err; } diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 356193e44cf0..292d273a2c80 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -1685,10 +1685,9 @@ done: * For unwritten space on the page, we need to start the conversion to * regular allocated space. */ -static int -iomap_do_writepage(struct page *page, struct writeback_control *wbc, void *data) +static int iomap_do_writepage(struct folio *folio, + struct writeback_control *wbc, void *data) { - struct folio *folio = page_folio(page); struct iomap_writepage_ctx *wpc = data; struct inode *inode = folio->mapping->host; u64 end_pos, isize; diff --git a/fs/mpage.c b/fs/mpage.c index 55988ea994ee..4890369bb10a 100644 --- a/fs/mpage.c +++ b/fs/mpage.c @@ -440,9 +440,10 @@ void clean_page_buffers(struct page *page) clean_buffers(page, ~0U); } -static int __mpage_writepage(struct page *page, struct writeback_control *wbc, +static int __mpage_writepage(struct folio *folio, struct writeback_control *wbc, void *data) { + struct page *page = &folio->page; struct mpage_data *mpd = data; struct bio *bio = mpd->bio; struct address_space *mapping = page->mapping; diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 80c240e50952..9d6432cb3f44 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -689,13 +689,14 @@ int nfs_writepage(struct page *page, struct writeback_control *wbc) return ret; } -static int nfs_writepages_callback(struct page *page, struct writeback_control *wbc, void *data) +static int nfs_writepages_callback(struct folio *folio, + struct writeback_control *wbc, void *data) { int ret; - ret = nfs_do_writepage(page, wbc, data); + ret = nfs_do_writepage(&folio->page, wbc, data); if (ret != AOP_WRITEPAGE_ACTIVATE) - unlock_page(page); + folio_unlock(folio); return ret; } diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c index 6b50b6e32378..9c646615f714 100644 --- a/fs/ntfs3/inode.c +++ b/fs/ntfs3/inode.c @@ -832,7 +832,7 @@ out: return err; } -static int ntfs_resident_writepage(struct page *page, +static int ntfs_resident_writepage(struct folio *folio, struct writeback_control *wbc, void *data) { struct address_space *mapping = data; @@ -840,11 +840,11 @@ static int ntfs_resident_writepage(struct page *page, int ret; ni_lock(ni); - ret = attr_data_write_resident(ni, page); + ret = attr_data_write_resident(ni, &folio->page); ni_unlock(ni); if (ret != E_NTFS_NONRESIDENT) - unlock_page(page); + folio_unlock(folio); mapping_set_error(mapping, ret); return ret; } diff --git a/fs/orangefs/inode.c b/fs/orangefs/inode.c index 4df560894386..c25468974c8a 100644 --- a/fs/orangefs/inode.c +++ b/fs/orangefs/inode.c @@ -154,21 +154,20 @@ static int orangefs_writepages_work(struct orangefs_writepages *ow, return ret; } -static int orangefs_writepages_callback(struct page *page, - struct writeback_control *wbc, void *data) +static int orangefs_writepages_callback(struct folio *folio, + struct writeback_control *wbc, void *data) { struct orangefs_writepages *ow = data; - struct orangefs_write_range *wr; + struct orangefs_write_range *wr = folio->private; int ret; - if (!PagePrivate(page)) { - unlock_page(page); + if (!wr) { + folio_unlock(folio); /* It's not private so there's nothing to write, right? */ printk("writepages_callback not private!\n"); BUG(); return 0; } - wr = (struct orangefs_write_range *)page_private(page); ret = -1; if (ow->npages == 0) { @@ -176,7 +175,7 @@ static int orangefs_writepages_callback(struct page *page, ow->len = wr->len; ow->uid = wr->uid; ow->gid = wr->gid; - ow->pages[ow->npages++] = page; + ow->pages[ow->npages++] = &folio->page; ret = 0; goto done; } @@ -188,7 +187,7 @@ static int orangefs_writepages_callback(struct page *page, } if (ow->off + ow->len == wr->pos) { ow->len += wr->len; - ow->pages[ow->npages++] = page; + ow->pages[ow->npages++] = &folio->page; ret = 0; goto done; } @@ -198,10 +197,10 @@ done: orangefs_writepages_work(ow, wbc); ow->npages = 0; } - ret = orangefs_writepage_locked(page, wbc); - mapping_set_error(page->mapping, ret); - unlock_page(page); - end_page_writeback(page); + ret = orangefs_writepage_locked(&folio->page, wbc); + mapping_set_error(folio->mapping, ret); + folio_unlock(folio); + folio_end_writeback(folio); } else { if (ow->npages == ow->maxpages) { orangefs_writepages_work(ow, wbc); diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 3f1491b07474..46020373e155 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -366,7 +366,7 @@ int balance_dirty_pages_ratelimited_flags(struct address_space *mapping, bool wb_over_bg_thresh(struct bdi_writeback *wb); -typedef int (*writepage_t)(struct page *page, struct writeback_control *wbc, +typedef int (*writepage_t)(struct folio *folio, struct writeback_control *wbc, void *data); void tag_pages_for_writeback(struct address_space *mapping, diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 92b90d2ab513..516b1aa247e8 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2470,7 +2470,7 @@ continue_unlock: goto continue_unlock; trace_wbc_writepage(wbc, inode_to_bdi(mapping->host)); - error = writepage(&folio->page, wbc, data); + error = writepage(folio, wbc, data); if (unlikely(error)) { /* * Handle errors according to the type of @@ -2528,11 +2528,11 @@ continue_unlock: } EXPORT_SYMBOL(write_cache_pages); -static int writepage_cb(struct page *page, struct writeback_control *wbc, +static int writepage_cb(struct folio *folio, struct writeback_control *wbc, void *data) { struct address_space *mapping = data; - int ret = mapping->a_ops->writepage(page, wbc); + int ret = mapping->a_ops->writepage(&folio->page, wbc); mapping_set_error(mapping, ret); return ret; } -- cgit v1.2.3 From 6338bb05c15f88e2f4beae296ef389224837758c Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu (Google) Date: Mon, 12 Dec 2022 11:46:44 +0900 Subject: error-injection: remove EI_ETYPE_NONE Patch series "error-injection: Clarify the requirements of error injectable functions". Patches for clarifying the requirement of error injectable functions and to remove the confusing EI_ETYPE_NONE. This patch (of 2): Since the EI_ETYPE_NONE is confusing type, replace it with appropriate errno. The EI_ETYPE_NONE has been introduced for a dummy (error) value, but it can mislead people that they can use ALLOW_ERROR_INJECTION(func, NONE). So remove it from the EI_ETYPE and use appropriate errno instead. [akpm@linux-foundation.org: include/linux/error-injection.h needs errno.h] Link: https://lkml.kernel.org/r/167081319306.387937.10079195394503045678.stgit@devnote3 Link: https://lkml.kernel.org/r/167081320421.387937.4259807348852421112.stgit@devnote3 Fixes: 663faf9f7bee ("error-injection: Add injectable error types") Signed-off-by: Masami Hiramatsu (Google) Cc: Alexei Starovoitov Cc: Borislav Petkov (AMD) Cc: Chris Mason Cc: Christoph Hellwig Cc: Florent Revest Cc: Greg Kroah-Hartman Cc: Jonathan Corbet Cc: Josh Poimboeuf Cc: Kees Cook Cc: KP Singh Cc: Mark Rutland Cc: Peter Zijlstra Cc: Steven Rostedt (Google) Signed-off-by: Andrew Morton --- include/asm-generic/error-injection.h | 1 - include/linux/error-injection.h | 3 ++- lib/error-inject.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/asm-generic/error-injection.h b/include/asm-generic/error-injection.h index fbca56bd9cbc..c0b9d3217ed9 100644 --- a/include/asm-generic/error-injection.h +++ b/include/asm-generic/error-injection.h @@ -4,7 +4,6 @@ #if defined(__KERNEL__) && !defined(__ASSEMBLY__) enum { - EI_ETYPE_NONE, /* Dummy value for undefined case */ EI_ETYPE_NULL, /* Return NULL if failure */ EI_ETYPE_ERRNO, /* Return -ERRNO if failure */ EI_ETYPE_ERRNO_NULL, /* Return -ERRNO or NULL if failure */ diff --git a/include/linux/error-injection.h b/include/linux/error-injection.h index 635a95caf29f..20e738f4eae8 100644 --- a/include/linux/error-injection.h +++ b/include/linux/error-injection.h @@ -3,6 +3,7 @@ #define _LINUX_ERROR_INJECTION_H #include +#include #include #ifdef CONFIG_FUNCTION_ERROR_INJECTION @@ -19,7 +20,7 @@ static inline bool within_error_injection_list(unsigned long addr) static inline int get_injectable_error_type(unsigned long addr) { - return EI_ETYPE_NONE; + return -EOPNOTSUPP; } #endif diff --git a/lib/error-inject.c b/lib/error-inject.c index 1afca1b1cdea..32c14770508e 100644 --- a/lib/error-inject.c +++ b/lib/error-inject.c @@ -40,7 +40,7 @@ bool within_error_injection_list(unsigned long addr) int get_injectable_error_type(unsigned long addr) { struct ei_entry *ent; - int ei_type = EI_ETYPE_NONE; + int ei_type = -EINVAL; mutex_lock(&ei_mutex); list_for_each_entry(ent, &error_injection_list, list) { -- cgit v1.2.3 From 88ad32a799ddc92eafd2ae204cb43f04ac20a05c Mon Sep 17 00:00:00 2001 From: Manfred Spraul Date: Fri, 16 Dec 2022 16:04:40 +0100 Subject: include/linux/percpu_counter.h: race in uniprocessor percpu_counter_add() The percpu interface is supposed to be preempt and irq safe. But: The uniprocessor implementation of percpu_counter_add() is not irq safe: if an interrupt happens during the +=, then the result is undefined. Therefore: switch from preempt_disable() to local_irq_save(). This prevents interrupts from interrupting the +=, and as a side effect prevents preemption. Link: https://lkml.kernel.org/r/20221216150441.200533-2-manfred@colorfullife.com Signed-off-by: Manfred Spraul Cc: "Sun, Jiebin" Cc: <1vier1@web.de> Cc: Alexander Sverdlin Cc: Thomas Gleixner Signed-off-by: Andrew Morton --- include/linux/percpu_counter.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h index a3aae8d57a42..521a733e21a9 100644 --- a/include/linux/percpu_counter.h +++ b/include/linux/percpu_counter.h @@ -152,9 +152,11 @@ __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch) static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount) { - preempt_disable(); + unsigned long flags; + + local_irq_save(flags); fbc->count += amount; - preempt_enable(); + local_irq_restore(flags); } /* non-SMP percpu_counter_add_local is the same with percpu_counter_add */ -- cgit v1.2.3 From 9456d539acde9f92a52ffe477b4b86e35d214d1a Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 3 Jan 2023 14:19:37 +0200 Subject: util_macros.h: add missing inclusion The header is the direct user of definitions from the math.h, include it. Link: https://lkml.kernel.org/r/20230103121937.32085-1-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Signed-off-by: Andrew Morton --- include/linux/util_macros.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/util_macros.h b/include/linux/util_macros.h index 72299f261b25..b641ec00be3e 100644 --- a/include/linux/util_macros.h +++ b/include/linux/util_macros.h @@ -2,6 +2,8 @@ #ifndef _LINUX_HELPER_MACROS_H_ #define _LINUX_HELPER_MACROS_H_ +#include + #define __find_closest(x, a, as, op) \ ({ \ typeof(as) __fc_i, __fc_as = (as) - 1; \ -- cgit v1.2.3 From 7e99f8b69c11c104933b9bc8fda226ebfb8aaaa5 Mon Sep 17 00:00:00 2001 From: Ricardo Ribalda Date: Wed, 4 Jan 2023 15:38:47 +0100 Subject: kexec: factor out kexec_load_permitted Both syscalls (kexec and kexec_file) do the same check, let's factor it out. Link: https://lkml.kernel.org/r/20221114-disable-kexec-reset-v6-2-6a8531a09b9a@chromium.org Signed-off-by: Ricardo Ribalda Reviewed-by: Steven Rostedt (Google) Acked-by: Baoquan He Cc: Bagas Sanjaya Cc: "Eric W. Biederman" Cc: Guilherme G. Piccoli Cc: Joel Fernandes (Google) Cc: Jonathan Corbet Cc: Philipp Rudo Cc: Ross Zwisler Cc: Sergey Senozhatsky Signed-off-by: Andrew Morton --- include/linux/kexec.h | 3 ++- kernel/kexec.c | 2 +- kernel/kexec_core.c | 11 ++++++++++- kernel/kexec_file.c | 2 +- 4 files changed, 14 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 5dd4343c1bbe..f18a3c9e813b 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -403,7 +403,8 @@ extern int kimage_crash_copy_vmcoreinfo(struct kimage *image); extern struct kimage *kexec_image; extern struct kimage *kexec_crash_image; -extern int kexec_load_disabled; + +bool kexec_load_permitted(void); #ifndef kexec_flush_icache_page #define kexec_flush_icache_page(page) diff --git a/kernel/kexec.c b/kernel/kexec.c index cb8e6e6f983c..ce1bca874a8d 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -193,7 +193,7 @@ static inline int kexec_load_check(unsigned long nr_segments, int result; /* We only trust the superuser with rebooting the system. */ - if (!capable(CAP_SYS_BOOT) || kexec_load_disabled) + if (!kexec_load_permitted()) return -EPERM; /* Permit LSMs and IMA to fail the kexec */ diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index 969e8f52f7da..d51ebbaeb1b2 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -922,7 +922,7 @@ int kimage_load_segment(struct kimage *image, struct kimage *kexec_image; struct kimage *kexec_crash_image; -int kexec_load_disabled; +static int kexec_load_disabled; #ifdef CONFIG_SYSCTL static struct ctl_table kexec_core_sysctls[] = { { @@ -946,6 +946,15 @@ static int __init kexec_core_sysctl_init(void) late_initcall(kexec_core_sysctl_init); #endif +bool kexec_load_permitted(void) +{ + /* + * Only the superuser can use the kexec syscall and if it has not + * been disabled. + */ + return capable(CAP_SYS_BOOT) && !kexec_load_disabled; +} + /* * No panic_cpu check version of crash_kexec(). This function is called * only when panic_cpu holds the current CPU number; this is the only CPU diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index dd5983010b7b..c897eb4b8c8c 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -330,7 +330,7 @@ SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd, struct kimage **dest_image, *image; /* We only trust the superuser with rebooting the system. */ - if (!capable(CAP_SYS_BOOT) || kexec_load_disabled) + if (!kexec_load_permitted()) return -EPERM; /* Make sure we have a legal set of flags */ -- cgit v1.2.3 From a42aaad2e47b23d63037bfc0130e33fc0f74cd71 Mon Sep 17 00:00:00 2001 From: Ricardo Ribalda Date: Wed, 4 Jan 2023 15:38:48 +0100 Subject: kexec: introduce sysctl parameters kexec_load_limit_* kexec allows replacing the current kernel with a different one. This is usually a source of concerns for sysadmins that want to harden a system. Linux already provides a way to disable loading new kexec kernel via kexec_load_disabled, but that control is very coard, it is all or nothing and does not make distinction between a panic kexec and a normal kexec. This patch introduces new sysctl parameters, with finer tuning to specify how many times a kexec kernel can be loaded. The sysadmin can set different limits for kexec panic and kexec reboot kernels. The value can be modified at runtime via sysctl, but only with a stricter value. With these new parameters on place, a system with loadpin and verity enabled, using the following kernel parameters: sysctl.kexec_load_limit_reboot=0 sysct.kexec_load_limit_panic=1 can have a good warranty that if initrd tries to load a panic kernel, a malitious user will have small chances to replace that kernel with a different one, even if they can trigger timeouts on the disk where the panic kernel lives. Link: https://lkml.kernel.org/r/20221114-disable-kexec-reset-v6-3-6a8531a09b9a@chromium.org Signed-off-by: Ricardo Ribalda Reviewed-by: Steven Rostedt (Google) Acked-by: Baoquan He Cc: Bagas Sanjaya Cc: "Eric W. Biederman" Cc: Guilherme G. Piccoli # Steam Deck Cc: Joel Fernandes (Google) Cc: Jonathan Corbet Cc: Philipp Rudo Cc: Ross Zwisler Cc: Sergey Senozhatsky Signed-off-by: Andrew Morton --- Documentation/admin-guide/sysctl/kernel.rst | 18 ++++++ include/linux/kexec.h | 2 +- kernel/kexec.c | 4 +- kernel/kexec_core.c | 87 ++++++++++++++++++++++++++++- kernel/kexec_file.c | 11 ++-- 5 files changed, 114 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/Documentation/admin-guide/sysctl/kernel.rst b/Documentation/admin-guide/sysctl/kernel.rst index b53c0235cb43..4b7bfea28cd7 100644 --- a/Documentation/admin-guide/sysctl/kernel.rst +++ b/Documentation/admin-guide/sysctl/kernel.rst @@ -464,6 +464,24 @@ allowing a system to set up (and later use) an image without it being altered. Generally used together with the `modules_disabled`_ sysctl. +kexec_load_limit_panic +====================== + +This parameter specifies a limit to the number of times the syscalls +``kexec_load`` and ``kexec_file_load`` can be called with a crash +image. It can only be set with a more restrictive value than the +current one. + +== ====================================================== +-1 Unlimited calls to kexec. This is the default setting. +N Number of calls left. +== ====================================================== + +kexec_load_limit_reboot +======================= + +Similar functionality as ``kexec_load_limit_panic``, but for a normal +image. kptr_restrict ============= diff --git a/include/linux/kexec.h b/include/linux/kexec.h index f18a3c9e813b..6883c5922701 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -404,7 +404,7 @@ extern int kimage_crash_copy_vmcoreinfo(struct kimage *image); extern struct kimage *kexec_image; extern struct kimage *kexec_crash_image; -bool kexec_load_permitted(void); +bool kexec_load_permitted(int kexec_image_type); #ifndef kexec_flush_icache_page #define kexec_flush_icache_page(page) diff --git a/kernel/kexec.c b/kernel/kexec.c index ce1bca874a8d..92d301f98776 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -190,10 +190,12 @@ out_unlock: static inline int kexec_load_check(unsigned long nr_segments, unsigned long flags) { + int image_type = (flags & KEXEC_ON_CRASH) ? + KEXEC_TYPE_CRASH : KEXEC_TYPE_DEFAULT; int result; /* We only trust the superuser with rebooting the system. */ - if (!kexec_load_permitted()) + if (!kexec_load_permitted(image_type)) return -EPERM; /* Permit LSMs and IMA to fail the kexec */ diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index d51ebbaeb1b2..ab140098c3ad 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -920,10 +920,64 @@ int kimage_load_segment(struct kimage *image, return result; } +struct kexec_load_limit { + /* Mutex protects the limit count. */ + struct mutex mutex; + int limit; +}; + +static struct kexec_load_limit load_limit_reboot = { + .mutex = __MUTEX_INITIALIZER(load_limit_reboot.mutex), + .limit = -1, +}; + +static struct kexec_load_limit load_limit_panic = { + .mutex = __MUTEX_INITIALIZER(load_limit_panic.mutex), + .limit = -1, +}; + struct kimage *kexec_image; struct kimage *kexec_crash_image; static int kexec_load_disabled; + #ifdef CONFIG_SYSCTL +static int kexec_limit_handler(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + struct kexec_load_limit *limit = table->data; + int val; + struct ctl_table tmp = { + .data = &val, + .maxlen = sizeof(val), + .mode = table->mode, + }; + int ret; + + if (write) { + ret = proc_dointvec(&tmp, write, buffer, lenp, ppos); + if (ret) + return ret; + + if (val < 0) + return -EINVAL; + + mutex_lock(&limit->mutex); + if (limit->limit != -1 && val >= limit->limit) + ret = -EINVAL; + else + limit->limit = val; + mutex_unlock(&limit->mutex); + + return ret; + } + + mutex_lock(&limit->mutex); + val = limit->limit; + mutex_unlock(&limit->mutex); + + return proc_dointvec(&tmp, write, buffer, lenp, ppos); +} + static struct ctl_table kexec_core_sysctls[] = { { .procname = "kexec_load_disabled", @@ -935,6 +989,18 @@ static struct ctl_table kexec_core_sysctls[] = { .extra1 = SYSCTL_ONE, .extra2 = SYSCTL_ONE, }, + { + .procname = "kexec_load_limit_panic", + .data = &load_limit_panic, + .mode = 0644, + .proc_handler = kexec_limit_handler, + }, + { + .procname = "kexec_load_limit_reboot", + .data = &load_limit_reboot, + .mode = 0644, + .proc_handler = kexec_limit_handler, + }, { } }; @@ -946,13 +1012,30 @@ static int __init kexec_core_sysctl_init(void) late_initcall(kexec_core_sysctl_init); #endif -bool kexec_load_permitted(void) +bool kexec_load_permitted(int kexec_image_type) { + struct kexec_load_limit *limit; + /* * Only the superuser can use the kexec syscall and if it has not * been disabled. */ - return capable(CAP_SYS_BOOT) && !kexec_load_disabled; + if (!capable(CAP_SYS_BOOT) || kexec_load_disabled) + return false; + + /* Check limit counter and decrease it.*/ + limit = (kexec_image_type == KEXEC_TYPE_CRASH) ? + &load_limit_panic : &load_limit_reboot; + mutex_lock(&limit->mutex); + if (!limit->limit) { + mutex_unlock(&limit->mutex); + return false; + } + if (limit->limit != -1) + limit->limit--; + mutex_unlock(&limit->mutex); + + return true; } /* diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index c897eb4b8c8c..f1a0e4e3fb5c 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -326,11 +326,13 @@ SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd, unsigned long, cmdline_len, const char __user *, cmdline_ptr, unsigned long, flags) { - int ret = 0, i; + int image_type = (flags & KEXEC_FILE_ON_CRASH) ? + KEXEC_TYPE_CRASH : KEXEC_TYPE_DEFAULT; struct kimage **dest_image, *image; + int ret = 0, i; /* We only trust the superuser with rebooting the system. */ - if (!kexec_load_permitted()) + if (!kexec_load_permitted(image_type)) return -EPERM; /* Make sure we have a legal set of flags */ @@ -342,11 +344,12 @@ SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd, if (!kexec_trylock()) return -EBUSY; - dest_image = &kexec_image; - if (flags & KEXEC_FILE_ON_CRASH) { + if (image_type == KEXEC_TYPE_CRASH) { dest_image = &kexec_crash_image; if (kexec_crash_image) arch_kexec_unprotect_crashkres(); + } else { + dest_image = &kexec_image; } if (flags & KEXEC_FILE_UNLOAD) -- cgit v1.2.3 From d82e6ae67ac2f9d6ba51690353c477b340bba6b5 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Tue, 31 Jan 2023 15:37:29 +0800 Subject: iommu/vt-d: Remove include/linux/intel-svm.h There's no need to have a public header for Intel SVA implementation. The device driver should interact with Intel SVA implementation via the IOMMU generic APIs. Reviewed-by: Kevin Tian Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20230109014955.147068-2-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- MAINTAINERS | 1 - drivers/iommu/intel/iommu.c | 1 - drivers/iommu/intel/iommu.h | 5 +++++ drivers/iommu/intel/svm.c | 1 - include/linux/intel-svm.h | 16 ---------------- 5 files changed, 5 insertions(+), 19 deletions(-) delete mode 100644 include/linux/intel-svm.h (limited to 'include/linux') diff --git a/MAINTAINERS b/MAINTAINERS index a36df9ed283d..43fd97f0e1df 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -10459,7 +10459,6 @@ L: iommu@lists.linux.dev S: Supported T: git git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu.git F: drivers/iommu/intel/ -F: include/linux/intel-svm.h INTEL IPU3 CSI-2 CIO2 DRIVER M: Yong Zhi diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 59df7e42fd53..317af67b6098 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -16,7 +16,6 @@ #include #include #include -#include #include #include #include diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h index 06e61e474856..f89f63d7a72a 100644 --- a/drivers/iommu/intel/iommu.h +++ b/drivers/iommu/intel/iommu.h @@ -438,6 +438,11 @@ struct q_inval { int free_cnt; }; +/* Page Request Queue depth */ +#define PRQ_ORDER 4 +#define PRQ_RING_MASK ((0x1000 << PRQ_ORDER) - 0x20) +#define PRQ_DEPTH ((0x1000 << PRQ_ORDER) >> 5) + struct dmar_pci_notify_info; #ifdef CONFIG_IRQ_REMAP diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c index c76b66263467..d38a54396c23 100644 --- a/drivers/iommu/intel/svm.c +++ b/drivers/iommu/intel/svm.c @@ -9,7 +9,6 @@ #include #include #include -#include #include #include #include diff --git a/include/linux/intel-svm.h b/include/linux/intel-svm.h deleted file mode 100644 index f9a0d44f6fdb..000000000000 --- a/include/linux/intel-svm.h +++ /dev/null @@ -1,16 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright © 2015 Intel Corporation. - * - * Authors: David Woodhouse - */ - -#ifndef __INTEL_SVM_H__ -#define __INTEL_SVM_H__ - -/* Page Request Queue depth */ -#define PRQ_ORDER 4 -#define PRQ_RING_MASK ((0x1000 << PRQ_ORDER) - 0x20) -#define PRQ_DEPTH ((0x1000 << PRQ_ORDER) >> 5) - -#endif /* __INTEL_SVM_H__ */ -- cgit v1.2.3 From 4db96bfe9d7772d6ddedd62ce478895999043fd7 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Tue, 31 Jan 2023 15:37:34 +0800 Subject: iommu/vt-d: Support size of the register set in DRHD A new field, which indicates the size of the remapping hardware register set for this remapping unit, is introduced in the DMA-remapping hardware unit definition (DRHD) structure with the VT-d Spec 4.0. With this information, SW doesn't need to 'guess' the size of the register set anymore. Update the struct acpi_dmar_hardware_unit to reflect the field. Store the size of the register set in struct dmar_drhd_unit for each dmar device. The 'size' information is ResvZ for the old BIOS and platforms. Fall back to the old guessing method. There is nothing changed. Signed-off-by: Kan Liang Link: https://lore.kernel.org/r/20230128200428.1459118-2-kan.liang@linux.intel.com Signed-off-by: Lu Baolu Signed-off-by: Joerg Roedel --- drivers/iommu/intel/dmar.c | 11 +++++++---- include/acpi/actbl1.h | 2 +- include/linux/dmar.h | 1 + 3 files changed, 9 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c index b00a0ceb2d13..3a40fef1ec1b 100644 --- a/drivers/iommu/intel/dmar.c +++ b/drivers/iommu/intel/dmar.c @@ -427,6 +427,8 @@ static int dmar_parse_one_drhd(struct acpi_dmar_header *header, void *arg) memcpy(dmaru->hdr, header, header->length); dmaru->reg_base_addr = drhd->address; dmaru->segment = drhd->segment; + /* The size of the register set is 2 ^ N 4 KB pages. */ + dmaru->reg_size = 1UL << (drhd->size + 12); dmaru->include_all = drhd->flags & 0x1; /* BIT0: INCLUDE_ALL */ dmaru->devices = dmar_alloc_dev_scope((void *)(drhd + 1), ((void *)drhd) + drhd->header.length, @@ -956,17 +958,18 @@ static void unmap_iommu(struct intel_iommu *iommu) /** * map_iommu: map the iommu's registers * @iommu: the iommu to map - * @phys_addr: the physical address of the base resgister + * @drhd: DMA remapping hardware definition structure * * Memory map the iommu's registers. Start w/ a single page, and * possibly expand if that turns out to be insufficent. */ -static int map_iommu(struct intel_iommu *iommu, u64 phys_addr) +static int map_iommu(struct intel_iommu *iommu, struct dmar_drhd_unit *drhd) { + u64 phys_addr = drhd->reg_base_addr; int map_size, err=0; iommu->reg_phys = phys_addr; - iommu->reg_size = VTD_PAGE_SIZE; + iommu->reg_size = drhd->reg_size; if (!request_mem_region(iommu->reg_phys, iommu->reg_size, iommu->name)) { pr_err("Can't reserve memory\n"); @@ -1050,7 +1053,7 @@ static int alloc_iommu(struct dmar_drhd_unit *drhd) } sprintf(iommu->name, "dmar%d", iommu->seq_id); - err = map_iommu(iommu, drhd->reg_base_addr); + err = map_iommu(iommu, drhd); if (err) { pr_err("Failed to map %s\n", iommu->name); goto error_free_seq_id; diff --git a/include/acpi/actbl1.h b/include/acpi/actbl1.h index 4175dce3967c..bdded0ac46eb 100644 --- a/include/acpi/actbl1.h +++ b/include/acpi/actbl1.h @@ -802,7 +802,7 @@ struct acpi_dmar_pci_path { struct acpi_dmar_hardware_unit { struct acpi_dmar_header header; u8 flags; - u8 reserved; + u8 size; /* Size of the register set */ u16 segment; u64 address; /* Register Base Address */ }; diff --git a/include/linux/dmar.h b/include/linux/dmar.h index d81a51978d01..725d5e6acec0 100644 --- a/include/linux/dmar.h +++ b/include/linux/dmar.h @@ -39,6 +39,7 @@ struct dmar_drhd_unit { struct list_head list; /* list of drhd units */ struct acpi_dmar_header *hdr; /* ACPI header */ u64 reg_base_addr; /* register base address*/ + unsigned long reg_size; /* size of register set */ struct dmar_dev_scope *devices;/* target device array */ int devices_cnt; /* target device count */ u16 segment; /* PCI domain */ -- cgit v1.2.3 From 46284c6ceb5e4dfddcb00dafb7c2f3c1437fdca4 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Tue, 31 Jan 2023 15:37:38 +0800 Subject: iommu/vt-d: Support cpumask for IOMMU perfmon The perf subsystem assumes that all counters are by default per-CPU. So the user space tool reads a counter from each CPU. However, the IOMMU counters are system-wide and can be read from any CPU. Here we use a CPU mask to restrict counting to one CPU to handle the issue. (with CPU hotplug notifier to choose a different CPU if the chosen one is taken off-line). The CPU is exposed to /sys/bus/event_source/devices/dmar*/cpumask for the user space perf tool. Signed-off-by: Kan Liang Link: https://lore.kernel.org/r/20230128200428.1459118-6-kan.liang@linux.intel.com Signed-off-by: Lu Baolu Signed-off-by: Joerg Roedel --- .../testing/sysfs-bus-event_source-devices-iommu | 8 ++ drivers/iommu/intel/perfmon.c | 113 +++++++++++++++++++-- include/linux/cpuhotplug.h | 1 + 3 files changed, 114 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/Documentation/ABI/testing/sysfs-bus-event_source-devices-iommu b/Documentation/ABI/testing/sysfs-bus-event_source-devices-iommu index 988210a0e8ce..d7af4919302e 100644 --- a/Documentation/ABI/testing/sysfs-bus-event_source-devices-iommu +++ b/Documentation/ABI/testing/sysfs-bus-event_source-devices-iommu @@ -27,3 +27,11 @@ Description: Read-only. Attribute group to describe the magic bits filter_pasid = "config2:0-21" - PASID filter filter_ats = "config2:24-28" - Address Type filter filter_page_table = "config2:32-36" - Page Table Level filter + +What: /sys/bus/event_source/devices/dmar*/cpumask +Date: Jan 2023 +KernelVersion: 6.3 +Contact: Kan Liang +Description: Read-only. This file always returns the CPU to which the + IOMMU pmu is bound for access to all IOMMU pmu performance + monitoring events. diff --git a/drivers/iommu/intel/perfmon.c b/drivers/iommu/intel/perfmon.c index df9b78736462..322d362b85e4 100644 --- a/drivers/iommu/intel/perfmon.c +++ b/drivers/iommu/intel/perfmon.c @@ -34,9 +34,28 @@ static struct attribute_group iommu_pmu_events_attr_group = { .attrs = attrs_empty, }; +static cpumask_t iommu_pmu_cpu_mask; + +static ssize_t +cpumask_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpumap_print_to_pagebuf(true, buf, &iommu_pmu_cpu_mask); +} +static DEVICE_ATTR_RO(cpumask); + +static struct attribute *iommu_pmu_cpumask_attrs[] = { + &dev_attr_cpumask.attr, + NULL +}; + +static struct attribute_group iommu_pmu_cpumask_attr_group = { + .attrs = iommu_pmu_cpumask_attrs, +}; + static const struct attribute_group *iommu_pmu_attr_groups[] = { &iommu_pmu_format_attr_group, &iommu_pmu_events_attr_group, + &iommu_pmu_cpumask_attr_group, NULL }; @@ -679,20 +698,98 @@ void free_iommu_pmu(struct intel_iommu *iommu) iommu->pmu = NULL; } +static int iommu_pmu_cpu_online(unsigned int cpu) +{ + if (cpumask_empty(&iommu_pmu_cpu_mask)) + cpumask_set_cpu(cpu, &iommu_pmu_cpu_mask); + + return 0; +} + +static int iommu_pmu_cpu_offline(unsigned int cpu) +{ + struct dmar_drhd_unit *drhd; + struct intel_iommu *iommu; + int target; + + if (!cpumask_test_and_clear_cpu(cpu, &iommu_pmu_cpu_mask)) + return 0; + + target = cpumask_any_but(cpu_online_mask, cpu); + + if (target < nr_cpu_ids) + cpumask_set_cpu(target, &iommu_pmu_cpu_mask); + else + target = -1; + + rcu_read_lock(); + + for_each_iommu(iommu, drhd) { + if (!iommu->pmu) + continue; + perf_pmu_migrate_context(&iommu->pmu->pmu, cpu, target); + } + rcu_read_unlock(); + + return 0; +} + +static int nr_iommu_pmu; + +static int iommu_pmu_cpuhp_setup(struct iommu_pmu *iommu_pmu) +{ + int ret; + + if (nr_iommu_pmu++) + return 0; + + ret = cpuhp_setup_state(CPUHP_AP_PERF_X86_IOMMU_PERF_ONLINE, + "driver/iommu/intel/perfmon:online", + iommu_pmu_cpu_online, + iommu_pmu_cpu_offline); + if (ret) + nr_iommu_pmu = 0; + + return ret; +} + +static void iommu_pmu_cpuhp_free(struct iommu_pmu *iommu_pmu) +{ + if (--nr_iommu_pmu) + return; + + cpuhp_remove_state(CPUHP_AP_PERF_X86_IOMMU_PERF_ONLINE); +} + void iommu_pmu_register(struct intel_iommu *iommu) { - if (!iommu->pmu) + struct iommu_pmu *iommu_pmu = iommu->pmu; + + if (!iommu_pmu) return; - if (__iommu_pmu_register(iommu)) { - pr_err("Failed to register PMU for iommu (seq_id = %d)\n", - iommu->seq_id); - free_iommu_pmu(iommu); - } + if (__iommu_pmu_register(iommu)) + goto err; + + if (iommu_pmu_cpuhp_setup(iommu_pmu)) + goto unregister; + + return; + +unregister: + perf_pmu_unregister(&iommu_pmu->pmu); +err: + pr_err("Failed to register PMU for iommu (seq_id = %d)\n", iommu->seq_id); + free_iommu_pmu(iommu); } void iommu_pmu_unregister(struct intel_iommu *iommu) { - if (iommu->pmu) - perf_pmu_unregister(&iommu->pmu->pmu); + struct iommu_pmu *iommu_pmu = iommu->pmu; + + if (!iommu_pmu) + return; + + iommu_pmu_cpuhp_free(iommu_pmu); + perf_pmu_unregister(&iommu_pmu->pmu); } diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 6c6859bfc454..f2ea348ce3b0 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -221,6 +221,7 @@ enum cpuhp_state { CPUHP_AP_PERF_X86_CQM_ONLINE, CPUHP_AP_PERF_X86_CSTATE_ONLINE, CPUHP_AP_PERF_X86_IDXD_ONLINE, + CPUHP_AP_PERF_X86_IOMMU_PERF_ONLINE, CPUHP_AP_PERF_S390_CF_ONLINE, CPUHP_AP_PERF_S390_SF_ONLINE, CPUHP_AP_PERF_ARM_CCI_ONLINE, -- cgit v1.2.3 From 0c05e7bd2d017a3a9a0f4e9a19ad4acf1f616f12 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Wed, 25 Jan 2023 10:54:01 -0800 Subject: livepatch,x86: Clear relocation targets on a module removal Josh reported a bug: When the object to be patched is a module, and that module is rmmod'ed and reloaded, it fails to load with: module: x86/modules: Skipping invalid relocation target, existing value is nonzero for type 2, loc 00000000ba0302e9, val ffffffffa03e293c livepatch: failed to initialize patch 'livepatch_nfsd' for module 'nfsd' (-8) livepatch: patch 'livepatch_nfsd' failed for module 'nfsd', refusing to load module 'nfsd' The livepatch module has a relocation which references a symbol in the _previous_ loading of nfsd. When apply_relocate_add() tries to replace the old relocation with a new one, it sees that the previous one is nonzero and it errors out. He also proposed three different solutions. We could remove the error check in apply_relocate_add() introduced by commit eda9cec4c9a1 ("x86/module: Detect and skip invalid relocations"). However the check is useful for detecting corrupted modules. We could also deny the patched modules to be removed. If it proved to be a major drawback for users, we could still implement a different approach. The solution would also complicate the existing code a lot. We thus decided to reverse the relocation patching (clear all relocation targets on x86_64). The solution is not universal and is too much arch-specific, but it may prove to be simpler in the end. Reported-by: Josh Poimboeuf Originally-by: Miroslav Benes Signed-off-by: Song Liu Acked-by: Miroslav Benes Reviewed-by: Petr Mladek Acked-by: Josh Poimboeuf Reviewed-by: Joe Lawrence Tested-by: Joe Lawrence Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20230125185401.279042-2-song@kernel.org --- arch/x86/kernel/module.c | 93 ++++++++++++++++++++++++++++---------------- include/linux/moduleloader.h | 17 ++++++++ kernel/livepatch/core.c | 62 ++++++++++++++++++++++------- 3 files changed, 126 insertions(+), 46 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index 0a09d816794b..790fa9f4a342 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -128,22 +128,27 @@ int apply_relocate(Elf32_Shdr *sechdrs, return 0; } #else /*X86_64*/ -static int __apply_relocate_add(Elf64_Shdr *sechdrs, +static int __write_relocate_add(Elf64_Shdr *sechdrs, const char *strtab, unsigned int symindex, unsigned int relsec, struct module *me, - void *(*write)(void *dest, const void *src, size_t len)) + void *(*write)(void *dest, const void *src, size_t len), + bool apply) { unsigned int i; Elf64_Rela *rel = (void *)sechdrs[relsec].sh_addr; Elf64_Sym *sym; void *loc; u64 val; + u64 zero = 0ULL; - DEBUGP("Applying relocate section %u to %u\n", + DEBUGP("%s relocate section %u to %u\n", + apply ? "Applying" : "Clearing", relsec, sechdrs[relsec].sh_info); for (i = 0; i < sechdrs[relsec].sh_size / sizeof(*rel); i++) { + size_t size; + /* This is where to make the change */ loc = (void *)sechdrs[sechdrs[relsec].sh_info].sh_addr + rel[i].r_offset; @@ -161,52 +166,53 @@ static int __apply_relocate_add(Elf64_Shdr *sechdrs, switch (ELF64_R_TYPE(rel[i].r_info)) { case R_X86_64_NONE: - break; + continue; /* nothing to write */ case R_X86_64_64: - if (*(u64 *)loc != 0) - goto invalid_relocation; - write(loc, &val, 8); + size = 8; break; case R_X86_64_32: - if (*(u32 *)loc != 0) - goto invalid_relocation; - write(loc, &val, 4); - if (val != *(u32 *)loc) + if (val != *(u32 *)&val) goto overflow; + size = 4; break; case R_X86_64_32S: - if (*(s32 *)loc != 0) - goto invalid_relocation; - write(loc, &val, 4); - if ((s64)val != *(s32 *)loc) + if ((s64)val != *(s32 *)&val) goto overflow; + size = 4; break; case R_X86_64_PC32: case R_X86_64_PLT32: - if (*(u32 *)loc != 0) - goto invalid_relocation; val -= (u64)loc; - write(loc, &val, 4); + size = 4; break; case R_X86_64_PC64: - if (*(u64 *)loc != 0) - goto invalid_relocation; val -= (u64)loc; - write(loc, &val, 8); + size = 8; break; default: pr_err("%s: Unknown rela relocation: %llu\n", me->name, ELF64_R_TYPE(rel[i].r_info)); return -ENOEXEC; } + + if (apply) { + if (memcmp(loc, &zero, size)) { + pr_err("x86/modules: Invalid relocation target, existing value is nonzero for type %d, loc %p, val %Lx\n", + (int)ELF64_R_TYPE(rel[i].r_info), loc, val); + return -ENOEXEC; + } + write(loc, &val, size); + } else { + if (memcmp(loc, &val, size)) { + pr_warn("x86/modules: Invalid relocation target, existing value does not match expected value for type %d, loc %p, val %Lx\n", + (int)ELF64_R_TYPE(rel[i].r_info), loc, val); + return -ENOEXEC; + } + write(loc, &zero, size); + } } return 0; -invalid_relocation: - pr_err("x86/modules: Skipping invalid relocation target, existing value is nonzero for type %d, loc %p, val %Lx\n", - (int)ELF64_R_TYPE(rel[i].r_info), loc, val); - return -ENOEXEC; - overflow: pr_err("overflow in relocation type %d val %Lx\n", (int)ELF64_R_TYPE(rel[i].r_info), val); @@ -215,11 +221,12 @@ overflow: return -ENOEXEC; } -int apply_relocate_add(Elf64_Shdr *sechdrs, - const char *strtab, - unsigned int symindex, - unsigned int relsec, - struct module *me) +static int write_relocate_add(Elf64_Shdr *sechdrs, + const char *strtab, + unsigned int symindex, + unsigned int relsec, + struct module *me, + bool apply) { int ret; bool early = me->state == MODULE_STATE_UNFORMED; @@ -230,8 +237,8 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, mutex_lock(&text_mutex); } - ret = __apply_relocate_add(sechdrs, strtab, symindex, relsec, me, - write); + ret = __write_relocate_add(sechdrs, strtab, symindex, relsec, me, + write, apply); if (!early) { text_poke_sync(); @@ -241,6 +248,26 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, return ret; } +int apply_relocate_add(Elf64_Shdr *sechdrs, + const char *strtab, + unsigned int symindex, + unsigned int relsec, + struct module *me) +{ + return write_relocate_add(sechdrs, strtab, symindex, relsec, me, true); +} + +#ifdef CONFIG_LIVEPATCH +void clear_relocate_add(Elf64_Shdr *sechdrs, + const char *strtab, + unsigned int symindex, + unsigned int relsec, + struct module *me) +{ + write_relocate_add(sechdrs, strtab, symindex, relsec, me, false); +} +#endif + #endif int module_finalize(const Elf_Ehdr *hdr, diff --git a/include/linux/moduleloader.h b/include/linux/moduleloader.h index 9e09d11ffe5b..2ba4bc834a4f 100644 --- a/include/linux/moduleloader.h +++ b/include/linux/moduleloader.h @@ -72,6 +72,23 @@ int apply_relocate_add(Elf_Shdr *sechdrs, unsigned int symindex, unsigned int relsec, struct module *mod); +#ifdef CONFIG_LIVEPATCH +/* + * Some architectures (namely x86_64 and ppc64) perform sanity checks when + * applying relocations. If a patched module gets unloaded and then later + * reloaded (and re-patched), klp re-applies relocations to the replacement + * function(s). Any leftover relocations from the previous loading of the + * patched module might trigger the sanity checks. + * + * To prevent that, when unloading a patched module, clear out any relocations + * that might trigger arch-specific sanity checks on a future module reload. + */ +void clear_relocate_add(Elf_Shdr *sechdrs, + const char *strtab, + unsigned int symindex, + unsigned int relsec, + struct module *me); +#endif #else static inline int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab, diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c index 9ada0bc5247b..0168c38ba187 100644 --- a/kernel/livepatch/core.c +++ b/kernel/livepatch/core.c @@ -261,6 +261,14 @@ static int klp_resolve_symbols(Elf_Shdr *sechdrs, const char *strtab, return 0; } +void __weak clear_relocate_add(Elf_Shdr *sechdrs, + const char *strtab, + unsigned int symindex, + unsigned int relsec, + struct module *me) +{ +} + /* * At a high-level, there are two types of klp relocation sections: those which * reference symbols which live in vmlinux; and those which reference symbols @@ -284,10 +292,10 @@ static int klp_resolve_symbols(Elf_Shdr *sechdrs, const char *strtab, * the to-be-patched module to be loaded and patched sometime *after* the * klp module is loaded. */ -int klp_apply_section_relocs(struct module *pmod, Elf_Shdr *sechdrs, - const char *shstrtab, const char *strtab, - unsigned int symndx, unsigned int secndx, - const char *objname) +static int klp_write_section_relocs(struct module *pmod, Elf_Shdr *sechdrs, + const char *shstrtab, const char *strtab, + unsigned int symndx, unsigned int secndx, + const char *objname, bool apply) { int cnt, ret; char sec_objname[MODULE_NAME_LEN]; @@ -309,11 +317,26 @@ int klp_apply_section_relocs(struct module *pmod, Elf_Shdr *sechdrs, if (strcmp(objname ? objname : "vmlinux", sec_objname)) return 0; - ret = klp_resolve_symbols(sechdrs, strtab, symndx, sec, sec_objname); - if (ret) - return ret; + if (apply) { + ret = klp_resolve_symbols(sechdrs, strtab, symndx, + sec, sec_objname); + if (ret) + return ret; + + return apply_relocate_add(sechdrs, strtab, symndx, secndx, pmod); + } + + clear_relocate_add(sechdrs, strtab, symndx, secndx, pmod); + return 0; +} - return apply_relocate_add(sechdrs, strtab, symndx, secndx, pmod); +int klp_apply_section_relocs(struct module *pmod, Elf_Shdr *sechdrs, + const char *shstrtab, const char *strtab, + unsigned int symndx, unsigned int secndx, + const char *objname) +{ + return klp_write_section_relocs(pmod, sechdrs, shstrtab, strtab, symndx, + secndx, objname, true); } /* @@ -762,8 +785,9 @@ static int klp_init_func(struct klp_object *obj, struct klp_func *func) func->old_sympos ? func->old_sympos : 1); } -static int klp_apply_object_relocs(struct klp_patch *patch, - struct klp_object *obj) +static int klp_write_object_relocs(struct klp_patch *patch, + struct klp_object *obj, + bool apply) { int i, ret; struct klp_modinfo *info = patch->mod->klp_info; @@ -774,10 +798,10 @@ static int klp_apply_object_relocs(struct klp_patch *patch, if (!(sec->sh_flags & SHF_RELA_LIVEPATCH)) continue; - ret = klp_apply_section_relocs(patch->mod, info->sechdrs, + ret = klp_write_section_relocs(patch->mod, info->sechdrs, info->secstrings, patch->mod->core_kallsyms.strtab, - info->symndx, i, obj->name); + info->symndx, i, obj->name, apply); if (ret) return ret; } @@ -785,6 +809,18 @@ static int klp_apply_object_relocs(struct klp_patch *patch, return 0; } +static int klp_apply_object_relocs(struct klp_patch *patch, + struct klp_object *obj) +{ + return klp_write_object_relocs(patch, obj, true); +} + +static void klp_clear_object_relocs(struct klp_patch *patch, + struct klp_object *obj) +{ + klp_write_object_relocs(patch, obj, false); +} + /* parts of the initialization that is done only when the object is loaded */ static int klp_init_object_loaded(struct klp_patch *patch, struct klp_object *obj) @@ -1172,7 +1208,7 @@ static void klp_cleanup_module_patches_limited(struct module *mod, klp_unpatch_object(obj); klp_post_unpatch_callback(obj); - + klp_clear_object_relocs(patch, obj); klp_free_object_loaded(obj); break; } -- cgit v1.2.3 From 234fa51db95f3236a049557db735606908747f38 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Fri, 3 Feb 2023 17:39:38 +0100 Subject: efi: Drop minimum EFI version check at boot We currently pass a minimum major version to the generic EFI helper that checks the system table magic and version, and refuse to boot if the value is lower. The motivation for this check is unknown, and even the code that uses major version 2 as the minimum (ARM, arm64 and RISC-V) should make it past this check without problems, and boot to a point where we have access to a console or some other means to inform the user that the firmware's major revision number made us unhappy. (Revision 2.0 of the UEFI specification was released in January 2006, whereas ARM, arm64 and RISC-V support where added in 2009, 2013 and 2017, respectively, so checking for major version 2 or higher is completely arbitrary) So just drop the check. Signed-off-by: Ard Biesheuvel --- arch/ia64/kernel/efi.c | 2 +- arch/x86/platform/efi/efi.c | 2 +- drivers/firmware/efi/efi-init.c | 2 +- drivers/firmware/efi/efi.c | 9 +-------- include/linux/efi.h | 3 +-- 5 files changed, 5 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/arch/ia64/kernel/efi.c b/arch/ia64/kernel/efi.c index 31149e41f9be..21dfa4aa35bb 100644 --- a/arch/ia64/kernel/efi.c +++ b/arch/ia64/kernel/efi.c @@ -525,7 +525,7 @@ efi_init (void) */ if (efi_systab == NULL) panic("Whoa! Can't find EFI system table.\n"); - if (efi_systab_check_header(&efi_systab->hdr, 1)) + if (efi_systab_check_header(&efi_systab->hdr)) panic("Whoa! EFI system table signature incorrect\n"); efi_systab_report_header(&efi_systab->hdr, efi_systab->fw_vendor); diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 55d9caf66401..f3f2d87cce1b 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -380,7 +380,7 @@ static int __init efi_systab_init(unsigned long phys) return -ENOMEM; } - ret = efi_systab_check_header(hdr, 1); + ret = efi_systab_check_header(hdr); if (ret) { early_memunmap(p, size); return ret; diff --git a/drivers/firmware/efi/efi-init.c b/drivers/firmware/efi/efi-init.c index 1639159493e3..2c16080e1f71 100644 --- a/drivers/firmware/efi/efi-init.c +++ b/drivers/firmware/efi/efi-init.c @@ -92,7 +92,7 @@ static int __init uefi_init(u64 efi_system_table) if (IS_ENABLED(CONFIG_64BIT)) set_bit(EFI_64BIT, &efi.flags); - retval = efi_systab_check_header(&systab->hdr, 2); + retval = efi_systab_check_header(&systab->hdr); if (retval) goto out; diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index 52146f95d58e..53fa4d14da65 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -759,20 +759,13 @@ int __init efi_config_parse_tables(const efi_config_table_t *config_tables, return 0; } -int __init efi_systab_check_header(const efi_table_hdr_t *systab_hdr, - int min_major_version) +int __init efi_systab_check_header(const efi_table_hdr_t *systab_hdr) { if (systab_hdr->signature != EFI_SYSTEM_TABLE_SIGNATURE) { pr_err("System table signature incorrect!\n"); return -EINVAL; } - if ((systab_hdr->revision >> 16) < min_major_version) - pr_err("Warning: System table version %d.%02d, expected %d.00 or greater!\n", - systab_hdr->revision >> 16, - systab_hdr->revision & 0xffff, - min_major_version); - return 0; } diff --git a/include/linux/efi.h b/include/linux/efi.h index 507390dda8b9..9d455d502ac9 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -721,8 +721,7 @@ static inline void efi_esrt_init(void) { } extern int efi_config_parse_tables(const efi_config_table_t *config_tables, int count, const efi_config_table_type_t *arch_tables); -extern int efi_systab_check_header(const efi_table_hdr_t *systab_hdr, - int min_major_version); +extern int efi_systab_check_header(const efi_table_hdr_t *systab_hdr); extern void efi_systab_report_header(const efi_table_hdr_t *systab_hdr, unsigned long fw_vendor); extern u64 efi_get_iobase (void); -- cgit v1.2.3 From c9a397cee9f5c93a7f48e18038b14057044db6ba Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Wed, 18 Jan 2023 13:50:28 -0400 Subject: vfio: Support VFIO_NOIOMMU with iommufd Add a small amount of emulation to vfio_compat to accept the SET_IOMMU to VFIO_NOIOMMU_IOMMU and have vfio just ignore iommufd if it is working on a no-iommu enabled device. Move the enable_unsafe_noiommu_mode module out of container.c into vfio_main.c so that it is always available even if VFIO_CONTAINER=n. This passes Alex's mini-test: https://github.com/awilliam/tests/blob/master/vfio-noiommu-pci-device-open.c Link: https://lore.kernel.org/r/0-v3-480cd64a16f7+1ad0-iommufd_noiommu_jgg@nvidia.com Reviewed-by: Kevin Tian Acked-by: Alex Williamson Signed-off-by: Jason Gunthorpe --- drivers/iommu/iommufd/Kconfig | 2 +- drivers/iommu/iommufd/iommufd_private.h | 2 + drivers/iommu/iommufd/vfio_compat.c | 105 ++++++++++++++++++++++++++------ drivers/vfio/Kconfig | 2 +- drivers/vfio/container.c | 7 --- drivers/vfio/group.c | 7 ++- drivers/vfio/iommufd.c | 19 +++++- drivers/vfio/vfio.h | 8 ++- drivers/vfio/vfio_main.c | 7 +++ include/linux/iommufd.h | 12 +++- 10 files changed, 136 insertions(+), 35 deletions(-) (limited to 'include/linux') diff --git a/drivers/iommu/iommufd/Kconfig b/drivers/iommu/iommufd/Kconfig index 8306616b6d81..ada693ea51a7 100644 --- a/drivers/iommu/iommufd/Kconfig +++ b/drivers/iommu/iommufd/Kconfig @@ -23,7 +23,7 @@ config IOMMUFD_VFIO_CONTAINER removed. IOMMUFD VFIO container emulation is known to lack certain features - of the native VFIO container, such as no-IOMMU support, peer-to-peer + of the native VFIO container, such as peer-to-peer DMA mapping, PPC IOMMU support, as well as other potentially undiscovered gaps. This option is currently intended for the purpose of testing IOMMUFD with unmodified userspace supporting VFIO diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h index 222e86591f8a..9d7f71510ca1 100644 --- a/drivers/iommu/iommufd/iommufd_private.h +++ b/drivers/iommu/iommufd/iommufd_private.h @@ -18,6 +18,8 @@ struct iommufd_ctx { struct xarray objects; u8 account_mode; + /* Compatibility with VFIO no iommu */ + u8 no_iommu_mode; struct iommufd_ioas *vfio_ioas; }; diff --git a/drivers/iommu/iommufd/vfio_compat.c b/drivers/iommu/iommufd/vfio_compat.c index 3ceca0e8311c..8e38bb02d5e1 100644 --- a/drivers/iommu/iommufd/vfio_compat.c +++ b/drivers/iommu/iommufd/vfio_compat.c @@ -26,39 +26,84 @@ out_unlock: } /** - * iommufd_vfio_compat_ioas_id - Return the IOAS ID that vfio should use + * iommufd_vfio_compat_ioas_get_id - Ensure a compat IOAS exists + * @ictx: Context to operate on + * @out_ioas_id: The IOAS ID of the compatibility IOAS + * + * Return the ID of the current compatibility IOAS. The ID can be passed into + * other functions that take an ioas_id. + */ +int iommufd_vfio_compat_ioas_get_id(struct iommufd_ctx *ictx, u32 *out_ioas_id) +{ + struct iommufd_ioas *ioas; + + ioas = get_compat_ioas(ictx); + if (IS_ERR(ioas)) + return PTR_ERR(ioas); + *out_ioas_id = ioas->obj.id; + iommufd_put_object(&ioas->obj); + return 0; +} +EXPORT_SYMBOL_NS_GPL(iommufd_vfio_compat_ioas_get_id, IOMMUFD_VFIO); + +/** + * iommufd_vfio_compat_set_no_iommu - Called when a no-iommu device is attached + * @ictx: Context to operate on + * + * This allows selecting the VFIO_NOIOMMU_IOMMU and blocks normal types. + */ +int iommufd_vfio_compat_set_no_iommu(struct iommufd_ctx *ictx) +{ + int ret; + + xa_lock(&ictx->objects); + if (!ictx->vfio_ioas) { + ictx->no_iommu_mode = 1; + ret = 0; + } else { + ret = -EINVAL; + } + xa_unlock(&ictx->objects); + return ret; +} +EXPORT_SYMBOL_NS_GPL(iommufd_vfio_compat_set_no_iommu, IOMMUFD_VFIO); + +/** + * iommufd_vfio_compat_ioas_create - Ensure the compat IOAS is created * @ictx: Context to operate on - * @out_ioas_id: The ioas_id the caller should use * * The compatibility IOAS is the IOAS that the vfio compatibility ioctls operate * on since they do not have an IOAS ID input in their ABI. Only attaching a - * group should cause a default creation of the internal ioas, this returns the - * existing ioas if it has already been assigned somehow. + * group should cause a default creation of the internal ioas, this does nothing + * if an existing ioas has already been assigned somehow. */ -int iommufd_vfio_compat_ioas_id(struct iommufd_ctx *ictx, u32 *out_ioas_id) +int iommufd_vfio_compat_ioas_create(struct iommufd_ctx *ictx) { struct iommufd_ioas *ioas = NULL; - struct iommufd_ioas *out_ioas; + int ret; ioas = iommufd_ioas_alloc(ictx); if (IS_ERR(ioas)) return PTR_ERR(ioas); xa_lock(&ictx->objects); - if (ictx->vfio_ioas && iommufd_lock_obj(&ictx->vfio_ioas->obj)) - out_ioas = ictx->vfio_ioas; - else { - out_ioas = ioas; - ictx->vfio_ioas = ioas; + /* + * VFIO won't allow attaching a container to both iommu and no iommu + * operation + */ + if (ictx->no_iommu_mode) { + ret = -EINVAL; + goto out_abort; } - xa_unlock(&ictx->objects); - *out_ioas_id = out_ioas->obj.id; - if (out_ioas != ioas) { - iommufd_put_object(&out_ioas->obj); - iommufd_object_abort(ictx, &ioas->obj); - return 0; + if (ictx->vfio_ioas && iommufd_lock_obj(&ictx->vfio_ioas->obj)) { + ret = 0; + iommufd_put_object(&ictx->vfio_ioas->obj); + goto out_abort; } + ictx->vfio_ioas = ioas; + xa_unlock(&ictx->objects); + /* * An automatically created compat IOAS is treated as a userspace * created object. Userspace can learn the ID via IOMMU_VFIO_IOAS_GET, @@ -67,8 +112,13 @@ int iommufd_vfio_compat_ioas_id(struct iommufd_ctx *ictx, u32 *out_ioas_id) */ iommufd_object_finalize(ictx, &ioas->obj); return 0; + +out_abort: + xa_unlock(&ictx->objects); + iommufd_object_abort(ictx, &ioas->obj); + return ret; } -EXPORT_SYMBOL_NS_GPL(iommufd_vfio_compat_ioas_id, IOMMUFD_VFIO); +EXPORT_SYMBOL_NS_GPL(iommufd_vfio_compat_ioas_create, IOMMUFD_VFIO); int iommufd_vfio_ioas(struct iommufd_ucmd *ucmd) { @@ -235,6 +285,9 @@ static int iommufd_vfio_check_extension(struct iommufd_ctx *ictx, case VFIO_UNMAP_ALL: return 1; + case VFIO_NOIOMMU_IOMMU: + return IS_ENABLED(CONFIG_VFIO_NOIOMMU); + case VFIO_DMA_CC_IOMMU: return iommufd_vfio_cc_iommu(ictx); @@ -261,10 +314,24 @@ static int iommufd_vfio_check_extension(struct iommufd_ctx *ictx, static int iommufd_vfio_set_iommu(struct iommufd_ctx *ictx, unsigned long type) { + bool no_iommu_mode = READ_ONCE(ictx->no_iommu_mode); struct iommufd_ioas *ioas = NULL; int rc = 0; - if (type != VFIO_TYPE1_IOMMU && type != VFIO_TYPE1v2_IOMMU) + /* + * Emulation for NOIOMMU is imperfect in that VFIO blocks almost all + * other ioctls. We let them keep working but they mostly fail since no + * IOAS should exist. + */ + if (IS_ENABLED(CONFIG_VFIO_NOIOMMU) && type == VFIO_NOIOMMU_IOMMU && + no_iommu_mode) { + if (!capable(CAP_SYS_RAWIO)) + return -EPERM; + return 0; + } + + if ((type != VFIO_TYPE1_IOMMU && type != VFIO_TYPE1v2_IOMMU) || + no_iommu_mode) return -EINVAL; /* VFIO fails the set_iommu if there is no group */ diff --git a/drivers/vfio/Kconfig b/drivers/vfio/Kconfig index a8f544629467..89e06c981e43 100644 --- a/drivers/vfio/Kconfig +++ b/drivers/vfio/Kconfig @@ -32,6 +32,7 @@ config VFIO_IOMMU_SPAPR_TCE tristate depends on SPAPR_TCE_IOMMU default VFIO +endif config VFIO_NOIOMMU bool "VFIO No-IOMMU support" @@ -46,7 +47,6 @@ config VFIO_NOIOMMU this mode since there is no IOMMU to provide DMA translation. If you don't know what to do here, say N. -endif config VFIO_VIRQFD bool diff --git a/drivers/vfio/container.c b/drivers/vfio/container.c index b7a9560ab25e..89f10becf962 100644 --- a/drivers/vfio/container.c +++ b/drivers/vfio/container.c @@ -29,13 +29,6 @@ static struct vfio { struct mutex iommu_drivers_lock; } vfio; -#ifdef CONFIG_VFIO_NOIOMMU -bool vfio_noiommu __read_mostly; -module_param_named(enable_unsafe_noiommu_mode, - vfio_noiommu, bool, S_IRUGO | S_IWUSR); -MODULE_PARM_DESC(enable_unsafe_noiommu_mode, "Enable UNSAFE, no-IOMMU mode. This mode provides no device isolation, no DMA translation, no host kernel protection, cannot be used for device assignment to virtual machines, requires RAWIO permissions, and will taint the kernel. If you do not know what this is for, step away. (default: false)"); -#endif - static void *vfio_noiommu_open(unsigned long arg) { if (arg != VFIO_NOIOMMU_IOMMU) diff --git a/drivers/vfio/group.c b/drivers/vfio/group.c index bb24b2f0271e..e166ad7ce6e7 100644 --- a/drivers/vfio/group.c +++ b/drivers/vfio/group.c @@ -133,9 +133,12 @@ static int vfio_group_ioctl_set_container(struct vfio_group *group, iommufd = iommufd_ctx_from_file(f.file); if (!IS_ERR(iommufd)) { - u32 ioas_id; + if (IS_ENABLED(CONFIG_VFIO_NOIOMMU) && + group->type == VFIO_NO_IOMMU) + ret = iommufd_vfio_compat_set_no_iommu(iommufd); + else + ret = iommufd_vfio_compat_ioas_create(iommufd); - ret = iommufd_vfio_compat_ioas_id(iommufd, &ioas_id); if (ret) { iommufd_ctx_put(group->iommufd); goto out_unlock; diff --git a/drivers/vfio/iommufd.c b/drivers/vfio/iommufd.c index 4f82a6fa7c6c..db4efbd56042 100644 --- a/drivers/vfio/iommufd.c +++ b/drivers/vfio/iommufd.c @@ -18,6 +18,20 @@ int vfio_iommufd_bind(struct vfio_device *vdev, struct iommufd_ctx *ictx) lockdep_assert_held(&vdev->dev_set->lock); + if (vfio_device_is_noiommu(vdev)) { + if (!capable(CAP_SYS_RAWIO)) + return -EPERM; + + /* + * Require no compat ioas to be assigned to proceed. The basic + * statement is that the user cannot have done something that + * implies they expected translation to exist + */ + if (!iommufd_vfio_compat_ioas_get_id(ictx, &ioas_id)) + return -EPERM; + return 0; + } + /* * If the driver doesn't provide this op then it means the device does * not do DMA at all. So nothing to do. @@ -29,7 +43,7 @@ int vfio_iommufd_bind(struct vfio_device *vdev, struct iommufd_ctx *ictx) if (ret) return ret; - ret = iommufd_vfio_compat_ioas_id(ictx, &ioas_id); + ret = iommufd_vfio_compat_ioas_get_id(ictx, &ioas_id); if (ret) goto err_unbind; ret = vdev->ops->attach_ioas(vdev, &ioas_id); @@ -52,6 +66,9 @@ void vfio_iommufd_unbind(struct vfio_device *vdev) { lockdep_assert_held(&vdev->dev_set->lock); + if (vfio_device_is_noiommu(vdev)) + return; + if (vdev->ops->unbind_iommufd) vdev->ops->unbind_iommufd(vdev); } diff --git a/drivers/vfio/vfio.h b/drivers/vfio/vfio.h index f8219a438bfb..9e94abcf8ee1 100644 --- a/drivers/vfio/vfio.h +++ b/drivers/vfio/vfio.h @@ -10,10 +10,10 @@ #include #include #include +#include struct iommufd_ctx; struct iommu_group; -struct vfio_device; struct vfio_container; void vfio_device_put_registration(struct vfio_device *device); @@ -88,6 +88,12 @@ bool vfio_device_has_container(struct vfio_device *device); int __init vfio_group_init(void); void vfio_group_cleanup(void); +static inline bool vfio_device_is_noiommu(struct vfio_device *vdev) +{ + return IS_ENABLED(CONFIG_VFIO_NOIOMMU) && + vdev->group->type == VFIO_NO_IOMMU; +} + #if IS_ENABLED(CONFIG_VFIO_CONTAINER) /* events for the backend driver notify callback */ enum vfio_iommu_notify_type { diff --git a/drivers/vfio/vfio_main.c b/drivers/vfio/vfio_main.c index 5177bb061b17..90541fc94988 100644 --- a/drivers/vfio/vfio_main.c +++ b/drivers/vfio/vfio_main.c @@ -45,6 +45,13 @@ static struct vfio { struct ida device_ida; } vfio; +#ifdef CONFIG_VFIO_NOIOMMU +bool vfio_noiommu __read_mostly; +module_param_named(enable_unsafe_noiommu_mode, + vfio_noiommu, bool, S_IRUGO | S_IWUSR); +MODULE_PARM_DESC(enable_unsafe_noiommu_mode, "Enable UNSAFE, no-IOMMU mode. This mode provides no device isolation, no DMA translation, no host kernel protection, cannot be used for device assignment to virtual machines, requires RAWIO permissions, and will taint the kernel. If you do not know what this is for, step away. (default: false)"); +#endif + static DEFINE_XARRAY(vfio_device_set_xa); int vfio_assign_device_set(struct vfio_device *device, void *set_id) diff --git a/include/linux/iommufd.h b/include/linux/iommufd.h index 650d45629647..c0b5b3ac34f1 100644 --- a/include/linux/iommufd.h +++ b/include/linux/iommufd.h @@ -57,7 +57,9 @@ void iommufd_access_unpin_pages(struct iommufd_access *access, unsigned long iova, unsigned long length); int iommufd_access_rw(struct iommufd_access *access, unsigned long iova, void *data, size_t len, unsigned int flags); -int iommufd_vfio_compat_ioas_id(struct iommufd_ctx *ictx, u32 *out_ioas_id); +int iommufd_vfio_compat_ioas_get_id(struct iommufd_ctx *ictx, u32 *out_ioas_id); +int iommufd_vfio_compat_ioas_create(struct iommufd_ctx *ictx); +int iommufd_vfio_compat_set_no_iommu(struct iommufd_ctx *ictx); #else /* !CONFIG_IOMMUFD */ static inline struct iommufd_ctx *iommufd_ctx_from_file(struct file *file) { @@ -89,8 +91,12 @@ static inline int iommufd_access_rw(struct iommufd_access *access, unsigned long return -EOPNOTSUPP; } -static inline int iommufd_vfio_compat_ioas_id(struct iommufd_ctx *ictx, - u32 *out_ioas_id) +static inline int iommufd_vfio_compat_ioas_create(struct iommufd_ctx *ictx) +{ + return -EOPNOTSUPP; +} + +static inline int iommufd_vfio_compat_set_no_iommu(struct iommufd_ctx *ictx) { return -EOPNOTSUPP; } -- cgit v1.2.3 From b0048092f7d3921d56f2c5bfa32062fac5e7500b Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 3 Feb 2023 11:26:49 -0800 Subject: efi/cper, cxl: Remove cxl_err.h While going to create include/linux/cxl.h for some cross-subsystem CXL definitions I noticed that include/linux/cxl_err.h was already present. That header has no reason to be global, and it duplicates the RAS Capability Structure definitions in drivers/cxl/cxl.h. A follow-on patch can consider unifying the CXL native error tracing with the CPER error printing. Also fixed up the spec reference as the latest released spec is v3.0. Cc: Smita Koralahalli Signed-off-by: Dan Williams Reviewed-by: Ira Weiny Signed-off-by: Ard Biesheuvel --- drivers/firmware/efi/cper_cxl.c | 12 +++++++++++- include/linux/cxl_err.h | 22 ---------------------- 2 files changed, 11 insertions(+), 23 deletions(-) delete mode 100644 include/linux/cxl_err.h (limited to 'include/linux') diff --git a/drivers/firmware/efi/cper_cxl.c b/drivers/firmware/efi/cper_cxl.c index 53e435c4f310..a55771b99a97 100644 --- a/drivers/firmware/efi/cper_cxl.c +++ b/drivers/firmware/efi/cper_cxl.c @@ -9,7 +9,6 @@ #include #include "cper_cxl.h" -#include #define PROT_ERR_VALID_AGENT_TYPE BIT_ULL(0) #define PROT_ERR_VALID_AGENT_ADDRESS BIT_ULL(1) @@ -19,6 +18,17 @@ #define PROT_ERR_VALID_DVSEC BIT_ULL(5) #define PROT_ERR_VALID_ERROR_LOG BIT_ULL(6) +/* CXL RAS Capability Structure, CXL v3.0 sec 8.2.4.16 */ +struct cxl_ras_capability_regs { + u32 uncor_status; + u32 uncor_mask; + u32 uncor_severity; + u32 cor_status; + u32 cor_mask; + u32 cap_control; + u32 header_log[16]; +}; + static const char * const prot_err_agent_type_strs[] = { "Restricted CXL Device", "Restricted CXL Host Downstream Port", diff --git a/include/linux/cxl_err.h b/include/linux/cxl_err.h deleted file mode 100644 index 629e1bdeda44..000000000000 --- a/include/linux/cxl_err.h +++ /dev/null @@ -1,22 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2022 Advanced Micro Devices, Inc. - * - * Author: Smita Koralahalli - */ - -#ifndef LINUX_CXL_ERR_H -#define LINUX_CXL_ERR_H - -/* CXL RAS Capability Structure, CXL v3.1 sec 8.2.4.16 */ -struct cxl_ras_capability_regs { - u32 uncor_status; - u32 uncor_mask; - u32 uncor_severity; - u32 cor_status; - u32 cor_mask; - u32 cap_control; - u32 header_log[16]; -}; - -#endif //__CXL_ERR_ -- cgit v1.2.3 From cf1d2ffcc6f17b422239f6ab34b078945d07f9aa Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 1 Feb 2023 09:48:12 +0100 Subject: efi: Discover BTI support in runtime services regions Add the generic plumbing to detect whether or not the runtime code regions were constructed with BTI/IBT landing pads by the firmware, permitting the OS to enable enforcement when mapping these regions into the OS's address space. Signed-off-by: Ard Biesheuvel Reviewed-by: Kees Cook --- arch/arm/include/asm/efi.h | 2 +- arch/arm/kernel/efi.c | 5 +++-- arch/arm64/include/asm/efi.h | 3 ++- arch/arm64/kernel/efi.c | 3 ++- arch/riscv/include/asm/efi.h | 2 +- arch/riscv/kernel/efi.c | 3 ++- arch/x86/platform/efi/efi_64.c | 3 ++- drivers/firmware/efi/memattr.c | 7 ++++++- include/linux/efi.h | 8 ++++++-- 9 files changed, 25 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/include/asm/efi.h b/arch/arm/include/asm/efi.h index b95241b1ca65..78282ced5038 100644 --- a/arch/arm/include/asm/efi.h +++ b/arch/arm/include/asm/efi.h @@ -20,7 +20,7 @@ void efi_init(void); void arm_efi_init(void); int efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md); -int efi_set_mapping_permissions(struct mm_struct *mm, efi_memory_desc_t *md); +int efi_set_mapping_permissions(struct mm_struct *mm, efi_memory_desc_t *md, bool); #define arch_efi_call_virt_setup() efi_virtmap_load() #define arch_efi_call_virt_teardown() efi_virtmap_unload() diff --git a/arch/arm/kernel/efi.c b/arch/arm/kernel/efi.c index 882104f43b3b..e2b9d2618c67 100644 --- a/arch/arm/kernel/efi.c +++ b/arch/arm/kernel/efi.c @@ -23,7 +23,8 @@ static int __init set_permissions(pte_t *ptep, unsigned long addr, void *data) } int __init efi_set_mapping_permissions(struct mm_struct *mm, - efi_memory_desc_t *md) + efi_memory_desc_t *md, + bool ignored) { unsigned long base, size; @@ -71,7 +72,7 @@ int __init efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md) * If stricter permissions were specified, apply them now. */ if (md->attribute & (EFI_MEMORY_RO | EFI_MEMORY_XP)) - return efi_set_mapping_permissions(mm, md); + return efi_set_mapping_permissions(mm, md, false); return 0; } diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h index 31d13a6001df..5d47d429672b 100644 --- a/arch/arm64/include/asm/efi.h +++ b/arch/arm64/include/asm/efi.h @@ -27,7 +27,8 @@ bool efi_runtime_fixup_exception(struct pt_regs *regs, const char *msg) #endif int efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md); -int efi_set_mapping_permissions(struct mm_struct *mm, efi_memory_desc_t *md); +int efi_set_mapping_permissions(struct mm_struct *mm, efi_memory_desc_t *md, + bool has_bti); #define arch_efi_call_virt_setup() \ ({ \ diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c index fab05de2e12d..78ffd5aaddcb 100644 --- a/arch/arm64/kernel/efi.c +++ b/arch/arm64/kernel/efi.c @@ -110,7 +110,8 @@ static int __init set_permissions(pte_t *ptep, unsigned long addr, void *data) } int __init efi_set_mapping_permissions(struct mm_struct *mm, - efi_memory_desc_t *md) + efi_memory_desc_t *md, + bool has_bti) { BUG_ON(md->type != EFI_RUNTIME_SERVICES_CODE && md->type != EFI_RUNTIME_SERVICES_DATA); diff --git a/arch/riscv/include/asm/efi.h b/arch/riscv/include/asm/efi.h index 47d3ab0fcc36..29e9a0d84b16 100644 --- a/arch/riscv/include/asm/efi.h +++ b/arch/riscv/include/asm/efi.h @@ -19,7 +19,7 @@ extern void efi_init(void); #endif int efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md); -int efi_set_mapping_permissions(struct mm_struct *mm, efi_memory_desc_t *md); +int efi_set_mapping_permissions(struct mm_struct *mm, efi_memory_desc_t *md, bool); #define arch_efi_call_virt_setup() ({ \ sync_kernel_mappings(efi_mm.pgd); \ diff --git a/arch/riscv/kernel/efi.c b/arch/riscv/kernel/efi.c index 1aa540350abd..aa6209a74c83 100644 --- a/arch/riscv/kernel/efi.c +++ b/arch/riscv/kernel/efi.c @@ -78,7 +78,8 @@ static int __init set_permissions(pte_t *ptep, unsigned long addr, void *data) } int __init efi_set_mapping_permissions(struct mm_struct *mm, - efi_memory_desc_t *md) + efi_memory_desc_t *md, + bool ignored) { BUG_ON(md->type != EFI_RUNTIME_SERVICES_CODE && md->type != EFI_RUNTIME_SERVICES_DATA); diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index b36596bf0fc3..2e6fe430cb07 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -389,7 +389,8 @@ static int __init efi_update_mappings(efi_memory_desc_t *md, unsigned long pf) return err1 || err2; } -static int __init efi_update_mem_attr(struct mm_struct *mm, efi_memory_desc_t *md) +static int __init efi_update_mem_attr(struct mm_struct *mm, efi_memory_desc_t *md, + bool has_ibt) { unsigned long pf = 0; diff --git a/drivers/firmware/efi/memattr.c b/drivers/firmware/efi/memattr.c index 0a9aba5f9cef..3cbf00f04c5b 100644 --- a/drivers/firmware/efi/memattr.c +++ b/drivers/firmware/efi/memattr.c @@ -129,6 +129,7 @@ int __init efi_memattr_apply_permissions(struct mm_struct *mm, efi_memattr_perm_setter fn) { efi_memory_attributes_table_t *tbl; + bool has_bti = false; int i, ret; if (tbl_size <= sizeof(*tbl)) @@ -150,6 +151,10 @@ int __init efi_memattr_apply_permissions(struct mm_struct *mm, return -ENOMEM; } + if (tbl->version > 1 && + (tbl->flags & EFI_MEMORY_ATTRIBUTES_FLAGS_RT_FORWARD_CONTROL_FLOW_GUARD)) + has_bti = true; + if (efi_enabled(EFI_DBG)) pr_info("Processing EFI Memory Attributes table:\n"); @@ -169,7 +174,7 @@ int __init efi_memattr_apply_permissions(struct mm_struct *mm, efi_md_typeattr_format(buf, sizeof(buf), &md)); if (valid) { - ret = fn(mm, &md); + ret = fn(mm, &md, has_bti); if (ret) pr_err("Error updating mappings, skipping subsequent md's\n"); } diff --git a/include/linux/efi.h b/include/linux/efi.h index 9d455d502ac9..df88786b5947 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -584,11 +584,15 @@ typedef struct { #define EFI_INVALID_TABLE_ADDR (~0UL) +// BIT0 implies that Runtime code includes the forward control flow guard +// instruction, such as X86 CET-IBT or ARM BTI. +#define EFI_MEMORY_ATTRIBUTES_FLAGS_RT_FORWARD_CONTROL_FLOW_GUARD 0x1 + typedef struct { u32 version; u32 num_entries; u32 desc_size; - u32 reserved; + u32 flags; efi_memory_desc_t entry[0]; } efi_memory_attributes_table_t; @@ -751,7 +755,7 @@ extern unsigned long efi_mem_attr_table; * argument in the page tables referred to by the * first argument. */ -typedef int (*efi_memattr_perm_setter)(struct mm_struct *, efi_memory_desc_t *); +typedef int (*efi_memattr_perm_setter)(struct mm_struct *, efi_memory_desc_t *, bool); extern int efi_memattr_init(void); extern int efi_memattr_apply_permissions(struct mm_struct *mm, -- cgit v1.2.3 From 8d9ef69487e114f80e20ffbec14ca8684953fef0 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Thu, 26 Jan 2023 16:38:21 +0100 Subject: mfd: intel_soc_pmic_chtwc: Add Lenovo Yoga Tab 3 X90F to intel_cht_wc_models The drivers for various CHT Whiskey Cove PMIC child-devices need to know the model, since they have model specific behavior. The DMI match table for this is shared between the child-device-drivers inside the MFD driver. Add the Lenovo Yoga Tab 3 X90F, which is a previously unknown tablet model with a CHT Whiskey Cove PMIC, to the intel_cht_wc_models enum and to the DMI match table. Signed-off-by: Hans de Goede Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230126153823.22146-2-hdegoede@redhat.com --- drivers/mfd/intel_soc_pmic_chtwc.c | 8 ++++++++ include/linux/mfd/intel_soc_pmic.h | 1 + 2 files changed, 9 insertions(+) (limited to 'include/linux') diff --git a/drivers/mfd/intel_soc_pmic_chtwc.c b/drivers/mfd/intel_soc_pmic_chtwc.c index 9216f0d34206..d53dae255490 100644 --- a/drivers/mfd/intel_soc_pmic_chtwc.c +++ b/drivers/mfd/intel_soc_pmic_chtwc.c @@ -165,6 +165,14 @@ static const struct dmi_system_id cht_wc_model_dmi_ids[] = { /* Non exact match to match all versions */ DMI_MATCH(DMI_PRODUCT_NAME, "Lenovo YB1-X9"), }, + }, { + /* Lenovo Yoga Tab 3 Pro YT3-X90F */ + .driver_data = (void *)(long)INTEL_CHT_WC_LENOVO_YT3_X90, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Intel Corporation"), + DMI_MATCH(DMI_PRODUCT_NAME, "CHERRYVIEW D1 PLATFORM"), + DMI_MATCH(DMI_PRODUCT_VERSION, "Blade3-10A-001"), + }, }, { } }; diff --git a/include/linux/mfd/intel_soc_pmic.h b/include/linux/mfd/intel_soc_pmic.h index 945bde1fe55c..9ba2c1a8d836 100644 --- a/include/linux/mfd/intel_soc_pmic.h +++ b/include/linux/mfd/intel_soc_pmic.h @@ -18,6 +18,7 @@ enum intel_cht_wc_models { INTEL_CHT_WC_GPD_WIN_POCKET, INTEL_CHT_WC_XIAOMI_MIPAD2, INTEL_CHT_WC_LENOVO_YOGABOOK1, + INTEL_CHT_WC_LENOVO_YT3_X90, }; /** -- cgit v1.2.3 From 58ef4ece1e41ac525db3e79529909683325d85df Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Tue, 31 Jan 2023 20:18:51 -0800 Subject: soc: qcom: pmic_glink: Introduce base PMIC GLINK driver The PMIC GLINK service runs on one of the co-processors of some modern Qualcomm platforms and implements USB-C and battery managements. It uses a message based protocol over GLINK for communication with the OS, hence the name. The driver implemented provides the rpmsg device for communication and uses auxiliary bus to spawn off individual devices in respective subsystem. The auxiliary devices are spawned off from a platform_device, so that the drm_bridge is available early, to allow the DisplayPort driver to probe even before the remoteproc has spun up. Signed-off-by: Bjorn Andersson Tested-by: Konrad Dybcio # SM8350 PDX215 Reviewed-by: Neil Armstrong Tested-by: Neil Armstrong # on SM8550-MTP & SM8450-HDK Signed-off-by: Bjorn Andersson Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230201041853.1934355-3-quic_bjorande@quicinc.com --- drivers/soc/qcom/Kconfig | 15 ++ drivers/soc/qcom/Makefile | 1 + drivers/soc/qcom/pmic_glink.c | 336 ++++++++++++++++++++++++++++++++++++ include/linux/soc/qcom/pmic_glink.h | 32 ++++ 4 files changed, 384 insertions(+) create mode 100644 drivers/soc/qcom/pmic_glink.c create mode 100644 include/linux/soc/qcom/pmic_glink.h (limited to 'include/linux') diff --git a/drivers/soc/qcom/Kconfig b/drivers/soc/qcom/Kconfig index ae504c43d9e7..df6ff7bf90cb 100644 --- a/drivers/soc/qcom/Kconfig +++ b/drivers/soc/qcom/Kconfig @@ -92,6 +92,21 @@ config QCOM_PDR_HELPERS tristate select QCOM_QMI_HELPERS +config QCOM_PMIC_GLINK + tristate "Qualcomm PMIC GLINK driver" + depends on RPMSG + depends on TYPEC + depends on DRM + select AUXILIARY_BUS + select QCOM_PDR_HELPERS + help + The Qualcomm PMIC GLINK driver provides access, over GLINK, to the + USB and battery firmware running on one of the coprocessors in + several modern Qualcomm platforms. + + Say yes here to support USB-C and battery status on modern Qualcomm + platforms. + config QCOM_QMI_HELPERS tristate depends on NET diff --git a/drivers/soc/qcom/Makefile b/drivers/soc/qcom/Makefile index d66604aff2b0..fbbd1231e554 100644 --- a/drivers/soc/qcom/Makefile +++ b/drivers/soc/qcom/Makefile @@ -8,6 +8,7 @@ obj-$(CONFIG_QCOM_GSBI) += qcom_gsbi.o obj-$(CONFIG_QCOM_MDT_LOADER) += mdt_loader.o obj-$(CONFIG_QCOM_OCMEM) += ocmem.o obj-$(CONFIG_QCOM_PDR_HELPERS) += pdr_interface.o +obj-$(CONFIG_QCOM_PMIC_GLINK) += pmic_glink.o obj-$(CONFIG_QCOM_QMI_HELPERS) += qmi_helpers.o qmi_helpers-y += qmi_encdec.o qmi_interface.o obj-$(CONFIG_QCOM_RMTFS_MEM) += rmtfs_mem.o diff --git a/drivers/soc/qcom/pmic_glink.c b/drivers/soc/qcom/pmic_glink.c new file mode 100644 index 000000000000..bb3fb57abcc6 --- /dev/null +++ b/drivers/soc/qcom/pmic_glink.c @@ -0,0 +1,336 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2019-2020, The Linux Foundation. All rights reserved. + * Copyright (c) 2022, Linaro Ltd + */ +#include +#include +#include +#include +#include +#include +#include + +struct pmic_glink { + struct device *dev; + struct pdr_handle *pdr; + + struct rpmsg_endpoint *ept; + + struct auxiliary_device altmode_aux; + struct auxiliary_device ps_aux; + struct auxiliary_device ucsi_aux; + + /* serializing client_state and pdr_state updates */ + struct mutex state_lock; + unsigned int client_state; + unsigned int pdr_state; + + /* serializing clients list updates */ + struct mutex client_lock; + struct list_head clients; +}; + +static struct pmic_glink *__pmic_glink; +static DEFINE_MUTEX(__pmic_glink_lock); + +struct pmic_glink_client { + struct list_head node; + + struct pmic_glink *pg; + unsigned int id; + + void (*cb)(const void *data, size_t len, void *priv); + void (*pdr_notify)(void *priv, int state); + void *priv; +}; + +static void _devm_pmic_glink_release_client(struct device *dev, void *res) +{ + struct pmic_glink_client *client = (struct pmic_glink_client *)res; + struct pmic_glink *pg = client->pg; + + mutex_lock(&pg->client_lock); + list_del(&client->node); + mutex_unlock(&pg->client_lock); +} + +struct pmic_glink_client *devm_pmic_glink_register_client(struct device *dev, + unsigned int id, + void (*cb)(const void *, size_t, void *), + void (*pdr)(void *, int), + void *priv) +{ + struct pmic_glink_client *client; + struct pmic_glink *pg = dev_get_drvdata(dev->parent); + + client = devres_alloc(_devm_pmic_glink_release_client, sizeof(*client), GFP_KERNEL); + if (!client) + return ERR_PTR(-ENOMEM); + + client->pg = pg; + client->id = id; + client->cb = cb; + client->pdr_notify = pdr; + client->priv = priv; + + mutex_lock(&pg->client_lock); + list_add(&client->node, &pg->clients); + mutex_unlock(&pg->client_lock); + + devres_add(dev, client); + + return client; +} +EXPORT_SYMBOL_GPL(devm_pmic_glink_register_client); + +int pmic_glink_send(struct pmic_glink_client *client, void *data, size_t len) +{ + struct pmic_glink *pg = client->pg; + + return rpmsg_send(pg->ept, data, len); +} +EXPORT_SYMBOL_GPL(pmic_glink_send); + +static int pmic_glink_rpmsg_callback(struct rpmsg_device *rpdev, void *data, + int len, void *priv, u32 addr) +{ + struct pmic_glink_client *client; + struct pmic_glink_hdr *hdr; + struct pmic_glink *pg = dev_get_drvdata(&rpdev->dev); + + if (len < sizeof(*hdr)) { + dev_warn(pg->dev, "ignoring truncated message\n"); + return 0; + } + + hdr = data; + + list_for_each_entry(client, &pg->clients, node) { + if (client->id == le32_to_cpu(hdr->owner)) + client->cb(data, len, client->priv); + } + + return 0; +} + +static void pmic_glink_aux_release(struct device *dev) {} + +static int pmic_glink_add_aux_device(struct pmic_glink *pg, + struct auxiliary_device *aux, + const char *name) +{ + struct device *parent = pg->dev; + int ret; + + aux->name = name; + aux->dev.parent = parent; + aux->dev.release = pmic_glink_aux_release; + device_set_of_node_from_dev(&aux->dev, parent); + ret = auxiliary_device_init(aux); + if (ret) + return ret; + + ret = auxiliary_device_add(aux); + if (ret) + auxiliary_device_uninit(aux); + + return ret; +} + +static void pmic_glink_del_aux_device(struct pmic_glink *pg, + struct auxiliary_device *aux) +{ + auxiliary_device_delete(aux); + auxiliary_device_uninit(aux); +} + +static void pmic_glink_state_notify_clients(struct pmic_glink *pg) +{ + struct pmic_glink_client *client; + unsigned int new_state = pg->client_state; + + if (pg->client_state != SERVREG_SERVICE_STATE_UP) { + if (pg->pdr_state == SERVREG_SERVICE_STATE_UP && pg->ept) + new_state = SERVREG_SERVICE_STATE_UP; + } else { + if (pg->pdr_state == SERVREG_SERVICE_STATE_UP && pg->ept) + new_state = SERVREG_SERVICE_STATE_DOWN; + } + + if (new_state != pg->client_state) { + list_for_each_entry(client, &pg->clients, node) + client->pdr_notify(client->priv, new_state); + pg->client_state = new_state; + } +} + +static void pmic_glink_pdr_callback(int state, char *svc_path, void *priv) +{ + struct pmic_glink *pg = priv; + + mutex_lock(&pg->state_lock); + pg->pdr_state = state; + + pmic_glink_state_notify_clients(pg); + mutex_unlock(&pg->state_lock); +} + +static int pmic_glink_rpmsg_probe(struct rpmsg_device *rpdev) +{ + struct pmic_glink *pg = __pmic_glink; + int ret = 0; + + mutex_lock(&__pmic_glink_lock); + if (!pg) { + ret = dev_err_probe(&rpdev->dev, -ENODEV, "no pmic_glink device to attach to\n"); + goto out_unlock; + } + + dev_set_drvdata(&rpdev->dev, pg); + + mutex_lock(&pg->state_lock); + pg->ept = rpdev->ept; + pmic_glink_state_notify_clients(pg); + mutex_unlock(&pg->state_lock); + +out_unlock: + mutex_unlock(&__pmic_glink_lock); + return ret; +} + +static void pmic_glink_rpmsg_remove(struct rpmsg_device *rpdev) +{ + struct pmic_glink *pg; + + mutex_lock(&__pmic_glink_lock); + pg = __pmic_glink; + if (!pg) + goto out_unlock; + + mutex_lock(&pg->state_lock); + pg->ept = NULL; + pmic_glink_state_notify_clients(pg); + mutex_unlock(&pg->state_lock); +out_unlock: + mutex_unlock(&__pmic_glink_lock); +} + +static const struct rpmsg_device_id pmic_glink_rpmsg_id_match[] = { + { "PMIC_RTR_ADSP_APPS" }, + {} +}; + +static struct rpmsg_driver pmic_glink_rpmsg_driver = { + .probe = pmic_glink_rpmsg_probe, + .remove = pmic_glink_rpmsg_remove, + .callback = pmic_glink_rpmsg_callback, + .id_table = pmic_glink_rpmsg_id_match, + .drv = { + .name = "qcom_pmic_glink_rpmsg", + }, +}; + +static int pmic_glink_probe(struct platform_device *pdev) +{ + struct pdr_service *service; + struct pmic_glink *pg; + int ret; + + pg = devm_kzalloc(&pdev->dev, sizeof(*pg), GFP_KERNEL); + if (!pg) + return -ENOMEM; + + dev_set_drvdata(&pdev->dev, pg); + + pg->dev = &pdev->dev; + + INIT_LIST_HEAD(&pg->clients); + mutex_init(&pg->client_lock); + mutex_init(&pg->state_lock); + + ret = pmic_glink_add_aux_device(pg, &pg->altmode_aux, "altmode"); + if (ret) + return ret; + ret = pmic_glink_add_aux_device(pg, &pg->ps_aux, "power-supply"); + if (ret) + goto out_release_altmode_aux; + + pg->pdr = pdr_handle_alloc(pmic_glink_pdr_callback, pg); + if (IS_ERR(pg->pdr)) { + ret = dev_err_probe(&pdev->dev, PTR_ERR(pg->pdr), "failed to initialize pdr\n"); + goto out_release_aux_devices; + } + + service = pdr_add_lookup(pg->pdr, "tms/servreg", "msm/adsp/charger_pd"); + if (IS_ERR(service)) { + ret = dev_err_probe(&pdev->dev, PTR_ERR(service), + "failed adding pdr lookup for charger_pd\n"); + goto out_release_pdr_handle; + } + + mutex_lock(&__pmic_glink_lock); + __pmic_glink = pg; + mutex_unlock(&__pmic_glink_lock); + + return 0; + +out_release_pdr_handle: + pdr_handle_release(pg->pdr); +out_release_aux_devices: + pmic_glink_del_aux_device(pg, &pg->ps_aux); +out_release_altmode_aux: + pmic_glink_del_aux_device(pg, &pg->altmode_aux); + + return ret; +} + +static int pmic_glink_remove(struct platform_device *pdev) +{ + struct pmic_glink *pg = dev_get_drvdata(&pdev->dev); + + pdr_handle_release(pg->pdr); + + pmic_glink_del_aux_device(pg, &pg->ps_aux); + pmic_glink_del_aux_device(pg, &pg->altmode_aux); + + mutex_lock(&__pmic_glink_lock); + __pmic_glink = NULL; + mutex_unlock(&__pmic_glink_lock); + + return 0; +} + +static const struct of_device_id pmic_glink_of_match[] = { + { .compatible = "qcom,pmic-glink", }, + {} +}; +MODULE_DEVICE_TABLE(of, pmic_glink_of_match); + +static struct platform_driver pmic_glink_driver = { + .probe = pmic_glink_probe, + .remove = pmic_glink_remove, + .driver = { + .name = "qcom_pmic_glink", + .of_match_table = pmic_glink_of_match, + }, +}; + +static int pmic_glink_init(void) +{ + platform_driver_register(&pmic_glink_driver); + register_rpmsg_driver(&pmic_glink_rpmsg_driver); + + return 0; +}; +module_init(pmic_glink_init); + +static void pmic_glink_exit(void) +{ + unregister_rpmsg_driver(&pmic_glink_rpmsg_driver); + platform_driver_unregister(&pmic_glink_driver); +}; +module_exit(pmic_glink_exit); + +MODULE_DESCRIPTION("Qualcomm PMIC GLINK driver"); +MODULE_LICENSE("GPL"); diff --git a/include/linux/soc/qcom/pmic_glink.h b/include/linux/soc/qcom/pmic_glink.h new file mode 100644 index 000000000000..fd124aa18c81 --- /dev/null +++ b/include/linux/soc/qcom/pmic_glink.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2022, Linaro Ltd + */ +#ifndef __SOC_QCOM_PMIC_GLINK_H__ +#define __SOC_QCOM_PMIC_GLINK_H__ + +struct pmic_glink; +struct pmic_glink_client; + +#define PMIC_GLINK_OWNER_BATTMGR 32778 +#define PMIC_GLINK_OWNER_USBC 32779 +#define PMIC_GLINK_OWNER_USBC_PAN 32780 + +#define PMIC_GLINK_REQ_RESP 1 +#define PMIC_GLINK_NOTIFY 2 + +struct pmic_glink_hdr { + __le32 owner; + __le32 type; + __le32 opcode; +}; + +int pmic_glink_send(struct pmic_glink_client *client, void *data, size_t len); + +struct pmic_glink_client *devm_pmic_glink_register_client(struct device *dev, + unsigned int id, + void (*cb)(const void *, size_t, void *), + void (*pdr)(void *, int), + void *priv); + +#endif -- cgit v1.2.3 From fb6211f1584aad12c267c3333273f42f69438ced Mon Sep 17 00:00:00 2001 From: Jó Ágila Bitsch Date: Sat, 4 Feb 2023 13:15:01 +0100 Subject: usb: gadget: add doc to struct usb_composite_dev Added documentation to new struct members for WebUSB: * bcd_webusb_version * b_webusb_vendor_code * landing_page * use_webusb to avoid warnings in the build of htmldocs Fixes: 93c473948c58 ("usb: gadget: add WebUSB landing page support") Reported-by: Stephen Rothwell Signed-off-by: Jó Ágila Bitsch Link: https://lore.kernel.org/r/Y95MRZZz3yC5lETB@jo-einhundert Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/composite.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h index 91d22c3ed458..7ef8cea67f50 100644 --- a/include/linux/usb/composite.h +++ b/include/linux/usb/composite.h @@ -432,6 +432,10 @@ static inline struct usb_composite_driver *to_cdriver( * @qw_sign: qwSignature part of the OS string * @b_vendor_code: bMS_VendorCode part of the OS string * @use_os_string: false by default, interested gadgets set it + * @bcd_webusb_version: 0x0100 by default, WebUSB specification version + * @b_webusb_vendor_code: 0x0 by default, vendor code for WebUSB + * @landing_page: empty by default, landing page to announce in WebUSB + * @use_webusb:: false by default, interested gadgets set it * @os_desc_config: the configuration to be used with OS descriptors * @setup_pending: true when setup request is queued but not completed * @os_desc_pending: true when os_desc request is queued but not completed -- cgit v1.2.3 From eca0edaf6caa66b6eb26277a7dce5d7296cedfca Mon Sep 17 00:00:00 2001 From: Marcos Paulo de Souza Date: Fri, 3 Feb 2023 09:22:21 -0300 Subject: module.h: Document klp_modinfo struct using kdoc Previously the documentation existed only in Documentation/livepatch directory. Signed-off-by: Marcos Paulo de Souza Signed-off-by: Luis Chamberlain --- include/linux/module.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index 8c5909c0076c..6449ea59c074 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -352,6 +352,14 @@ struct mod_kallsyms { }; #ifdef CONFIG_LIVEPATCH +/** + * struct klp_modinfo - Elf information preserved from the livepatch module + * + * @hdr: Elf header + * @sechdrs: Section header table + * @secstrings: String table for the section headers + * @symndx: The symbol table section index + */ struct klp_modinfo { Elf_Ehdr hdr; Elf_Shdr *sechdrs; -- cgit v1.2.3 From 20f6d4f2a474fc2dc502358dcee3c9b18304ec1e Mon Sep 17 00:00:00 2001 From: Thomas Weißschuh Date: Sat, 4 Feb 2023 05:47:03 +0000 Subject: of: make of_node_ktype constant Since commit ee6d3dd4ed48 ("driver core: make kobj_type constant.") the driver core allows the usage of const struct kobj_type. Take advantage of this to constify the structure definition to prevent modification at runtime. Signed-off-by: Thomas Weißschuh Link: https://lore.kernel.org/r/20230204-kobj_type-of-v1-1-5910c8ecb7a3@weissschuh.net Signed-off-by: Rob Herring --- drivers/of/kobj.c | 2 +- include/linux/of.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/of/kobj.c b/drivers/of/kobj.c index 7d3853a5a09a..3dbce1e6f184 100644 --- a/drivers/of/kobj.c +++ b/drivers/of/kobj.c @@ -24,7 +24,7 @@ static void of_node_release(struct kobject *kobj) } #endif /* CONFIG_OF_DYNAMIC */ -struct kobj_type of_node_ktype = { +const struct kobj_type of_node_ktype = { .release = of_node_release, }; diff --git a/include/linux/of.h b/include/linux/of.h index 8b9f94386dc3..8bb348666709 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -101,7 +101,7 @@ struct of_reconfig_data { }; /* initialize a node */ -extern struct kobj_type of_node_ktype; +extern const struct kobj_type of_node_ktype; extern const struct fwnode_operations of_fwnode_ops; static inline void of_node_init(struct device_node *node) { -- cgit v1.2.3 From 7390609b0121a1b982c5ecdfcd72dc328e5784ee Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Mon, 6 Feb 2023 13:43:42 +0000 Subject: net: add helper eth_addr_add() Add a helper to add an offset to a ethernet address. This comes in handy if you have a base ethernet address for multiple interfaces. Signed-off-by: Michael Walle Reviewed-by: Andrew Lunn Acked-by: Jakub Kicinski Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230206134356.839737-9-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/etherdevice.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index a541f0c4f146..224645f17c33 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -507,6 +507,20 @@ static inline void eth_addr_inc(u8 *addr) u64_to_ether_addr(u, addr); } +/** + * eth_addr_add() - Add (or subtract) an offset to/from the given MAC address. + * + * @offset: Offset to add. + * @addr: Pointer to a six-byte array containing Ethernet address to increment. + */ +static inline void eth_addr_add(u8 *addr, long offset) +{ + u64 u = ether_addr_to_u64(addr); + + u += offset; + u64_to_ether_addr(u, addr); +} + /** * is_etherdev_addr - Tell if given Ethernet address belongs to the device. * @dev: Pointer to a device structure -- cgit v1.2.3 From c5d264d4b527c96ae8903376a4b195df47b05203 Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Mon, 6 Feb 2023 13:43:43 +0000 Subject: of: base: add of_parse_phandle_with_optional_args() Add a new variant of the of_parse_phandle_with_args() which treats the cells name as optional. If it's missing, it is assumed that the phandle has no arguments. Up until now, a nvmem node didn't have any arguments, so all the device trees haven't any '#*-cells' property. But there is a need for an additional argument for the phandle, for which we need a '#*-cells' property. Therefore, we need to support nvmem nodes with and without this property. Signed-off-by: Michael Walle Reviewed-by: Rob Herring Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230206134356.839737-10-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/of.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index 8b9f94386dc3..98c252d2d851 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -1008,6 +1008,31 @@ static inline int of_parse_phandle_with_fixed_args(const struct device_node *np, index, out_args); } +/** + * of_parse_phandle_with_optional_args() - Find a node pointed by phandle in a list + * @np: pointer to a device tree node containing a list + * @list_name: property name that contains a list + * @cells_name: property name that specifies phandles' arguments count + * @index: index of a phandle to parse out + * @out_args: optional pointer to output arguments structure (will be filled) + * + * Same as of_parse_phandle_with_args() except that if the cells_name property + * is not found, cell_count of 0 is assumed. + * + * This is used to useful, if you have a phandle which didn't have arguments + * before and thus doesn't have a '#*-cells' property but is now migrated to + * having arguments while retaining backwards compatibility. + */ +static inline int of_parse_phandle_with_optional_args(const struct device_node *np, + const char *list_name, + const char *cells_name, + int index, + struct of_phandle_args *out_args) +{ + return __of_parse_phandle_with_args(np, list_name, cells_name, + 0, index, out_args); +} + /** * of_property_count_u8_elems - Count the number of u8 elements in a property * -- cgit v1.2.3 From 5d8e6e6c10a3d37486d263b16ddc15991a7e4a88 Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Mon, 6 Feb 2023 13:43:46 +0000 Subject: nvmem: core: add an index parameter to the cell Sometimes a cell can represend multiple values. For example, a base ethernet address stored in the NVMEM can be expanded into multiple discreet ones by adding an offset. For this use case, introduce an index parameter which is then used to distiguish between values. This parameter will then be passed to the post process hook which can then use it to create different values during reading. At the moment, there is only support for the device tree path. You can add the index to the phandle, e.g. &net { nvmem-cells = <&base_mac_address 2>; nvmem-cell-names = "mac-address"; }; &nvmem_provider { base_mac_address: base-mac-address@0 { #nvmem-cell-cells = <1>; reg = <0 6>; }; }; Signed-off-by: Michael Walle Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230206134356.839737-13-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/core.c | 37 ++++++++++++++++++++++++++----------- drivers/nvmem/imx-ocotp.c | 4 ++-- include/linux/nvmem-provider.h | 4 ++-- 3 files changed, 30 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c index 233c6c275031..30567dd51fba 100644 --- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -60,6 +60,7 @@ struct nvmem_cell_entry { struct nvmem_cell { struct nvmem_cell_entry *entry; const char *id; + int index; }; static DEFINE_MUTEX(nvmem_mutex); @@ -1122,7 +1123,8 @@ struct nvmem_device *devm_nvmem_device_get(struct device *dev, const char *id) } EXPORT_SYMBOL_GPL(devm_nvmem_device_get); -static struct nvmem_cell *nvmem_create_cell(struct nvmem_cell_entry *entry, const char *id) +static struct nvmem_cell *nvmem_create_cell(struct nvmem_cell_entry *entry, + const char *id, int index) { struct nvmem_cell *cell; const char *name = NULL; @@ -1141,6 +1143,7 @@ static struct nvmem_cell *nvmem_create_cell(struct nvmem_cell_entry *entry, cons cell->id = name; cell->entry = entry; + cell->index = index; return cell; } @@ -1179,7 +1182,7 @@ nvmem_cell_get_from_lookup(struct device *dev, const char *con_id) __nvmem_device_put(nvmem); cell = ERR_PTR(-ENOENT); } else { - cell = nvmem_create_cell(cell_entry, con_id); + cell = nvmem_create_cell(cell_entry, con_id, 0); if (IS_ERR(cell)) __nvmem_device_put(nvmem); } @@ -1227,15 +1230,27 @@ struct nvmem_cell *of_nvmem_cell_get(struct device_node *np, const char *id) struct nvmem_device *nvmem; struct nvmem_cell_entry *cell_entry; struct nvmem_cell *cell; + struct of_phandle_args cell_spec; int index = 0; + int cell_index = 0; + int ret; /* if cell name exists, find index to the name */ if (id) index = of_property_match_string(np, "nvmem-cell-names", id); - cell_np = of_parse_phandle(np, "nvmem-cells", index); - if (!cell_np) - return ERR_PTR(-ENOENT); + ret = of_parse_phandle_with_optional_args(np, "nvmem-cells", + "#nvmem-cell-cells", + index, &cell_spec); + if (ret) + return ERR_PTR(ret); + + if (cell_spec.args_count > 1) + return ERR_PTR(-EINVAL); + + cell_np = cell_spec.np; + if (cell_spec.args_count) + cell_index = cell_spec.args[0]; nvmem_np = of_get_parent(cell_np); if (!nvmem_np) { @@ -1257,7 +1272,7 @@ struct nvmem_cell *of_nvmem_cell_get(struct device_node *np, const char *id) return ERR_PTR(-ENOENT); } - cell = nvmem_create_cell(cell_entry, id); + cell = nvmem_create_cell(cell_entry, id, cell_index); if (IS_ERR(cell)) __nvmem_device_put(nvmem); @@ -1410,8 +1425,8 @@ static void nvmem_shift_read_buffer_in_place(struct nvmem_cell_entry *cell, void } static int __nvmem_cell_read(struct nvmem_device *nvmem, - struct nvmem_cell_entry *cell, - void *buf, size_t *len, const char *id) + struct nvmem_cell_entry *cell, + void *buf, size_t *len, const char *id, int index) { int rc; @@ -1425,7 +1440,7 @@ static int __nvmem_cell_read(struct nvmem_device *nvmem, nvmem_shift_read_buffer_in_place(cell, buf); if (nvmem->cell_post_process) { - rc = nvmem->cell_post_process(nvmem->priv, id, + rc = nvmem->cell_post_process(nvmem->priv, id, index, cell->offset, buf, cell->bytes); if (rc) return rc; @@ -1460,7 +1475,7 @@ void *nvmem_cell_read(struct nvmem_cell *cell, size_t *len) if (!buf) return ERR_PTR(-ENOMEM); - rc = __nvmem_cell_read(nvmem, cell->entry, buf, len, cell->id); + rc = __nvmem_cell_read(nvmem, cell->entry, buf, len, cell->id, cell->index); if (rc) { kfree(buf); return ERR_PTR(rc); @@ -1773,7 +1788,7 @@ ssize_t nvmem_device_cell_read(struct nvmem_device *nvmem, if (rc) return rc; - rc = __nvmem_cell_read(nvmem, &cell, buf, &len, NULL); + rc = __nvmem_cell_read(nvmem, &cell, buf, &len, NULL, 0); if (rc) return rc; diff --git a/drivers/nvmem/imx-ocotp.c b/drivers/nvmem/imx-ocotp.c index 14284e866f26..e9b52ecb3f72 100644 --- a/drivers/nvmem/imx-ocotp.c +++ b/drivers/nvmem/imx-ocotp.c @@ -222,8 +222,8 @@ read_end: return ret; } -static int imx_ocotp_cell_pp(void *context, const char *id, unsigned int offset, - void *data, size_t bytes) +static int imx_ocotp_cell_pp(void *context, const char *id, int index, + unsigned int offset, void *data, size_t bytes) { struct ocotp_priv *priv = context; diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index bb15c9234e21..55181d837969 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -20,8 +20,8 @@ typedef int (*nvmem_reg_read_t)(void *priv, unsigned int offset, typedef int (*nvmem_reg_write_t)(void *priv, unsigned int offset, void *val, size_t bytes); /* used for vendor specific post processing of cell data */ -typedef int (*nvmem_cell_post_process_t)(void *priv, const char *id, unsigned int offset, - void *buf, size_t bytes); +typedef int (*nvmem_cell_post_process_t)(void *priv, const char *id, int index, + unsigned int offset, void *buf, size_t bytes); enum nvmem_type { NVMEM_TYPE_UNKNOWN = 0, -- cgit v1.2.3 From fbd03d27776c6121a483921601418e3c8f0ff37e Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Mon, 6 Feb 2023 13:43:47 +0000 Subject: nvmem: core: move struct nvmem_cell_info to nvmem-provider.h struct nvmem_cell_info is used to describe a cell. Thus this should really be in the nvmem-provider's header. There are two (unused) nvmem access methods which use the nvmem_cell_info to describe the cell to be accesses. One can argue, that they will create a cell before accessing, thus they are both a provider and a consumer. struct nvmem_cell_info will get used more and more by nvmem-providers, don't force them to also include the consumer header, although they are not. Signed-off-by: Michael Walle Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230206134356.839737-14-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/nvmem-consumer.h | 10 +--------- include/linux/nvmem-provider.h | 19 ++++++++++++++++++- 2 files changed, 19 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nvmem-consumer.h b/include/linux/nvmem-consumer.h index 980f9c9ac0bc..1f62f7ba71ca 100644 --- a/include/linux/nvmem-consumer.h +++ b/include/linux/nvmem-consumer.h @@ -18,15 +18,7 @@ struct device_node; /* consumer cookie */ struct nvmem_cell; struct nvmem_device; - -struct nvmem_cell_info { - const char *name; - unsigned int offset; - unsigned int bytes; - unsigned int bit_offset; - unsigned int nbits; - struct device_node *np; -}; +struct nvmem_cell_info; /** * struct nvmem_cell_lookup - cell lookup entry diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index 55181d837969..a953a3a59535 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -14,7 +14,6 @@ #include struct nvmem_device; -struct nvmem_cell_info; typedef int (*nvmem_reg_read_t)(void *priv, unsigned int offset, void *val, size_t bytes); typedef int (*nvmem_reg_write_t)(void *priv, unsigned int offset, @@ -47,6 +46,24 @@ struct nvmem_keepout { unsigned char value; }; +/** + * struct nvmem_cell_info - NVMEM cell description + * @name: Name. + * @offset: Offset within the NVMEM device. + * @bytes: Length of the cell. + * @bit_offset: Bit offset if cell is smaller than a byte. + * @nbits: Number of bits. + * @np: Optional device_node pointer. + */ +struct nvmem_cell_info { + const char *name; + unsigned int offset; + unsigned int bytes; + unsigned int bit_offset; + unsigned int nbits; + struct device_node *np; +}; + /** * struct nvmem_config - NVMEM device configuration * -- cgit v1.2.3 From 2ded6830d376d5e7bf43d59f7f7fdf1a59abc676 Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Mon, 6 Feb 2023 13:43:49 +0000 Subject: nvmem: core: add nvmem_add_one_cell() Add a new function to add exactly one cell. This will be used by the nvmem layout drivers to add custom cells. In contrast to the nvmem_add_cells(), this has the advantage that we don't have to assemble a list of cells on runtime. Signed-off-by: Michael Walle Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230206134356.839737-16-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/core.c | 59 +++++++++++++++++++++++++----------------- include/linux/nvmem-provider.h | 8 ++++++ 2 files changed, 43 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c index 98ae70695f36..58f8e33e7a8c 100644 --- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -501,6 +501,36 @@ static int nvmem_cell_info_to_nvmem_cell_entry(struct nvmem_device *nvmem, return 0; } +/** + * nvmem_add_one_cell() - Add one cell information to an nvmem device + * + * @nvmem: nvmem device to add cells to. + * @info: nvmem cell info to add to the device + * + * Return: 0 or negative error code on failure. + */ +int nvmem_add_one_cell(struct nvmem_device *nvmem, + const struct nvmem_cell_info *info) +{ + struct nvmem_cell_entry *cell; + int rval; + + cell = kzalloc(sizeof(*cell), GFP_KERNEL); + if (!cell) + return -ENOMEM; + + rval = nvmem_cell_info_to_nvmem_cell_entry(nvmem, info, cell); + if (rval) { + kfree(cell); + return rval; + } + + nvmem_cell_entry_add(cell); + + return 0; +} +EXPORT_SYMBOL_GPL(nvmem_add_one_cell); + /** * nvmem_add_cells() - Add cell information to an nvmem device * @@ -514,34 +544,15 @@ static int nvmem_add_cells(struct nvmem_device *nvmem, const struct nvmem_cell_info *info, int ncells) { - struct nvmem_cell_entry **cells; - int i, rval = 0; - - cells = kcalloc(ncells, sizeof(*cells), GFP_KERNEL); - if (!cells) - return -ENOMEM; + int i, rval; for (i = 0; i < ncells; i++) { - cells[i] = kzalloc(sizeof(**cells), GFP_KERNEL); - if (!cells[i]) { - rval = -ENOMEM; - goto out; - } - - rval = nvmem_cell_info_to_nvmem_cell_entry(nvmem, &info[i], cells[i]); - if (rval) { - kfree(cells[i]); - goto out; - } - - nvmem_cell_entry_add(cells[i]); + rval = nvmem_add_one_cell(nvmem, &info[i]); + if (rval) + return rval; } -out: - /* remove tmp array */ - kfree(cells); - - return rval; + return 0; } /** diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index a953a3a59535..0262b86194eb 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -153,6 +153,9 @@ struct nvmem_device *devm_nvmem_register(struct device *dev, void nvmem_add_cell_table(struct nvmem_cell_table *table); void nvmem_del_cell_table(struct nvmem_cell_table *table); +int nvmem_add_one_cell(struct nvmem_device *nvmem, + const struct nvmem_cell_info *info); + #else static inline struct nvmem_device *nvmem_register(const struct nvmem_config *c) @@ -170,6 +173,11 @@ devm_nvmem_register(struct device *dev, const struct nvmem_config *c) static inline void nvmem_add_cell_table(struct nvmem_cell_table *table) {} static inline void nvmem_del_cell_table(struct nvmem_cell_table *table) {} +static inline int nvmem_add_one_cell(struct nvmem_device *nvmem, + const struct nvmem_cell_info *info) +{ + return -EOPNOTSUPP; +} #endif /* CONFIG_NVMEM */ #endif /* ifndef _LINUX_NVMEM_PROVIDER_H */ -- cgit v1.2.3 From 15a7cf8caabee4613764abe7814dd3162cb64137 Mon Sep 17 00:00:00 2001 From: Daniel Scally Date: Mon, 6 Feb 2023 16:17:57 +0000 Subject: usb: gadget: configfs: Support arbitrary string descriptors Add a framework to allow users to define arbitrary string descriptors for a USB Gadget. This is modelled as a new type of config item rather than as hardcoded attributes so as to be as flexible as possible. Signed-off-by: Daniel Scally Link: https://lore.kernel.org/r/20230206161802.892954-7-dan.scally@ideasonboard.com Signed-off-by: Greg Kroah-Hartman --- Documentation/usb/gadget_configfs.rst | 10 ++ drivers/usb/gadget/configfs.c | 172 +++++++++++++++++++++++++++++++++- include/linux/usb/gadget.h | 11 +++ 3 files changed, 191 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/Documentation/usb/gadget_configfs.rst b/Documentation/usb/gadget_configfs.rst index e4566ffb223f..868e118a2644 100644 --- a/Documentation/usb/gadget_configfs.rst +++ b/Documentation/usb/gadget_configfs.rst @@ -90,6 +90,16 @@ Then the strings can be specified:: $ echo > strings/0x409/manufacturer $ echo > strings/0x409/product +Further custom string descriptors can be created as directories within the +language's directory, with the string text being written to the "s" attribute +within the string's directory: + + $ mkdir strings/0x409/xu.0 + $ echo > strings/0x409/xu.0/s + +Where function drivers support it, functions may allow symlinks to these custom +string descriptors to associate those strings with class descriptors. + 2. Creating the configurations ------------------------------ diff --git a/drivers/usb/gadget/configfs.c b/drivers/usb/gadget/configfs.c index 3beeafcf2e3b..ac275855eeb6 100644 --- a/drivers/usb/gadget/configfs.c +++ b/drivers/usb/gadget/configfs.c @@ -95,6 +95,8 @@ struct gadget_language { struct config_group group; struct list_head list; + struct list_head gadget_strings; + unsigned int nstrings; }; struct gadget_config_name { @@ -791,8 +793,174 @@ static void gadget_language_attr_release(struct config_item *item) kfree(gs); } -USB_CONFIG_STRING_RW_OPS(gadget_language); -USB_CONFIG_STRINGS_LANG(gadget_language, gadget_info); +static struct configfs_item_operations gadget_language_langid_item_ops = { + .release = gadget_language_attr_release, +}; + +static ssize_t gadget_string_id_show(struct config_item *item, char *page) +{ + struct gadget_string *string = to_gadget_string(item); + int ret; + + ret = sprintf(page, "%u\n", string->usb_string.id); + return ret; +} +CONFIGFS_ATTR_RO(gadget_string_, id); + +static ssize_t gadget_string_s_show(struct config_item *item, char *page) +{ + struct gadget_string *string = to_gadget_string(item); + int ret; + + ret = snprintf(page, sizeof(string->string), "%s\n", string->string); + return ret; +} + +static ssize_t gadget_string_s_store(struct config_item *item, const char *page, + size_t len) +{ + struct gadget_string *string = to_gadget_string(item); + int size = min(sizeof(string->string), len + 1); + int ret; + + if (len > USB_MAX_STRING_LEN) + return -EINVAL; + + ret = strscpy(string->string, page, size); + return len; +} +CONFIGFS_ATTR(gadget_string_, s); + +static struct configfs_attribute *gadget_string_attrs[] = { + &gadget_string_attr_id, + &gadget_string_attr_s, + NULL, +}; + +static void gadget_string_release(struct config_item *item) +{ + struct gadget_string *string = to_gadget_string(item); + + kfree(string); +} + +static struct configfs_item_operations gadget_string_item_ops = { + .release = gadget_string_release, +}; + +static const struct config_item_type gadget_string_type = { + .ct_item_ops = &gadget_string_item_ops, + .ct_attrs = gadget_string_attrs, + .ct_owner = THIS_MODULE, +}; + +static struct config_item *gadget_language_string_make(struct config_group *group, + const char *name) +{ + struct gadget_language *language; + struct gadget_string *string; + + language = to_gadget_language(&group->cg_item); + + string = kzalloc(sizeof(*string), GFP_KERNEL); + if (!string) + return ERR_PTR(-ENOMEM); + + string->usb_string.id = language->nstrings++; + string->usb_string.s = string->string; + list_add_tail(&string->list, &language->gadget_strings); + + config_item_init_type_name(&string->item, name, &gadget_string_type); + + return &string->item; +} + +static void gadget_language_string_drop(struct config_group *group, + struct config_item *item) +{ + struct gadget_language *language; + struct gadget_string *string; + unsigned int i = USB_GADGET_FIRST_AVAIL_IDX; + + language = to_gadget_language(&group->cg_item); + string = to_gadget_string(item); + + list_del(&string->list); + language->nstrings--; + + /* Reset the ids for the language's strings to guarantee a continuous set */ + list_for_each_entry(string, &language->gadget_strings, list) + string->usb_string.id = i++; +} + +static struct configfs_group_operations gadget_language_langid_group_ops = { + .make_item = gadget_language_string_make, + .drop_item = gadget_language_string_drop, +}; + +static struct config_item_type gadget_language_type = { + .ct_item_ops = &gadget_language_langid_item_ops, + .ct_group_ops = &gadget_language_langid_group_ops, + .ct_attrs = gadget_language_langid_attrs, + .ct_owner = THIS_MODULE, +}; + +static struct config_group *gadget_language_make(struct config_group *group, + const char *name) +{ + struct gadget_info *gi; + struct gadget_language *gs; + struct gadget_language *new; + int langs = 0; + int ret; + + new = kzalloc(sizeof(*new), GFP_KERNEL); + if (!new) + return ERR_PTR(-ENOMEM); + + ret = check_user_usb_string(name, &new->stringtab_dev); + if (ret) + goto err; + config_group_init_type_name(&new->group, name, + &gadget_language_type); + + gi = container_of(group, struct gadget_info, strings_group); + ret = -EEXIST; + list_for_each_entry(gs, &gi->string_list, list) { + if (gs->stringtab_dev.language == new->stringtab_dev.language) + goto err; + langs++; + } + ret = -EOVERFLOW; + if (langs >= MAX_USB_STRING_LANGS) + goto err; + + list_add_tail(&new->list, &gi->string_list); + INIT_LIST_HEAD(&new->gadget_strings); + + /* We have the default manufacturer, product and serialnumber strings */ + new->nstrings = 3; + return &new->group; +err: + kfree(new); + return ERR_PTR(ret); +} + +static void gadget_language_drop(struct config_group *group, + struct config_item *item) +{ + config_item_put(item); +} + +static struct configfs_group_operations gadget_language_group_ops = { + .make_group = &gadget_language_make, + .drop_item = &gadget_language_drop, +}; + +static struct config_item_type gadget_language_strings_type = { + .ct_group_ops = &gadget_language_group_ops, + .ct_owner = THIS_MODULE, +}; static inline struct gadget_info *webusb_item_to_gadget_info( struct config_item *item) diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index dc3092cea99e..00750f7020f3 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -15,6 +15,7 @@ #ifndef __LINUX_USB_GADGET_H #define __LINUX_USB_GADGET_H +#include #include #include #include @@ -821,6 +822,16 @@ int usb_gadget_get_string(const struct usb_gadget_strings *table, int id, u8 *bu /* check if the given language identifier is valid */ bool usb_validate_langid(u16 langid); +struct gadget_string { + struct config_item item; + struct list_head list; + char string[USB_MAX_STRING_LEN]; + struct usb_string usb_string; +}; + +#define to_gadget_string(str_item)\ +container_of(str_item, struct gadget_string, item) + /*-------------------------------------------------------------------------*/ /* utility to simplify managing config descriptors */ -- cgit v1.2.3 From c033563220e0f7a82f4ae8d698284cced94fd6cf Mon Sep 17 00:00:00 2001 From: Daniel Scally Date: Mon, 6 Feb 2023 16:17:58 +0000 Subject: usb: gadget: configfs: Attach arbitrary strings to cdev Attach any arbitrary strings that are defined to the composite dev. We handle the old-style manufacturer, product and serialnumbers strings in the same function for simplicity. Signed-off-by: Daniel Scally Link: https://lore.kernel.org/r/20230206161802.892954-8-dan.scally@ideasonboard.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/configfs.c | 93 +++++++++++++++++++++++++++++++++++-------- include/linux/usb/composite.h | 1 + 2 files changed, 78 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/drivers/usb/gadget/configfs.c b/drivers/usb/gadget/configfs.c index ac275855eeb6..06a0b73e0546 100644 --- a/drivers/usb/gadget/configfs.c +++ b/drivers/usb/gadget/configfs.c @@ -1597,6 +1597,80 @@ static void purge_configs_funcs(struct gadget_info *gi) } } +static struct usb_string * +configfs_attach_gadget_strings(struct gadget_info *gi) +{ + struct usb_gadget_strings **gadget_strings; + struct gadget_language *language; + struct gadget_string *string; + unsigned int nlangs = 0; + struct list_head *iter; + struct usb_string *us; + unsigned int i = 0; + int nstrings = -1; + unsigned int j; + + list_for_each(iter, &gi->string_list) + nlangs++; + + /* Bail out early if no languages are configured */ + if (!nlangs) + return NULL; + + gadget_strings = kcalloc(nlangs + 1, /* including NULL terminator */ + sizeof(struct usb_gadget_strings *), GFP_KERNEL); + if (!gadget_strings) + return ERR_PTR(-ENOMEM); + + list_for_each_entry(language, &gi->string_list, list) { + struct usb_string *stringtab; + + if (nstrings == -1) { + nstrings = language->nstrings; + } else if (nstrings != language->nstrings) { + pr_err("languages must contain the same number of strings\n"); + us = ERR_PTR(-EINVAL); + goto cleanup; + } + + stringtab = kcalloc(language->nstrings + 1, sizeof(struct usb_string), + GFP_KERNEL); + if (!stringtab) { + us = ERR_PTR(-ENOMEM); + goto cleanup; + } + + stringtab[USB_GADGET_MANUFACTURER_IDX].id = USB_GADGET_MANUFACTURER_IDX; + stringtab[USB_GADGET_MANUFACTURER_IDX].s = language->manufacturer; + stringtab[USB_GADGET_PRODUCT_IDX].id = USB_GADGET_PRODUCT_IDX; + stringtab[USB_GADGET_PRODUCT_IDX].s = language->product; + stringtab[USB_GADGET_SERIAL_IDX].id = USB_GADGET_SERIAL_IDX; + stringtab[USB_GADGET_SERIAL_IDX].s = language->serialnumber; + + j = USB_GADGET_FIRST_AVAIL_IDX; + list_for_each_entry(string, &language->gadget_strings, list) { + memcpy(&stringtab[j], &string->usb_string, sizeof(struct usb_string)); + j++; + } + + language->stringtab_dev.strings = stringtab; + gadget_strings[i] = &language->stringtab_dev; + i++; + } + + us = usb_gstrings_attach(&gi->cdev, gadget_strings, nstrings); + +cleanup: + list_for_each_entry(language, &gi->string_list, list) { + kfree(language->stringtab_dev.strings); + language->stringtab_dev.strings = NULL; + } + + kfree(gadget_strings); + + return us; +} + static int configfs_composite_bind(struct usb_gadget *gadget, struct usb_gadget_driver *gdriver) { @@ -1640,22 +1714,7 @@ static int configfs_composite_bind(struct usb_gadget *gadget, /* init all strings */ if (!list_empty(&gi->string_list)) { - struct gadget_language *gs; - - i = 0; - list_for_each_entry(gs, &gi->string_list, list) { - - gi->gstrings[i] = &gs->stringtab_dev; - gs->stringtab_dev.strings = gs->strings; - gs->strings[USB_GADGET_MANUFACTURER_IDX].s = - gs->manufacturer; - gs->strings[USB_GADGET_PRODUCT_IDX].s = gs->product; - gs->strings[USB_GADGET_SERIAL_IDX].s = gs->serialnumber; - i++; - } - gi->gstrings[i] = NULL; - s = usb_gstrings_attach(&gi->cdev, gi->gstrings, - USB_GADGET_FIRST_AVAIL_IDX); + s = configfs_attach_gadget_strings(gi); if (IS_ERR(s)) { ret = PTR_ERR(s); goto err_comp_cleanup; @@ -1664,6 +1723,8 @@ static int configfs_composite_bind(struct usb_gadget *gadget, gi->cdev.desc.iManufacturer = s[USB_GADGET_MANUFACTURER_IDX].id; gi->cdev.desc.iProduct = s[USB_GADGET_PRODUCT_IDX].id; gi->cdev.desc.iSerialNumber = s[USB_GADGET_SERIAL_IDX].id; + + gi->cdev.usb_strings = s; } if (gi->use_webusb) { diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h index 7ef8cea67f50..608dc962748b 100644 --- a/include/linux/usb/composite.h +++ b/include/linux/usb/composite.h @@ -494,6 +494,7 @@ struct usb_composite_dev { struct usb_composite_driver *driver; u8 next_string_id; char *def_manufacturer; + struct usb_string *usb_strings; /* the gadget driver won't enable the data pullup * while the deactivation count is nonzero. -- cgit v1.2.3 From 585e351ff359c032ea7ab48d999b252ba09f8051 Mon Sep 17 00:00:00 2001 From: Atish Patra Date: Sat, 4 Feb 2023 17:15:02 -0800 Subject: perf: RISC-V: Define helper functions expose hpm counter width and count KVM module needs to know how many hardware counters and the counter width that the platform supports. Otherwise, it will not be able to show optimal value of virtual counters to the guest. The virtual hardware counters also need to have the same width as the logical hardware counters for simplicity. However, there shouldn't be mapping between virtual hardware counters and logical hardware counters. As we don't support hetergeneous harts or counters with different width as of now, the implementation relies on the counter width of the first available programmable counter. Reviewed-by: Anup Patel Reviewed-by: Andrew Jones Signed-off-by: Atish Patra Signed-off-by: Anup Patel --- drivers/perf/riscv_pmu_sbi.c | 37 +++++++++++++++++++++++++++++++++++-- include/linux/perf/riscv_pmu.h | 3 +++ 2 files changed, 38 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c index f6507efe2a58..6b53adc81f47 100644 --- a/drivers/perf/riscv_pmu_sbi.c +++ b/drivers/perf/riscv_pmu_sbi.c @@ -44,7 +44,7 @@ static const struct attribute_group *riscv_pmu_attr_groups[] = { }; /* - * RISC-V doesn't have hetergenous harts yet. This need to be part of + * RISC-V doesn't have heterogeneous harts yet. This need to be part of * per_cpu in case of harts with different pmu counters */ static union sbi_pmu_ctr_info *pmu_ctr_list; @@ -52,6 +52,9 @@ static bool riscv_pmu_use_irq; static unsigned int riscv_pmu_irq_num; static unsigned int riscv_pmu_irq; +/* Cache the available counters in a bitmask */ +static unsigned long cmask; + struct sbi_pmu_event_data { union { union { @@ -267,6 +270,37 @@ static bool pmu_sbi_ctr_is_fw(int cidx) return (info->type == SBI_PMU_CTR_TYPE_FW) ? true : false; } +/* + * Returns the counter width of a programmable counter and number of hardware + * counters. As we don't support heterogeneous CPUs yet, it is okay to just + * return the counter width of the first programmable counter. + */ +int riscv_pmu_get_hpm_info(u32 *hw_ctr_width, u32 *num_hw_ctr) +{ + int i; + union sbi_pmu_ctr_info *info; + u32 hpm_width = 0, hpm_count = 0; + + if (!cmask) + return -EINVAL; + + for_each_set_bit(i, &cmask, RISCV_MAX_COUNTERS) { + info = &pmu_ctr_list[i]; + if (!info) + continue; + if (!hpm_width && info->csr != CSR_CYCLE && info->csr != CSR_INSTRET) + hpm_width = info->width; + if (info->type == SBI_PMU_CTR_TYPE_HW) + hpm_count++; + } + + *hw_ctr_width = hpm_width; + *num_hw_ctr = hpm_count; + + return 0; +} +EXPORT_SYMBOL_GPL(riscv_pmu_get_hpm_info); + static int pmu_sbi_ctr_get_idx(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; @@ -812,7 +846,6 @@ static void riscv_pmu_destroy(struct riscv_pmu *pmu) static int pmu_sbi_device_probe(struct platform_device *pdev) { struct riscv_pmu *pmu = NULL; - unsigned long cmask = 0; int ret = -ENODEV; int num_counters; diff --git a/include/linux/perf/riscv_pmu.h b/include/linux/perf/riscv_pmu.h index e17e86ad6f3a..a1c3f7771481 100644 --- a/include/linux/perf/riscv_pmu.h +++ b/include/linux/perf/riscv_pmu.h @@ -73,6 +73,9 @@ void riscv_pmu_legacy_skip_init(void); static inline void riscv_pmu_legacy_skip_init(void) {}; #endif struct riscv_pmu *riscv_pmu_alloc(void); +#ifdef CONFIG_RISCV_PMU_SBI +int riscv_pmu_get_hpm_info(u32 *hw_ctr_width, u32 *num_hw_ctr); +#endif #endif /* CONFIG_RISCV_PMU */ -- cgit v1.2.3 From 8929283a687bb4b71ec9d3f1e827aecf829c6b1a Mon Sep 17 00:00:00 2001 From: Atish Patra Date: Sat, 4 Feb 2023 17:15:03 -0800 Subject: perf: RISC-V: Improve privilege mode filtering for perf Currently, the host driver doesn't have any method to identify if the requested perf event is from kvm or bare metal. As KVM runs in HS mode, there are no separate hypervisor privilege mode to distinguish between the attributes for guest/host. Improve the privilege mode filtering by using the event specific config1 field. Reviewed-by: Andrew Jones Reviewed-by: Anup Patel Signed-off-by: Atish Patra Signed-off-by: Anup Patel --- drivers/perf/riscv_pmu_sbi.c | 27 ++++++++++++++++++++++----- include/linux/perf/riscv_pmu.h | 2 ++ 2 files changed, 24 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c index 6b53adc81f47..71174fa593f4 100644 --- a/drivers/perf/riscv_pmu_sbi.c +++ b/drivers/perf/riscv_pmu_sbi.c @@ -301,6 +301,27 @@ int riscv_pmu_get_hpm_info(u32 *hw_ctr_width, u32 *num_hw_ctr) } EXPORT_SYMBOL_GPL(riscv_pmu_get_hpm_info); +static unsigned long pmu_sbi_get_filter_flags(struct perf_event *event) +{ + unsigned long cflags = 0; + bool guest_events = false; + + if (event->attr.config1 & RISCV_PMU_CONFIG1_GUEST_EVENTS) + guest_events = true; + if (event->attr.exclude_kernel) + cflags |= guest_events ? SBI_PMU_CFG_FLAG_SET_VSINH : SBI_PMU_CFG_FLAG_SET_SINH; + if (event->attr.exclude_user) + cflags |= guest_events ? SBI_PMU_CFG_FLAG_SET_VUINH : SBI_PMU_CFG_FLAG_SET_UINH; + if (guest_events && event->attr.exclude_hv) + cflags |= SBI_PMU_CFG_FLAG_SET_SINH; + if (event->attr.exclude_host) + cflags |= SBI_PMU_CFG_FLAG_SET_UINH | SBI_PMU_CFG_FLAG_SET_SINH; + if (event->attr.exclude_guest) + cflags |= SBI_PMU_CFG_FLAG_SET_VSINH | SBI_PMU_CFG_FLAG_SET_VUINH; + + return cflags; +} + static int pmu_sbi_ctr_get_idx(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; @@ -311,11 +332,7 @@ static int pmu_sbi_ctr_get_idx(struct perf_event *event) uint64_t cbase = 0; unsigned long cflags = 0; - if (event->attr.exclude_kernel) - cflags |= SBI_PMU_CFG_FLAG_SET_SINH; - if (event->attr.exclude_user) - cflags |= SBI_PMU_CFG_FLAG_SET_UINH; - + cflags = pmu_sbi_get_filter_flags(event); /* retrieve the available counter index */ #if defined(CONFIG_32BIT) ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_CFG_MATCH, cbase, diff --git a/include/linux/perf/riscv_pmu.h b/include/linux/perf/riscv_pmu.h index a1c3f7771481..43fc892aa7d9 100644 --- a/include/linux/perf/riscv_pmu.h +++ b/include/linux/perf/riscv_pmu.h @@ -26,6 +26,8 @@ #define RISCV_PMU_STOP_FLAG_RESET 1 +#define RISCV_PMU_CONFIG1_GUEST_EVENTS 0x1 + struct cpu_hw_events { /* currently enabled events */ int n_events; -- cgit v1.2.3 From a9c4bdd505630469f93f5efedfc7a9ca254996c8 Mon Sep 17 00:00:00 2001 From: Linyu Yuan Date: Mon, 30 Jan 2023 15:54:09 +0800 Subject: tracing: Acquire buffer from temparary trace sequence there is one dwc3 trace event declare as below, DECLARE_EVENT_CLASS(dwc3_log_event, TP_PROTO(u32 event, struct dwc3 *dwc), TP_ARGS(event, dwc), TP_STRUCT__entry( __field(u32, event) __field(u32, ep0state) __dynamic_array(char, str, DWC3_MSG_MAX) ), TP_fast_assign( __entry->event = event; __entry->ep0state = dwc->ep0state; ), TP_printk("event (%08x): %s", __entry->event, dwc3_decode_event(__get_str(str), DWC3_MSG_MAX, __entry->event, __entry->ep0state)) ); the problem is when trace function called, it will allocate up to DWC3_MSG_MAX bytes from trace event buffer, but never fill the buffer during fast assignment, it only fill the buffer when output function are called, so this means if output function are not called, the buffer will never used. add __get_buf(len) which acquiree buffer from iter->tmp_seq when trace output function called, it allow user write string to acquired buffer. the mentioned dwc3 trace event will changed as below, DECLARE_EVENT_CLASS(dwc3_log_event, TP_PROTO(u32 event, struct dwc3 *dwc), TP_ARGS(event, dwc), TP_STRUCT__entry( __field(u32, event) __field(u32, ep0state) ), TP_fast_assign( __entry->event = event; __entry->ep0state = dwc->ep0state; ), TP_printk("event (%08x): %s", __entry->event, dwc3_decode_event(__get_buf(DWC3_MSG_MAX), DWC3_MSG_MAX, __entry->event, __entry->ep0state)) );. Link: https://lore.kernel.org/linux-trace-kernel/1675065249-23368-1-git-send-email-quic_linyyuan@quicinc.com Cc: Masami Hiramatsu Signed-off-by: Linyu Yuan Signed-off-by: Steven Rostedt (Google) --- include/linux/trace_seq.h | 5 +++++ include/trace/stages/stage3_trace_output.h | 3 +++ include/trace/stages/stage7_class_define.h | 1 + kernel/trace/trace_seq.c | 23 +++++++++++++++++++++++ 4 files changed, 32 insertions(+) (limited to 'include/linux') diff --git a/include/linux/trace_seq.h b/include/linux/trace_seq.h index 0c4c7587d6c3..6be92bf559fe 100644 --- a/include/linux/trace_seq.h +++ b/include/linux/trace_seq.h @@ -95,6 +95,7 @@ extern void trace_seq_bitmask(struct trace_seq *s, const unsigned long *maskp, extern int trace_seq_hex_dump(struct trace_seq *s, const char *prefix_str, int prefix_type, int rowsize, int groupsize, const void *buf, size_t len, bool ascii); +char *trace_seq_acquire(struct trace_seq *s, unsigned int len); #else /* CONFIG_TRACING */ static inline __printf(2, 3) @@ -139,6 +140,10 @@ static inline int trace_seq_path(struct trace_seq *s, const struct path *path) { return 0; } +static inline char *trace_seq_acquire(struct trace_seq *s, unsigned int len) +{ + return NULL; +} #endif /* CONFIG_TRACING */ #endif /* _LINUX_TRACE_SEQ_H */ diff --git a/include/trace/stages/stage3_trace_output.h b/include/trace/stages/stage3_trace_output.h index 66374df61ed3..c1fb1355d309 100644 --- a/include/trace/stages/stage3_trace_output.h +++ b/include/trace/stages/stage3_trace_output.h @@ -139,3 +139,6 @@ u64 ____val = (u64)(value); \ (u32) do_div(____val, NSEC_PER_SEC); \ }) + +#undef __get_buf +#define __get_buf(len) trace_seq_acquire(p, (len)) diff --git a/include/trace/stages/stage7_class_define.h b/include/trace/stages/stage7_class_define.h index 8795429f388b..bcb960d16fc0 100644 --- a/include/trace/stages/stage7_class_define.h +++ b/include/trace/stages/stage7_class_define.h @@ -23,6 +23,7 @@ #undef __get_rel_sockaddr #undef __print_array #undef __print_hex_dump +#undef __get_buf /* * The below is not executed in the kernel. It is only what is diff --git a/kernel/trace/trace_seq.c b/kernel/trace/trace_seq.c index 9c90b3a7dce2..e5e299260d0c 100644 --- a/kernel/trace/trace_seq.c +++ b/kernel/trace/trace_seq.c @@ -403,3 +403,26 @@ int trace_seq_hex_dump(struct trace_seq *s, const char *prefix_str, return 1; } EXPORT_SYMBOL(trace_seq_hex_dump); + +/* + * trace_seq_acquire - acquire seq buffer with size len + * @s: trace sequence descriptor + * @len: size of buffer to be acquired + * + * acquire buffer with size of @len from trace_seq for output usage, + * user can fill string into that buffer. + * + * Returns start address of acquired buffer. + * + * it allow multiple usage in one trace output function call. + */ +char *trace_seq_acquire(struct trace_seq *s, unsigned int len) +{ + char *ret = trace_seq_buffer_ptr(s); + + if (!WARN_ON_ONCE(seq_buf_buffer_left(&s->seq) < len)) + seq_buf_commit(&s->seq, len); + + return ret; +} +EXPORT_SYMBOL(trace_seq_acquire); -- cgit v1.2.3 From d503b8f7474fe7ac616518f7fc49773cbab49f36 Mon Sep 17 00:00:00 2001 From: Steven Rostedt (Google) Date: Tue, 7 Feb 2023 12:28:52 -0500 Subject: tracing: Add trace_array_puts() to write into instance Add a generic trace_array_puts() that can be used to "trace_puts()" into an allocated trace_array instance. This is just another variant of trace_array_printk(). Link: https://lkml.kernel.org/r/20230207173026.584717290@goodmis.org Cc: Masami Hiramatsu Cc: Andrew Morton Reviewed-by: Ross Zwisler Signed-off-by: Steven Rostedt (Google) --- include/linux/trace.h | 12 ++++++++++++ kernel/trace/trace.c | 27 +++++++++++++++++---------- 2 files changed, 29 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/trace.h b/include/linux/trace.h index 80ffda871749..2a70a447184c 100644 --- a/include/linux/trace.h +++ b/include/linux/trace.h @@ -33,6 +33,18 @@ struct trace_array; int register_ftrace_export(struct trace_export *export); int unregister_ftrace_export(struct trace_export *export); +/** + * trace_array_puts - write a constant string into the trace buffer. + * @tr: The trace array to write to + * @str: The constant string to write + */ +#define trace_array_puts(tr, str) \ + ({ \ + str ? __trace_array_puts(tr, _THIS_IP_, str, strlen(str)) : -1; \ + }) +int __trace_array_puts(struct trace_array *tr, unsigned long ip, + const char *str, int size); + void trace_printk_init_buffers(void); __printf(3, 4) int trace_array_printk(struct trace_array *tr, unsigned long ip, diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 5b16af9e7d30..9918bf7441ed 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1023,13 +1023,8 @@ __buffer_unlock_commit(struct trace_buffer *buffer, struct ring_buffer_event *ev ring_buffer_unlock_commit(buffer); } -/** - * __trace_puts - write a constant string into the trace buffer. - * @ip: The address of the caller - * @str: The constant string to write - * @size: The size of the string. - */ -int __trace_puts(unsigned long ip, const char *str, int size) +int __trace_array_puts(struct trace_array *tr, unsigned long ip, + const char *str, int size) { struct ring_buffer_event *event; struct trace_buffer *buffer; @@ -1037,7 +1032,7 @@ int __trace_puts(unsigned long ip, const char *str, int size) unsigned int trace_ctx; int alloc; - if (!(global_trace.trace_flags & TRACE_ITER_PRINTK)) + if (!(tr->trace_flags & TRACE_ITER_PRINTK)) return 0; if (unlikely(tracing_selftest_running || tracing_disabled)) @@ -1046,7 +1041,7 @@ int __trace_puts(unsigned long ip, const char *str, int size) alloc = sizeof(*entry) + size + 2; /* possible \n added */ trace_ctx = tracing_gen_ctx(); - buffer = global_trace.array_buffer.buffer; + buffer = tr->array_buffer.buffer; ring_buffer_nest_start(buffer); event = __trace_buffer_lock_reserve(buffer, TRACE_PRINT, alloc, trace_ctx); @@ -1068,11 +1063,23 @@ int __trace_puts(unsigned long ip, const char *str, int size) entry->buf[size] = '\0'; __buffer_unlock_commit(buffer, event); - ftrace_trace_stack(&global_trace, buffer, trace_ctx, 4, NULL); + ftrace_trace_stack(tr, buffer, trace_ctx, 4, NULL); out: ring_buffer_nest_end(buffer); return size; } +EXPORT_SYMBOL_GPL(__trace_array_puts); + +/** + * __trace_puts - write a constant string into the trace buffer. + * @ip: The address of the caller + * @str: The constant string to write + * @size: The size of the string. + */ +int __trace_puts(unsigned long ip, const char *str, int size) +{ + return __trace_array_puts(&global_trace, ip, str, size); +} EXPORT_SYMBOL_GPL(__trace_puts); /** -- cgit v1.2.3 From 5bad5d55d884d57acba92a3309cde4cbb26dfefc Mon Sep 17 00:00:00 2001 From: Wang Yong Date: Thu, 2 Feb 2023 08:13:42 +0000 Subject: KVM: update code comment in struct kvm_vcpu Commit c5b077549136 ("KVM: Convert the kvm->vcpus array to a xarray") changed kvm->vcpus array to a xarray, so update the code comment of kvm_vcpu->vcpu_idx accordingly. Signed-off-by: Wang Yong Link: https://lore.kernel.org/r/20230202081342.856687-1-yongw.kernel@gmail.com Signed-off-by: Sean Christopherson --- include/linux/kvm_host.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index a7d6a6111f5e..8ada23756b0e 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -324,7 +324,7 @@ struct kvm_vcpu { #endif int cpu; int vcpu_id; /* id given by userspace at creation */ - int vcpu_idx; /* index in kvm->vcpus array */ + int vcpu_idx; /* index into kvm->vcpu_array */ int ____srcu_idx; /* Don't use this directly. You've been warned. */ #ifdef CONFIG_PROVE_RCU int srcu_depth; -- cgit v1.2.3 From 67cad5c67019c38126b749621665b6723d3ae7e6 Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Mon, 6 Feb 2023 17:41:57 -0800 Subject: driver core: fw_devlink: Add DL_FLAG_CYCLE support to device links fw_devlink uses DL_FLAG_SYNC_STATE_ONLY device link flag for two purposes: 1. To allow a parent device to proxy its child device's dependency on a supplier so that the supplier doesn't get its sync_state() callback before the child device/consumer can be added and probed. In this usage scenario, we need to ignore cycles for ensure correctness of sync_state() callbacks. 2. When there are dependency cycles in firmware, we don't know which of those dependencies are valid. So, we have to ignore them all wrt probe ordering while still making sure the sync_state() callbacks come correctly. However, when detecting dependency cycles, there can be multiple dependency cycles between two devices that we need to detect. For example: A -> B -> A and A -> C -> B -> A. To detect multiple cycles correct, we need to be able to differentiate DL_FLAG_SYNC_STATE_ONLY device links used for (1) vs (2) above. To allow this differentiation, add a DL_FLAG_CYCLE that can be use to mark use case (2). We can then use the DL_FLAG_CYCLE to decide which DL_FLAG_SYNC_STATE_ONLY device links to follow when looking for dependency cycles. Fixes: 2de9d8e0d2fe ("driver core: fw_devlink: Improve handling of cyclic dependencies") Signed-off-by: Saravana Kannan Tested-by: Colin Foster Tested-by: Sudeep Holla Tested-by: Douglas Anderson Tested-by: Geert Uytterhoeven Tested-by: Luca Weiss # qcom/sm7225-fairphone-fp4 Link: https://lore.kernel.org/r/20230207014207.1678715-6-saravanak@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/base/core.c | 28 ++++++++++++++++++---------- include/linux/device.h | 1 + 2 files changed, 19 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/core.c b/drivers/base/core.c index 3daaa7ffe751..ac19752422e0 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -322,6 +322,12 @@ static bool device_is_ancestor(struct device *dev, struct device *target) return false; } +static inline bool device_link_flag_is_sync_state_only(u32 flags) +{ + return (flags & ~(DL_FLAG_INFERRED | DL_FLAG_CYCLE)) == + (DL_FLAG_SYNC_STATE_ONLY | DL_FLAG_MANAGED); +} + /** * device_is_dependent - Check if one device depends on another one * @dev: Device to check dependencies for. @@ -348,8 +354,7 @@ int device_is_dependent(struct device *dev, void *target) return ret; list_for_each_entry(link, &dev->links.consumers, s_node) { - if ((link->flags & ~DL_FLAG_INFERRED) == - (DL_FLAG_SYNC_STATE_ONLY | DL_FLAG_MANAGED)) + if (device_link_flag_is_sync_state_only(link->flags)) continue; if (link->consumer == target) @@ -422,8 +427,7 @@ static int device_reorder_to_tail(struct device *dev, void *not_used) device_for_each_child(dev, NULL, device_reorder_to_tail); list_for_each_entry(link, &dev->links.consumers, s_node) { - if ((link->flags & ~DL_FLAG_INFERRED) == - (DL_FLAG_SYNC_STATE_ONLY | DL_FLAG_MANAGED)) + if (device_link_flag_is_sync_state_only(link->flags)) continue; device_reorder_to_tail(link->consumer, NULL); } @@ -684,7 +688,8 @@ postcore_initcall(devlink_class_init); DL_FLAG_AUTOREMOVE_SUPPLIER | \ DL_FLAG_AUTOPROBE_CONSUMER | \ DL_FLAG_SYNC_STATE_ONLY | \ - DL_FLAG_INFERRED) + DL_FLAG_INFERRED | \ + DL_FLAG_CYCLE) #define DL_ADD_VALID_FLAGS (DL_MANAGED_LINK_FLAGS | DL_FLAG_STATELESS | \ DL_FLAG_PM_RUNTIME | DL_FLAG_RPM_ACTIVE) @@ -753,8 +758,6 @@ struct device_link *device_link_add(struct device *consumer, if (!consumer || !supplier || consumer == supplier || flags & ~DL_ADD_VALID_FLAGS || (flags & DL_FLAG_STATELESS && flags & DL_MANAGED_LINK_FLAGS) || - (flags & DL_FLAG_SYNC_STATE_ONLY && - (flags & ~DL_FLAG_INFERRED) != DL_FLAG_SYNC_STATE_ONLY) || (flags & DL_FLAG_AUTOPROBE_CONSUMER && flags & (DL_FLAG_AUTOREMOVE_CONSUMER | DL_FLAG_AUTOREMOVE_SUPPLIER))) @@ -770,6 +773,10 @@ struct device_link *device_link_add(struct device *consumer, if (!(flags & DL_FLAG_STATELESS)) flags |= DL_FLAG_MANAGED; + if (flags & DL_FLAG_SYNC_STATE_ONLY && + !device_link_flag_is_sync_state_only(flags)) + return NULL; + device_links_write_lock(); device_pm_lock(); @@ -1729,7 +1736,7 @@ static void fw_devlink_relax_link(struct device_link *link) if (!(link->flags & DL_FLAG_INFERRED)) return; - if (link->flags == (DL_FLAG_MANAGED | FW_DEVLINK_FLAGS_PERMISSIVE)) + if (device_link_flag_is_sync_state_only(link->flags)) return; pm_runtime_drop_link(link); @@ -1853,8 +1860,8 @@ static int fw_devlink_relax_cycle(struct device *con, void *sup) return ret; list_for_each_entry(link, &con->links.consumers, s_node) { - if ((link->flags & ~DL_FLAG_INFERRED) == - (DL_FLAG_SYNC_STATE_ONLY | DL_FLAG_MANAGED)) + if (!(link->flags & DL_FLAG_CYCLE) && + device_link_flag_is_sync_state_only(link->flags)) continue; if (!fw_devlink_relax_cycle(link->consumer, sup)) @@ -1863,6 +1870,7 @@ static int fw_devlink_relax_cycle(struct device *con, void *sup) ret = 1; fw_devlink_relax_link(link); + link->flags |= DL_FLAG_CYCLE; } return ret; } diff --git a/include/linux/device.h b/include/linux/device.h index 90aaf308c259..1508e637bb26 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -328,6 +328,7 @@ enum device_link_state { #define DL_FLAG_MANAGED BIT(6) #define DL_FLAG_SYNC_STATE_ONLY BIT(7) #define DL_FLAG_INFERRED BIT(8) +#define DL_FLAG_CYCLE BIT(9) /** * enum dl_dev_state - Device driver presence tracking information. -- cgit v1.2.3 From 6a6dfdf8b3ff337be5a447e9f4e71969f18370ad Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Mon, 6 Feb 2023 17:41:58 -0800 Subject: driver core: fw_devlink: Allow marking a fwnode link as being part of a cycle To improve detection and handling of dependency cycles, we need to be able to mark fwnode links as being part of cycles. fwnode links marked as being part of a cycle should not block their consumers from probing. Fixes: 2de9d8e0d2fe ("driver core: fw_devlink: Improve handling of cyclic dependencies") Signed-off-by: Saravana Kannan Tested-by: Colin Foster Tested-by: Sudeep Holla Tested-by: Douglas Anderson Tested-by: Geert Uytterhoeven Tested-by: Luca Weiss # qcom/sm7225-fairphone-fp4 Link: https://lore.kernel.org/r/20230207014207.1678715-7-saravanak@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/base/core.c | 50 ++++++++++++++++++++++++++++++++++++++++---------- include/linux/fwnode.h | 11 ++++++++++- 2 files changed, 50 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/core.c b/drivers/base/core.c index ac19752422e0..6639f90cf301 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -76,13 +76,15 @@ static bool fw_devlink_best_effort; * are ignored and there is no reference counting. */ static int __fwnode_link_add(struct fwnode_handle *con, - struct fwnode_handle *sup) + struct fwnode_handle *sup, u8 flags) { struct fwnode_link *link; list_for_each_entry(link, &sup->consumers, s_hook) - if (link->consumer == con) + if (link->consumer == con) { + link->flags |= flags; return 0; + } link = kzalloc(sizeof(*link), GFP_KERNEL); if (!link) @@ -92,6 +94,7 @@ static int __fwnode_link_add(struct fwnode_handle *con, INIT_LIST_HEAD(&link->s_hook); link->consumer = con; INIT_LIST_HEAD(&link->c_hook); + link->flags = flags; list_add(&link->s_hook, &sup->consumers); list_add(&link->c_hook, &con->suppliers); @@ -106,7 +109,7 @@ int fwnode_link_add(struct fwnode_handle *con, struct fwnode_handle *sup) int ret; mutex_lock(&fwnode_link_lock); - ret = __fwnode_link_add(con, sup); + ret = __fwnode_link_add(con, sup, 0); mutex_unlock(&fwnode_link_lock); return ret; } @@ -126,6 +129,19 @@ static void __fwnode_link_del(struct fwnode_link *link) kfree(link); } +/** + * __fwnode_link_cycle - Mark a fwnode link as being part of a cycle. + * @link: the fwnode_link to be marked + * + * The fwnode_link_lock needs to be held when this function is called. + */ +static void __fwnode_link_cycle(struct fwnode_link *link) +{ + pr_debug("%pfwf: Relaxing link with %pfwf\n", + link->consumer, link->supplier); + link->flags |= FWLINK_FLAG_CYCLE; +} + /** * fwnode_links_purge_suppliers - Delete all supplier links of fwnode_handle. * @fwnode: fwnode whose supplier links need to be deleted @@ -199,7 +215,7 @@ static void __fwnode_links_move_consumers(struct fwnode_handle *from, struct fwnode_link *link, *tmp; list_for_each_entry_safe(link, tmp, &from->consumers, s_hook) { - __fwnode_link_add(link->consumer, to); + __fwnode_link_add(link->consumer, to, link->flags); __fwnode_link_del(link); } } @@ -1041,6 +1057,21 @@ static bool dev_is_best_effort(struct device *dev) (dev->fwnode && (dev->fwnode->flags & FWNODE_FLAG_BEST_EFFORT)); } +static struct fwnode_handle *fwnode_links_check_suppliers( + struct fwnode_handle *fwnode) +{ + struct fwnode_link *link; + + if (!fwnode || fw_devlink_is_permissive()) + return NULL; + + list_for_each_entry(link, &fwnode->suppliers, c_hook) + if (!(link->flags & FWLINK_FLAG_CYCLE)) + return link->supplier; + + return NULL; +} + /** * device_links_check_suppliers - Check presence of supplier drivers. * @dev: Consumer device. @@ -1068,11 +1099,8 @@ int device_links_check_suppliers(struct device *dev) * probe. */ mutex_lock(&fwnode_link_lock); - if (dev->fwnode && !list_empty(&dev->fwnode->suppliers) && - !fw_devlink_is_permissive()) { - sup_fw = list_first_entry(&dev->fwnode->suppliers, - struct fwnode_link, - c_hook)->supplier; + sup_fw = fwnode_links_check_suppliers(dev->fwnode); + if (sup_fw) { if (!dev_is_best_effort(dev)) { fwnode_ret = -EPROBE_DEFER; dev_err_probe(dev, -EPROBE_DEFER, @@ -1261,7 +1289,9 @@ static ssize_t waiting_for_supplier_show(struct device *dev, bool val; device_lock(dev); - val = !list_empty(&dev->fwnode->suppliers); + mutex_lock(&fwnode_link_lock); + val = !!fwnode_links_check_suppliers(dev->fwnode); + mutex_unlock(&fwnode_link_lock); device_unlock(dev); return sysfs_emit(buf, "%u\n", val); } diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h index 89b9bdfca925..fdf2ee0285b7 100644 --- a/include/linux/fwnode.h +++ b/include/linux/fwnode.h @@ -18,7 +18,7 @@ struct fwnode_operations; struct device; /* - * fwnode link flags + * fwnode flags * * LINKS_ADDED: The fwnode has already be parsed to add fwnode links. * NOT_DEVICE: The fwnode will never be populated as a struct device. @@ -36,6 +36,7 @@ struct device; #define FWNODE_FLAG_INITIALIZED BIT(2) #define FWNODE_FLAG_NEEDS_CHILD_BOUND_ON_ADD BIT(3) #define FWNODE_FLAG_BEST_EFFORT BIT(4) +#define FWNODE_FLAG_VISITED BIT(5) struct fwnode_handle { struct fwnode_handle *secondary; @@ -46,11 +47,19 @@ struct fwnode_handle { u8 flags; }; +/* + * fwnode link flags + * + * CYCLE: The fwnode link is part of a cycle. Don't defer probe. + */ +#define FWLINK_FLAG_CYCLE BIT(0) + struct fwnode_link { struct fwnode_handle *supplier; struct list_head s_hook; struct fwnode_handle *consumer; struct list_head c_hook; + u8 flags; }; /** -- cgit v1.2.3 From cd115c0409f283edde94bd5a9a42dc42bee0aba8 Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Mon, 6 Feb 2023 17:41:59 -0800 Subject: driver core: fw_devlink: Consolidate device link flag computation Consolidate the code that computes the flags to be used when creating a device link from a fwnode link. Fixes: 2de9d8e0d2fe ("driver core: fw_devlink: Improve handling of cyclic dependencies") Signed-off-by: Saravana Kannan Tested-by: Colin Foster Tested-by: Sudeep Holla Tested-by: Douglas Anderson Tested-by: Geert Uytterhoeven Tested-by: Luca Weiss # qcom/sm7225-fairphone-fp4 Link: https://lore.kernel.org/r/20230207014207.1678715-8-saravanak@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/base/core.c | 28 +++++++++++++++------------- include/linux/fwnode.h | 1 - 2 files changed, 15 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/core.c b/drivers/base/core.c index 6639f90cf301..0a8a5ab344c1 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -1727,8 +1727,11 @@ static int __init fw_devlink_strict_setup(char *arg) } early_param("fw_devlink.strict", fw_devlink_strict_setup); -u32 fw_devlink_get_flags(void) +static inline u32 fw_devlink_get_flags(u8 fwlink_flags) { + if (fwlink_flags & FWLINK_FLAG_CYCLE) + return FW_DEVLINK_FLAGS_PERMISSIVE | DL_FLAG_CYCLE; + return fw_devlink_flags; } @@ -1938,7 +1941,7 @@ static bool fwnode_ancestor_init_without_drv(struct fwnode_handle *fwnode) * fw_devlink_create_devlink - Create a device link from a consumer to fwnode * @con: consumer device for the device link * @sup_handle: fwnode handle of supplier - * @flags: devlink flags + * @link: fwnode link that's being converted to a device link * * This function will try to create a device link between the consumer device * @con and the supplier device represented by @sup_handle. @@ -1955,10 +1958,17 @@ static bool fwnode_ancestor_init_without_drv(struct fwnode_handle *fwnode) * possible to do that in the future */ static int fw_devlink_create_devlink(struct device *con, - struct fwnode_handle *sup_handle, u32 flags) + struct fwnode_handle *sup_handle, + struct fwnode_link *link) { struct device *sup_dev; int ret = 0; + u32 flags; + + if (con->fwnode == link->consumer) + flags = fw_devlink_get_flags(link->flags); + else + flags = FW_DEVLINK_FLAGS_PERMISSIVE; /* * In some cases, a device P might also be a supplier to its child node @@ -2091,7 +2101,6 @@ static void __fw_devlink_link_to_consumers(struct device *dev) struct fwnode_link *link, *tmp; list_for_each_entry_safe(link, tmp, &fwnode->consumers, s_hook) { - u32 dl_flags = fw_devlink_get_flags(); struct device *con_dev; bool own_link = true; int ret; @@ -2121,14 +2130,13 @@ static void __fw_devlink_link_to_consumers(struct device *dev) con_dev = NULL; } else { own_link = false; - dl_flags = FW_DEVLINK_FLAGS_PERMISSIVE; } } if (!con_dev) continue; - ret = fw_devlink_create_devlink(con_dev, fwnode, dl_flags); + ret = fw_devlink_create_devlink(con_dev, fwnode, link); put_device(con_dev); if (!own_link || ret == -EAGAIN) continue; @@ -2169,19 +2177,13 @@ static void __fw_devlink_link_to_suppliers(struct device *dev, bool own_link = (dev->fwnode == fwnode); struct fwnode_link *link, *tmp; struct fwnode_handle *child = NULL; - u32 dl_flags; - - if (own_link) - dl_flags = fw_devlink_get_flags(); - else - dl_flags = FW_DEVLINK_FLAGS_PERMISSIVE; list_for_each_entry_safe(link, tmp, &fwnode->suppliers, c_hook) { int ret; struct device *sup_dev; struct fwnode_handle *sup = link->supplier; - ret = fw_devlink_create_devlink(dev, sup, dl_flags); + ret = fw_devlink_create_devlink(dev, sup, link); if (!own_link || ret == -EAGAIN) continue; diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h index fdf2ee0285b7..5700451b300f 100644 --- a/include/linux/fwnode.h +++ b/include/linux/fwnode.h @@ -207,7 +207,6 @@ static inline void fwnode_dev_initialized(struct fwnode_handle *fwnode, fwnode->flags &= ~FWNODE_FLAG_INITIALIZED; } -extern u32 fw_devlink_get_flags(void); extern bool fw_devlink_is_strict(void); int fwnode_link_add(struct fwnode_handle *con, struct fwnode_handle *sup); void fwnode_links_purge(struct fwnode_handle *fwnode); -- cgit v1.2.3 From 3bf90eca76c98c55c975fa817799789b9176f9f3 Mon Sep 17 00:00:00 2001 From: Elliot Berman Date: Fri, 3 Feb 2023 13:09:52 -0800 Subject: firmware: qcom_scm: Move qcom_scm.h to include/linux/firmware/qcom/ Move include/linux/qcom_scm.h to include/linux/firmware/qcom/qcom_scm.h. This removes 1 of a few remaining Qualcomm-specific headers into a more approciate subdirectory under include/. Suggested-by: Bjorn Andersson Signed-off-by: Elliot Berman Reviewed-by: Guru Das Srinagesh Acked-by: Mukesh Ojha Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230203210956.3580811-1-quic_eberman@quicinc.com --- arch/arm/mach-qcom/platsmp.c | 2 +- drivers/cpuidle/cpuidle-qcom-spm.c | 2 +- drivers/firmware/qcom_scm-legacy.c | 2 +- drivers/firmware/qcom_scm-smc.c | 2 +- drivers/firmware/qcom_scm.c | 2 +- drivers/gpu/drm/msm/adreno/a5xx_gpu.c | 2 +- drivers/gpu/drm/msm/adreno/adreno_gpu.c | 2 +- drivers/gpu/drm/msm/hdmi/hdmi_hdcp.c | 2 +- drivers/iommu/arm/arm-smmu/arm-smmu-qcom-debug.c | 2 +- drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c | 2 +- drivers/iommu/arm/arm-smmu/qcom_iommu.c | 2 +- drivers/media/platform/qcom/venus/firmware.c | 2 +- drivers/misc/fastrpc.c | 2 +- drivers/mmc/host/sdhci-msm.c | 2 +- drivers/net/ipa/ipa_main.c | 2 +- drivers/net/wireless/ath/ath10k/qmi.c | 2 +- drivers/pinctrl/qcom/pinctrl-msm.c | 2 +- drivers/remoteproc/qcom_q6v5_mss.c | 2 +- drivers/remoteproc/qcom_q6v5_pas.c | 2 +- drivers/remoteproc/qcom_wcnss.c | 2 +- drivers/soc/qcom/mdt_loader.c | 2 +- drivers/soc/qcom/ocmem.c | 2 +- drivers/soc/qcom/rmtfs_mem.c | 2 +- drivers/thermal/qcom/lmh.c | 2 +- drivers/ufs/host/ufs-qcom-ice.c | 2 +- include/linux/firmware/qcom/qcom_scm.h | 125 +++++++++++++++++++++++ include/linux/qcom_scm.h | 125 ----------------------- 27 files changed, 150 insertions(+), 150 deletions(-) create mode 100644 include/linux/firmware/qcom/qcom_scm.h delete mode 100644 include/linux/qcom_scm.h (limited to 'include/linux') diff --git a/arch/arm/mach-qcom/platsmp.c b/arch/arm/mach-qcom/platsmp.c index 5d2f386a46d8..eca2fe0f4314 100644 --- a/arch/arm/mach-qcom/platsmp.c +++ b/arch/arm/mach-qcom/platsmp.c @@ -14,7 +14,7 @@ #include #include #include -#include +#include #include diff --git a/drivers/cpuidle/cpuidle-qcom-spm.c b/drivers/cpuidle/cpuidle-qcom-spm.c index beedf22cbe78..4ac83918edf2 100644 --- a/drivers/cpuidle/cpuidle-qcom-spm.c +++ b/drivers/cpuidle/cpuidle-qcom-spm.c @@ -17,7 +17,7 @@ #include #include #include -#include +#include #include #include diff --git a/drivers/firmware/qcom_scm-legacy.c b/drivers/firmware/qcom_scm-legacy.c index 9f918b9e6f8f..029e6d117cb8 100644 --- a/drivers/firmware/qcom_scm-legacy.c +++ b/drivers/firmware/qcom_scm-legacy.c @@ -9,7 +9,7 @@ #include #include #include -#include +#include #include #include diff --git a/drivers/firmware/qcom_scm-smc.c b/drivers/firmware/qcom_scm-smc.c index bb3235a64b8f..16cf88acfa8e 100644 --- a/drivers/firmware/qcom_scm-smc.c +++ b/drivers/firmware/qcom_scm-smc.c @@ -8,7 +8,7 @@ #include #include #include -#include +#include #include #include diff --git a/drivers/firmware/qcom_scm.c b/drivers/firmware/qcom_scm.c index 2000323722bf..468d4d5ab550 100644 --- a/drivers/firmware/qcom_scm.c +++ b/drivers/firmware/qcom_scm.c @@ -12,7 +12,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c index 660ba0db8900..d09221f97f71 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c @@ -5,7 +5,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c index 57586c794b84..89ff978b81bb 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c @@ -8,7 +8,7 @@ #include #include -#include +#include #include #include #include diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_hdcp.c b/drivers/gpu/drm/msm/hdmi/hdmi_hdcp.c index e7748461cffc..0752fe373351 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi_hdcp.c +++ b/drivers/gpu/drm/msm/hdmi/hdmi_hdcp.c @@ -3,7 +3,7 @@ */ #include "hdmi.h" -#include +#include #define HDCP_REG_ENABLE 0x01 #define HDCP_REG_DISABLE 0x00 diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom-debug.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom-debug.c index 74e9ef2fd580..b5b14108e086 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom-debug.c +++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom-debug.c @@ -4,7 +4,7 @@ */ #include -#include +#include #include #include "arm-smmu.h" diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c index 91d404deb115..ef42329e82ce 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c +++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c @@ -7,7 +7,7 @@ #include #include #include -#include +#include #include "arm-smmu.h" #include "arm-smmu-qcom.h" diff --git a/drivers/iommu/arm/arm-smmu/qcom_iommu.c b/drivers/iommu/arm/arm-smmu/qcom_iommu.c index 270c3d9128ba..1e0b7b2e9fbd 100644 --- a/drivers/iommu/arm/arm-smmu/qcom_iommu.c +++ b/drivers/iommu/arm/arm-smmu/qcom_iommu.c @@ -27,7 +27,7 @@ #include #include #include -#include +#include #include #include diff --git a/drivers/media/platform/qcom/venus/firmware.c b/drivers/media/platform/qcom/venus/firmware.c index 142d4c74017c..e5759d7e9ede 100644 --- a/drivers/media/platform/qcom/venus/firmware.c +++ b/drivers/media/platform/qcom/venus/firmware.c @@ -12,7 +12,7 @@ #include #include #include -#include +#include #include #include diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c index c9902a1dcf5d..04f80e754477 100644 --- a/drivers/misc/fastrpc.c +++ b/drivers/misc/fastrpc.c @@ -18,7 +18,7 @@ #include #include #include -#include +#include #include #include diff --git a/drivers/mmc/host/sdhci-msm.c b/drivers/mmc/host/sdhci-msm.c index 4ac8651d0b29..8ac81d57a3df 100644 --- a/drivers/mmc/host/sdhci-msm.c +++ b/drivers/mmc/host/sdhci-msm.c @@ -13,7 +13,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/drivers/net/ipa/ipa_main.c b/drivers/net/ipa/ipa_main.c index 4fb92f771974..90baf7a54d9a 100644 --- a/drivers/net/ipa/ipa_main.c +++ b/drivers/net/ipa/ipa_main.c @@ -16,7 +16,7 @@ #include #include #include -#include +#include #include #include "ipa.h" diff --git a/drivers/net/wireless/ath/ath10k/qmi.c b/drivers/net/wireless/ath/ath10k/qmi.c index 3f94fbf83702..90f457b8e1fe 100644 --- a/drivers/net/wireless/ath/ath10k/qmi.c +++ b/drivers/net/wireless/ath/ath10k/qmi.c @@ -13,7 +13,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c index 47e9a8b0d474..e0128c69bfbf 100644 --- a/drivers/pinctrl/qcom/pinctrl-msm.c +++ b/drivers/pinctrl/qcom/pinctrl-msm.c @@ -14,7 +14,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/drivers/remoteproc/qcom_q6v5_mss.c b/drivers/remoteproc/qcom_q6v5_mss.c index fddb63cffee0..da2513bb6387 100644 --- a/drivers/remoteproc/qcom_q6v5_mss.c +++ b/drivers/remoteproc/qcom_q6v5_mss.c @@ -34,7 +34,7 @@ #include "qcom_pil_info.h" #include "qcom_q6v5.h" -#include +#include #define MPSS_CRASH_REASON_SMEM 421 diff --git a/drivers/remoteproc/qcom_q6v5_pas.c b/drivers/remoteproc/qcom_q6v5_pas.c index dc6f07ca8341..d5a049669616 100644 --- a/drivers/remoteproc/qcom_q6v5_pas.c +++ b/drivers/remoteproc/qcom_q6v5_pas.c @@ -18,7 +18,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/drivers/remoteproc/qcom_wcnss.c b/drivers/remoteproc/qcom_wcnss.c index 68f37296b151..9881443cb8df 100644 --- a/drivers/remoteproc/qcom_wcnss.c +++ b/drivers/remoteproc/qcom_wcnss.c @@ -19,7 +19,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/drivers/soc/qcom/mdt_loader.c b/drivers/soc/qcom/mdt_loader.c index 3f11554df2f3..33dd8c315eb7 100644 --- a/drivers/soc/qcom/mdt_loader.c +++ b/drivers/soc/qcom/mdt_loader.c @@ -12,7 +12,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/drivers/soc/qcom/ocmem.c b/drivers/soc/qcom/ocmem.c index c92d26b73e6f..199fe9872035 100644 --- a/drivers/soc/qcom/ocmem.c +++ b/drivers/soc/qcom/ocmem.c @@ -16,7 +16,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/drivers/soc/qcom/rmtfs_mem.c b/drivers/soc/qcom/rmtfs_mem.c index 9d59ad509a5c..2d3ee22b9249 100644 --- a/drivers/soc/qcom/rmtfs_mem.c +++ b/drivers/soc/qcom/rmtfs_mem.c @@ -14,7 +14,7 @@ #include #include #include -#include +#include #define QCOM_RMTFS_MEM_DEV_MAX (MINORMASK + 1) #define NUM_MAX_VMIDS 2 diff --git a/drivers/thermal/qcom/lmh.c b/drivers/thermal/qcom/lmh.c index 4122a51e9874..f6edb12ec004 100644 --- a/drivers/thermal/qcom/lmh.c +++ b/drivers/thermal/qcom/lmh.c @@ -10,7 +10,7 @@ #include #include #include -#include +#include #define LMH_NODE_DCVS 0x44435653 #define LMH_CLUSTER0_NODE_ID 0x6370302D diff --git a/drivers/ufs/host/ufs-qcom-ice.c b/drivers/ufs/host/ufs-qcom-ice.c index 62387ccd5b30..453978877ae9 100644 --- a/drivers/ufs/host/ufs-qcom-ice.c +++ b/drivers/ufs/host/ufs-qcom-ice.c @@ -8,7 +8,7 @@ #include #include -#include +#include #include "ufs-qcom.h" diff --git a/include/linux/firmware/qcom/qcom_scm.h b/include/linux/firmware/qcom/qcom_scm.h new file mode 100644 index 000000000000..1e449a5d7f5c --- /dev/null +++ b/include/linux/firmware/qcom/qcom_scm.h @@ -0,0 +1,125 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (c) 2010-2015, 2018-2019 The Linux Foundation. All rights reserved. + * Copyright (C) 2015 Linaro Ltd. + */ +#ifndef __QCOM_SCM_H +#define __QCOM_SCM_H + +#include +#include +#include + +#include + +#define QCOM_SCM_VERSION(major, minor) (((major) << 16) | ((minor) & 0xFF)) +#define QCOM_SCM_CPU_PWR_DOWN_L2_ON 0x0 +#define QCOM_SCM_CPU_PWR_DOWN_L2_OFF 0x1 +#define QCOM_SCM_HDCP_MAX_REQ_CNT 5 + +struct qcom_scm_hdcp_req { + u32 addr; + u32 val; +}; + +struct qcom_scm_vmperm { + int vmid; + int perm; +}; + +enum qcom_scm_ocmem_client { + QCOM_SCM_OCMEM_UNUSED_ID = 0x0, + QCOM_SCM_OCMEM_GRAPHICS_ID, + QCOM_SCM_OCMEM_VIDEO_ID, + QCOM_SCM_OCMEM_LP_AUDIO_ID, + QCOM_SCM_OCMEM_SENSORS_ID, + QCOM_SCM_OCMEM_OTHER_OS_ID, + QCOM_SCM_OCMEM_DEBUG_ID, +}; + +enum qcom_scm_sec_dev_id { + QCOM_SCM_MDSS_DEV_ID = 1, + QCOM_SCM_OCMEM_DEV_ID = 5, + QCOM_SCM_PCIE0_DEV_ID = 11, + QCOM_SCM_PCIE1_DEV_ID = 12, + QCOM_SCM_GFX_DEV_ID = 18, + QCOM_SCM_UFS_DEV_ID = 19, + QCOM_SCM_ICE_DEV_ID = 20, +}; + +enum qcom_scm_ice_cipher { + QCOM_SCM_ICE_CIPHER_AES_128_XTS = 0, + QCOM_SCM_ICE_CIPHER_AES_128_CBC = 1, + QCOM_SCM_ICE_CIPHER_AES_256_XTS = 3, + QCOM_SCM_ICE_CIPHER_AES_256_CBC = 4, +}; + +#define QCOM_SCM_PERM_READ 0x4 +#define QCOM_SCM_PERM_WRITE 0x2 +#define QCOM_SCM_PERM_EXEC 0x1 +#define QCOM_SCM_PERM_RW (QCOM_SCM_PERM_READ | QCOM_SCM_PERM_WRITE) +#define QCOM_SCM_PERM_RWX (QCOM_SCM_PERM_RW | QCOM_SCM_PERM_EXEC) + +extern bool qcom_scm_is_available(void); + +extern int qcom_scm_set_cold_boot_addr(void *entry); +extern int qcom_scm_set_warm_boot_addr(void *entry); +extern void qcom_scm_cpu_power_down(u32 flags); +extern int qcom_scm_set_remote_state(u32 state, u32 id); + +struct qcom_scm_pas_metadata { + void *ptr; + dma_addr_t phys; + ssize_t size; +}; + +extern int qcom_scm_pas_init_image(u32 peripheral, const void *metadata, + size_t size, + struct qcom_scm_pas_metadata *ctx); +void qcom_scm_pas_metadata_release(struct qcom_scm_pas_metadata *ctx); +extern int qcom_scm_pas_mem_setup(u32 peripheral, phys_addr_t addr, + phys_addr_t size); +extern int qcom_scm_pas_auth_and_reset(u32 peripheral); +extern int qcom_scm_pas_shutdown(u32 peripheral); +extern bool qcom_scm_pas_supported(u32 peripheral); + +extern int qcom_scm_io_readl(phys_addr_t addr, unsigned int *val); +extern int qcom_scm_io_writel(phys_addr_t addr, unsigned int val); + +extern bool qcom_scm_restore_sec_cfg_available(void); +extern int qcom_scm_restore_sec_cfg(u32 device_id, u32 spare); +extern int qcom_scm_iommu_secure_ptbl_size(u32 spare, size_t *size); +extern int qcom_scm_iommu_secure_ptbl_init(u64 addr, u32 size, u32 spare); +extern int qcom_scm_iommu_set_cp_pool_size(u32 spare, u32 size); +extern int qcom_scm_mem_protect_video_var(u32 cp_start, u32 cp_size, + u32 cp_nonpixel_start, + u32 cp_nonpixel_size); +extern int qcom_scm_assign_mem(phys_addr_t mem_addr, size_t mem_sz, + unsigned int *src, + const struct qcom_scm_vmperm *newvm, + unsigned int dest_cnt); + +extern bool qcom_scm_ocmem_lock_available(void); +extern int qcom_scm_ocmem_lock(enum qcom_scm_ocmem_client id, u32 offset, + u32 size, u32 mode); +extern int qcom_scm_ocmem_unlock(enum qcom_scm_ocmem_client id, u32 offset, + u32 size); + +extern bool qcom_scm_ice_available(void); +extern int qcom_scm_ice_invalidate_key(u32 index); +extern int qcom_scm_ice_set_key(u32 index, const u8 *key, u32 key_size, + enum qcom_scm_ice_cipher cipher, + u32 data_unit_size); + +extern bool qcom_scm_hdcp_available(void); +extern int qcom_scm_hdcp_req(struct qcom_scm_hdcp_req *req, u32 req_cnt, + u32 *resp); + +extern int qcom_scm_iommu_set_pt_format(u32 sec_id, u32 ctx_num, u32 pt_fmt); +extern int qcom_scm_qsmmu500_wait_safe_toggle(bool en); + +extern int qcom_scm_lmh_dcvsh(u32 payload_fn, u32 payload_reg, u32 payload_val, + u64 limit_node, u32 node_id, u64 version); +extern int qcom_scm_lmh_profile_change(u32 profile_id); +extern bool qcom_scm_lmh_dcvsh_available(void); + +#endif diff --git a/include/linux/qcom_scm.h b/include/linux/qcom_scm.h deleted file mode 100644 index 1e449a5d7f5c..000000000000 --- a/include/linux/qcom_scm.h +++ /dev/null @@ -1,125 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* Copyright (c) 2010-2015, 2018-2019 The Linux Foundation. All rights reserved. - * Copyright (C) 2015 Linaro Ltd. - */ -#ifndef __QCOM_SCM_H -#define __QCOM_SCM_H - -#include -#include -#include - -#include - -#define QCOM_SCM_VERSION(major, minor) (((major) << 16) | ((minor) & 0xFF)) -#define QCOM_SCM_CPU_PWR_DOWN_L2_ON 0x0 -#define QCOM_SCM_CPU_PWR_DOWN_L2_OFF 0x1 -#define QCOM_SCM_HDCP_MAX_REQ_CNT 5 - -struct qcom_scm_hdcp_req { - u32 addr; - u32 val; -}; - -struct qcom_scm_vmperm { - int vmid; - int perm; -}; - -enum qcom_scm_ocmem_client { - QCOM_SCM_OCMEM_UNUSED_ID = 0x0, - QCOM_SCM_OCMEM_GRAPHICS_ID, - QCOM_SCM_OCMEM_VIDEO_ID, - QCOM_SCM_OCMEM_LP_AUDIO_ID, - QCOM_SCM_OCMEM_SENSORS_ID, - QCOM_SCM_OCMEM_OTHER_OS_ID, - QCOM_SCM_OCMEM_DEBUG_ID, -}; - -enum qcom_scm_sec_dev_id { - QCOM_SCM_MDSS_DEV_ID = 1, - QCOM_SCM_OCMEM_DEV_ID = 5, - QCOM_SCM_PCIE0_DEV_ID = 11, - QCOM_SCM_PCIE1_DEV_ID = 12, - QCOM_SCM_GFX_DEV_ID = 18, - QCOM_SCM_UFS_DEV_ID = 19, - QCOM_SCM_ICE_DEV_ID = 20, -}; - -enum qcom_scm_ice_cipher { - QCOM_SCM_ICE_CIPHER_AES_128_XTS = 0, - QCOM_SCM_ICE_CIPHER_AES_128_CBC = 1, - QCOM_SCM_ICE_CIPHER_AES_256_XTS = 3, - QCOM_SCM_ICE_CIPHER_AES_256_CBC = 4, -}; - -#define QCOM_SCM_PERM_READ 0x4 -#define QCOM_SCM_PERM_WRITE 0x2 -#define QCOM_SCM_PERM_EXEC 0x1 -#define QCOM_SCM_PERM_RW (QCOM_SCM_PERM_READ | QCOM_SCM_PERM_WRITE) -#define QCOM_SCM_PERM_RWX (QCOM_SCM_PERM_RW | QCOM_SCM_PERM_EXEC) - -extern bool qcom_scm_is_available(void); - -extern int qcom_scm_set_cold_boot_addr(void *entry); -extern int qcom_scm_set_warm_boot_addr(void *entry); -extern void qcom_scm_cpu_power_down(u32 flags); -extern int qcom_scm_set_remote_state(u32 state, u32 id); - -struct qcom_scm_pas_metadata { - void *ptr; - dma_addr_t phys; - ssize_t size; -}; - -extern int qcom_scm_pas_init_image(u32 peripheral, const void *metadata, - size_t size, - struct qcom_scm_pas_metadata *ctx); -void qcom_scm_pas_metadata_release(struct qcom_scm_pas_metadata *ctx); -extern int qcom_scm_pas_mem_setup(u32 peripheral, phys_addr_t addr, - phys_addr_t size); -extern int qcom_scm_pas_auth_and_reset(u32 peripheral); -extern int qcom_scm_pas_shutdown(u32 peripheral); -extern bool qcom_scm_pas_supported(u32 peripheral); - -extern int qcom_scm_io_readl(phys_addr_t addr, unsigned int *val); -extern int qcom_scm_io_writel(phys_addr_t addr, unsigned int val); - -extern bool qcom_scm_restore_sec_cfg_available(void); -extern int qcom_scm_restore_sec_cfg(u32 device_id, u32 spare); -extern int qcom_scm_iommu_secure_ptbl_size(u32 spare, size_t *size); -extern int qcom_scm_iommu_secure_ptbl_init(u64 addr, u32 size, u32 spare); -extern int qcom_scm_iommu_set_cp_pool_size(u32 spare, u32 size); -extern int qcom_scm_mem_protect_video_var(u32 cp_start, u32 cp_size, - u32 cp_nonpixel_start, - u32 cp_nonpixel_size); -extern int qcom_scm_assign_mem(phys_addr_t mem_addr, size_t mem_sz, - unsigned int *src, - const struct qcom_scm_vmperm *newvm, - unsigned int dest_cnt); - -extern bool qcom_scm_ocmem_lock_available(void); -extern int qcom_scm_ocmem_lock(enum qcom_scm_ocmem_client id, u32 offset, - u32 size, u32 mode); -extern int qcom_scm_ocmem_unlock(enum qcom_scm_ocmem_client id, u32 offset, - u32 size); - -extern bool qcom_scm_ice_available(void); -extern int qcom_scm_ice_invalidate_key(u32 index); -extern int qcom_scm_ice_set_key(u32 index, const u8 *key, u32 key_size, - enum qcom_scm_ice_cipher cipher, - u32 data_unit_size); - -extern bool qcom_scm_hdcp_available(void); -extern int qcom_scm_hdcp_req(struct qcom_scm_hdcp_req *req, u32 req_cnt, - u32 *resp); - -extern int qcom_scm_iommu_set_pt_format(u32 sec_id, u32 ctx_num, u32 pt_fmt); -extern int qcom_scm_qsmmu500_wait_safe_toggle(bool en); - -extern int qcom_scm_lmh_dcvsh(u32 payload_fn, u32 payload_reg, u32 payload_val, - u64 limit_node, u32 node_id, u64 version); -extern int qcom_scm_lmh_profile_change(u32 profile_id); -extern bool qcom_scm_lmh_dcvsh_available(void); - -#endif -- cgit v1.2.3 From e0766ea4c8f8f94a605e291aa3672a703dc1d2e4 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 8 Feb 2023 12:13:12 +0100 Subject: driver core: bus: constantify the bus_find_* functions All of the bus find and iterator functions do not modify the struct bus_type passed to them, so mark them as constant to enforce this rule. Cc: "Rafael J. Wysocki" Link: https://lore.kernel.org/r/20230208111330.439504-4-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/base/bus.c | 6 +++--- include/linux/device/bus.h | 20 ++++++++++---------- 2 files changed, 13 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/bus.c b/drivers/base/bus.c index 8f46ab84e81a..b27ddf957f8b 100644 --- a/drivers/base/bus.c +++ b/drivers/base/bus.c @@ -331,7 +331,7 @@ static struct device *next_device(struct klist_iter *i) * to retain this data, it should do so, and increment the reference * count in the supplied callback. */ -int bus_for_each_dev(struct bus_type *bus, struct device *start, +int bus_for_each_dev(const struct bus_type *bus, struct device *start, void *data, int (*fn)(struct device *, void *)) { struct klist_iter i; @@ -365,7 +365,7 @@ EXPORT_SYMBOL_GPL(bus_for_each_dev); * if it does. If the callback returns non-zero, this function will * return to the caller and not iterate over any more devices. */ -struct device *bus_find_device(struct bus_type *bus, +struct device *bus_find_device(const struct bus_type *bus, struct device *start, const void *data, int (*match)(struct device *dev, const void *data)) { @@ -416,7 +416,7 @@ static struct device_driver *next_driver(struct klist_iter *i) * in the callback. It must also be sure to increment the refcount * so it doesn't disappear before returning to the caller. */ -int bus_for_each_drv(struct bus_type *bus, struct device_driver *start, +int bus_for_each_drv(const struct bus_type *bus, struct device_driver *start, void *data, int (*fn)(struct device_driver *, void *)) { struct klist_iter i; diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h index e3094db1e9fa..f0c8bf91b07a 100644 --- a/include/linux/device/bus.h +++ b/include/linux/device/bus.h @@ -149,9 +149,9 @@ int device_match_acpi_handle(struct device *dev, const void *handle); int device_match_any(struct device *dev, const void *unused); /* iterator helpers for buses */ -int bus_for_each_dev(struct bus_type *bus, struct device *start, void *data, +int bus_for_each_dev(const struct bus_type *bus, struct device *start, void *data, int (*fn)(struct device *dev, void *data)); -struct device *bus_find_device(struct bus_type *bus, struct device *start, +struct device *bus_find_device(const struct bus_type *bus, struct device *start, const void *data, int (*match)(struct device *dev, const void *data)); /** @@ -161,7 +161,7 @@ struct device *bus_find_device(struct bus_type *bus, struct device *start, * @start: Device to begin with * @name: name of the device to match */ -static inline struct device *bus_find_device_by_name(struct bus_type *bus, +static inline struct device *bus_find_device_by_name(const struct bus_type *bus, struct device *start, const char *name) { @@ -175,7 +175,7 @@ static inline struct device *bus_find_device_by_name(struct bus_type *bus, * @np: of_node of the device to match. */ static inline struct device * -bus_find_device_by_of_node(struct bus_type *bus, const struct device_node *np) +bus_find_device_by_of_node(const struct bus_type *bus, const struct device_node *np) { return bus_find_device(bus, NULL, np, device_match_of_node); } @@ -187,7 +187,7 @@ bus_find_device_by_of_node(struct bus_type *bus, const struct device_node *np) * @fwnode: fwnode of the device to match. */ static inline struct device * -bus_find_device_by_fwnode(struct bus_type *bus, const struct fwnode_handle *fwnode) +bus_find_device_by_fwnode(const struct bus_type *bus, const struct fwnode_handle *fwnode) { return bus_find_device(bus, NULL, fwnode, device_match_fwnode); } @@ -198,7 +198,7 @@ bus_find_device_by_fwnode(struct bus_type *bus, const struct fwnode_handle *fwno * @bus: bus type * @devt: device type of the device to match. */ -static inline struct device *bus_find_device_by_devt(struct bus_type *bus, +static inline struct device *bus_find_device_by_devt(const struct bus_type *bus, dev_t devt) { return bus_find_device(bus, NULL, &devt, device_match_devt); @@ -211,7 +211,7 @@ static inline struct device *bus_find_device_by_devt(struct bus_type *bus, * @cur: device to begin the search with. */ static inline struct device * -bus_find_next_device(struct bus_type *bus,struct device *cur) +bus_find_next_device(const struct bus_type *bus,struct device *cur) { return bus_find_device(bus, cur, NULL, device_match_any); } @@ -226,19 +226,19 @@ struct acpi_device; * @adev: ACPI COMPANION device to match. */ static inline struct device * -bus_find_device_by_acpi_dev(struct bus_type *bus, const struct acpi_device *adev) +bus_find_device_by_acpi_dev(const struct bus_type *bus, const struct acpi_device *adev) { return bus_find_device(bus, NULL, adev, device_match_acpi_dev); } #else static inline struct device * -bus_find_device_by_acpi_dev(struct bus_type *bus, const void *adev) +bus_find_device_by_acpi_dev(const struct bus_type *bus, const void *adev) { return NULL; } #endif -int bus_for_each_drv(struct bus_type *bus, struct device_driver *start, +int bus_for_each_drv(const struct bus_type *bus, struct device_driver *start, void *data, int (*fn)(struct device_driver *, void *)); void bus_sort_breadthfirst(struct bus_type *bus, int (*compare)(const struct device *a, -- cgit v1.2.3 From 0396f2863f7af3c588033d270f7d979d11cd4708 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 8 Feb 2023 12:13:13 +0100 Subject: driver core: bus: convert bus_create/remove_file to be constant bus_create_file() and bus_remove_file() can be made to take a constant bus pointer, as it should not be modifying anything in the bus structure. Make this change and move the functions to use the internal subsys_get/put() logic as well, to prevent the use of the back-pointer in struct bus_type. Cc: "Rafael J. Wysocki" Link: https://lore.kernel.org/r/20230208111330.439504-5-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/base/bus.c | 28 +++++++++++++++++----------- include/linux/device/bus.h | 5 ++--- 2 files changed, 19 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/bus.c b/drivers/base/bus.c index b27ddf957f8b..6552d385fcb9 100644 --- a/drivers/base/bus.c +++ b/drivers/base/bus.c @@ -175,24 +175,30 @@ static const struct sysfs_ops bus_sysfs_ops = { .store = bus_attr_store, }; -int bus_create_file(struct bus_type *bus, struct bus_attribute *attr) +int bus_create_file(const struct bus_type *bus, struct bus_attribute *attr) { + struct subsys_private *sp = bus_to_subsys(bus); int error; - if (bus_get(bus)) { - error = sysfs_create_file(&bus->p->subsys.kobj, &attr->attr); - bus_put(bus); - } else - error = -EINVAL; + + if (!sp) + return -EINVAL; + + error = sysfs_create_file(&sp->subsys.kobj, &attr->attr); + + subsys_put(sp); return error; } EXPORT_SYMBOL_GPL(bus_create_file); -void bus_remove_file(struct bus_type *bus, struct bus_attribute *attr) +void bus_remove_file(const struct bus_type *bus, struct bus_attribute *attr) { - if (bus_get(bus)) { - sysfs_remove_file(&bus->p->subsys.kobj, &attr->attr); - bus_put(bus); - } + struct subsys_private *sp = bus_to_subsys(bus); + + if (!sp) + return; + + sysfs_remove_file(&sp->subsys.kobj, &attr->attr); + subsys_put(sp); } EXPORT_SYMBOL_GPL(bus_remove_file); diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h index f0c8bf91b07a..f6537f5fc535 100644 --- a/include/linux/device/bus.h +++ b/include/linux/device/bus.h @@ -135,9 +135,8 @@ struct bus_attribute { #define BUS_ATTR_WO(_name) \ struct bus_attribute bus_attr_##_name = __ATTR_WO(_name) -extern int __must_check bus_create_file(struct bus_type *, - struct bus_attribute *); -extern void bus_remove_file(struct bus_type *, struct bus_attribute *); +int __must_check bus_create_file(const struct bus_type *bus, struct bus_attribute *attr); +void bus_remove_file(const struct bus_type *bus, struct bus_attribute *attr); /* Generic device matching functions that all busses can use to match with */ int device_match_name(struct device *dev, const void *name); -- cgit v1.2.3 From d2bf38c088e0d5467a0e8a2055d6f95dff5c2125 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 8 Feb 2023 12:13:26 +0100 Subject: driver core: remove private pointer from struct bus_type Now that the driver code has been refactored to not rely on the pointer from a struct bus_type to the private structure it can be safely removed from the structure entirely. This will allow most bus_type structures to now be marked as const. Cc: "Rafael J. Wysocki" Link: https://lore.kernel.org/r/20230208111330.439504-18-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/base/bus.c | 4 ---- include/linux/device/bus.h | 4 ---- 2 files changed, 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/bus.c b/drivers/base/bus.c index c82c65fde8a1..719cd3a1354c 100644 --- a/drivers/base/bus.c +++ b/drivers/base/bus.c @@ -205,11 +205,9 @@ EXPORT_SYMBOL_GPL(bus_remove_file); static void bus_release(struct kobject *kobj) { struct subsys_private *priv = to_subsys_private(kobj); - struct bus_type *bus = priv->bus; lockdep_unregister_key(&priv->lock_key); kfree(priv); - bus->p = NULL; } static const struct kobj_type bus_ktype = { @@ -854,7 +852,6 @@ int bus_register(struct bus_type *bus) return -ENOMEM; priv->bus = bus; - bus->p = priv; BLOCKING_INIT_NOTIFIER_HEAD(&priv->bus_notifier); @@ -917,7 +914,6 @@ bus_uevent_fail: kset_unregister(&priv->subsys); out: kfree(priv); - bus->p = NULL; return retval; } EXPORT_SYMBOL_GPL(bus_register); diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h index f6537f5fc535..22bf63469275 100644 --- a/include/linux/device/bus.h +++ b/include/linux/device/bus.h @@ -66,8 +66,6 @@ struct fwnode_handle; * @iommu_ops: IOMMU specific operations for this bus, used to attach IOMMU * driver implementations to a bus and allow the driver to do * bus-specific setup - * @p: The private data of the driver core, only the driver core can - * touch this. * @lock_key: Lock class key for use by the lock validator * @need_parent_lock: When probing or removing a device on this bus, the * device core should lock the device's parent. @@ -111,8 +109,6 @@ struct bus_type { const struct iommu_ops *iommu_ops; - struct subsys_private *p; - bool need_parent_lock; }; -- cgit v1.2.3 From bc8b7931012f0511f016e2f048d1f4222db8e08f Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 8 Feb 2023 12:13:27 +0100 Subject: driver core: bus: constify bus_register/unregister_notifier() The bus_register_notifier() and bus_unregister_notifier() functions should be taking a const * to bus_type, not just a * so fix that up. Cc: "Rafael J. Wysocki" Link: https://lore.kernel.org/r/20230208111330.439504-19-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/base/bus.c | 4 ++-- include/linux/device/bus.h | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/bus.c b/drivers/base/bus.c index 719cd3a1354c..0920fb117896 100644 --- a/drivers/base/bus.c +++ b/drivers/base/bus.c @@ -949,7 +949,7 @@ void bus_unregister(struct bus_type *bus) } EXPORT_SYMBOL_GPL(bus_unregister); -int bus_register_notifier(struct bus_type *bus, struct notifier_block *nb) +int bus_register_notifier(const struct bus_type *bus, struct notifier_block *nb) { struct subsys_private *sp = bus_to_subsys(bus); int retval; @@ -963,7 +963,7 @@ int bus_register_notifier(struct bus_type *bus, struct notifier_block *nb) } EXPORT_SYMBOL_GPL(bus_register_notifier); -int bus_unregister_notifier(struct bus_type *bus, struct notifier_block *nb) +int bus_unregister_notifier(const struct bus_type *bus, struct notifier_block *nb) { struct subsys_private *sp = bus_to_subsys(bus); int retval; diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h index 22bf63469275..c0a034ff59b7 100644 --- a/include/linux/device/bus.h +++ b/include/linux/device/bus.h @@ -246,9 +246,9 @@ void bus_sort_breadthfirst(struct bus_type *bus, */ struct notifier_block; -extern int bus_register_notifier(struct bus_type *bus, +extern int bus_register_notifier(const struct bus_type *bus, struct notifier_block *nb); -extern int bus_unregister_notifier(struct bus_type *bus, +extern int bus_unregister_notifier(const struct bus_type *bus, struct notifier_block *nb); /** -- cgit v1.2.3 From f91482be9b480dfce2616f5ba3fa548b8ed41efb Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 8 Feb 2023 12:13:28 +0100 Subject: driver core: bus: constify bus_get_kset() The bus_get_kset() function should be taking a const * to bus_type, not just a * so fix that up. Cc: "Rafael J. Wysocki" Link: https://lore.kernel.org/r/20230208111330.439504-20-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/base/bus.c | 2 +- include/linux/device/bus.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/bus.c b/drivers/base/bus.c index 0920fb117896..c394727b8253 100644 --- a/drivers/base/bus.c +++ b/drivers/base/bus.c @@ -987,7 +987,7 @@ void bus_notify(struct device *dev, enum bus_notifier_event value) subsys_put(sp); } -struct kset *bus_get_kset(struct bus_type *bus) +struct kset *bus_get_kset(const struct bus_type *bus) { struct subsys_private *sp = bus_to_subsys(bus); struct kset *kset; diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h index c0a034ff59b7..425d79d6cf69 100644 --- a/include/linux/device/bus.h +++ b/include/linux/device/bus.h @@ -281,6 +281,6 @@ enum bus_notifier_event { BUS_NOTIFY_DRIVER_NOT_BOUND, }; -extern struct kset *bus_get_kset(struct bus_type *bus); +extern struct kset *bus_get_kset(const struct bus_type *bus); #endif -- cgit v1.2.3 From ad8685d0f61a6fc1dc2e5874f4924ff5028c5954 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 8 Feb 2023 12:13:30 +0100 Subject: driver core: bus: constify bus_unregister() The bus_unregister() function can now take a const * to bus_type, not just a * so fix that up. Cc: "Rafael J. Wysocki" Link: https://lore.kernel.org/r/20230208111330.439504-22-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/base/bus.c | 2 +- include/linux/device/bus.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/bus.c b/drivers/base/bus.c index bcff24b11bb3..301b9c6ece86 100644 --- a/drivers/base/bus.c +++ b/drivers/base/bus.c @@ -925,7 +925,7 @@ EXPORT_SYMBOL_GPL(bus_register); * Unregister the child subsystems and the bus itself. * Finally, we call bus_put() to release the refcount */ -void bus_unregister(struct bus_type *bus) +void bus_unregister(const struct bus_type *bus) { struct subsys_private *sp = bus_to_subsys(bus); struct kobject *bus_kobj; diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h index 425d79d6cf69..31be18608f83 100644 --- a/include/linux/device/bus.h +++ b/include/linux/device/bus.h @@ -114,7 +114,7 @@ struct bus_type { extern int __must_check bus_register(struct bus_type *bus); -extern void bus_unregister(struct bus_type *bus); +extern void bus_unregister(const struct bus_type *bus); extern int __must_check bus_rescan_devices(struct bus_type *bus); -- cgit v1.2.3 From 491581f40e4c52c4b36c83e8c75b2210ed7c358a Mon Sep 17 00:00:00 2001 From: Elliot Berman Date: Fri, 3 Feb 2023 13:01:32 -0800 Subject: soc: qcom: geni-se: Move qcom-geni-se.h to linux/soc/qcom/geni-se.h Move include/linux/qcom-geni-se.h to include/linux/soc/qcom/geni-se.h. This removes 1 of a few remaining Qualcomm-specific headers into a more approciate subdirectory under include/. Signed-off-by: Elliot Berman Acked-by: Bjorn Andersson Acked-by: Wolfram Sang # for I2C Reviewed-by: Guru Das Srinagesh Link: https://lore.kernel.org/r/20230203210133.3552796-1-quic_eberman@quicinc.com Signed-off-by: Greg Kroah-Hartman --- drivers/i2c/busses/i2c-qcom-geni.c | 2 +- drivers/soc/qcom/qcom-geni-se.c | 2 +- drivers/spi/spi-geni-qcom.c | 2 +- drivers/tty/serial/qcom_geni_serial.c | 2 +- include/linux/qcom-geni-se.h | 482 ---------------------------------- include/linux/soc/qcom/geni-se.h | 482 ++++++++++++++++++++++++++++++++++ 6 files changed, 486 insertions(+), 486 deletions(-) delete mode 100644 include/linux/qcom-geni-se.h create mode 100644 include/linux/soc/qcom/geni-se.h (limited to 'include/linux') diff --git a/drivers/i2c/busses/i2c-qcom-geni.c b/drivers/i2c/busses/i2c-qcom-geni.c index fd70794bfcee..80d586b0be7a 100644 --- a/drivers/i2c/busses/i2c-qcom-geni.c +++ b/drivers/i2c/busses/i2c-qcom-geni.c @@ -14,7 +14,7 @@ #include #include #include -#include +#include #include #define SE_I2C_TX_TRANS_LEN 0x26c diff --git a/drivers/soc/qcom/qcom-geni-se.c b/drivers/soc/qcom/qcom-geni-se.c index f0475b93ca73..795a2e1d59b3 100644 --- a/drivers/soc/qcom/qcom-geni-se.c +++ b/drivers/soc/qcom/qcom-geni-se.c @@ -14,7 +14,7 @@ #include #include #include -#include +#include /** * DOC: Overview diff --git a/drivers/spi/spi-geni-qcom.c b/drivers/spi/spi-geni-qcom.c index 4e83cc5b445d..e05e40a49294 100644 --- a/drivers/spi/spi-geni-qcom.c +++ b/drivers/spi/spi-geni-qcom.c @@ -12,7 +12,7 @@ #include #include #include -#include +#include #include #include diff --git a/drivers/tty/serial/qcom_geni_serial.c b/drivers/tty/serial/qcom_geni_serial.c index 7c49194ec8ac..d69592e5e2ec 100644 --- a/drivers/tty/serial/qcom_geni_serial.c +++ b/drivers/tty/serial/qcom_geni_serial.c @@ -16,7 +16,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/include/linux/qcom-geni-se.h b/include/linux/qcom-geni-se.h deleted file mode 100644 index 400213daa461..000000000000 --- a/include/linux/qcom-geni-se.h +++ /dev/null @@ -1,482 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Copyright (c) 2017-2018, The Linux Foundation. All rights reserved. - */ - -#ifndef _LINUX_QCOM_GENI_SE -#define _LINUX_QCOM_GENI_SE - -#include - -/** - * enum geni_se_xfer_mode: Transfer modes supported by Serial Engines - * - * @GENI_SE_INVALID: Invalid mode - * @GENI_SE_FIFO: FIFO mode. Data is transferred with SE FIFO - * by programmed IO method - * @GENI_SE_DMA: Serial Engine DMA mode. Data is transferred - * with SE by DMAengine internal to SE - * @GENI_GPI_DMA: GPI DMA mode. Data is transferred using a DMAengine - * configured by a firmware residing on a GSI engine. This DMA name is - * interchangeably used as GSI or GPI which seem to imply the same DMAengine - */ - -enum geni_se_xfer_mode { - GENI_SE_INVALID, - GENI_SE_FIFO, - GENI_SE_DMA, - GENI_GPI_DMA, -}; - -/* Protocols supported by GENI Serial Engines */ -enum geni_se_protocol_type { - GENI_SE_NONE, - GENI_SE_SPI, - GENI_SE_UART, - GENI_SE_I2C, - GENI_SE_I3C, -}; - -struct geni_wrapper; -struct clk; - -enum geni_icc_path_index { - GENI_TO_CORE, - CPU_TO_GENI, - GENI_TO_DDR -}; - -struct geni_icc_path { - struct icc_path *path; - unsigned int avg_bw; -}; - -/** - * struct geni_se - GENI Serial Engine - * @base: Base Address of the Serial Engine's register block - * @dev: Pointer to the Serial Engine device - * @wrapper: Pointer to the parent QUP Wrapper core - * @clk: Handle to the core serial engine clock - * @num_clk_levels: Number of valid clock levels in clk_perf_tbl - * @clk_perf_tbl: Table of clock frequency input to serial engine clock - * @icc_paths: Array of ICC paths for SE - */ -struct geni_se { - void __iomem *base; - struct device *dev; - struct geni_wrapper *wrapper; - struct clk *clk; - unsigned int num_clk_levels; - unsigned long *clk_perf_tbl; - struct geni_icc_path icc_paths[3]; -}; - -/* Common SE registers */ -#define GENI_FORCE_DEFAULT_REG 0x20 -#define SE_GENI_STATUS 0x40 -#define GENI_SER_M_CLK_CFG 0x48 -#define GENI_SER_S_CLK_CFG 0x4c -#define GENI_IF_DISABLE_RO 0x64 -#define GENI_FW_REVISION_RO 0x68 -#define SE_GENI_CLK_SEL 0x7c -#define SE_GENI_DMA_MODE_EN 0x258 -#define SE_GENI_M_CMD0 0x600 -#define SE_GENI_M_CMD_CTRL_REG 0x604 -#define SE_GENI_M_IRQ_STATUS 0x610 -#define SE_GENI_M_IRQ_EN 0x614 -#define SE_GENI_M_IRQ_CLEAR 0x618 -#define SE_GENI_S_CMD0 0x630 -#define SE_GENI_S_CMD_CTRL_REG 0x634 -#define SE_GENI_S_IRQ_STATUS 0x640 -#define SE_GENI_S_IRQ_EN 0x644 -#define SE_GENI_S_IRQ_CLEAR 0x648 -#define SE_GENI_TX_FIFOn 0x700 -#define SE_GENI_RX_FIFOn 0x780 -#define SE_GENI_TX_FIFO_STATUS 0x800 -#define SE_GENI_RX_FIFO_STATUS 0x804 -#define SE_GENI_TX_WATERMARK_REG 0x80c -#define SE_GENI_RX_WATERMARK_REG 0x810 -#define SE_GENI_RX_RFR_WATERMARK_REG 0x814 -#define SE_GENI_IOS 0x908 -#define SE_DMA_TX_IRQ_STAT 0xc40 -#define SE_DMA_TX_IRQ_CLR 0xc44 -#define SE_DMA_TX_FSM_RST 0xc58 -#define SE_DMA_RX_IRQ_STAT 0xd40 -#define SE_DMA_RX_IRQ_CLR 0xd44 -#define SE_DMA_RX_LEN_IN 0xd54 -#define SE_DMA_RX_FSM_RST 0xd58 -#define SE_HW_PARAM_0 0xe24 -#define SE_HW_PARAM_1 0xe28 - -/* GENI_FORCE_DEFAULT_REG fields */ -#define FORCE_DEFAULT BIT(0) - -/* GENI_STATUS fields */ -#define M_GENI_CMD_ACTIVE BIT(0) -#define S_GENI_CMD_ACTIVE BIT(12) - -/* GENI_SER_M_CLK_CFG/GENI_SER_S_CLK_CFG */ -#define SER_CLK_EN BIT(0) -#define CLK_DIV_MSK GENMASK(15, 4) -#define CLK_DIV_SHFT 4 - -/* GENI_IF_DISABLE_RO fields */ -#define FIFO_IF_DISABLE (BIT(0)) - -/* GENI_FW_REVISION_RO fields */ -#define FW_REV_PROTOCOL_MSK GENMASK(15, 8) -#define FW_REV_PROTOCOL_SHFT 8 - -/* GENI_CLK_SEL fields */ -#define CLK_SEL_MSK GENMASK(2, 0) - -/* SE_GENI_DMA_MODE_EN */ -#define GENI_DMA_MODE_EN BIT(0) - -/* GENI_M_CMD0 fields */ -#define M_OPCODE_MSK GENMASK(31, 27) -#define M_OPCODE_SHFT 27 -#define M_PARAMS_MSK GENMASK(26, 0) - -/* GENI_M_CMD_CTRL_REG */ -#define M_GENI_CMD_CANCEL BIT(2) -#define M_GENI_CMD_ABORT BIT(1) -#define M_GENI_DISABLE BIT(0) - -/* GENI_S_CMD0 fields */ -#define S_OPCODE_MSK GENMASK(31, 27) -#define S_OPCODE_SHFT 27 -#define S_PARAMS_MSK GENMASK(26, 0) - -/* GENI_S_CMD_CTRL_REG */ -#define S_GENI_CMD_CANCEL BIT(2) -#define S_GENI_CMD_ABORT BIT(1) -#define S_GENI_DISABLE BIT(0) - -/* GENI_M_IRQ_EN fields */ -#define M_CMD_DONE_EN BIT(0) -#define M_CMD_OVERRUN_EN BIT(1) -#define M_ILLEGAL_CMD_EN BIT(2) -#define M_CMD_FAILURE_EN BIT(3) -#define M_CMD_CANCEL_EN BIT(4) -#define M_CMD_ABORT_EN BIT(5) -#define M_TIMESTAMP_EN BIT(6) -#define M_RX_IRQ_EN BIT(7) -#define M_GP_SYNC_IRQ_0_EN BIT(8) -#define M_GP_IRQ_0_EN BIT(9) -#define M_GP_IRQ_1_EN BIT(10) -#define M_GP_IRQ_2_EN BIT(11) -#define M_GP_IRQ_3_EN BIT(12) -#define M_GP_IRQ_4_EN BIT(13) -#define M_GP_IRQ_5_EN BIT(14) -#define M_IO_DATA_DEASSERT_EN BIT(22) -#define M_IO_DATA_ASSERT_EN BIT(23) -#define M_RX_FIFO_RD_ERR_EN BIT(24) -#define M_RX_FIFO_WR_ERR_EN BIT(25) -#define M_RX_FIFO_WATERMARK_EN BIT(26) -#define M_RX_FIFO_LAST_EN BIT(27) -#define M_TX_FIFO_RD_ERR_EN BIT(28) -#define M_TX_FIFO_WR_ERR_EN BIT(29) -#define M_TX_FIFO_WATERMARK_EN BIT(30) -#define M_SEC_IRQ_EN BIT(31) -#define M_COMMON_GENI_M_IRQ_EN (GENMASK(6, 1) | \ - M_IO_DATA_DEASSERT_EN | \ - M_IO_DATA_ASSERT_EN | M_RX_FIFO_RD_ERR_EN | \ - M_RX_FIFO_WR_ERR_EN | M_TX_FIFO_RD_ERR_EN | \ - M_TX_FIFO_WR_ERR_EN) - -/* GENI_S_IRQ_EN fields */ -#define S_CMD_DONE_EN BIT(0) -#define S_CMD_OVERRUN_EN BIT(1) -#define S_ILLEGAL_CMD_EN BIT(2) -#define S_CMD_FAILURE_EN BIT(3) -#define S_CMD_CANCEL_EN BIT(4) -#define S_CMD_ABORT_EN BIT(5) -#define S_GP_SYNC_IRQ_0_EN BIT(8) -#define S_GP_IRQ_0_EN BIT(9) -#define S_GP_IRQ_1_EN BIT(10) -#define S_GP_IRQ_2_EN BIT(11) -#define S_GP_IRQ_3_EN BIT(12) -#define S_GP_IRQ_4_EN BIT(13) -#define S_GP_IRQ_5_EN BIT(14) -#define S_IO_DATA_DEASSERT_EN BIT(22) -#define S_IO_DATA_ASSERT_EN BIT(23) -#define S_RX_FIFO_RD_ERR_EN BIT(24) -#define S_RX_FIFO_WR_ERR_EN BIT(25) -#define S_RX_FIFO_WATERMARK_EN BIT(26) -#define S_RX_FIFO_LAST_EN BIT(27) -#define S_COMMON_GENI_S_IRQ_EN (GENMASK(5, 1) | GENMASK(13, 9) | \ - S_RX_FIFO_RD_ERR_EN | S_RX_FIFO_WR_ERR_EN) - -/* GENI_/TX/RX/RX_RFR/_WATERMARK_REG fields */ -#define WATERMARK_MSK GENMASK(5, 0) - -/* GENI_TX_FIFO_STATUS fields */ -#define TX_FIFO_WC GENMASK(27, 0) - -/* GENI_RX_FIFO_STATUS fields */ -#define RX_LAST BIT(31) -#define RX_LAST_BYTE_VALID_MSK GENMASK(30, 28) -#define RX_LAST_BYTE_VALID_SHFT 28 -#define RX_FIFO_WC_MSK GENMASK(24, 0) - -/* SE_GENI_IOS fields */ -#define IO2_DATA_IN BIT(1) -#define RX_DATA_IN BIT(0) - -/* SE_DMA_TX_IRQ_STAT Register fields */ -#define TX_DMA_DONE BIT(0) -#define TX_EOT BIT(1) -#define TX_SBE BIT(2) -#define TX_RESET_DONE BIT(3) - -/* SE_DMA_RX_IRQ_STAT Register fields */ -#define RX_DMA_DONE BIT(0) -#define RX_EOT BIT(1) -#define RX_SBE BIT(2) -#define RX_RESET_DONE BIT(3) -#define RX_FLUSH_DONE BIT(4) -#define RX_DMA_PARITY_ERR BIT(5) -#define RX_DMA_BREAK GENMASK(8, 7) -#define RX_GENI_GP_IRQ GENMASK(10, 5) -#define RX_GENI_CANCEL_IRQ BIT(11) -#define RX_GENI_GP_IRQ_EXT GENMASK(13, 12) - -/* SE_HW_PARAM_0 fields */ -#define TX_FIFO_WIDTH_MSK GENMASK(29, 24) -#define TX_FIFO_WIDTH_SHFT 24 -#define TX_FIFO_DEPTH_MSK GENMASK(21, 16) -#define TX_FIFO_DEPTH_SHFT 16 - -/* SE_HW_PARAM_1 fields */ -#define RX_FIFO_WIDTH_MSK GENMASK(29, 24) -#define RX_FIFO_WIDTH_SHFT 24 -#define RX_FIFO_DEPTH_MSK GENMASK(21, 16) -#define RX_FIFO_DEPTH_SHFT 16 - -#define HW_VER_MAJOR_MASK GENMASK(31, 28) -#define HW_VER_MAJOR_SHFT 28 -#define HW_VER_MINOR_MASK GENMASK(27, 16) -#define HW_VER_MINOR_SHFT 16 -#define HW_VER_STEP_MASK GENMASK(15, 0) - -#define GENI_SE_VERSION_MAJOR(ver) ((ver & HW_VER_MAJOR_MASK) >> HW_VER_MAJOR_SHFT) -#define GENI_SE_VERSION_MINOR(ver) ((ver & HW_VER_MINOR_MASK) >> HW_VER_MINOR_SHFT) -#define GENI_SE_VERSION_STEP(ver) (ver & HW_VER_STEP_MASK) - -/* QUP SE VERSION value for major number 2 and minor number 5 */ -#define QUP_SE_VERSION_2_5 0x20050000 - -/* - * Define bandwidth thresholds that cause the underlying Core 2X interconnect - * clock to run at the named frequency. These baseline values are recommended - * by the hardware team, and are not dynamically scaled with GENI bandwidth - * beyond basic on/off. - */ -#define CORE_2X_19_2_MHZ 960 -#define CORE_2X_50_MHZ 2500 -#define CORE_2X_100_MHZ 5000 -#define CORE_2X_150_MHZ 7500 -#define CORE_2X_200_MHZ 10000 -#define CORE_2X_236_MHZ 16383 - -#define GENI_DEFAULT_BW Bps_to_icc(1000) - -#if IS_ENABLED(CONFIG_QCOM_GENI_SE) - -u32 geni_se_get_qup_hw_version(struct geni_se *se); - -/** - * geni_se_read_proto() - Read the protocol configured for a serial engine - * @se: Pointer to the concerned serial engine. - * - * Return: Protocol value as configured in the serial engine. - */ -static inline u32 geni_se_read_proto(struct geni_se *se) -{ - u32 val; - - val = readl_relaxed(se->base + GENI_FW_REVISION_RO); - - return (val & FW_REV_PROTOCOL_MSK) >> FW_REV_PROTOCOL_SHFT; -} - -/** - * geni_se_setup_m_cmd() - Setup the primary sequencer - * @se: Pointer to the concerned serial engine. - * @cmd: Command/Operation to setup in the primary sequencer. - * @params: Parameter for the sequencer command. - * - * This function is used to configure the primary sequencer with the - * command and its associated parameters. - */ -static inline void geni_se_setup_m_cmd(struct geni_se *se, u32 cmd, u32 params) -{ - u32 m_cmd; - - m_cmd = (cmd << M_OPCODE_SHFT) | (params & M_PARAMS_MSK); - writel(m_cmd, se->base + SE_GENI_M_CMD0); -} - -/** - * geni_se_setup_s_cmd() - Setup the secondary sequencer - * @se: Pointer to the concerned serial engine. - * @cmd: Command/Operation to setup in the secondary sequencer. - * @params: Parameter for the sequencer command. - * - * This function is used to configure the secondary sequencer with the - * command and its associated parameters. - */ -static inline void geni_se_setup_s_cmd(struct geni_se *se, u32 cmd, u32 params) -{ - u32 s_cmd; - - s_cmd = readl_relaxed(se->base + SE_GENI_S_CMD0); - s_cmd &= ~(S_OPCODE_MSK | S_PARAMS_MSK); - s_cmd |= (cmd << S_OPCODE_SHFT); - s_cmd |= (params & S_PARAMS_MSK); - writel(s_cmd, se->base + SE_GENI_S_CMD0); -} - -/** - * geni_se_cancel_m_cmd() - Cancel the command configured in the primary - * sequencer - * @se: Pointer to the concerned serial engine. - * - * This function is used to cancel the currently configured command in the - * primary sequencer. - */ -static inline void geni_se_cancel_m_cmd(struct geni_se *se) -{ - writel_relaxed(M_GENI_CMD_CANCEL, se->base + SE_GENI_M_CMD_CTRL_REG); -} - -/** - * geni_se_cancel_s_cmd() - Cancel the command configured in the secondary - * sequencer - * @se: Pointer to the concerned serial engine. - * - * This function is used to cancel the currently configured command in the - * secondary sequencer. - */ -static inline void geni_se_cancel_s_cmd(struct geni_se *se) -{ - writel_relaxed(S_GENI_CMD_CANCEL, se->base + SE_GENI_S_CMD_CTRL_REG); -} - -/** - * geni_se_abort_m_cmd() - Abort the command configured in the primary sequencer - * @se: Pointer to the concerned serial engine. - * - * This function is used to force abort the currently configured command in the - * primary sequencer. - */ -static inline void geni_se_abort_m_cmd(struct geni_se *se) -{ - writel_relaxed(M_GENI_CMD_ABORT, se->base + SE_GENI_M_CMD_CTRL_REG); -} - -/** - * geni_se_abort_s_cmd() - Abort the command configured in the secondary - * sequencer - * @se: Pointer to the concerned serial engine. - * - * This function is used to force abort the currently configured command in the - * secondary sequencer. - */ -static inline void geni_se_abort_s_cmd(struct geni_se *se) -{ - writel_relaxed(S_GENI_CMD_ABORT, se->base + SE_GENI_S_CMD_CTRL_REG); -} - -/** - * geni_se_get_tx_fifo_depth() - Get the TX fifo depth of the serial engine - * @se: Pointer to the concerned serial engine. - * - * This function is used to get the depth i.e. number of elements in the - * TX fifo of the serial engine. - * - * Return: TX fifo depth in units of FIFO words. - */ -static inline u32 geni_se_get_tx_fifo_depth(struct geni_se *se) -{ - u32 val; - - val = readl_relaxed(se->base + SE_HW_PARAM_0); - - return (val & TX_FIFO_DEPTH_MSK) >> TX_FIFO_DEPTH_SHFT; -} - -/** - * geni_se_get_tx_fifo_width() - Get the TX fifo width of the serial engine - * @se: Pointer to the concerned serial engine. - * - * This function is used to get the width i.e. word size per element in the - * TX fifo of the serial engine. - * - * Return: TX fifo width in bits - */ -static inline u32 geni_se_get_tx_fifo_width(struct geni_se *se) -{ - u32 val; - - val = readl_relaxed(se->base + SE_HW_PARAM_0); - - return (val & TX_FIFO_WIDTH_MSK) >> TX_FIFO_WIDTH_SHFT; -} - -/** - * geni_se_get_rx_fifo_depth() - Get the RX fifo depth of the serial engine - * @se: Pointer to the concerned serial engine. - * - * This function is used to get the depth i.e. number of elements in the - * RX fifo of the serial engine. - * - * Return: RX fifo depth in units of FIFO words - */ -static inline u32 geni_se_get_rx_fifo_depth(struct geni_se *se) -{ - u32 val; - - val = readl_relaxed(se->base + SE_HW_PARAM_1); - - return (val & RX_FIFO_DEPTH_MSK) >> RX_FIFO_DEPTH_SHFT; -} - -void geni_se_init(struct geni_se *se, u32 rx_wm, u32 rx_rfr); - -void geni_se_select_mode(struct geni_se *se, enum geni_se_xfer_mode mode); - -void geni_se_config_packing(struct geni_se *se, int bpw, int pack_words, - bool msb_to_lsb, bool tx_cfg, bool rx_cfg); - -int geni_se_resources_off(struct geni_se *se); - -int geni_se_resources_on(struct geni_se *se); - -int geni_se_clk_tbl_get(struct geni_se *se, unsigned long **tbl); - -int geni_se_clk_freq_match(struct geni_se *se, unsigned long req_freq, - unsigned int *index, unsigned long *res_freq, - bool exact); - -int geni_se_tx_dma_prep(struct geni_se *se, void *buf, size_t len, - dma_addr_t *iova); - -int geni_se_rx_dma_prep(struct geni_se *se, void *buf, size_t len, - dma_addr_t *iova); - -void geni_se_tx_dma_unprep(struct geni_se *se, dma_addr_t iova, size_t len); - -void geni_se_rx_dma_unprep(struct geni_se *se, dma_addr_t iova, size_t len); - -int geni_icc_get(struct geni_se *se, const char *icc_ddr); - -int geni_icc_set_bw(struct geni_se *se); -void geni_icc_set_tag(struct geni_se *se, u32 tag); - -int geni_icc_enable(struct geni_se *se); - -int geni_icc_disable(struct geni_se *se); -#endif -#endif diff --git a/include/linux/soc/qcom/geni-se.h b/include/linux/soc/qcom/geni-se.h new file mode 100644 index 000000000000..400213daa461 --- /dev/null +++ b/include/linux/soc/qcom/geni-se.h @@ -0,0 +1,482 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2017-2018, The Linux Foundation. All rights reserved. + */ + +#ifndef _LINUX_QCOM_GENI_SE +#define _LINUX_QCOM_GENI_SE + +#include + +/** + * enum geni_se_xfer_mode: Transfer modes supported by Serial Engines + * + * @GENI_SE_INVALID: Invalid mode + * @GENI_SE_FIFO: FIFO mode. Data is transferred with SE FIFO + * by programmed IO method + * @GENI_SE_DMA: Serial Engine DMA mode. Data is transferred + * with SE by DMAengine internal to SE + * @GENI_GPI_DMA: GPI DMA mode. Data is transferred using a DMAengine + * configured by a firmware residing on a GSI engine. This DMA name is + * interchangeably used as GSI or GPI which seem to imply the same DMAengine + */ + +enum geni_se_xfer_mode { + GENI_SE_INVALID, + GENI_SE_FIFO, + GENI_SE_DMA, + GENI_GPI_DMA, +}; + +/* Protocols supported by GENI Serial Engines */ +enum geni_se_protocol_type { + GENI_SE_NONE, + GENI_SE_SPI, + GENI_SE_UART, + GENI_SE_I2C, + GENI_SE_I3C, +}; + +struct geni_wrapper; +struct clk; + +enum geni_icc_path_index { + GENI_TO_CORE, + CPU_TO_GENI, + GENI_TO_DDR +}; + +struct geni_icc_path { + struct icc_path *path; + unsigned int avg_bw; +}; + +/** + * struct geni_se - GENI Serial Engine + * @base: Base Address of the Serial Engine's register block + * @dev: Pointer to the Serial Engine device + * @wrapper: Pointer to the parent QUP Wrapper core + * @clk: Handle to the core serial engine clock + * @num_clk_levels: Number of valid clock levels in clk_perf_tbl + * @clk_perf_tbl: Table of clock frequency input to serial engine clock + * @icc_paths: Array of ICC paths for SE + */ +struct geni_se { + void __iomem *base; + struct device *dev; + struct geni_wrapper *wrapper; + struct clk *clk; + unsigned int num_clk_levels; + unsigned long *clk_perf_tbl; + struct geni_icc_path icc_paths[3]; +}; + +/* Common SE registers */ +#define GENI_FORCE_DEFAULT_REG 0x20 +#define SE_GENI_STATUS 0x40 +#define GENI_SER_M_CLK_CFG 0x48 +#define GENI_SER_S_CLK_CFG 0x4c +#define GENI_IF_DISABLE_RO 0x64 +#define GENI_FW_REVISION_RO 0x68 +#define SE_GENI_CLK_SEL 0x7c +#define SE_GENI_DMA_MODE_EN 0x258 +#define SE_GENI_M_CMD0 0x600 +#define SE_GENI_M_CMD_CTRL_REG 0x604 +#define SE_GENI_M_IRQ_STATUS 0x610 +#define SE_GENI_M_IRQ_EN 0x614 +#define SE_GENI_M_IRQ_CLEAR 0x618 +#define SE_GENI_S_CMD0 0x630 +#define SE_GENI_S_CMD_CTRL_REG 0x634 +#define SE_GENI_S_IRQ_STATUS 0x640 +#define SE_GENI_S_IRQ_EN 0x644 +#define SE_GENI_S_IRQ_CLEAR 0x648 +#define SE_GENI_TX_FIFOn 0x700 +#define SE_GENI_RX_FIFOn 0x780 +#define SE_GENI_TX_FIFO_STATUS 0x800 +#define SE_GENI_RX_FIFO_STATUS 0x804 +#define SE_GENI_TX_WATERMARK_REG 0x80c +#define SE_GENI_RX_WATERMARK_REG 0x810 +#define SE_GENI_RX_RFR_WATERMARK_REG 0x814 +#define SE_GENI_IOS 0x908 +#define SE_DMA_TX_IRQ_STAT 0xc40 +#define SE_DMA_TX_IRQ_CLR 0xc44 +#define SE_DMA_TX_FSM_RST 0xc58 +#define SE_DMA_RX_IRQ_STAT 0xd40 +#define SE_DMA_RX_IRQ_CLR 0xd44 +#define SE_DMA_RX_LEN_IN 0xd54 +#define SE_DMA_RX_FSM_RST 0xd58 +#define SE_HW_PARAM_0 0xe24 +#define SE_HW_PARAM_1 0xe28 + +/* GENI_FORCE_DEFAULT_REG fields */ +#define FORCE_DEFAULT BIT(0) + +/* GENI_STATUS fields */ +#define M_GENI_CMD_ACTIVE BIT(0) +#define S_GENI_CMD_ACTIVE BIT(12) + +/* GENI_SER_M_CLK_CFG/GENI_SER_S_CLK_CFG */ +#define SER_CLK_EN BIT(0) +#define CLK_DIV_MSK GENMASK(15, 4) +#define CLK_DIV_SHFT 4 + +/* GENI_IF_DISABLE_RO fields */ +#define FIFO_IF_DISABLE (BIT(0)) + +/* GENI_FW_REVISION_RO fields */ +#define FW_REV_PROTOCOL_MSK GENMASK(15, 8) +#define FW_REV_PROTOCOL_SHFT 8 + +/* GENI_CLK_SEL fields */ +#define CLK_SEL_MSK GENMASK(2, 0) + +/* SE_GENI_DMA_MODE_EN */ +#define GENI_DMA_MODE_EN BIT(0) + +/* GENI_M_CMD0 fields */ +#define M_OPCODE_MSK GENMASK(31, 27) +#define M_OPCODE_SHFT 27 +#define M_PARAMS_MSK GENMASK(26, 0) + +/* GENI_M_CMD_CTRL_REG */ +#define M_GENI_CMD_CANCEL BIT(2) +#define M_GENI_CMD_ABORT BIT(1) +#define M_GENI_DISABLE BIT(0) + +/* GENI_S_CMD0 fields */ +#define S_OPCODE_MSK GENMASK(31, 27) +#define S_OPCODE_SHFT 27 +#define S_PARAMS_MSK GENMASK(26, 0) + +/* GENI_S_CMD_CTRL_REG */ +#define S_GENI_CMD_CANCEL BIT(2) +#define S_GENI_CMD_ABORT BIT(1) +#define S_GENI_DISABLE BIT(0) + +/* GENI_M_IRQ_EN fields */ +#define M_CMD_DONE_EN BIT(0) +#define M_CMD_OVERRUN_EN BIT(1) +#define M_ILLEGAL_CMD_EN BIT(2) +#define M_CMD_FAILURE_EN BIT(3) +#define M_CMD_CANCEL_EN BIT(4) +#define M_CMD_ABORT_EN BIT(5) +#define M_TIMESTAMP_EN BIT(6) +#define M_RX_IRQ_EN BIT(7) +#define M_GP_SYNC_IRQ_0_EN BIT(8) +#define M_GP_IRQ_0_EN BIT(9) +#define M_GP_IRQ_1_EN BIT(10) +#define M_GP_IRQ_2_EN BIT(11) +#define M_GP_IRQ_3_EN BIT(12) +#define M_GP_IRQ_4_EN BIT(13) +#define M_GP_IRQ_5_EN BIT(14) +#define M_IO_DATA_DEASSERT_EN BIT(22) +#define M_IO_DATA_ASSERT_EN BIT(23) +#define M_RX_FIFO_RD_ERR_EN BIT(24) +#define M_RX_FIFO_WR_ERR_EN BIT(25) +#define M_RX_FIFO_WATERMARK_EN BIT(26) +#define M_RX_FIFO_LAST_EN BIT(27) +#define M_TX_FIFO_RD_ERR_EN BIT(28) +#define M_TX_FIFO_WR_ERR_EN BIT(29) +#define M_TX_FIFO_WATERMARK_EN BIT(30) +#define M_SEC_IRQ_EN BIT(31) +#define M_COMMON_GENI_M_IRQ_EN (GENMASK(6, 1) | \ + M_IO_DATA_DEASSERT_EN | \ + M_IO_DATA_ASSERT_EN | M_RX_FIFO_RD_ERR_EN | \ + M_RX_FIFO_WR_ERR_EN | M_TX_FIFO_RD_ERR_EN | \ + M_TX_FIFO_WR_ERR_EN) + +/* GENI_S_IRQ_EN fields */ +#define S_CMD_DONE_EN BIT(0) +#define S_CMD_OVERRUN_EN BIT(1) +#define S_ILLEGAL_CMD_EN BIT(2) +#define S_CMD_FAILURE_EN BIT(3) +#define S_CMD_CANCEL_EN BIT(4) +#define S_CMD_ABORT_EN BIT(5) +#define S_GP_SYNC_IRQ_0_EN BIT(8) +#define S_GP_IRQ_0_EN BIT(9) +#define S_GP_IRQ_1_EN BIT(10) +#define S_GP_IRQ_2_EN BIT(11) +#define S_GP_IRQ_3_EN BIT(12) +#define S_GP_IRQ_4_EN BIT(13) +#define S_GP_IRQ_5_EN BIT(14) +#define S_IO_DATA_DEASSERT_EN BIT(22) +#define S_IO_DATA_ASSERT_EN BIT(23) +#define S_RX_FIFO_RD_ERR_EN BIT(24) +#define S_RX_FIFO_WR_ERR_EN BIT(25) +#define S_RX_FIFO_WATERMARK_EN BIT(26) +#define S_RX_FIFO_LAST_EN BIT(27) +#define S_COMMON_GENI_S_IRQ_EN (GENMASK(5, 1) | GENMASK(13, 9) | \ + S_RX_FIFO_RD_ERR_EN | S_RX_FIFO_WR_ERR_EN) + +/* GENI_/TX/RX/RX_RFR/_WATERMARK_REG fields */ +#define WATERMARK_MSK GENMASK(5, 0) + +/* GENI_TX_FIFO_STATUS fields */ +#define TX_FIFO_WC GENMASK(27, 0) + +/* GENI_RX_FIFO_STATUS fields */ +#define RX_LAST BIT(31) +#define RX_LAST_BYTE_VALID_MSK GENMASK(30, 28) +#define RX_LAST_BYTE_VALID_SHFT 28 +#define RX_FIFO_WC_MSK GENMASK(24, 0) + +/* SE_GENI_IOS fields */ +#define IO2_DATA_IN BIT(1) +#define RX_DATA_IN BIT(0) + +/* SE_DMA_TX_IRQ_STAT Register fields */ +#define TX_DMA_DONE BIT(0) +#define TX_EOT BIT(1) +#define TX_SBE BIT(2) +#define TX_RESET_DONE BIT(3) + +/* SE_DMA_RX_IRQ_STAT Register fields */ +#define RX_DMA_DONE BIT(0) +#define RX_EOT BIT(1) +#define RX_SBE BIT(2) +#define RX_RESET_DONE BIT(3) +#define RX_FLUSH_DONE BIT(4) +#define RX_DMA_PARITY_ERR BIT(5) +#define RX_DMA_BREAK GENMASK(8, 7) +#define RX_GENI_GP_IRQ GENMASK(10, 5) +#define RX_GENI_CANCEL_IRQ BIT(11) +#define RX_GENI_GP_IRQ_EXT GENMASK(13, 12) + +/* SE_HW_PARAM_0 fields */ +#define TX_FIFO_WIDTH_MSK GENMASK(29, 24) +#define TX_FIFO_WIDTH_SHFT 24 +#define TX_FIFO_DEPTH_MSK GENMASK(21, 16) +#define TX_FIFO_DEPTH_SHFT 16 + +/* SE_HW_PARAM_1 fields */ +#define RX_FIFO_WIDTH_MSK GENMASK(29, 24) +#define RX_FIFO_WIDTH_SHFT 24 +#define RX_FIFO_DEPTH_MSK GENMASK(21, 16) +#define RX_FIFO_DEPTH_SHFT 16 + +#define HW_VER_MAJOR_MASK GENMASK(31, 28) +#define HW_VER_MAJOR_SHFT 28 +#define HW_VER_MINOR_MASK GENMASK(27, 16) +#define HW_VER_MINOR_SHFT 16 +#define HW_VER_STEP_MASK GENMASK(15, 0) + +#define GENI_SE_VERSION_MAJOR(ver) ((ver & HW_VER_MAJOR_MASK) >> HW_VER_MAJOR_SHFT) +#define GENI_SE_VERSION_MINOR(ver) ((ver & HW_VER_MINOR_MASK) >> HW_VER_MINOR_SHFT) +#define GENI_SE_VERSION_STEP(ver) (ver & HW_VER_STEP_MASK) + +/* QUP SE VERSION value for major number 2 and minor number 5 */ +#define QUP_SE_VERSION_2_5 0x20050000 + +/* + * Define bandwidth thresholds that cause the underlying Core 2X interconnect + * clock to run at the named frequency. These baseline values are recommended + * by the hardware team, and are not dynamically scaled with GENI bandwidth + * beyond basic on/off. + */ +#define CORE_2X_19_2_MHZ 960 +#define CORE_2X_50_MHZ 2500 +#define CORE_2X_100_MHZ 5000 +#define CORE_2X_150_MHZ 7500 +#define CORE_2X_200_MHZ 10000 +#define CORE_2X_236_MHZ 16383 + +#define GENI_DEFAULT_BW Bps_to_icc(1000) + +#if IS_ENABLED(CONFIG_QCOM_GENI_SE) + +u32 geni_se_get_qup_hw_version(struct geni_se *se); + +/** + * geni_se_read_proto() - Read the protocol configured for a serial engine + * @se: Pointer to the concerned serial engine. + * + * Return: Protocol value as configured in the serial engine. + */ +static inline u32 geni_se_read_proto(struct geni_se *se) +{ + u32 val; + + val = readl_relaxed(se->base + GENI_FW_REVISION_RO); + + return (val & FW_REV_PROTOCOL_MSK) >> FW_REV_PROTOCOL_SHFT; +} + +/** + * geni_se_setup_m_cmd() - Setup the primary sequencer + * @se: Pointer to the concerned serial engine. + * @cmd: Command/Operation to setup in the primary sequencer. + * @params: Parameter for the sequencer command. + * + * This function is used to configure the primary sequencer with the + * command and its associated parameters. + */ +static inline void geni_se_setup_m_cmd(struct geni_se *se, u32 cmd, u32 params) +{ + u32 m_cmd; + + m_cmd = (cmd << M_OPCODE_SHFT) | (params & M_PARAMS_MSK); + writel(m_cmd, se->base + SE_GENI_M_CMD0); +} + +/** + * geni_se_setup_s_cmd() - Setup the secondary sequencer + * @se: Pointer to the concerned serial engine. + * @cmd: Command/Operation to setup in the secondary sequencer. + * @params: Parameter for the sequencer command. + * + * This function is used to configure the secondary sequencer with the + * command and its associated parameters. + */ +static inline void geni_se_setup_s_cmd(struct geni_se *se, u32 cmd, u32 params) +{ + u32 s_cmd; + + s_cmd = readl_relaxed(se->base + SE_GENI_S_CMD0); + s_cmd &= ~(S_OPCODE_MSK | S_PARAMS_MSK); + s_cmd |= (cmd << S_OPCODE_SHFT); + s_cmd |= (params & S_PARAMS_MSK); + writel(s_cmd, se->base + SE_GENI_S_CMD0); +} + +/** + * geni_se_cancel_m_cmd() - Cancel the command configured in the primary + * sequencer + * @se: Pointer to the concerned serial engine. + * + * This function is used to cancel the currently configured command in the + * primary sequencer. + */ +static inline void geni_se_cancel_m_cmd(struct geni_se *se) +{ + writel_relaxed(M_GENI_CMD_CANCEL, se->base + SE_GENI_M_CMD_CTRL_REG); +} + +/** + * geni_se_cancel_s_cmd() - Cancel the command configured in the secondary + * sequencer + * @se: Pointer to the concerned serial engine. + * + * This function is used to cancel the currently configured command in the + * secondary sequencer. + */ +static inline void geni_se_cancel_s_cmd(struct geni_se *se) +{ + writel_relaxed(S_GENI_CMD_CANCEL, se->base + SE_GENI_S_CMD_CTRL_REG); +} + +/** + * geni_se_abort_m_cmd() - Abort the command configured in the primary sequencer + * @se: Pointer to the concerned serial engine. + * + * This function is used to force abort the currently configured command in the + * primary sequencer. + */ +static inline void geni_se_abort_m_cmd(struct geni_se *se) +{ + writel_relaxed(M_GENI_CMD_ABORT, se->base + SE_GENI_M_CMD_CTRL_REG); +} + +/** + * geni_se_abort_s_cmd() - Abort the command configured in the secondary + * sequencer + * @se: Pointer to the concerned serial engine. + * + * This function is used to force abort the currently configured command in the + * secondary sequencer. + */ +static inline void geni_se_abort_s_cmd(struct geni_se *se) +{ + writel_relaxed(S_GENI_CMD_ABORT, se->base + SE_GENI_S_CMD_CTRL_REG); +} + +/** + * geni_se_get_tx_fifo_depth() - Get the TX fifo depth of the serial engine + * @se: Pointer to the concerned serial engine. + * + * This function is used to get the depth i.e. number of elements in the + * TX fifo of the serial engine. + * + * Return: TX fifo depth in units of FIFO words. + */ +static inline u32 geni_se_get_tx_fifo_depth(struct geni_se *se) +{ + u32 val; + + val = readl_relaxed(se->base + SE_HW_PARAM_0); + + return (val & TX_FIFO_DEPTH_MSK) >> TX_FIFO_DEPTH_SHFT; +} + +/** + * geni_se_get_tx_fifo_width() - Get the TX fifo width of the serial engine + * @se: Pointer to the concerned serial engine. + * + * This function is used to get the width i.e. word size per element in the + * TX fifo of the serial engine. + * + * Return: TX fifo width in bits + */ +static inline u32 geni_se_get_tx_fifo_width(struct geni_se *se) +{ + u32 val; + + val = readl_relaxed(se->base + SE_HW_PARAM_0); + + return (val & TX_FIFO_WIDTH_MSK) >> TX_FIFO_WIDTH_SHFT; +} + +/** + * geni_se_get_rx_fifo_depth() - Get the RX fifo depth of the serial engine + * @se: Pointer to the concerned serial engine. + * + * This function is used to get the depth i.e. number of elements in the + * RX fifo of the serial engine. + * + * Return: RX fifo depth in units of FIFO words + */ +static inline u32 geni_se_get_rx_fifo_depth(struct geni_se *se) +{ + u32 val; + + val = readl_relaxed(se->base + SE_HW_PARAM_1); + + return (val & RX_FIFO_DEPTH_MSK) >> RX_FIFO_DEPTH_SHFT; +} + +void geni_se_init(struct geni_se *se, u32 rx_wm, u32 rx_rfr); + +void geni_se_select_mode(struct geni_se *se, enum geni_se_xfer_mode mode); + +void geni_se_config_packing(struct geni_se *se, int bpw, int pack_words, + bool msb_to_lsb, bool tx_cfg, bool rx_cfg); + +int geni_se_resources_off(struct geni_se *se); + +int geni_se_resources_on(struct geni_se *se); + +int geni_se_clk_tbl_get(struct geni_se *se, unsigned long **tbl); + +int geni_se_clk_freq_match(struct geni_se *se, unsigned long req_freq, + unsigned int *index, unsigned long *res_freq, + bool exact); + +int geni_se_tx_dma_prep(struct geni_se *se, void *buf, size_t len, + dma_addr_t *iova); + +int geni_se_rx_dma_prep(struct geni_se *se, void *buf, size_t len, + dma_addr_t *iova); + +void geni_se_tx_dma_unprep(struct geni_se *se, dma_addr_t iova, size_t len); + +void geni_se_rx_dma_unprep(struct geni_se *se, dma_addr_t iova, size_t len); + +int geni_icc_get(struct geni_se *se, const char *icc_ddr); + +int geni_icc_set_bw(struct geni_se *se); +void geni_icc_set_tag(struct geni_se *se, u32 tag); + +int geni_icc_enable(struct geni_se *se); + +int geni_icc_disable(struct geni_se *se); +#endif +#endif -- cgit v1.2.3 From 2b48f52f2bff8e8926165983f3a3d7b89b33de08 Mon Sep 17 00:00:00 2001 From: Matthew Rosato Date: Fri, 3 Feb 2023 16:50:26 -0500 Subject: vfio: fix deadlock between group lock and kvm lock After 51cdc8bc120e, we have another deadlock scenario between the kvm->lock and the vfio group_lock with two different codepaths acquiring the locks in different order. Specifically in vfio_open_device, vfio holds the vfio group_lock when issuing device->ops->open_device but some drivers (like vfio-ap) need to acquire kvm->lock during their open_device routine; Meanwhile, kvm_vfio_release will acquire the kvm->lock first before calling vfio_file_set_kvm which will acquire the vfio group_lock. To resolve this, let's remove the need for the vfio group_lock from the kvm_vfio_release codepath. This is done by introducing a new spinlock to protect modifications to the vfio group kvm pointer, and acquiring a kvm ref from within vfio while holding this spinlock, with the reference held until the last close for the device in question. Fixes: 51cdc8bc120e ("kvm/vfio: Fix potential deadlock on vfio group_lock") Reported-by: Anthony Krowiak Suggested-by: Jason Gunthorpe Signed-off-by: Matthew Rosato Tested-by: Tony Krowiak Reviewed-by: Kevin Tian Reviewed-by: Yi Liu Link: https://lore.kernel.org/r/20230203215027.151988-2-mjrosato@linux.ibm.com Signed-off-by: Alex Williamson --- drivers/vfio/group.c | 44 +++++++++++++++++++++++++++------ drivers/vfio/vfio.h | 15 ++++++++++++ drivers/vfio/vfio_main.c | 63 ++++++++++++++++++++++++++++++++++++++++++------ include/linux/vfio.h | 2 +- 4 files changed, 109 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/drivers/vfio/group.c b/drivers/vfio/group.c index bb24b2f0271e..98621ac082f0 100644 --- a/drivers/vfio/group.c +++ b/drivers/vfio/group.c @@ -154,6 +154,18 @@ out_unlock: return ret; } +static void vfio_device_group_get_kvm_safe(struct vfio_device *device) +{ + spin_lock(&device->group->kvm_ref_lock); + if (!device->group->kvm) + goto unlock; + + _vfio_device_get_kvm_safe(device, device->group->kvm); + +unlock: + spin_unlock(&device->group->kvm_ref_lock); +} + static int vfio_device_group_open(struct vfio_device *device) { int ret; @@ -164,13 +176,23 @@ static int vfio_device_group_open(struct vfio_device *device) goto out_unlock; } + mutex_lock(&device->dev_set->lock); + /* - * Here we pass the KVM pointer with the group under the lock. If the - * device driver will use it, it must obtain a reference and release it - * during close_device. + * Before the first device open, get the KVM pointer currently + * associated with the group (if there is one) and obtain a reference + * now that will be held until the open_count reaches 0 again. Save + * the pointer in the device for use by drivers. */ - ret = vfio_device_open(device, device->group->iommufd, - device->group->kvm); + if (device->open_count == 0) + vfio_device_group_get_kvm_safe(device); + + ret = vfio_device_open(device, device->group->iommufd, device->kvm); + + if (device->open_count == 0) + vfio_device_put_kvm(device); + + mutex_unlock(&device->dev_set->lock); out_unlock: mutex_unlock(&device->group->group_lock); @@ -180,7 +202,14 @@ out_unlock: void vfio_device_group_close(struct vfio_device *device) { mutex_lock(&device->group->group_lock); + mutex_lock(&device->dev_set->lock); + vfio_device_close(device, device->group->iommufd); + + if (device->open_count == 0) + vfio_device_put_kvm(device); + + mutex_unlock(&device->dev_set->lock); mutex_unlock(&device->group->group_lock); } @@ -450,6 +479,7 @@ static struct vfio_group *vfio_group_alloc(struct iommu_group *iommu_group, refcount_set(&group->drivers, 1); mutex_init(&group->group_lock); + spin_lock_init(&group->kvm_ref_lock); INIT_LIST_HEAD(&group->device_list); mutex_init(&group->device_lock); group->iommu_group = iommu_group; @@ -803,9 +833,9 @@ void vfio_file_set_kvm(struct file *file, struct kvm *kvm) if (!vfio_file_is_group(file)) return; - mutex_lock(&group->group_lock); + spin_lock(&group->kvm_ref_lock); group->kvm = kvm; - mutex_unlock(&group->group_lock); + spin_unlock(&group->kvm_ref_lock); } EXPORT_SYMBOL_GPL(vfio_file_set_kvm); diff --git a/drivers/vfio/vfio.h b/drivers/vfio/vfio.h index d5fa896b5a85..8ec3a5db23f5 100644 --- a/drivers/vfio/vfio.h +++ b/drivers/vfio/vfio.h @@ -74,6 +74,7 @@ struct vfio_group { struct file *opened_file; struct blocking_notifier_head notifier; struct iommufd_ctx *iommufd; + spinlock_t kvm_ref_lock; }; int vfio_device_set_group(struct vfio_device *device, @@ -244,4 +245,18 @@ extern bool vfio_noiommu __read_mostly; enum { vfio_noiommu = false }; #endif +#ifdef CONFIG_HAVE_KVM +void _vfio_device_get_kvm_safe(struct vfio_device *device, struct kvm *kvm); +void vfio_device_put_kvm(struct vfio_device *device); +#else +static inline void _vfio_device_get_kvm_safe(struct vfio_device *device, + struct kvm *kvm) +{ +} + +static inline void vfio_device_put_kvm(struct vfio_device *device) +{ +} +#endif + #endif diff --git a/drivers/vfio/vfio_main.c b/drivers/vfio/vfio_main.c index 5177bb061b17..28c47cd6a6b5 100644 --- a/drivers/vfio/vfio_main.c +++ b/drivers/vfio/vfio_main.c @@ -16,6 +16,9 @@ #include #include #include +#ifdef CONFIG_HAVE_KVM +#include +#endif #include #include #include @@ -338,6 +341,55 @@ void vfio_unregister_group_dev(struct vfio_device *device) } EXPORT_SYMBOL_GPL(vfio_unregister_group_dev); +#ifdef CONFIG_HAVE_KVM +void _vfio_device_get_kvm_safe(struct vfio_device *device, struct kvm *kvm) +{ + void (*pfn)(struct kvm *kvm); + bool (*fn)(struct kvm *kvm); + bool ret; + + lockdep_assert_held(&device->dev_set->lock); + + pfn = symbol_get(kvm_put_kvm); + if (WARN_ON(!pfn)) + return; + + fn = symbol_get(kvm_get_kvm_safe); + if (WARN_ON(!fn)) { + symbol_put(kvm_put_kvm); + return; + } + + ret = fn(kvm); + symbol_put(kvm_get_kvm_safe); + if (!ret) { + symbol_put(kvm_put_kvm); + return; + } + + device->put_kvm = pfn; + device->kvm = kvm; +} + +void vfio_device_put_kvm(struct vfio_device *device) +{ + lockdep_assert_held(&device->dev_set->lock); + + if (!device->kvm) + return; + + if (WARN_ON(!device->put_kvm)) + goto clear; + + device->put_kvm(device->kvm); + device->put_kvm = NULL; + symbol_put(kvm_put_kvm); + +clear: + device->kvm = NULL; +} +#endif + /* true if the vfio_device has open_device() called but not close_device() */ static bool vfio_assert_device_open(struct vfio_device *device) { @@ -361,7 +413,6 @@ static int vfio_device_first_open(struct vfio_device *device, if (ret) goto err_module_put; - device->kvm = kvm; if (device->ops->open_device) { ret = device->ops->open_device(device); if (ret) @@ -370,7 +421,6 @@ static int vfio_device_first_open(struct vfio_device *device, return 0; err_unuse_iommu: - device->kvm = NULL; if (iommufd) vfio_iommufd_unbind(device); else @@ -387,7 +437,6 @@ static void vfio_device_last_close(struct vfio_device *device, if (device->ops->close_device) device->ops->close_device(device); - device->kvm = NULL; if (iommufd) vfio_iommufd_unbind(device); else @@ -400,14 +449,14 @@ int vfio_device_open(struct vfio_device *device, { int ret = 0; - mutex_lock(&device->dev_set->lock); + lockdep_assert_held(&device->dev_set->lock); + device->open_count++; if (device->open_count == 1) { ret = vfio_device_first_open(device, iommufd, kvm); if (ret) device->open_count--; } - mutex_unlock(&device->dev_set->lock); return ret; } @@ -415,12 +464,12 @@ int vfio_device_open(struct vfio_device *device, void vfio_device_close(struct vfio_device *device, struct iommufd_ctx *iommufd) { - mutex_lock(&device->dev_set->lock); + lockdep_assert_held(&device->dev_set->lock); + vfio_assert_device_open(device); if (device->open_count == 1) vfio_device_last_close(device, iommufd); device->open_count--; - mutex_unlock(&device->dev_set->lock); } /* diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 35be78e9ae57..87ff862ff555 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -46,7 +46,6 @@ struct vfio_device { struct vfio_device_set *dev_set; struct list_head dev_set_list; unsigned int migration_flags; - /* Driver must reference the kvm during open_device or never touch it */ struct kvm *kvm; /* Members below here are private, not for driver use */ @@ -58,6 +57,7 @@ struct vfio_device { struct list_head group_next; struct list_head iommu_entry; struct iommufd_access *iommufd_access; + void (*put_kvm)(struct kvm *kvm); #if IS_ENABLED(CONFIG_IOMMUFD) struct iommufd_device *iommufd_device; struct iommufd_ctx *iommufd_ictx; -- cgit v1.2.3 From fae9068022186b832534ea8b325d5242586c4303 Mon Sep 17 00:00:00 2001 From: Yi Liu Date: Thu, 9 Feb 2023 00:12:09 -0800 Subject: vfio: Update the kdoc for vfio_device_ops this is missed when adding bind_iommufd/unbind_iommufd and attach_ioas. Signed-off-by: Yi Liu Reviewed-by: Kevin Tian Link: https://lore.kernel.org/r/20230209081210.141372-2-yi.l.liu@intel.com Signed-off-by: Alex Williamson --- include/linux/vfio.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 87ff862ff555..93134b023968 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -70,6 +70,10 @@ struct vfio_device { * * @init: initialize private fields in device structure * @release: Reclaim private fields in device structure + * @bind_iommufd: Called when binding the device to an iommufd + * @unbind_iommufd: Opposite of bind_iommufd + * @attach_ioas: Called when attaching device to an IOAS/HWPT managed by the + * bound iommufd. Undo in unbind_iommufd. * @open_device: Called when the first file descriptor is opened for this device * @close_device: Opposite of open_device * @read: Perform read(2) on device file descriptor -- cgit v1.2.3 From 19409796578c879a41e88ddbdbce50c19457658d Mon Sep 17 00:00:00 2001 From: Ahmad Fatoum Date: Wed, 23 Nov 2022 10:55:26 +0100 Subject: include/linux/bcd.h: provide bcd_is_valid() helper bcd2bin(0x0A) happily returns 10, despite this being an invalid BCD value. RTC drivers converting possibly corrupted BCD timestamps might want to validate their input before calling bcd2bin(). Provide a macro to do so. Unlike bcd2bin and bin2bcd, out-of-line versions are not implemented. Should the macro experience enough use, this can be retrofitted. Signed-off-by: Ahmad Fatoum Signed-off-by: Sascha Hauer Link: https://lore.kernel.org/r/20221123095527.2771434-2-s.hauer@pengutronix.de Signed-off-by: Alexandre Belloni --- include/linux/bcd.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bcd.h b/include/linux/bcd.h index 118bea36d7d4..abbc8149178e 100644 --- a/include/linux/bcd.h +++ b/include/linux/bcd.h @@ -14,8 +14,12 @@ const_bin2bcd(x) : \ _bin2bcd(x)) +#define bcd_is_valid(x) \ + const_bcd_is_valid(x) + #define const_bcd2bin(x) (((x) & 0x0f) + ((x) >> 4) * 10) #define const_bin2bcd(x) ((((x) / 10) << 4) + (x) % 10) +#define const_bcd_is_valid(x) (((x) & 0x0f) < 10 && ((x) >> 4) < 10) unsigned _bcd2bin(unsigned char val) __attribute_const__; unsigned char _bin2bcd(unsigned val) __attribute_const__; -- cgit v1.2.3 From c643e6ebedb435bcf863001f5e69a578f2658055 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox (Oracle) Date: Fri, 3 Feb 2023 16:28:40 -0500 Subject: mm: fix memcpy_from_file_folio() integer underflow If we have a HIGHMEM system with a large folio, 'offset' may be larger than PAGE_SIZE, and so min_t will cap at 'len' instead of the intended end-of-page. That can overflow into the next page which is likely to be unmapped and fault, but could theoretically copy the wrong data. Link: https://lkml.kernel.org/r/Y919vmSrtAgsf6K3@casper.infradead.org Fixes: 00cdf76012ab ("mm: add memcpy_from_file_folio()") Signed-off-by: Matthew Wilcox (Oracle) Cc: "Fabio M. De Francesco" Cc: Ira Weiny Signed-off-by: Andrew Morton --- include/linux/highmem.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 348701dae77f..b06254e76d99 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -431,9 +431,10 @@ static inline size_t memcpy_from_file_folio(char *to, struct folio *folio, size_t offset = offset_in_folio(folio, pos); char *from = kmap_local_folio(folio, offset); - if (folio_test_highmem(folio)) + if (folio_test_highmem(folio)) { + offset = offset_in_page(offset); len = min_t(size_t, len, PAGE_SIZE - offset); - else + } else len = min(len, folio_size(folio) - offset); memcpy(to, from, len); -- cgit v1.2.3 From e7f43ca99fc8bff2333547bb08dae20a35a23450 Mon Sep 17 00:00:00 2001 From: Liam R. Howlett Date: Fri, 20 Jan 2023 11:26:02 -0500 Subject: maple_tree: add mas_init() function Patch series "VMA tree type safety and remove __vma_adjust()", v4. This patchset does two things: 1. Clean up, including removal of __vma_adjust() and 2. Extends the VMA iterator API to provide type safety to the VMA operations using the maple tree, as requested by Linus [1]. It also addresses another issue of usability brought up by Linus about needing to modify the maple state within the loops. The maple state has been replaced by the VMA iterator and the iterator is now modified within the MM code so the caller should not need to worry about doing the work themselves when tree modifications occur. This brought up a potential inconsistency of the iterator state and what the user expects, so the inconsistency is addressed to keep the VMA iterator safe for use after the looping over a VMA range. This is addressed in patch 3 ("maple_tree: Reduce user error potential") and 4 ("test_maple_tree: Test modifications while iterating"). While cleaning up the state, the duplicate locking code in mm/mmap.c introduced by the maple tree has been address by abstracting it to two functions: vma_prepare() and vma_complete(). These abstractions allowed for a much simpler __vma_adjust(), which eventually leads to the removal of the __vma_adjust() function by placing the logic into the vma_merge() function itself. 1. https://lore.kernel.org/linux-mm/CAHk-=wg9WQXBGkNdKD2bqocnN73rDswuWsavBB7T-tekykEn_A@mail.gmail.com/ This patch (of 49): Add a function that will zero out the maple state struct and set some basic defaults. Link: https://lkml.kernel.org/r/20230120162650.984577-1-Liam.Howlett@oracle.com Link: https://lkml.kernel.org/r/20230120162650.984577-2-Liam.Howlett@oracle.com Signed-off-by: Liam R. Howlett Signed-off-by: Andrew Morton --- include/linux/maple_tree.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/maple_tree.h b/include/linux/maple_tree.h index a7bf58fd7cc6..1fadb5f5978b 100644 --- a/include/linux/maple_tree.h +++ b/include/linux/maple_tree.h @@ -432,6 +432,7 @@ struct ma_wr_state { .min = 0, \ .max = ULONG_MAX, \ .alloc = NULL, \ + .mas_flags = 0, \ } #define MA_WR_STATE(name, ma_state, wr_entry) \ @@ -470,6 +471,16 @@ void *mas_next(struct ma_state *mas, unsigned long max); int mas_empty_area(struct ma_state *mas, unsigned long min, unsigned long max, unsigned long size); +static inline void mas_init(struct ma_state *mas, struct maple_tree *tree, + unsigned long addr) +{ + memset(mas, 0, sizeof(struct ma_state)); + mas->tree = tree; + mas->index = mas->last = addr; + mas->max = ULONG_MAX; + mas->node = MAS_START; +} + /* Checks if a mas has not found anything */ static inline bool mas_is_none(struct ma_state *mas) { -- cgit v1.2.3 From b62b633e048bbddef90b2e55d2e33823187b425f Mon Sep 17 00:00:00 2001 From: Liam R. Howlett Date: Fri, 20 Jan 2023 11:26:08 -0500 Subject: mm: expand vma iterator interface Add wrappers for the maple tree to the vma iterator. This will provide type safety at compile time. Link: https://lkml.kernel.org/r/20230120162650.984577-8-Liam.Howlett@oracle.com Signed-off-by: Liam R. Howlett Signed-off-by: Andrew Morton --- include/linux/mm.h | 46 +++++++++++++++++++++++++++++++--- include/linux/mm_types.h | 4 +-- mm/internal.h | 64 ++++++++++++++++++++++++++++++++++++++++++++++++ mm/mmap.c | 18 ++++++++++++++ 4 files changed, 125 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index c9db257f09b3..b977a90d9829 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -670,16 +670,16 @@ static inline bool vma_is_accessible(struct vm_area_struct *vma) static inline struct vm_area_struct *vma_find(struct vma_iterator *vmi, unsigned long max) { - return mas_find(&vmi->mas, max); + return mas_find(&vmi->mas, max - 1); } static inline struct vm_area_struct *vma_next(struct vma_iterator *vmi) { /* - * Uses vma_find() to get the first VMA when the iterator starts. + * Uses mas_find() to get the first VMA when the iterator starts. * Calling mas_next() could skip the first entry. */ - return vma_find(vmi, ULONG_MAX); + return mas_find(&vmi->mas, ULONG_MAX); } static inline struct vm_area_struct *vma_prev(struct vma_iterator *vmi) @@ -692,12 +692,50 @@ static inline unsigned long vma_iter_addr(struct vma_iterator *vmi) return vmi->mas.index; } +static inline unsigned long vma_iter_end(struct vma_iterator *vmi) +{ + return vmi->mas.last + 1; +} +static inline int vma_iter_bulk_alloc(struct vma_iterator *vmi, + unsigned long count) +{ + return mas_expected_entries(&vmi->mas, count); +} + +/* Free any unused preallocations */ +static inline void vma_iter_free(struct vma_iterator *vmi) +{ + mas_destroy(&vmi->mas); +} + +static inline int vma_iter_bulk_store(struct vma_iterator *vmi, + struct vm_area_struct *vma) +{ + vmi->mas.index = vma->vm_start; + vmi->mas.last = vma->vm_end - 1; + mas_store(&vmi->mas, vma); + if (unlikely(mas_is_err(&vmi->mas))) + return -ENOMEM; + + return 0; +} + +static inline void vma_iter_invalidate(struct vma_iterator *vmi) +{ + mas_pause(&vmi->mas); +} + +static inline void vma_iter_set(struct vma_iterator *vmi, unsigned long addr) +{ + mas_set(&vmi->mas, addr); +} + #define for_each_vma(__vmi, __vma) \ while (((__vma) = vma_next(&(__vmi))) != NULL) /* The MM code likes to work with exclusive end addresses */ #define for_each_vma_range(__vmi, __vma, __end) \ - while (((__vma) = vma_find(&(__vmi), (__end) - 1)) != NULL) + while (((__vma) = vma_find(&(__vmi), (__end))) != NULL) #ifdef CONFIG_SHMEM /* diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 452920467223..5ca11c6c46e8 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -849,9 +849,7 @@ struct vma_iterator { static inline void vma_iter_init(struct vma_iterator *vmi, struct mm_struct *mm, unsigned long addr) { - vmi->mas.tree = &mm->mm_mt; - vmi->mas.index = addr; - vmi->mas.node = MAS_START; + mas_init(&vmi->mas, &mm->mm_mt, addr); } struct mmu_gather; diff --git a/mm/internal.h b/mm/internal.h index 2d1b9fa8083e..ffd65248f266 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -877,4 +877,68 @@ static inline bool vma_soft_dirty_enabled(struct vm_area_struct *vma) return !(vma->vm_flags & VM_SOFTDIRTY); } +/* + * VMA Iterator functions shared between nommu and mmap + */ +static inline int vma_iter_prealloc(struct vma_iterator *vmi) +{ + return mas_preallocate(&vmi->mas, GFP_KERNEL); +} + +static inline void vma_iter_clear(struct vma_iterator *vmi, + unsigned long start, unsigned long end) +{ + mas_set_range(&vmi->mas, start, end - 1); + mas_store_prealloc(&vmi->mas, NULL); +} + +static inline struct vm_area_struct *vma_iter_load(struct vma_iterator *vmi) +{ + return mas_walk(&vmi->mas); +} + +/* Store a VMA with preallocated memory */ +static inline void vma_iter_store(struct vma_iterator *vmi, + struct vm_area_struct *vma) +{ + +#if defined(CONFIG_DEBUG_VM_MAPLE_TREE) + if (WARN_ON(vmi->mas.node != MAS_START && vmi->mas.index > vma->vm_start)) { + printk("%lu > %lu\n", vmi->mas.index, vma->vm_start); + printk("store of vma %lu-%lu", vma->vm_start, vma->vm_end); + printk("into slot %lu-%lu", vmi->mas.index, vmi->mas.last); + mt_dump(vmi->mas.tree); + } + if (WARN_ON(vmi->mas.node != MAS_START && vmi->mas.last < vma->vm_start)) { + printk("%lu < %lu\n", vmi->mas.last, vma->vm_start); + printk("store of vma %lu-%lu", vma->vm_start, vma->vm_end); + printk("into slot %lu-%lu", vmi->mas.index, vmi->mas.last); + mt_dump(vmi->mas.tree); + } +#endif + + if (vmi->mas.node != MAS_START && + ((vmi->mas.index > vma->vm_start) || (vmi->mas.last < vma->vm_start))) + vma_iter_invalidate(vmi); + + vmi->mas.index = vma->vm_start; + vmi->mas.last = vma->vm_end - 1; + mas_store_prealloc(&vmi->mas, vma); +} + +static inline int vma_iter_store_gfp(struct vma_iterator *vmi, + struct vm_area_struct *vma, gfp_t gfp) +{ + if (vmi->mas.node != MAS_START && + ((vmi->mas.index > vma->vm_start) || (vmi->mas.last < vma->vm_start))) + vma_iter_invalidate(vmi); + + vmi->mas.index = vma->vm_start; + vmi->mas.last = vma->vm_end - 1; + mas_store_gfp(&vmi->mas, vma, gfp); + if (unlikely(mas_is_err(&vmi->mas))) + return -ENOMEM; + + return 0; +} #endif /* __MM_INTERNAL_H */ diff --git a/mm/mmap.c b/mm/mmap.c index ffc0815cd7fb..db70f3e2181e 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -144,6 +144,24 @@ static void remove_vma(struct vm_area_struct *vma) vm_area_free(vma); } +static inline struct vm_area_struct *vma_prev_limit(struct vma_iterator *vmi, + unsigned long min) +{ + return mas_prev(&vmi->mas, min); +} + +static inline int vma_iter_clear_gfp(struct vma_iterator *vmi, + unsigned long start, unsigned long end, gfp_t gfp) +{ + vmi->mas.index = start; + vmi->mas.last = end - 1; + mas_store_gfp(&vmi->mas, NULL, gfp); + if (unlikely(mas_is_err(&vmi->mas))) + return -ENOMEM; + + return 0; +} + /* * check_brk_limits() - Use platform specific check of range & verify mlock * limits. -- cgit v1.2.3 From 183654ce26a5d5bd7bc11bcb02e8086f02f66d7d Mon Sep 17 00:00:00 2001 From: Liam R. Howlett Date: Fri, 20 Jan 2023 11:26:13 -0500 Subject: mmap: change do_mas_munmap and do_mas_aligned_munmap() to use vma iterator Start passing the vma iterator through the mm code. This will allow for reuse of the state and cleaner invalidation if necessary. Link: https://lkml.kernel.org/r/20230120162650.984577-13-Liam.Howlett@oracle.com Signed-off-by: Liam R. Howlett Signed-off-by: Andrew Morton --- include/linux/mm.h | 2 +- mm/mmap.c | 77 +++++++++++++++++++++++++----------------------------- mm/mremap.c | 6 ++--- 3 files changed, 39 insertions(+), 46 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index b977a90d9829..152a1362b800 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2905,7 +2905,7 @@ extern unsigned long mmap_region(struct file *file, unsigned long addr, extern unsigned long do_mmap(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, unsigned long pgoff, unsigned long *populate, struct list_head *uf); -extern int do_mas_munmap(struct ma_state *mas, struct mm_struct *mm, +extern int do_vmi_munmap(struct vma_iterator *vmi, struct mm_struct *mm, unsigned long start, size_t len, struct list_head *uf, bool downgrade); extern int do_munmap(struct mm_struct *, unsigned long, size_t, diff --git a/mm/mmap.c b/mm/mmap.c index d46a798c38ab..5b83023ba6a6 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2305,8 +2305,8 @@ static inline int munmap_sidetree(struct vm_area_struct *vma, } /* - * do_mas_align_munmap() - munmap the aligned region from @start to @end. - * @mas: The maple_state, ideally set up to alter the correct tree location. + * do_vmi_align_munmap() - munmap the aligned region from @start to @end. + * @vmi: The vma iterator * @vma: The starting vm_area_struct * @mm: The mm_struct * @start: The aligned start address to munmap. @@ -2317,7 +2317,7 @@ static inline int munmap_sidetree(struct vm_area_struct *vma, * If @downgrade is true, check return code for potential release of the lock. */ static int -do_mas_align_munmap(struct ma_state *mas, struct vm_area_struct *vma, +do_vmi_align_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma, struct mm_struct *mm, unsigned long start, unsigned long end, struct list_head *uf, bool downgrade) { @@ -2329,7 +2329,6 @@ do_mas_align_munmap(struct ma_state *mas, struct vm_area_struct *vma, mt_init_flags(&mt_detach, MT_FLAGS_LOCK_EXTERN); mt_set_external_lock(&mt_detach, &mm->mmap_lock); - mas->last = end - 1; /* * If we need to split any vma, do it now to save pain later. * @@ -2349,27 +2348,23 @@ do_mas_align_munmap(struct ma_state *mas, struct vm_area_struct *vma, if (end < vma->vm_end && mm->map_count >= sysctl_max_map_count) goto map_count_exceeded; - /* - * mas_pause() is not needed since mas->index needs to be set - * differently than vma->vm_end anyways. - */ error = __split_vma(mm, vma, start, 0); if (error) goto start_split_failed; - mas_set(mas, start); - vma = mas_walk(mas); + vma_iter_set(vmi, start); + vma = vma_find(vmi, end); } - prev = mas_prev(mas, 0); + prev = vma_prev(vmi); if (unlikely((!prev))) - mas_set(mas, start); + vma_iter_set(vmi, start); /* * Detach a range of VMAs from the mm. Using next as a temp variable as * it is always overwritten. */ - mas_for_each(mas, next, end - 1) { + for_each_vma_range(*vmi, next, end) { /* Does it split the end? */ if (next->vm_end > end) { struct vm_area_struct *split; @@ -2378,8 +2373,8 @@ do_mas_align_munmap(struct ma_state *mas, struct vm_area_struct *vma, if (error) goto end_split_failed; - mas_set(mas, end); - split = mas_prev(mas, 0); + vma_iter_set(vmi, end); + split = vma_prev(vmi); error = munmap_sidetree(split, &mas_detach); if (error) goto munmap_sidetree_failed; @@ -2401,7 +2396,7 @@ do_mas_align_munmap(struct ma_state *mas, struct vm_area_struct *vma, } if (!next) - next = mas_next(mas, ULONG_MAX); + next = vma_next(vmi); if (unlikely(uf)) { /* @@ -2426,10 +2421,10 @@ do_mas_align_munmap(struct ma_state *mas, struct vm_area_struct *vma, struct vm_area_struct *vma_mas, *vma_test; int test_count = 0; - mas_set_range(mas, start, end - 1); + vma_iter_set(vmi, start); rcu_read_lock(); vma_test = mas_find(&test, end - 1); - mas_for_each(mas, vma_mas, end - 1) { + for_each_vma_range(*vmi, vma_mas, end) { BUG_ON(vma_mas != vma_test); test_count++; vma_test = mas_next(&test, end - 1); @@ -2439,8 +2434,8 @@ do_mas_align_munmap(struct ma_state *mas, struct vm_area_struct *vma, } #endif /* Point of no return */ - mas_set_range(mas, start, end - 1); - if (mas_store_gfp(mas, NULL, GFP_KERNEL)) + vma_iter_set(vmi, start); + if (vma_iter_clear_gfp(vmi, start, end, GFP_KERNEL)) return -ENOMEM; mm->map_count -= count; @@ -2478,8 +2473,8 @@ map_count_exceeded: } /* - * do_mas_munmap() - munmap a given range. - * @mas: The maple state + * do_vmi_munmap() - munmap a given range. + * @vmi: The vma iterator * @mm: The mm_struct * @start: The start address to munmap * @len: The length of the range to munmap @@ -2493,7 +2488,7 @@ map_count_exceeded: * * Returns: -EINVAL on failure, 1 on success and unlock, 0 otherwise. */ -int do_mas_munmap(struct ma_state *mas, struct mm_struct *mm, +int do_vmi_munmap(struct vma_iterator *vmi, struct mm_struct *mm, unsigned long start, size_t len, struct list_head *uf, bool downgrade) { @@ -2511,11 +2506,11 @@ int do_mas_munmap(struct ma_state *mas, struct mm_struct *mm, arch_unmap(mm, start, end); /* Find the first overlapping VMA */ - vma = mas_find(mas, end - 1); + vma = vma_find(vmi, end); if (!vma) return 0; - return do_mas_align_munmap(mas, vma, mm, start, end, uf, downgrade); + return do_vmi_align_munmap(vmi, vma, mm, start, end, uf, downgrade); } /* do_munmap() - Wrapper function for non-maple tree aware do_munmap() calls. @@ -2527,9 +2522,9 @@ int do_mas_munmap(struct ma_state *mas, struct mm_struct *mm, int do_munmap(struct mm_struct *mm, unsigned long start, size_t len, struct list_head *uf) { - MA_STATE(mas, &mm->mm_mt, start, start); + VMA_ITERATOR(vmi, mm, start); - return do_mas_munmap(&mas, mm, start, len, uf, false); + return do_vmi_munmap(&vmi, mm, start, len, uf, false); } unsigned long mmap_region(struct file *file, unsigned long addr, @@ -2545,7 +2540,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr, unsigned long merge_start = addr, merge_end = end; pgoff_t vm_pgoff; int error; - MA_STATE(mas, &mm->mm_mt, addr, end - 1); + VMA_ITERATOR(vmi, mm, addr); /* Check against address space limit. */ if (!may_expand_vm(mm, vm_flags, len >> PAGE_SHIFT)) { @@ -2563,7 +2558,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr, } /* Unmap any existing mapping in the area */ - if (do_mas_munmap(&mas, mm, addr, len, uf, false)) + if (do_vmi_munmap(&vmi, mm, addr, len, uf, false)) return -ENOMEM; /* @@ -2576,8 +2571,8 @@ unsigned long mmap_region(struct file *file, unsigned long addr, vm_flags |= VM_ACCOUNT; } - next = mas_next(&mas, ULONG_MAX); - prev = mas_prev(&mas, 0); + next = vma_next(&vmi); + prev = vma_prev(&vmi); if (vm_flags & VM_SPECIAL) goto cannot_expand; @@ -2605,13 +2600,11 @@ unsigned long mmap_region(struct file *file, unsigned long addr, /* Actually expand, if possible */ if (vma && - !vma_expand(&mas, vma, merge_start, merge_end, vm_pgoff, next)) { + !vma_expand(&vmi.mas, vma, merge_start, merge_end, vm_pgoff, next)) { khugepaged_enter_vma(vma, vm_flags); goto expanded; } - mas.index = addr; - mas.last = end - 1; cannot_expand: /* * Determine the object being mapped and call the appropriate @@ -2650,7 +2643,7 @@ cannot_expand: error = -EINVAL; goto close_and_free_vma; } - mas_reset(&mas); + vma_iter_set(&vmi, addr); /* * If vm_flags changed after call_mmap(), we should try merge @@ -2706,7 +2699,7 @@ cannot_expand: goto free_vma; } - if (mas_preallocate(&mas, GFP_KERNEL)) { + if (vma_iter_prealloc(&vmi)) { error = -ENOMEM; if (file) goto close_and_free_vma; @@ -2719,7 +2712,7 @@ cannot_expand: if (vma->vm_file) i_mmap_lock_write(vma->vm_file->f_mapping); - vma_mas_store(vma, &mas); + vma_iter_store(&vmi, vma); mm->map_count++; if (vma->vm_file) { if (vma->vm_flags & VM_SHARED) @@ -2780,7 +2773,7 @@ unmap_and_free_vma: vma->vm_file = NULL; /* Undo any partial mapping done by a device driver. */ - unmap_region(mm, mas.tree, vma, prev, next, vma->vm_start, vma->vm_end); + unmap_region(mm, &mm->mm_mt, vma, prev, next, vma->vm_start, vma->vm_end); if (file && (vm_flags & VM_SHARED)) mapping_unmap_writable(file->f_mapping); free_vma: @@ -2797,12 +2790,12 @@ static int __vm_munmap(unsigned long start, size_t len, bool downgrade) int ret; struct mm_struct *mm = current->mm; LIST_HEAD(uf); - MA_STATE(mas, &mm->mm_mt, start, start); + VMA_ITERATOR(vmi, mm, start); if (mmap_write_lock_killable(mm)) return -EINTR; - ret = do_mas_munmap(&mas, mm, start, len, &uf, downgrade); + ret = do_vmi_munmap(&vmi, mm, start, len, &uf, downgrade); /* * Returning 1 indicates mmap_lock is downgraded. * But 1 is not legal return value of vm_munmap() and munmap(), reset @@ -2934,7 +2927,7 @@ static int do_brk_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma, int ret; arch_unmap(mm, newbrk, oldbrk); - ret = do_mas_align_munmap(&vmi->mas, vma, mm, newbrk, oldbrk, uf, true); + ret = do_vmi_align_munmap(vmi, vma, mm, newbrk, oldbrk, uf, true); validate_mm_mt(mm); return ret; } @@ -3057,7 +3050,7 @@ int vm_brk_flags(unsigned long addr, unsigned long request, unsigned long flags) if (ret) goto limits_failed; - ret = do_mas_munmap(&vmi.mas, mm, addr, len, &uf, 0); + ret = do_vmi_munmap(&vmi, mm, addr, len, &uf, 0); if (ret) goto munmap_failed; diff --git a/mm/mremap.c b/mm/mremap.c index 05f90f47e149..3cc64c3f8bdb 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -978,14 +978,14 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, /* * Always allow a shrinking remap: that just unmaps * the unnecessary pages.. - * do_mas_munmap does all the needed commit accounting, and + * do_vmi_munmap does all the needed commit accounting, and * downgrades mmap_lock to read if so directed. */ if (old_len >= new_len) { int retval; - MA_STATE(mas, &mm->mm_mt, addr + new_len, addr + new_len); + VMA_ITERATOR(vmi, mm, addr + new_len); - retval = do_mas_munmap(&mas, mm, addr + new_len, + retval = do_vmi_munmap(&vmi, mm, addr + new_len, old_len - new_len, &uf_unmap, true); /* Returning 1 indicates mmap_lock is downgraded to read. */ if (retval == 1) { -- cgit v1.2.3 From f2ebfe43ba6c845e70b6acbabd6c69ab74b3c52e Mon Sep 17 00:00:00 2001 From: Liam R. Howlett Date: Fri, 20 Jan 2023 11:26:15 -0500 Subject: mm: add temporary vma iterator versions of vma_merge(), split_vma(), and __split_vma() These wrappers are short-lived in this patch set so that each user can be converted on its own. In the end, these functions are renamed in one commit. Link: https://lkml.kernel.org/r/20230120162650.984577-15-Liam.Howlett@oracle.com Signed-off-by: Liam R. Howlett Signed-off-by: Andrew Morton --- include/linux/mm.h | 11 ++++++++++- mm/mmap.c | 44 ++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 54 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 152a1362b800..956025940053 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2843,11 +2843,20 @@ extern struct vm_area_struct *vma_merge(struct mm_struct *, struct vm_area_struct *prev, unsigned long addr, unsigned long end, unsigned long vm_flags, struct anon_vma *, struct file *, pgoff_t, struct mempolicy *, struct vm_userfaultfd_ctx, struct anon_vma_name *); +extern struct vm_area_struct *vmi_vma_merge(struct vma_iterator *vmi, + struct mm_struct *, struct vm_area_struct *prev, unsigned long addr, + unsigned long end, unsigned long vm_flags, struct anon_vma *, + struct file *, pgoff_t, struct mempolicy *, struct vm_userfaultfd_ctx, + struct anon_vma_name *); extern struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *); extern int __split_vma(struct mm_struct *, struct vm_area_struct *, - unsigned long addr, int new_below); + unsigned long addr, int new_below); +extern int vmi__split_vma(struct vma_iterator *vmi, struct mm_struct *, + struct vm_area_struct *, unsigned long addr, int new_below); extern int split_vma(struct mm_struct *, struct vm_area_struct *, unsigned long addr, int new_below); +extern int vmi_split_vma(struct vma_iterator *vmi, struct mm_struct *, + struct vm_area_struct *, unsigned long addr, int new_below); extern int insert_vm_struct(struct mm_struct *, struct vm_area_struct *); extern void unlink_file_vma(struct vm_area_struct *); extern struct vm_area_struct *copy_vma(struct vm_area_struct **, diff --git a/mm/mmap.c b/mm/mmap.c index 7e406416cf47..894017841d5d 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1091,6 +1091,25 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm, return res; } +struct vm_area_struct *vmi_vma_merge(struct vma_iterator *vmi, + struct mm_struct *mm, + struct vm_area_struct *prev, unsigned long addr, + unsigned long end, unsigned long vm_flags, + struct anon_vma *anon_vma, struct file *file, + pgoff_t pgoff, struct mempolicy *policy, + struct vm_userfaultfd_ctx vm_userfaultfd_ctx, + struct anon_vma_name *anon_name) +{ + struct vm_area_struct *tmp; + + tmp = vma_merge(mm, prev, addr, end, vm_flags, anon_vma, file, pgoff, + policy, vm_userfaultfd_ctx, anon_name); + if (tmp) + vma_iter_set(vmi, end); + + return tmp; +} + /* * Rough compatibility check to quickly see if it's even worth looking * at sharing an anon_vma. @@ -2276,6 +2295,18 @@ int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma, validate_mm_mt(mm); return err; } +int vmi__split_vma(struct vma_iterator *vmi, struct mm_struct *mm, + struct vm_area_struct *vma, unsigned long addr, int new_below) +{ + int ret; + unsigned long end = vma->vm_end; + + ret = __split_vma(mm, vma, addr, new_below); + if (!ret) + vma_iter_set(vmi, end); + + return ret; +} /* * Split a vma into two pieces at address 'addr', a new vma is allocated @@ -2290,6 +2321,19 @@ int split_vma(struct mm_struct *mm, struct vm_area_struct *vma, return __split_vma(mm, vma, addr, new_below); } +int vmi_split_vma(struct vma_iterator *vmi, struct mm_struct *mm, + struct vm_area_struct *vma, unsigned long addr, int new_below) +{ + int ret; + unsigned long end = vma->vm_end; + + ret = split_vma(mm, vma, addr, new_below); + if (!ret) + vma_iter_set(vmi, end); + + return ret; +} + static inline int munmap_sidetree(struct vm_area_struct *vma, struct ma_state *mas_detach) { -- cgit v1.2.3 From 27b267011296e35dd5c983bf6c53b7230c78f383 Mon Sep 17 00:00:00 2001 From: Liam R. Howlett Date: Thu, 26 Jan 2023 16:20:49 -0500 Subject: ipc/shm: introduce new do_vma_munmap() to munmap The shm already has the vma iterator in position for a write. do_vmi_munmap() searches for the correct position and aligns the write, so it is not the right function to use in this case. The shm VMA tree modification is similar to the brk munmap situation, the vma iterator is in position and the VMA is already known. This patch generalizes the brk munmap function do_brk_munmap() to be used for any other callers with the vma iterator already in position to munmap a VMA. Link: https://lkml.kernel.org/r/20230126212049.980501-1-Liam.Howlett@oracle.com Signed-off-by: Liam R. Howlett Reported-by: Sven Schnelle Link: https://lore.kernel.org/linux-mm/yt9dh6wec21a.fsf@linux.ibm.com/ Cc: Arnd Bergmann Signed-off-by: Andrew Morton --- include/linux/mm.h | 3 +++ ipc/shm.c | 11 ++++++----- mm/mmap.c | 38 ++++++++++++++++++-------------------- 3 files changed, 27 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 956025940053..5b5f26d6588a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2922,6 +2922,9 @@ extern int do_munmap(struct mm_struct *, unsigned long, size_t, extern int do_madvise(struct mm_struct *mm, unsigned long start, size_t len_in, int behavior); #ifdef CONFIG_MMU +extern int do_vma_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma, + unsigned long start, unsigned long end, + struct list_head *uf, bool downgrade); extern int __mm_populate(unsigned long addr, unsigned long len, int ignore_errors); static inline void mm_populate(unsigned long addr, unsigned long len) diff --git a/ipc/shm.c b/ipc/shm.c index 1c6a6b319a49..60e45e7045d4 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -1786,8 +1786,8 @@ long ksys_shmdt(char __user *shmaddr) */ file = vma->vm_file; size = i_size_read(file_inode(vma->vm_file)); - do_vmi_munmap(&vmi, mm, vma->vm_start, - vma->vm_end - vma->vm_start, NULL, false); + do_vma_munmap(&vmi, vma, vma->vm_start, vma->vm_end, + NULL, false); /* * We discovered the size of the shm segment, so * break out of here and fall through to the next @@ -1810,9 +1810,10 @@ long ksys_shmdt(char __user *shmaddr) /* finding a matching vma now does not alter retval */ if ((vma->vm_ops == &shm_vm_ops) && ((vma->vm_start - addr)/PAGE_SIZE == vma->vm_pgoff) && - (vma->vm_file == file)) - do_vmi_munmap(&vmi, mm, vma->vm_start, - vma->vm_end - vma->vm_start, NULL, false); + (vma->vm_file == file)) { + do_vma_munmap(&vmi, vma, vma->vm_start, vma->vm_end, + NULL, false); + } vma = vma_next(&vmi); } diff --git a/mm/mmap.c b/mm/mmap.c index 894017841d5d..408e9cc47333 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -180,9 +180,6 @@ static int check_brk_limits(unsigned long addr, unsigned long len) return mlock_future_check(current->mm, current->mm->def_flags, len); } -static int do_brk_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma, - unsigned long newbrk, unsigned long oldbrk, - struct list_head *uf); static int do_brk_flags(struct vma_iterator *vmi, struct vm_area_struct *brkvma, unsigned long addr, unsigned long request, unsigned long flags); SYSCALL_DEFINE1(brk, unsigned long, brk) @@ -236,7 +233,7 @@ SYSCALL_DEFINE1(brk, unsigned long, brk) /* * Always allow shrinking brk. - * do_brk_munmap() may downgrade mmap_lock to read. + * do_vma_munmap() may downgrade mmap_lock to read. */ if (brk <= mm->brk) { int ret; @@ -248,11 +245,11 @@ SYSCALL_DEFINE1(brk, unsigned long, brk) goto out; /* mapping intersects with an existing non-brk vma. */ /* * mm->brk must be protected by write mmap_lock. - * do_brk_munmap() may downgrade the lock, so update it - * before calling do_brk_munmap(). + * do_vma_munmap() may downgrade the lock, so update it + * before calling do_vma_munmap(). */ mm->brk = brk; - ret = do_brk_munmap(&vmi, brkvma, newbrk, oldbrk, &uf); + ret = do_vma_munmap(&vmi, brkvma, newbrk, oldbrk, &uf, true); if (ret == 1) { downgraded = true; goto success; @@ -2951,26 +2948,27 @@ out: } /* - * brk_munmap() - Unmap a full or partial vma. - * @vmi: The vma iterator - * @vma: The vma to be modified - * @newbrk: the start of the address to unmap - * @oldbrk: The end of the address to unmap + * do_vma_munmap() - Unmap a full or partial vma. + * @vmi: The vma iterator pointing at the vma + * @vma: The first vma to be munmapped + * @start: the start of the address to unmap + * @end: The end of the address to unmap * @uf: The userfaultfd list_head + * @downgrade: Attempt to downgrade or not * - * Returns: 1 on success. - * unmaps a partial VMA mapping. Does not handle alignment, downgrades lock if - * possible. + * Returns: 0 on success and not downgraded, 1 on success and downgraded. + * unmaps a VMA mapping when the vma iterator is already in position. + * Does not handle alignment. */ -static int do_brk_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma, - unsigned long newbrk, unsigned long oldbrk, - struct list_head *uf) +int do_vma_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma, + unsigned long start, unsigned long end, + struct list_head *uf, bool downgrade) { struct mm_struct *mm = vma->vm_mm; int ret; - arch_unmap(mm, newbrk, oldbrk); - ret = do_vmi_align_munmap(vmi, vma, mm, newbrk, oldbrk, uf, true); + arch_unmap(mm, start, end); + ret = do_vmi_align_munmap(vmi, vma, mm, start, end, uf, downgrade); validate_mm_mt(mm); return ret; } -- cgit v1.2.3 From 2286a6914c776ec34cd97e4573b1466d055cb9de Mon Sep 17 00:00:00 2001 From: Liam R. Howlett Date: Fri, 20 Jan 2023 11:26:18 -0500 Subject: mm: change mprotect_fixup to vma iterator Use the vma iterator so that the iterator can be invalidated or updated to avoid each caller doing so. Link: https://lkml.kernel.org/r/20230120162650.984577-18-Liam.Howlett@oracle.com Signed-off-by: Liam R. Howlett Signed-off-by: Andrew Morton --- fs/exec.c | 5 ++++- include/linux/mm.h | 6 +++--- mm/mprotect.c | 47 ++++++++++++++++++++++------------------------- 3 files changed, 29 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/fs/exec.c b/fs/exec.c index ab913243a367..b98647eeae9f 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -758,6 +758,7 @@ int setup_arg_pages(struct linux_binprm *bprm, unsigned long stack_expand; unsigned long rlim_stack; struct mmu_gather tlb; + struct vma_iterator vmi; #ifdef CONFIG_STACK_GROWSUP /* Limit stack size */ @@ -812,8 +813,10 @@ int setup_arg_pages(struct linux_binprm *bprm, vm_flags |= mm->def_flags; vm_flags |= VM_STACK_INCOMPLETE_SETUP; + vma_iter_init(&vmi, mm, vma->vm_start); + tlb_gather_mmu(&tlb, mm); - ret = mprotect_fixup(&tlb, vma, &prev, vma->vm_start, vma->vm_end, + ret = mprotect_fixup(&vmi, &tlb, vma, &prev, vma->vm_start, vma->vm_end, vm_flags); tlb_finish_mmu(&tlb); diff --git a/include/linux/mm.h b/include/linux/mm.h index 5b5f26d6588a..144ddfd65992 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2197,9 +2197,9 @@ bool can_change_pte_writable(struct vm_area_struct *vma, unsigned long addr, extern long change_protection(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, unsigned long end, unsigned long cp_flags); -extern int mprotect_fixup(struct mmu_gather *tlb, struct vm_area_struct *vma, - struct vm_area_struct **pprev, unsigned long start, - unsigned long end, unsigned long newflags); +extern int mprotect_fixup(struct vma_iterator *vmi, struct mmu_gather *tlb, + struct vm_area_struct *vma, struct vm_area_struct **pprev, + unsigned long start, unsigned long end, unsigned long newflags); /* * doesn't attempt to fault and will return short. diff --git a/mm/mprotect.c b/mm/mprotect.c index 6a22f3ad9b84..39b6335b8813 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -585,9 +585,9 @@ static const struct mm_walk_ops prot_none_walk_ops = { }; int -mprotect_fixup(struct mmu_gather *tlb, struct vm_area_struct *vma, - struct vm_area_struct **pprev, unsigned long start, - unsigned long end, unsigned long newflags) +mprotect_fixup(struct vma_iterator *vmi, struct mmu_gather *tlb, + struct vm_area_struct *vma, struct vm_area_struct **pprev, + unsigned long start, unsigned long end, unsigned long newflags) { struct mm_struct *mm = vma->vm_mm; unsigned long oldflags = vma->vm_flags; @@ -642,7 +642,7 @@ mprotect_fixup(struct mmu_gather *tlb, struct vm_area_struct *vma, * First try to merge with previous and/or next vma. */ pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); - *pprev = vma_merge(mm, *pprev, start, end, newflags, + *pprev = vmi_vma_merge(vmi, mm, *pprev, start, end, newflags, vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), vma->vm_userfaultfd_ctx, anon_vma_name(vma)); if (*pprev) { @@ -654,13 +654,13 @@ mprotect_fixup(struct mmu_gather *tlb, struct vm_area_struct *vma, *pprev = vma; if (start != vma->vm_start) { - error = split_vma(mm, vma, start, 1); + error = vmi_split_vma(vmi, mm, vma, start, 1); if (error) goto fail; } if (end != vma->vm_end) { - error = split_vma(mm, vma, end, 0); + error = vmi_split_vma(vmi, mm, vma, end, 0); if (error) goto fail; } @@ -709,7 +709,7 @@ static int do_mprotect_pkey(unsigned long start, size_t len, const bool rier = (current->personality & READ_IMPLIES_EXEC) && (prot & PROT_READ); struct mmu_gather tlb; - MA_STATE(mas, ¤t->mm->mm_mt, 0, 0); + struct vma_iterator vmi; start = untagged_addr(start); @@ -741,8 +741,8 @@ static int do_mprotect_pkey(unsigned long start, size_t len, if ((pkey != -1) && !mm_pkey_is_allocated(current->mm, pkey)) goto out; - mas_set(&mas, start); - vma = mas_find(&mas, ULONG_MAX); + vma_iter_init(&vmi, current->mm, start); + vma = vma_find(&vmi, end); error = -ENOMEM; if (!vma) goto out; @@ -765,18 +765,22 @@ static int do_mprotect_pkey(unsigned long start, size_t len, } } + prev = vma_prev(&vmi); if (start > vma->vm_start) prev = vma; - else - prev = mas_prev(&mas, 0); tlb_gather_mmu(&tlb, current->mm); - for (nstart = start ; ; ) { + nstart = start; + tmp = vma->vm_start; + for_each_vma_range(vmi, vma, end) { unsigned long mask_off_old_flags; unsigned long newflags; int new_vma_pkey; - /* Here we know that vma->vm_start <= nstart < vma->vm_end. */ + if (vma->vm_start != tmp) { + error = -ENOMEM; + break; + } /* Does the application expect PROT_READ to imply PROT_EXEC */ if (rier && (vma->vm_flags & VM_MAYEXEC)) @@ -824,25 +828,18 @@ static int do_mprotect_pkey(unsigned long start, size_t len, break; } - error = mprotect_fixup(&tlb, vma, &prev, nstart, tmp, newflags); + error = mprotect_fixup(&vmi, &tlb, vma, &prev, nstart, tmp, newflags); if (error) break; nstart = tmp; - - if (nstart < prev->vm_end) - nstart = prev->vm_end; - if (nstart >= end) - break; - - vma = find_vma(current->mm, prev->vm_end); - if (!vma || vma->vm_start != nstart) { - error = -ENOMEM; - break; - } prot = reqprot; } tlb_finish_mmu(&tlb); + + if (vma_iter_end(&vmi) < end) + error = -ENOMEM; + out: mmap_write_unlock(current->mm); return error; -- cgit v1.2.3 From 9760ebffbf5507320e0de41f5b80089bdef996a0 Mon Sep 17 00:00:00 2001 From: Liam R. Howlett Date: Fri, 20 Jan 2023 11:26:30 -0500 Subject: mm: switch vma_merge(), split_vma(), and __split_vma to vma iterator Drop the vmi_* functions and transition all users to use the vma iterator directly. Link: https://lkml.kernel.org/r/20230120162650.984577-30-Liam.Howlett@oracle.com Signed-off-by: Liam R. Howlett Signed-off-by: Andrew Morton --- fs/userfaultfd.c | 14 +++++----- include/linux/mm.h | 18 ++++--------- mm/madvise.c | 6 ++--- mm/mempolicy.c | 6 ++--- mm/mlock.c | 6 ++--- mm/mmap.c | 79 +++++++++++++++--------------------------------------- mm/mprotect.c | 6 ++--- mm/mremap.c | 10 +++---- mm/nommu.c | 8 +++--- 9 files changed, 55 insertions(+), 98 deletions(-) (limited to 'include/linux') diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 4334bd35984d..f3c75c6222de 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -909,7 +909,7 @@ static int userfaultfd_release(struct inode *inode, struct file *file) continue; } new_flags = vma->vm_flags & ~__VM_UFFD_FLAGS; - prev = vmi_vma_merge(&vmi, mm, prev, vma->vm_start, vma->vm_end, + prev = vma_merge(&vmi, mm, prev, vma->vm_start, vma->vm_end, new_flags, vma->anon_vma, vma->vm_file, vma->vm_pgoff, vma_policy(vma), @@ -1452,7 +1452,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, vma_end = min(end, vma->vm_end); new_flags = (vma->vm_flags & ~__VM_UFFD_FLAGS) | vm_flags; - prev = vmi_vma_merge(&vmi, mm, prev, start, vma_end, new_flags, + prev = vma_merge(&vmi, mm, prev, start, vma_end, new_flags, vma->anon_vma, vma->vm_file, vma->vm_pgoff, vma_policy(vma), ((struct vm_userfaultfd_ctx){ ctx }), @@ -1463,12 +1463,12 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, goto next; } if (vma->vm_start < start) { - ret = vmi_split_vma(&vmi, mm, vma, start, 1); + ret = split_vma(&vmi, vma, start, 1); if (ret) break; } if (vma->vm_end > end) { - ret = vmi_split_vma(&vmi, mm, vma, end, 0); + ret = split_vma(&vmi, vma, end, 0); if (ret) break; } @@ -1632,7 +1632,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, uffd_wp_range(mm, vma, start, vma_end - start, false); new_flags = vma->vm_flags & ~__VM_UFFD_FLAGS; - prev = vmi_vma_merge(&vmi, mm, prev, start, vma_end, new_flags, + prev = vma_merge(&vmi, mm, prev, start, vma_end, new_flags, vma->anon_vma, vma->vm_file, vma->vm_pgoff, vma_policy(vma), NULL_VM_UFFD_CTX, anon_vma_name(vma)); @@ -1641,12 +1641,12 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, goto next; } if (vma->vm_start < start) { - ret = vmi_split_vma(&vmi, mm, vma, start, 1); + ret = split_vma(&vmi, vma, start, 1); if (ret) break; } if (vma->vm_end > end) { - ret = vmi_split_vma(&vmi, mm, vma, end, 0); + ret = split_vma(&vmi, vma, end, 0); if (ret) break; } diff --git a/include/linux/mm.h b/include/linux/mm.h index 144ddfd65992..f3b49feb5c35 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2839,24 +2839,16 @@ static inline int vma_adjust(struct vm_area_struct *vma, unsigned long start, { return __vma_adjust(vma, start, end, pgoff, insert, NULL); } -extern struct vm_area_struct *vma_merge(struct mm_struct *, - struct vm_area_struct *prev, unsigned long addr, unsigned long end, - unsigned long vm_flags, struct anon_vma *, struct file *, pgoff_t, - struct mempolicy *, struct vm_userfaultfd_ctx, struct anon_vma_name *); -extern struct vm_area_struct *vmi_vma_merge(struct vma_iterator *vmi, +extern struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *, struct vm_area_struct *prev, unsigned long addr, unsigned long end, unsigned long vm_flags, struct anon_vma *, struct file *, pgoff_t, struct mempolicy *, struct vm_userfaultfd_ctx, struct anon_vma_name *); extern struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *); -extern int __split_vma(struct mm_struct *, struct vm_area_struct *, - unsigned long addr, int new_below); -extern int vmi__split_vma(struct vma_iterator *vmi, struct mm_struct *, - struct vm_area_struct *, unsigned long addr, int new_below); -extern int split_vma(struct mm_struct *, struct vm_area_struct *, - unsigned long addr, int new_below); -extern int vmi_split_vma(struct vma_iterator *vmi, struct mm_struct *, - struct vm_area_struct *, unsigned long addr, int new_below); +extern int __split_vma(struct vma_iterator *vmi, struct vm_area_struct *, + unsigned long addr, int new_below); +extern int split_vma(struct vma_iterator *vmi, struct vm_area_struct *, + unsigned long addr, int new_below); extern int insert_vm_struct(struct mm_struct *, struct vm_area_struct *); extern void unlink_file_vma(struct vm_area_struct *); extern struct vm_area_struct *copy_vma(struct vm_area_struct **, diff --git a/mm/madvise.c b/mm/madvise.c index 4d4471916465..02b317726c9a 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -150,7 +150,7 @@ static int madvise_update_vma(struct vm_area_struct *vma, } pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); - *prev = vmi_vma_merge(&vmi, mm, *prev, start, end, new_flags, + *prev = vma_merge(&vmi, mm, *prev, start, end, new_flags, vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), vma->vm_userfaultfd_ctx, anon_name); if (*prev) { @@ -163,7 +163,7 @@ static int madvise_update_vma(struct vm_area_struct *vma, if (start != vma->vm_start) { if (unlikely(mm->map_count >= sysctl_max_map_count)) return -ENOMEM; - error = vmi__split_vma(&vmi, mm, vma, start, 1); + error = __split_vma(&vmi, vma, start, 1); if (error) return error; } @@ -171,7 +171,7 @@ static int madvise_update_vma(struct vm_area_struct *vma, if (end != vma->vm_end) { if (unlikely(mm->map_count >= sysctl_max_map_count)) return -ENOMEM; - error = vmi__split_vma(&vmi, mm, vma, end, 0); + error = __split_vma(&vmi, vma, end, 0); if (error) return error; } diff --git a/mm/mempolicy.c b/mm/mempolicy.c index ed68bdf980d3..dd5ca942256f 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -810,7 +810,7 @@ static int mbind_range(struct mm_struct *mm, unsigned long start, pgoff = vma->vm_pgoff + ((vmstart - vma->vm_start) >> PAGE_SHIFT); - prev = vmi_vma_merge(&vmi, mm, prev, vmstart, vmend, vma->vm_flags, + prev = vma_merge(&vmi, mm, prev, vmstart, vmend, vma->vm_flags, vma->anon_vma, vma->vm_file, pgoff, new_pol, vma->vm_userfaultfd_ctx, anon_vma_name(vma)); @@ -819,12 +819,12 @@ static int mbind_range(struct mm_struct *mm, unsigned long start, goto replace; } if (vma->vm_start != vmstart) { - err = vmi_split_vma(&vmi, vma->vm_mm, vma, vmstart, 1); + err = split_vma(&vmi, vma, vmstart, 1); if (err) goto out; } if (vma->vm_end != vmend) { - err = vmi_split_vma(&vmi, vma->vm_mm, vma, vmend, 0); + err = split_vma(&vmi, vma, vmend, 0); if (err) goto out; } diff --git a/mm/mlock.c b/mm/mlock.c index 0d09b9070071..0336f52e03d7 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -418,7 +418,7 @@ static int mlock_fixup(struct vma_iterator *vmi, struct vm_area_struct *vma, goto out; pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); - *prev = vmi_vma_merge(vmi, mm, *prev, start, end, newflags, + *prev = vma_merge(vmi, mm, *prev, start, end, newflags, vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), vma->vm_userfaultfd_ctx, anon_vma_name(vma)); if (*prev) { @@ -427,13 +427,13 @@ static int mlock_fixup(struct vma_iterator *vmi, struct vm_area_struct *vma, } if (start != vma->vm_start) { - ret = vmi_split_vma(vmi, mm, vma, start, 1); + ret = split_vma(vmi, vma, start, 1); if (ret) goto out; } if (end != vma->vm_end) { - ret = vmi_split_vma(vmi, mm, vma, end, 0); + ret = split_vma(vmi, vma, end, 0); if (ret) goto out; } diff --git a/mm/mmap.c b/mm/mmap.c index 8806bfbaa505..afc65f122f7d 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1010,7 +1010,7 @@ can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags, * parameter) may establish ptes with the wrong permissions of NNNN * instead of the right permissions of XXXX. */ -struct vm_area_struct *vma_merge(struct mm_struct *mm, +struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, struct vm_area_struct *prev, unsigned long addr, unsigned long end, unsigned long vm_flags, struct anon_vma *anon_vma, struct file *file, @@ -1019,7 +1019,7 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm, struct anon_vma_name *anon_name) { pgoff_t pglen = (end - addr) >> PAGE_SHIFT; - struct vm_area_struct *mid, *next, *res; + struct vm_area_struct *mid, *next, *res = NULL; int err = -1; bool merge_prev = false; bool merge_next = false; @@ -1085,26 +1085,11 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm, if (err) return NULL; khugepaged_enter_vma(res, vm_flags); - return res; -} -struct vm_area_struct *vmi_vma_merge(struct vma_iterator *vmi, - struct mm_struct *mm, - struct vm_area_struct *prev, unsigned long addr, - unsigned long end, unsigned long vm_flags, - struct anon_vma *anon_vma, struct file *file, - pgoff_t pgoff, struct mempolicy *policy, - struct vm_userfaultfd_ctx vm_userfaultfd_ctx, - struct anon_vma_name *anon_name) -{ - struct vm_area_struct *tmp; - - tmp = vma_merge(mm, prev, addr, end, vm_flags, anon_vma, file, pgoff, - policy, vm_userfaultfd_ctx, anon_name); - if (tmp) + if (res) vma_iter_set(vmi, end); - return tmp; + return res; } /* @@ -2228,12 +2213,14 @@ static void unmap_region(struct mm_struct *mm, struct maple_tree *mt, * __split_vma() bypasses sysctl_max_map_count checking. We use this where it * has already been checked or doesn't make sense to fail. */ -int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma, +int __split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma, unsigned long addr, int new_below) { struct vm_area_struct *new; int err; - validate_mm_mt(mm); + unsigned long end = vma->vm_end; + + validate_mm_mt(vma->vm_mm); if (vma->vm_ops && vma->vm_ops->may_split) { err = vma->vm_ops->may_split(vma, addr); @@ -2273,8 +2260,10 @@ int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma, err = vma_adjust(vma, vma->vm_start, addr, vma->vm_pgoff, new); /* Success. */ - if (!err) + if (!err) { + vma_iter_set(vmi, end); return 0; + } /* Avoid vm accounting in close() operation */ new->vm_start = new->vm_end; @@ -2289,46 +2278,21 @@ int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma, mpol_put(vma_policy(new)); out_free_vma: vm_area_free(new); - validate_mm_mt(mm); + validate_mm_mt(vma->vm_mm); return err; } -int vmi__split_vma(struct vma_iterator *vmi, struct mm_struct *mm, - struct vm_area_struct *vma, unsigned long addr, int new_below) -{ - int ret; - unsigned long end = vma->vm_end; - - ret = __split_vma(mm, vma, addr, new_below); - if (!ret) - vma_iter_set(vmi, end); - - return ret; -} /* * Split a vma into two pieces at address 'addr', a new vma is allocated * either for the first part or the tail. */ -int split_vma(struct mm_struct *mm, struct vm_area_struct *vma, +int split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma, unsigned long addr, int new_below) { - if (mm->map_count >= sysctl_max_map_count) + if (vma->vm_mm->map_count >= sysctl_max_map_count) return -ENOMEM; - return __split_vma(mm, vma, addr, new_below); -} - -int vmi_split_vma(struct vma_iterator *vmi, struct mm_struct *mm, - struct vm_area_struct *vma, unsigned long addr, int new_below) -{ - int ret; - unsigned long end = vma->vm_end; - - ret = split_vma(mm, vma, addr, new_below); - if (!ret) - vma_iter_set(vmi, end); - - return ret; + return __split_vma(vmi, vma, addr, new_below); } static inline int munmap_sidetree(struct vm_area_struct *vma, @@ -2388,7 +2352,7 @@ do_vmi_align_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma, if (end < vma->vm_end && mm->map_count >= sysctl_max_map_count) goto map_count_exceeded; - error = vmi__split_vma(vmi, mm, vma, start, 0); + error = __split_vma(vmi, vma, start, 0); if (error) goto start_split_failed; @@ -2409,7 +2373,7 @@ do_vmi_align_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma, if (next->vm_end > end) { struct vm_area_struct *split; - error = vmi__split_vma(vmi, mm, next, end, 1); + error = __split_vma(vmi, next, end, 1); if (error) goto end_split_failed; @@ -2690,9 +2654,10 @@ cannot_expand: * vma again as we may succeed this time. */ if (unlikely(vm_flags != vma->vm_flags && prev)) { - merge = vmi_vma_merge(&vmi, mm, prev, vma->vm_start, - vma->vm_end, vma->vm_flags, NULL, vma->vm_file, - vma->vm_pgoff, NULL, NULL_VM_UFFD_CTX, NULL); + merge = vma_merge(&vmi, mm, prev, vma->vm_start, + vma->vm_end, vma->vm_flags, NULL, + vma->vm_file, vma->vm_pgoff, NULL, + NULL_VM_UFFD_CTX, NULL); if (merge) { /* * ->mmap() can change vma->vm_file and fput @@ -3249,7 +3214,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, if (new_vma && new_vma->vm_start < addr + len) return NULL; /* should never get here */ - new_vma = vmi_vma_merge(&vmi, mm, prev, addr, addr + len, vma->vm_flags, + new_vma = vma_merge(&vmi, mm, prev, addr, addr + len, vma->vm_flags, vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), vma->vm_userfaultfd_ctx, anon_vma_name(vma)); if (new_vma) { diff --git a/mm/mprotect.c b/mm/mprotect.c index 39b6335b8813..cce6a0e58fb5 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -642,7 +642,7 @@ mprotect_fixup(struct vma_iterator *vmi, struct mmu_gather *tlb, * First try to merge with previous and/or next vma. */ pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); - *pprev = vmi_vma_merge(vmi, mm, *pprev, start, end, newflags, + *pprev = vma_merge(vmi, mm, *pprev, start, end, newflags, vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), vma->vm_userfaultfd_ctx, anon_vma_name(vma)); if (*pprev) { @@ -654,13 +654,13 @@ mprotect_fixup(struct vma_iterator *vmi, struct mmu_gather *tlb, *pprev = vma; if (start != vma->vm_start) { - error = vmi_split_vma(vmi, mm, vma, start, 1); + error = split_vma(vmi, vma, start, 1); if (error) goto fail; } if (end != vma->vm_end) { - error = vmi_split_vma(vmi, mm, vma, end, 0); + error = split_vma(vmi, vma, end, 0); if (error) goto fail; } diff --git a/mm/mremap.c b/mm/mremap.c index f161516ab3c1..71ba8eddd836 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -1043,12 +1043,10 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, * when a vma would be actually removed due to a merge. */ if (!vma->vm_ops || !vma->vm_ops->close) { - vma = vmi_vma_merge(&vmi, mm, vma, - extension_start, extension_end, - vma->vm_flags, vma->anon_vma, - vma->vm_file, extension_pgoff, - vma_policy(vma), vma->vm_userfaultfd_ctx, - anon_vma_name(vma)); + vma = vma_merge(&vmi, mm, vma, extension_start, + extension_end, vma->vm_flags, vma->anon_vma, + vma->vm_file, extension_pgoff, vma_policy(vma), + vma->vm_userfaultfd_ctx, anon_vma_name(vma)); } else if (vma_adjust(vma, vma->vm_start, addr + new_len, vma->vm_pgoff, NULL)) { vma = NULL; diff --git a/mm/nommu.c b/mm/nommu.c index 9ddeb92600d6..9a166738909e 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -1297,18 +1297,20 @@ SYSCALL_DEFINE1(old_mmap, struct mmap_arg_struct __user *, arg) * split a vma into two pieces at address 'addr', a new vma is allocated either * for the first part or the tail. */ -int vmi_split_vma(struct vma_iterator *vmi, struct mm_struct *mm, - struct vm_area_struct *vma, unsigned long addr, int new_below) +int split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma, + unsigned long addr, int new_below) { struct vm_area_struct *new; struct vm_region *region; unsigned long npages; + struct mm_struct *mm; /* we're only permitted to split anonymous regions (these should have * only a single usage on the region) */ if (vma->vm_file) return -ENOMEM; + mm = vma->vm_mm; if (mm->map_count >= sysctl_max_map_count) return -ENOMEM; @@ -1465,7 +1467,7 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len, struct list if (end != vma->vm_end && offset_in_page(end)) return -EINVAL; if (start != vma->vm_start && end != vma->vm_end) { - ret = vmi_split_vma(&vmi, mm, vma, start, 1); + ret = split_vma(&vmi, vma, start, 1); if (ret < 0) return ret; } -- cgit v1.2.3 From fbcc3104b8437cc1babf04421e8bb8181561343e Mon Sep 17 00:00:00 2001 From: Liam R. Howlett Date: Fri, 20 Jan 2023 11:26:32 -0500 Subject: mmap: convert __vma_adjust() to use vma iterator Use the vma iterator internally for __vma_adjust(). Avoid using the maple tree interface directly for type safety. Link: https://lkml.kernel.org/r/20230120162650.984577-32-Liam.Howlett@oracle.com Signed-off-by: Liam R. Howlett Signed-off-by: Andrew Morton --- include/linux/mm.h | 3 --- mm/mmap.c | 75 ++++++++++-------------------------------------------- 2 files changed, 13 insertions(+), 65 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index f3b49feb5c35..2f62d687e9bd 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2856,9 +2856,6 @@ extern struct vm_area_struct *copy_vma(struct vm_area_struct **, bool *need_rmap_locks); extern void exit_mmap(struct mm_struct *); -void vma_mas_store(struct vm_area_struct *vma, struct ma_state *mas); -void vma_mas_remove(struct vm_area_struct *vma, struct ma_state *mas); - static inline int check_data_rlimit(unsigned long rlim, unsigned long new, unsigned long start, diff --git a/mm/mmap.c b/mm/mmap.c index afc65f122f7d..07ba54c34bd0 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -432,56 +432,6 @@ static void __vma_link_file(struct vm_area_struct *vma, flush_dcache_mmap_unlock(mapping); } -/* - * vma_mas_store() - Store a VMA in the maple tree. - * @vma: The vm_area_struct - * @mas: The maple state - * - * Efficient way to store a VMA in the maple tree when the @mas has already - * walked to the correct location. - * - * Note: the end address is inclusive in the maple tree. - */ -void vma_mas_store(struct vm_area_struct *vma, struct ma_state *mas) -{ - trace_vma_store(mas->tree, vma); - mas_set_range(mas, vma->vm_start, vma->vm_end - 1); - mas_store_prealloc(mas, vma); -} - -/* - * vma_mas_remove() - Remove a VMA from the maple tree. - * @vma: The vm_area_struct - * @mas: The maple state - * - * Efficient way to remove a VMA from the maple tree when the @mas has already - * been established and points to the correct location. - * Note: the end address is inclusive in the maple tree. - */ -void vma_mas_remove(struct vm_area_struct *vma, struct ma_state *mas) -{ - trace_vma_mas_szero(mas->tree, vma->vm_start, vma->vm_end - 1); - mas->index = vma->vm_start; - mas->last = vma->vm_end - 1; - mas_store_prealloc(mas, NULL); -} - -/* - * vma_mas_szero() - Set a given range to zero. Used when modifying a - * vm_area_struct start or end. - * - * @mas: The maple tree ma_state - * @start: The start address to zero - * @end: The end address to zero. - */ -static inline void vma_mas_szero(struct ma_state *mas, unsigned long start, - unsigned long end) -{ - trace_vma_mas_szero(mas->tree, start, end - 1); - mas_set_range(mas, start, end - 1); - mas_store_prealloc(mas, NULL); -} - static int vma_link(struct mm_struct *mm, struct vm_area_struct *vma) { VMA_ITERATOR(vmi, mm, 0); @@ -641,7 +591,7 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start, bool vma_changed = false; long adjust_next = 0; int remove_next = 0; - MA_STATE(mas, &mm->mm_mt, 0, 0); + VMA_ITERATOR(vmi, mm, 0); struct vm_area_struct *exporter = NULL, *importer = NULL; if (next && !insert) { @@ -726,7 +676,7 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start, } } - if (mas_preallocate(&mas, GFP_KERNEL)) + if (vma_iter_prealloc(&vmi)) return -ENOMEM; vma_adjust_trans_huge(orig_vma, start, end, adjust_next); @@ -772,7 +722,7 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start, if (start != vma->vm_start) { if ((vma->vm_start < start) && (!insert || (insert->vm_end != start))) { - vma_mas_szero(&mas, vma->vm_start, start); + vma_iter_clear(&vmi, vma->vm_start, start); VM_WARN_ON(insert && insert->vm_start > vma->vm_start); } else { vma_changed = true; @@ -782,8 +732,8 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start, if (end != vma->vm_end) { if (vma->vm_end > end) { if (!insert || (insert->vm_start != end)) { - vma_mas_szero(&mas, end, vma->vm_end); - mas_reset(&mas); + vma_iter_clear(&vmi, end, vma->vm_end); + vma_iter_set(&vmi, vma->vm_end); VM_WARN_ON(insert && insert->vm_end < vma->vm_end); } @@ -794,13 +744,13 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start, } if (vma_changed) - vma_mas_store(vma, &mas); + vma_iter_store(&vmi, vma); vma->vm_pgoff = pgoff; if (adjust_next) { next->vm_start += adjust_next; next->vm_pgoff += adjust_next >> PAGE_SHIFT; - vma_mas_store(next, &mas); + vma_iter_store(&vmi, next); } if (file) { @@ -820,8 +770,7 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start, * us to insert it before dropping the locks * (it may either follow vma or precede it). */ - mas_reset(&mas); - vma_mas_store(insert, &mas); + vma_iter_store(&vmi, insert); mm->map_count++; } @@ -867,7 +816,7 @@ again: if (insert && file) uprobe_mmap(insert); - mas_destroy(&mas); + vma_iter_free(&vmi); validate_mm(mm); return 0; @@ -1999,7 +1948,8 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address) anon_vma_interval_tree_pre_update_vma(vma); vma->vm_end = address; /* Overwrite old entry in mtree. */ - vma_mas_store(vma, &mas); + mas_set_range(&mas, vma->vm_start, address - 1); + mas_store_prealloc(&mas, vma); anon_vma_interval_tree_post_update_vma(vma); spin_unlock(&mm->page_table_lock); @@ -2081,7 +2031,8 @@ int expand_downwards(struct vm_area_struct *vma, unsigned long address) vma->vm_start = address; vma->vm_pgoff -= grow; /* Overwrite old entry in mtree. */ - vma_mas_store(vma, &mas); + mas_set_range(&mas, address, vma->vm_end - 1); + mas_store_prealloc(&mas, vma); anon_vma_interval_tree_post_update_vma(vma); spin_unlock(&mm->page_table_lock); -- cgit v1.2.3 From 9e56044625a1f472edc278105f41a60726991d89 Mon Sep 17 00:00:00 2001 From: Liam R. Howlett Date: Fri, 20 Jan 2023 11:26:33 -0500 Subject: mm: pass through vma iterator to __vma_adjust() Pass the vma iterator through to __vma_adjust() so the state can be updated. Link: https://lkml.kernel.org/r/20230120162650.984577-33-Liam.Howlett@oracle.com Signed-off-by: Liam R. Howlett Signed-off-by: Andrew Morton --- include/linux/mm.h | 6 ++++-- mm/mmap.c | 31 +++++++++++++++---------------- 2 files changed, 19 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 2f62d687e9bd..9c15f401f295 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2831,13 +2831,15 @@ void anon_vma_interval_tree_verify(struct anon_vma_chain *node); /* mmap.c */ extern int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin); -extern int __vma_adjust(struct vm_area_struct *vma, unsigned long start, +extern int __vma_adjust(struct vma_iterator *vmi, struct vm_area_struct *vma, unsigned long start, unsigned long end, pgoff_t pgoff, struct vm_area_struct *insert, struct vm_area_struct *expand); static inline int vma_adjust(struct vm_area_struct *vma, unsigned long start, unsigned long end, pgoff_t pgoff, struct vm_area_struct *insert) { - return __vma_adjust(vma, start, end, pgoff, insert, NULL); + VMA_ITERATOR(vmi, vma->vm_mm, start); + + return __vma_adjust(&vmi, vma, start, end, pgoff, insert, NULL); } extern struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *, struct vm_area_struct *prev, unsigned long addr, diff --git a/mm/mmap.c b/mm/mmap.c index 07ba54c34bd0..330de1ab6a8d 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -576,9 +576,9 @@ nomem: * are necessary. The "insert" vma (if any) is to be inserted * before we drop the necessary locks. */ -int __vma_adjust(struct vm_area_struct *vma, unsigned long start, - unsigned long end, pgoff_t pgoff, struct vm_area_struct *insert, - struct vm_area_struct *expand) +int __vma_adjust(struct vma_iterator *vmi, struct vm_area_struct *vma, + unsigned long start, unsigned long end, pgoff_t pgoff, + struct vm_area_struct *insert, struct vm_area_struct *expand) { struct mm_struct *mm = vma->vm_mm; struct vm_area_struct *next_next = NULL; /* uninit var warning */ @@ -591,7 +591,6 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start, bool vma_changed = false; long adjust_next = 0; int remove_next = 0; - VMA_ITERATOR(vmi, mm, 0); struct vm_area_struct *exporter = NULL, *importer = NULL; if (next && !insert) { @@ -676,7 +675,7 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start, } } - if (vma_iter_prealloc(&vmi)) + if (vma_iter_prealloc(vmi)) return -ENOMEM; vma_adjust_trans_huge(orig_vma, start, end, adjust_next); @@ -722,7 +721,7 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start, if (start != vma->vm_start) { if ((vma->vm_start < start) && (!insert || (insert->vm_end != start))) { - vma_iter_clear(&vmi, vma->vm_start, start); + vma_iter_clear(vmi, vma->vm_start, start); VM_WARN_ON(insert && insert->vm_start > vma->vm_start); } else { vma_changed = true; @@ -732,8 +731,8 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start, if (end != vma->vm_end) { if (vma->vm_end > end) { if (!insert || (insert->vm_start != end)) { - vma_iter_clear(&vmi, end, vma->vm_end); - vma_iter_set(&vmi, vma->vm_end); + vma_iter_clear(vmi, end, vma->vm_end); + vma_iter_set(vmi, vma->vm_end); VM_WARN_ON(insert && insert->vm_end < vma->vm_end); } @@ -744,13 +743,13 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start, } if (vma_changed) - vma_iter_store(&vmi, vma); + vma_iter_store(vmi, vma); vma->vm_pgoff = pgoff; if (adjust_next) { next->vm_start += adjust_next; next->vm_pgoff += adjust_next >> PAGE_SHIFT; - vma_iter_store(&vmi, next); + vma_iter_store(vmi, next); } if (file) { @@ -770,7 +769,7 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start, * us to insert it before dropping the locks * (it may either follow vma or precede it). */ - vma_iter_store(&vmi, insert); + vma_iter_store(vmi, insert); mm->map_count++; } @@ -816,7 +815,7 @@ again: if (insert && file) uprobe_mmap(insert); - vma_iter_free(&vmi); + vma_iter_free(vmi); validate_mm(mm); return 0; @@ -1010,20 +1009,20 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, if (merge_prev && merge_next && is_mergeable_anon_vma(prev->anon_vma, next->anon_vma, NULL)) { /* cases 1, 6 */ - err = __vma_adjust(prev, prev->vm_start, + err = __vma_adjust(vmi, prev, prev->vm_start, next->vm_end, prev->vm_pgoff, NULL, prev); res = prev; } else if (merge_prev) { /* cases 2, 5, 7 */ - err = __vma_adjust(prev, prev->vm_start, + err = __vma_adjust(vmi, prev, prev->vm_start, end, prev->vm_pgoff, NULL, prev); res = prev; } else if (merge_next) { if (prev && addr < prev->vm_end) /* case 4 */ - err = __vma_adjust(prev, prev->vm_start, + err = __vma_adjust(vmi, prev, prev->vm_start, addr, prev->vm_pgoff, NULL, next); else /* cases 3, 8 */ - err = __vma_adjust(mid, addr, next->vm_end, + err = __vma_adjust(vmi, mid, addr, next->vm_end, next->vm_pgoff - pglen, NULL, next); res = next; } -- cgit v1.2.3 From b373037fa9bb374f26bbabc0779fe990d02d33b7 Mon Sep 17 00:00:00 2001 From: Liam R. Howlett Date: Fri, 20 Jan 2023 11:26:37 -0500 Subject: mm: add vma iterator to vma_adjust() arguments Change the vma_adjust() function definition to accept the vma iterator and pass it through to __vma_adjust(). Update fs/exec to use the new vma_adjust() function parameters. Update mm/mremap to use the new vma_adjust() function parameters. Revert the __split_vma() calls back from __vma_adjust() to vma_adjust() and pass through the vma iterator. Link: https://lkml.kernel.org/r/20230120162650.984577-37-Liam.Howlett@oracle.com Signed-off-by: Liam R. Howlett Signed-off-by: Andrew Morton --- fs/exec.c | 11 ++++------- include/linux/mm.h | 9 ++++----- mm/mmap.c | 10 +++++----- mm/mremap.c | 4 ++-- 4 files changed, 15 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/fs/exec.c b/fs/exec.c index b98647eeae9f..76ee62e1d3f1 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -699,7 +699,7 @@ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift) /* * cover the whole range: [new_start, old_end) */ - if (vma_adjust(vma, new_start, old_end, vma->vm_pgoff, NULL)) + if (vma_adjust(&vmi, vma, new_start, old_end, vma->vm_pgoff, NULL)) return -ENOMEM; /* @@ -731,12 +731,9 @@ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift) } tlb_finish_mmu(&tlb); - /* - * Shrink the vma to just the new range. Always succeeds. - */ - vma_adjust(vma, new_start, new_end, vma->vm_pgoff, NULL); - - return 0; + vma_prev(&vmi); + /* Shrink the vma to just the new range */ + return vma_adjust(&vmi, vma, new_start, new_end, vma->vm_pgoff, NULL); } /* diff --git a/include/linux/mm.h b/include/linux/mm.h index 9c15f401f295..2e95287a9f74 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2834,12 +2834,11 @@ extern int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admi extern int __vma_adjust(struct vma_iterator *vmi, struct vm_area_struct *vma, unsigned long start, unsigned long end, pgoff_t pgoff, struct vm_area_struct *insert, struct vm_area_struct *expand); -static inline int vma_adjust(struct vm_area_struct *vma, unsigned long start, - unsigned long end, pgoff_t pgoff, struct vm_area_struct *insert) +static inline int vma_adjust(struct vma_iterator *vmi, + struct vm_area_struct *vma, unsigned long start, unsigned long end, + pgoff_t pgoff, struct vm_area_struct *insert) { - VMA_ITERATOR(vmi, vma->vm_mm, start); - - return __vma_adjust(&vmi, vma, start, end, pgoff, insert, NULL); + return __vma_adjust(vmi, vma, start, end, pgoff, insert, NULL); } extern struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *, struct vm_area_struct *prev, unsigned long addr, diff --git a/mm/mmap.c b/mm/mmap.c index 1bdf66b3b96e..f61e45caa32c 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2210,12 +2210,12 @@ int __split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma, new->vm_ops->open(new); if (new_below) - err = __vma_adjust(vmi, vma, addr, vma->vm_end, - vma->vm_pgoff + ((addr - new->vm_start) >> PAGE_SHIFT), - new, NULL); + err = vma_adjust(vmi, vma, addr, vma->vm_end, + vma->vm_pgoff + ((addr - new->vm_start) >> PAGE_SHIFT), + new); else - err = __vma_adjust(vmi, vma, vma->vm_start, addr, vma->vm_pgoff, - new, NULL); + err = vma_adjust(vmi, vma, vma->vm_start, addr, vma->vm_pgoff, + new); /* Success. */ if (!err) { diff --git a/mm/mremap.c b/mm/mremap.c index 71ba8eddd836..2176f0cc7f9a 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -1047,8 +1047,8 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, extension_end, vma->vm_flags, vma->anon_vma, vma->vm_file, extension_pgoff, vma_policy(vma), vma->vm_userfaultfd_ctx, anon_vma_name(vma)); - } else if (vma_adjust(vma, vma->vm_start, addr + new_len, - vma->vm_pgoff, NULL)) { + } else if (vma_adjust(&vmi, vma, vma->vm_start, + addr + new_len, vma->vm_pgoff, NULL)) { vma = NULL; } if (!vma) { -- cgit v1.2.3 From b2b3b886738fec5e89ca9ebc720eba1a8f615753 Mon Sep 17 00:00:00 2001 From: Liam R. Howlett Date: Fri, 20 Jan 2023 11:26:44 -0500 Subject: mm: don't use __vma_adjust() in __split_vma() Use the abstracted locking and maple tree operations. Since __split_vma() is the only user of the __vma_adjust() function to use the insert argument, drop that argument. Remove the NULL passed through from fs/exec's shift_arg_pages() and mremap() at the same time. Link: https://lkml.kernel.org/r/20230120162650.984577-44-Liam.Howlett@oracle.com Signed-off-by: Liam R. Howlett Signed-off-by: Andrew Morton --- fs/exec.c | 4 +- include/linux/mm.h | 7 ++-- mm/mmap.c | 118 +++++++++++++++++++++++++---------------------------- mm/mremap.c | 2 +- 4 files changed, 61 insertions(+), 70 deletions(-) (limited to 'include/linux') diff --git a/fs/exec.c b/fs/exec.c index 76ee62e1d3f1..d52fca2dd30b 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -699,7 +699,7 @@ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift) /* * cover the whole range: [new_start, old_end) */ - if (vma_adjust(&vmi, vma, new_start, old_end, vma->vm_pgoff, NULL)) + if (vma_adjust(&vmi, vma, new_start, old_end, vma->vm_pgoff)) return -ENOMEM; /* @@ -733,7 +733,7 @@ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift) vma_prev(&vmi); /* Shrink the vma to just the new range */ - return vma_adjust(&vmi, vma, new_start, new_end, vma->vm_pgoff, NULL); + return vma_adjust(&vmi, vma, new_start, new_end, vma->vm_pgoff); } /* diff --git a/include/linux/mm.h b/include/linux/mm.h index 2e95287a9f74..3845de5d2581 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2832,13 +2832,12 @@ void anon_vma_interval_tree_verify(struct anon_vma_chain *node); /* mmap.c */ extern int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin); extern int __vma_adjust(struct vma_iterator *vmi, struct vm_area_struct *vma, unsigned long start, - unsigned long end, pgoff_t pgoff, struct vm_area_struct *insert, - struct vm_area_struct *expand); + unsigned long end, pgoff_t pgoff, struct vm_area_struct *expand); static inline int vma_adjust(struct vma_iterator *vmi, struct vm_area_struct *vma, unsigned long start, unsigned long end, - pgoff_t pgoff, struct vm_area_struct *insert) + pgoff_t pgoff) { - return __vma_adjust(vmi, vma, start, end, pgoff, insert, NULL); + return __vma_adjust(vmi, vma, start, end, pgoff, NULL); } extern struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *, struct vm_area_struct *prev, unsigned long addr, diff --git a/mm/mmap.c b/mm/mmap.c index e259b33fcb52..3d08d7d243f0 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -691,7 +691,7 @@ nomem: */ int __vma_adjust(struct vma_iterator *vmi, struct vm_area_struct *vma, unsigned long start, unsigned long end, pgoff_t pgoff, - struct vm_area_struct *insert, struct vm_area_struct *expand) + struct vm_area_struct *expand) { struct mm_struct *mm = vma->vm_mm; struct vm_area_struct *remove2 = NULL; @@ -704,7 +704,7 @@ int __vma_adjust(struct vma_iterator *vmi, struct vm_area_struct *vma, struct vm_area_struct *exporter = NULL, *importer = NULL; struct vma_prepare vma_prep; - if (next && !insert) { + if (next) { if (end >= next->vm_end) { /* * vma expands, overlapping all the next, and @@ -795,39 +795,25 @@ int __vma_adjust(struct vma_iterator *vmi, struct vm_area_struct *vma, VM_WARN_ON(vma_prep.anon_vma && adjust_next && next->anon_vma && vma_prep.anon_vma != next->anon_vma); - vma_prep.insert = insert; vma_prepare(&vma_prep); - if (start != vma->vm_start) { - if (vma->vm_start < start) { - if (!insert || (insert->vm_end != start)) { - vma_iter_clear(vmi, vma->vm_start, start); - vma_iter_set(vmi, start); - VM_WARN_ON(insert && insert->vm_start > vma->vm_start); - } - } else { - vma_changed = true; - } - vma->vm_start = start; - } - if (end != vma->vm_end) { - if (vma->vm_end > end) { - if (!insert || (insert->vm_start != end)) { - vma_iter_clear(vmi, end, vma->vm_end); - vma_iter_set(vmi, vma->vm_end); - VM_WARN_ON(insert && - insert->vm_end < vma->vm_end); - } - } else { - vma_changed = true; - } - vma->vm_end = end; - } + if (vma->vm_start < start) + vma_iter_clear(vmi, vma->vm_start, start); + else if (start != vma->vm_start) + vma_changed = true; + + if (vma->vm_end > end) + vma_iter_clear(vmi, end, vma->vm_end); + else if (end != vma->vm_end) + vma_changed = true; + + vma->vm_start = start; + vma->vm_end = end; + vma->vm_pgoff = pgoff; if (vma_changed) vma_iter_store(vmi, vma); - vma->vm_pgoff = pgoff; if (adjust_next) { next->vm_start += adjust_next; next->vm_pgoff += adjust_next >> PAGE_SHIFT; @@ -846,9 +832,9 @@ int __vma_adjust(struct vma_iterator *vmi, struct vm_area_struct *vma, * per-vma resources, so we don't attempt to merge those. */ static inline int is_mergeable_vma(struct vm_area_struct *vma, - struct file *file, unsigned long vm_flags, - struct vm_userfaultfd_ctx vm_userfaultfd_ctx, - struct anon_vma_name *anon_name) + struct file *file, unsigned long vm_flags, + struct vm_userfaultfd_ctx vm_userfaultfd_ctx, + struct anon_vma_name *anon_name) { /* * VM_SOFTDIRTY should not prevent from VMA merging, if we @@ -1030,20 +1016,19 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, is_mergeable_anon_vma(prev->anon_vma, next->anon_vma, NULL)) { /* cases 1, 6 */ err = __vma_adjust(vmi, prev, prev->vm_start, - next->vm_end, prev->vm_pgoff, NULL, - prev); + next->vm_end, prev->vm_pgoff, prev); res = prev; } else if (merge_prev) { /* cases 2, 5, 7 */ err = __vma_adjust(vmi, prev, prev->vm_start, - end, prev->vm_pgoff, NULL, prev); + end, prev->vm_pgoff, prev); res = prev; } else if (merge_next) { if (prev && addr < prev->vm_end) /* case 4 */ err = __vma_adjust(vmi, prev, prev->vm_start, - addr, prev->vm_pgoff, NULL, next); + addr, prev->vm_pgoff, next); else /* cases 3, 8 */ err = __vma_adjust(vmi, mid, addr, next->vm_end, - next->vm_pgoff - pglen, NULL, next); + next->vm_pgoff - pglen, next); res = next; } @@ -2187,11 +2172,15 @@ static void unmap_region(struct mm_struct *mm, struct maple_tree *mt, int __split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma, unsigned long addr, int new_below) { + struct vma_prepare vp; struct vm_area_struct *new; int err; validate_mm_mt(vma->vm_mm); + WARN_ON(vma->vm_start >= addr); + WARN_ON(vma->vm_end <= addr); + if (vma->vm_ops && vma->vm_ops->may_split) { err = vma->vm_ops->may_split(vma, addr); if (err) @@ -2202,16 +2191,20 @@ int __split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma, if (!new) return -ENOMEM; - if (new_below) + err = -ENOMEM; + if (vma_iter_prealloc(vmi)) + goto out_free_vma; + + if (new_below) { new->vm_end = addr; - else { + } else { new->vm_start = addr; new->vm_pgoff += ((addr - vma->vm_start) >> PAGE_SHIFT); } err = vma_dup_policy(vma, new); if (err) - goto out_free_vma; + goto out_free_vmi; err = anon_vma_clone(new, vma); if (err) @@ -2223,33 +2216,32 @@ int __split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma, if (new->vm_ops && new->vm_ops->open) new->vm_ops->open(new); - if (new_below) - err = vma_adjust(vmi, vma, addr, vma->vm_end, - vma->vm_pgoff + ((addr - new->vm_start) >> PAGE_SHIFT), - new); - else - err = vma_adjust(vmi, vma, vma->vm_start, addr, vma->vm_pgoff, - new); + vma_adjust_trans_huge(vma, vma->vm_start, addr, 0); + init_vma_prep(&vp, vma); + vp.insert = new; + vma_prepare(&vp); - /* Success. */ - if (!err) { - if (new_below) - vma_next(vmi); - return 0; + if (new_below) { + vma->vm_start = addr; + vma->vm_pgoff += (addr - new->vm_start) >> PAGE_SHIFT; + } else { + vma->vm_end = addr; } - /* Avoid vm accounting in close() operation */ - new->vm_start = new->vm_end; - new->vm_pgoff = 0; - /* Clean everything up if vma_adjust failed. */ - if (new->vm_ops && new->vm_ops->close) - new->vm_ops->close(new); - if (new->vm_file) - fput(new->vm_file); - unlink_anon_vmas(new); - out_free_mpol: + /* vma_complete stores the new vma */ + vma_complete(&vp, vmi, vma->vm_mm); + + /* Success. */ + if (new_below) + vma_next(vmi); + validate_mm_mt(vma->vm_mm); + return 0; + +out_free_mpol: mpol_put(vma_policy(new)); - out_free_vma: +out_free_vmi: + vma_iter_free(vmi); +out_free_vma: vm_area_free(new); validate_mm_mt(vma->vm_mm); return err; diff --git a/mm/mremap.c b/mm/mremap.c index 6c7f49ab7d19..b98185f48ba5 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -1054,7 +1054,7 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, vma->vm_file, extension_pgoff, vma_policy(vma), vma->vm_userfaultfd_ctx, anon_vma_name(vma)); } else if (vma_adjust(&vmi, vma, vma->vm_start, - addr + new_len, vma->vm_pgoff, NULL)) { + addr + new_len, vma->vm_pgoff)) { vma = NULL; } if (!vma) { -- cgit v1.2.3 From 7c9813e886bb52495ff5b97d4b0f1320d36d869b Mon Sep 17 00:00:00 2001 From: Liam R. Howlett Date: Fri, 20 Jan 2023 11:26:45 -0500 Subject: mm/mremap: convert vma_adjust() to vma_expand() Stop using vma_adjust() in preparation for removing the function. Export vma_expand() to use instead. Link: https://lkml.kernel.org/r/20230120162650.984577-45-Liam.Howlett@oracle.com Signed-off-by: Liam R. Howlett Signed-off-by: Andrew Morton --- include/linux/mm.h | 3 +++ mm/mmap.c | 6 +++--- mm/mremap.c | 4 ++-- 3 files changed, 8 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 3845de5d2581..245fb30858c9 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2839,6 +2839,9 @@ static inline int vma_adjust(struct vma_iterator *vmi, { return __vma_adjust(vmi, vma, start, end, pgoff, NULL); } +extern int vma_expand(struct vma_iterator *vmi, struct vm_area_struct *vma, + unsigned long start, unsigned long end, pgoff_t pgoff, + struct vm_area_struct *next); extern struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *, struct vm_area_struct *prev, unsigned long addr, unsigned long end, unsigned long vm_flags, struct anon_vma *, diff --git a/mm/mmap.c b/mm/mmap.c index 3d08d7d243f0..9599db011b18 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -634,9 +634,9 @@ again: * * Returns: 0 on success */ -inline int vma_expand(struct vma_iterator *vmi, struct vm_area_struct *vma, - unsigned long start, unsigned long end, pgoff_t pgoff, - struct vm_area_struct *next) +int vma_expand(struct vma_iterator *vmi, struct vm_area_struct *vma, + unsigned long start, unsigned long end, pgoff_t pgoff, + struct vm_area_struct *next) { bool remove_next = false; struct vma_prepare vp; diff --git a/mm/mremap.c b/mm/mremap.c index b98185f48ba5..5c9a57909862 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -1053,8 +1053,8 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, extension_end, vma->vm_flags, vma->anon_vma, vma->vm_file, extension_pgoff, vma_policy(vma), vma->vm_userfaultfd_ctx, anon_vma_name(vma)); - } else if (vma_adjust(&vmi, vma, vma->vm_start, - addr + new_len, vma->vm_pgoff)) { + } else if (vma_expand(&vmi, vma, vma->vm_start, + addr + new_len, vma->vm_pgoff, NULL)) { vma = NULL; } if (!vma) { -- cgit v1.2.3 From cf51e86dfbe39b7cae3a9de650d035af22dd5fb4 Mon Sep 17 00:00:00 2001 From: Liam R. Howlett Date: Fri, 20 Jan 2023 11:26:46 -0500 Subject: mm/mmap: don't use __vma_adjust() in shift_arg_pages() Introduce shrink_vma() which uses the vma_prepare() and vma_complete() functions to reduce the vma coverage. Convert shift_arg_pages() to use expand_vma() and the new shrink_vma() function. Remove support from __vma_adjust() to reduce a vma size since shift_arg_pages() is the only user that shrinks a VMA in this way. Link: https://lkml.kernel.org/r/20230120162650.984577-46-Liam.Howlett@oracle.com Signed-off-by: Liam R. Howlett Signed-off-by: Andrew Morton --- fs/exec.c | 4 ++-- include/linux/mm.h | 10 ++-------- mm/mmap.c | 52 +++++++++++++++++++++++++++++++++++++++++++--------- 3 files changed, 47 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/fs/exec.c b/fs/exec.c index d52fca2dd30b..c0df813d2b45 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -699,7 +699,7 @@ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift) /* * cover the whole range: [new_start, old_end) */ - if (vma_adjust(&vmi, vma, new_start, old_end, vma->vm_pgoff)) + if (vma_expand(&vmi, vma, new_start, old_end, vma->vm_pgoff, NULL)) return -ENOMEM; /* @@ -733,7 +733,7 @@ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift) vma_prev(&vmi); /* Shrink the vma to just the new range */ - return vma_adjust(&vmi, vma, new_start, new_end, vma->vm_pgoff); + return vma_shrink(&vmi, vma, new_start, new_end, vma->vm_pgoff); } /* diff --git a/include/linux/mm.h b/include/linux/mm.h index 245fb30858c9..dcc34533d2f6 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2831,17 +2831,11 @@ void anon_vma_interval_tree_verify(struct anon_vma_chain *node); /* mmap.c */ extern int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin); -extern int __vma_adjust(struct vma_iterator *vmi, struct vm_area_struct *vma, unsigned long start, - unsigned long end, pgoff_t pgoff, struct vm_area_struct *expand); -static inline int vma_adjust(struct vma_iterator *vmi, - struct vm_area_struct *vma, unsigned long start, unsigned long end, - pgoff_t pgoff) -{ - return __vma_adjust(vmi, vma, start, end, pgoff, NULL); -} extern int vma_expand(struct vma_iterator *vmi, struct vm_area_struct *vma, unsigned long start, unsigned long end, pgoff_t pgoff, struct vm_area_struct *next); +extern int vma_shrink(struct vma_iterator *vmi, struct vm_area_struct *vma, + unsigned long start, unsigned long end, pgoff_t pgoff); extern struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *, struct vm_area_struct *prev, unsigned long addr, unsigned long end, unsigned long vm_flags, struct anon_vma *, diff --git a/mm/mmap.c b/mm/mmap.c index 9599db011b18..07b52acfd565 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -682,6 +682,44 @@ int vma_expand(struct vma_iterator *vmi, struct vm_area_struct *vma, nomem: return -ENOMEM; } + +/* + * vma_shrink() - Reduce an existing VMAs memory area + * @vmi: The vma iterator + * @vma: The VMA to modify + * @start: The new start + * @end: The new end + * + * Returns: 0 on success, -ENOMEM otherwise + */ +int vma_shrink(struct vma_iterator *vmi, struct vm_area_struct *vma, + unsigned long start, unsigned long end, pgoff_t pgoff) +{ + struct vma_prepare vp; + + WARN_ON((vma->vm_start != start) && (vma->vm_end != end)); + + if (vma_iter_prealloc(vmi)) + return -ENOMEM; + + init_vma_prep(&vp, vma); + vma_adjust_trans_huge(vma, start, end, 0); + vma_prepare(&vp); + + if (vma->vm_start < start) + vma_iter_clear(vmi, vma->vm_start, start); + + if (vma->vm_end > end) + vma_iter_clear(vmi, end, vma->vm_end); + + vma->vm_start = start; + vma->vm_end = end; + vma->vm_pgoff = pgoff; + vma_complete(&vp, vmi, vma->vm_mm); + validate_mm(vma->vm_mm); + return 0; +} + /* * We cannot adjust vm_start, vm_end, vm_pgoff fields of a vma that * is already present in an i_mmap tree without adjusting the tree. @@ -797,14 +835,7 @@ int __vma_adjust(struct vma_iterator *vmi, struct vm_area_struct *vma, vma_prepare(&vma_prep); - if (vma->vm_start < start) - vma_iter_clear(vmi, vma->vm_start, start); - else if (start != vma->vm_start) - vma_changed = true; - - if (vma->vm_end > end) - vma_iter_clear(vmi, end, vma->vm_end); - else if (end != vma->vm_end) + if (start < vma->vm_start || end > vma->vm_end) vma_changed = true; vma->vm_start = start; @@ -817,7 +848,10 @@ int __vma_adjust(struct vma_iterator *vmi, struct vm_area_struct *vma, if (adjust_next) { next->vm_start += adjust_next; next->vm_pgoff += adjust_next >> PAGE_SHIFT; - vma_iter_store(vmi, next); + if (adjust_next < 0) { + WARN_ON_ONCE(vma_changed); + vma_iter_store(vmi, next); + } } vma_complete(&vma_prep, vmi, mm); -- cgit v1.2.3 From bc292ab00f6c7a661a8a605c714e8a148f629ef6 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Thu, 26 Jan 2023 11:37:47 -0800 Subject: mm: introduce vma->vm_flags wrapper functions vm_flags are among VMA attributes which affect decisions like VMA merging and splitting. Therefore all vm_flags modifications are performed after taking exclusive mmap_lock to prevent vm_flags updates racing with such operations. Introduce modifier functions for vm_flags to be used whenever flags are updated. This way we can better check and control correct locking behavior during these updates. Link: https://lkml.kernel.org/r/20230126193752.297968-3-surenb@google.com Signed-off-by: Suren Baghdasaryan Reviewed-by: Davidlohr Bueso Acked-by: Michal Hocko Acked-by: Mel Gorman Acked-by: Mike Rapoport (IBM) Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Cc: Andy Lutomirski Cc: Arjun Roy Cc: Axel Rasmussen Cc: David Hildenbrand Cc: David Howells Cc: David Rientjes Cc: Eric Dumazet Cc: Greg Thelen Cc: Hugh Dickins Cc: Ingo Molnar Cc: Jann Horn Cc: Joel Fernandes Cc: Johannes Weiner Cc: Kent Overstreet Cc: Laurent Dufour Cc: Liam R. Howlett Cc: Lorenzo Stoakes Cc: Matthew Wilcox Cc: Minchan Kim Cc: Paul E. McKenney Cc: Peter Oskolkov Cc: Peter Xu Cc: Peter Zijlstra Cc: Punit Agrawal Cc: Sebastian Andrzej Siewior Cc: Sebastian Reichel Cc: Shakeel Butt Cc: Soheil Hassas Yeganeh Cc: Song Liu Cc: Vlastimil Babka Cc: Will Deacon Signed-off-by: Andrew Morton --- include/linux/mm.h | 40 ++++++++++++++++++++++++++++++++++++++++ include/linux/mm_types.h | 10 +++++++++- 2 files changed, 49 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index dcc34533d2f6..e2df5d122b67 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -627,6 +627,46 @@ static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm) INIT_LIST_HEAD(&vma->anon_vma_chain); } +/* Use when VMA is not part of the VMA tree and needs no locking */ +static inline void vm_flags_init(struct vm_area_struct *vma, + vm_flags_t flags) +{ + ACCESS_PRIVATE(vma, __vm_flags) = flags; +} + +/* Use when VMA is part of the VMA tree and modifications need coordination */ +static inline void vm_flags_reset(struct vm_area_struct *vma, + vm_flags_t flags) +{ + mmap_assert_write_locked(vma->vm_mm); + vm_flags_init(vma, flags); +} + +static inline void vm_flags_set(struct vm_area_struct *vma, + vm_flags_t flags) +{ + mmap_assert_write_locked(vma->vm_mm); + ACCESS_PRIVATE(vma, __vm_flags) |= flags; +} + +static inline void vm_flags_clear(struct vm_area_struct *vma, + vm_flags_t flags) +{ + mmap_assert_write_locked(vma->vm_mm); + ACCESS_PRIVATE(vma, __vm_flags) &= ~flags; +} + +/* + * Use only when the order of set/clear operations is unimportant, otherwise + * use vm_flags_{set|clear} explicitly. + */ +static inline void vm_flags_mod(struct vm_area_struct *vma, + vm_flags_t set, vm_flags_t clear) +{ + mmap_assert_write_locked(vma->vm_mm); + vm_flags_init(vma, (vma->vm_flags | set) & ~clear); +} + static inline void vma_set_anonymous(struct vm_area_struct *vma) { vma->vm_ops = NULL; diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 5ca11c6c46e8..10a1e41f4e70 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -491,7 +491,15 @@ struct vm_area_struct { * See vmf_insert_mixed_prot() for discussion. */ pgprot_t vm_page_prot; - unsigned long vm_flags; /* Flags, see mm.h. */ + + /* + * Flags, see mm.h. + * To modify use vm_flags_{init|reset|set|clear|mod} functions. + */ + union { + const vm_flags_t vm_flags; + vm_flags_t __private __vm_flags; + }; /* * For areas with an address space and backing store, -- cgit v1.2.3 From e430a95a04efc557bc4ff9b3035c7c85aee5d63f Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Thu, 26 Jan 2023 11:37:48 -0800 Subject: mm: replace VM_LOCKED_CLEAR_MASK with VM_LOCKED_MASK To simplify the usage of VM_LOCKED_CLEAR_MASK in vm_flags_clear(), replace it with VM_LOCKED_MASK bitmask and convert all users. Link: https://lkml.kernel.org/r/20230126193752.297968-4-surenb@google.com Signed-off-by: Suren Baghdasaryan Acked-by: Michal Hocko Acked-by: Mel Gorman Acked-by: Mike Rapoport (IBM) Reviewed-by: Davidlohr Bueso Cc: Andy Lutomirski Cc: Arjun Roy Cc: Axel Rasmussen Cc: David Hildenbrand Cc: David Howells Cc: David Rientjes Cc: Eric Dumazet Cc: Greg Thelen Cc: Hugh Dickins Cc: Ingo Molnar Cc: Jann Horn Cc: Joel Fernandes Cc: Johannes Weiner Cc: Kent Overstreet Cc: Laurent Dufour Cc: Liam R. Howlett Cc: Lorenzo Stoakes Cc: Matthew Wilcox Cc: Minchan Kim Cc: Paul E. McKenney Cc: Peter Oskolkov Cc: Peter Xu Cc: Peter Zijlstra Cc: Punit Agrawal Cc: Sebastian Andrzej Siewior Cc: Sebastian Reichel Cc: Shakeel Butt Cc: Soheil Hassas Yeganeh Cc: Song Liu Cc: Vlastimil Babka Cc: Will Deacon Signed-off-by: Andrew Morton --- include/linux/mm.h | 4 ++-- kernel/fork.c | 2 +- mm/hugetlb.c | 4 ++-- mm/mlock.c | 6 +++--- mm/mmap.c | 6 +++--- mm/mremap.c | 2 +- 6 files changed, 12 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index e2df5d122b67..663726ca2240 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -421,8 +421,8 @@ extern unsigned int kobjsize(const void *objp); /* This mask defines which mm->def_flags a process can inherit its parent */ #define VM_INIT_DEF_MASK VM_NOHUGEPAGE -/* This mask is used to clear all the VMA flags used by mlock */ -#define VM_LOCKED_CLEAR_MASK (~(VM_LOCKED | VM_LOCKONFAULT)) +/* This mask represents all the VMA flag bits used by mlock */ +#define VM_LOCKED_MASK (VM_LOCKED | VM_LOCKONFAULT) /* Arch-specific flags to clear when updating VM flags on protection change */ #ifndef VM_ARCH_CLEAR diff --git a/kernel/fork.c b/kernel/fork.c index 9260f975b8f4..5e3029ea8e1e 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -659,7 +659,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, tmp->anon_vma = NULL; } else if (anon_vma_fork(tmp, mpnt)) goto fail_nomem_anon_vma_fork; - tmp->vm_flags &= ~(VM_LOCKED | VM_LOCKONFAULT); + vm_flags_clear(tmp, VM_LOCKED_MASK); file = tmp->vm_file; if (file) { struct address_space *mapping = file->f_mapping; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 0f9df0143772..ab35b1cc9927 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -6969,8 +6969,8 @@ static unsigned long page_table_shareable(struct vm_area_struct *svma, unsigned long s_end = sbase + PUD_SIZE; /* Allow segments to share if only one is marked locked */ - unsigned long vm_flags = vma->vm_flags & VM_LOCKED_CLEAR_MASK; - unsigned long svm_flags = svma->vm_flags & VM_LOCKED_CLEAR_MASK; + unsigned long vm_flags = vma->vm_flags & ~VM_LOCKED_MASK; + unsigned long svm_flags = svma->vm_flags & ~VM_LOCKED_MASK; /* * match the virtual addresses, permission and the alignment of the diff --git a/mm/mlock.c b/mm/mlock.c index 0336f52e03d7..5c4fff93cd6b 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -497,7 +497,7 @@ static int apply_vma_lock_flags(unsigned long start, size_t len, if (vma->vm_start != tmp) return -ENOMEM; - newflags = vma->vm_flags & VM_LOCKED_CLEAR_MASK; + newflags = vma->vm_flags & ~VM_LOCKED_MASK; newflags |= flags; /* Here we know that vma->vm_start <= nstart < vma->vm_end. */ tmp = vma->vm_end; @@ -661,7 +661,7 @@ static int apply_mlockall_flags(int flags) struct vm_area_struct *vma, *prev = NULL; vm_flags_t to_add = 0; - current->mm->def_flags &= VM_LOCKED_CLEAR_MASK; + current->mm->def_flags &= ~VM_LOCKED_MASK; if (flags & MCL_FUTURE) { current->mm->def_flags |= VM_LOCKED; @@ -681,7 +681,7 @@ static int apply_mlockall_flags(int flags) for_each_vma(vmi, vma) { vm_flags_t newflags; - newflags = vma->vm_flags & VM_LOCKED_CLEAR_MASK; + newflags = vma->vm_flags & ~VM_LOCKED_MASK; newflags |= to_add; /* Ignore errors */ diff --git a/mm/mmap.c b/mm/mmap.c index b698a96d0511..03d7c37c5969 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2668,7 +2668,7 @@ expanded: if ((vm_flags & VM_SPECIAL) || vma_is_dax(vma) || is_vm_hugetlb_page(vma) || vma == get_gate_vma(current->mm)) - vma->vm_flags &= VM_LOCKED_CLEAR_MASK; + vm_flags_clear(vma, VM_LOCKED_MASK); else mm->locked_vm += (len >> PAGE_SHIFT); } @@ -3338,8 +3338,8 @@ static struct vm_area_struct *__install_special_mapping( vma->vm_start = addr; vma->vm_end = addr + len; - vma->vm_flags = vm_flags | mm->def_flags | VM_DONTEXPAND | VM_SOFTDIRTY; - vma->vm_flags &= VM_LOCKED_CLEAR_MASK; + vm_flags_init(vma, (vm_flags | mm->def_flags | + VM_DONTEXPAND | VM_SOFTDIRTY) & ~VM_LOCKED_MASK); vma->vm_page_prot = vm_get_page_prot(vma->vm_flags); vma->vm_ops = ops; diff --git a/mm/mremap.c b/mm/mremap.c index 5c9a57909862..d70d8063c6e2 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -687,7 +687,7 @@ static unsigned long move_vma(struct vm_area_struct *vma, if (unlikely(!err && (flags & MREMAP_DONTUNMAP))) { /* We always clear VM_LOCKED[ONFAULT] on the old vma */ - vma->vm_flags &= VM_LOCKED_CLEAR_MASK; + vm_flags_clear(vma, VM_LOCKED_MASK); /* * anon_vma links of the old vma is no longer needed after its page -- cgit v1.2.3 From 1c71222e5f2393b5ea1a41795c67589eea7e3490 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Thu, 26 Jan 2023 11:37:49 -0800 Subject: mm: replace vma->vm_flags direct modifications with modifier calls Replace direct modifications to vma->vm_flags with calls to modifier functions to be able to track flag changes and to keep vma locking correctness. [akpm@linux-foundation.org: fix drivers/misc/open-dice.c, per Hyeonggon Yoo] Link: https://lkml.kernel.org/r/20230126193752.297968-5-surenb@google.com Signed-off-by: Suren Baghdasaryan Acked-by: Michal Hocko Acked-by: Mel Gorman Acked-by: Mike Rapoport (IBM) Acked-by: Sebastian Reichel Reviewed-by: Liam R. Howlett Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Cc: Andy Lutomirski Cc: Arjun Roy Cc: Axel Rasmussen Cc: David Hildenbrand Cc: David Howells Cc: Davidlohr Bueso Cc: David Rientjes Cc: Eric Dumazet Cc: Greg Thelen Cc: Hugh Dickins Cc: Ingo Molnar Cc: Jann Horn Cc: Joel Fernandes Cc: Johannes Weiner Cc: Kent Overstreet Cc: Laurent Dufour Cc: Lorenzo Stoakes Cc: Matthew Wilcox Cc: Minchan Kim Cc: Paul E. McKenney Cc: Peter Oskolkov Cc: Peter Xu Cc: Peter Zijlstra Cc: Punit Agrawal Cc: Sebastian Andrzej Siewior Cc: Shakeel Butt Cc: Soheil Hassas Yeganeh Cc: Song Liu Cc: Vlastimil Babka Cc: Will Deacon Signed-off-by: Andrew Morton --- arch/arm/kernel/process.c | 2 +- arch/ia64/mm/init.c | 8 ++++---- arch/loongarch/include/asm/tlb.h | 2 +- arch/powerpc/kvm/book3s_xive_native.c | 2 +- arch/powerpc/mm/book3s64/subpage_prot.c | 2 +- arch/powerpc/platforms/book3s/vas-api.c | 2 +- arch/powerpc/platforms/cell/spufs/file.c | 14 +++++++------- arch/s390/mm/gmap.c | 3 +-- arch/x86/entry/vsyscall/vsyscall_64.c | 2 +- arch/x86/kernel/cpu/sgx/driver.c | 2 +- arch/x86/kernel/cpu/sgx/virt.c | 2 +- arch/x86/mm/pat/memtype.c | 6 +++--- arch/x86/um/mem_32.c | 2 +- drivers/acpi/pfr_telemetry.c | 2 +- drivers/android/binder.c | 3 +-- drivers/char/mspec.c | 2 +- drivers/crypto/hisilicon/qm.c | 2 +- drivers/dax/device.c | 2 +- drivers/dma/idxd/cdev.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c | 2 +- drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 4 ++-- drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c | 4 ++-- drivers/gpu/drm/amd/amdkfd/kfd_events.c | 4 ++-- drivers/gpu/drm/amd/amdkfd/kfd_process.c | 4 ++-- drivers/gpu/drm/drm_gem.c | 2 +- drivers/gpu/drm/drm_gem_dma_helper.c | 3 +-- drivers/gpu/drm/drm_gem_shmem_helper.c | 2 +- drivers/gpu/drm/drm_vm.c | 8 ++++---- drivers/gpu/drm/etnaviv/etnaviv_gem.c | 2 +- drivers/gpu/drm/exynos/exynos_drm_gem.c | 4 ++-- drivers/gpu/drm/gma500/framebuffer.c | 2 +- drivers/gpu/drm/i810/i810_dma.c | 2 +- drivers/gpu/drm/i915/gem/i915_gem_mman.c | 4 ++-- drivers/gpu/drm/mediatek/mtk_drm_gem.c | 2 +- drivers/gpu/drm/msm/msm_gem.c | 2 +- drivers/gpu/drm/omapdrm/omap_gem.c | 3 +-- drivers/gpu/drm/rockchip/rockchip_drm_gem.c | 3 +-- drivers/gpu/drm/tegra/gem.c | 5 ++--- drivers/gpu/drm/ttm/ttm_bo_vm.c | 3 +-- drivers/gpu/drm/virtio/virtgpu_vram.c | 2 +- drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c | 2 +- drivers/gpu/drm/xen/xen_drm_front_gem.c | 3 +-- drivers/hsi/clients/cmt_speech.c | 2 +- drivers/hwtracing/intel_th/msu.c | 2 +- drivers/hwtracing/stm/core.c | 2 +- drivers/infiniband/hw/hfi1/file_ops.c | 4 ++-- drivers/infiniband/hw/mlx5/main.c | 4 ++-- drivers/infiniband/hw/qib/qib_file_ops.c | 13 ++++++------- drivers/infiniband/hw/usnic/usnic_ib_verbs.c | 2 +- drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.c | 2 +- drivers/media/common/videobuf2/videobuf2-dma-contig.c | 2 +- drivers/media/common/videobuf2/videobuf2-vmalloc.c | 2 +- drivers/media/v4l2-core/videobuf-dma-contig.c | 2 +- drivers/media/v4l2-core/videobuf-dma-sg.c | 4 ++-- drivers/media/v4l2-core/videobuf-vmalloc.c | 2 +- drivers/misc/cxl/context.c | 2 +- drivers/misc/habanalabs/common/memory.c | 2 +- drivers/misc/habanalabs/gaudi/gaudi.c | 4 ++-- drivers/misc/habanalabs/gaudi2/gaudi2.c | 8 ++++---- drivers/misc/habanalabs/goya/goya.c | 4 ++-- drivers/misc/ocxl/context.c | 4 ++-- drivers/misc/ocxl/sysfs.c | 2 +- drivers/misc/open-dice.c | 4 ++-- drivers/misc/sgi-gru/grufile.c | 4 ++-- drivers/misc/uacce/uacce.c | 2 +- drivers/sbus/char/oradax.c | 2 +- drivers/scsi/cxlflash/ocxl_hw.c | 2 +- drivers/scsi/sg.c | 2 +- drivers/staging/media/atomisp/pci/hmm/hmm_bo.c | 2 +- drivers/staging/media/deprecated/meye/meye.c | 4 ++-- drivers/staging/media/deprecated/stkwebcam/stk-webcam.c | 2 +- drivers/target/target_core_user.c | 2 +- drivers/uio/uio.c | 2 +- drivers/usb/core/devio.c | 3 +-- drivers/usb/mon/mon_bin.c | 3 +-- drivers/vdpa/vdpa_user/iova_domain.c | 2 +- drivers/vfio/pci/vfio_pci_core.c | 2 +- drivers/vhost/vdpa.c | 2 +- drivers/video/fbdev/68328fb.c | 2 +- drivers/video/fbdev/core/fb_defio.c | 4 ++-- drivers/xen/gntalloc.c | 2 +- drivers/xen/gntdev.c | 4 ++-- drivers/xen/privcmd-buf.c | 2 +- drivers/xen/privcmd.c | 4 ++-- fs/aio.c | 2 +- fs/cramfs/inode.c | 2 +- fs/erofs/data.c | 2 +- fs/exec.c | 4 ++-- fs/ext4/file.c | 2 +- fs/fuse/dax.c | 2 +- fs/hugetlbfs/inode.c | 4 ++-- fs/orangefs/file.c | 3 +-- fs/proc/task_mmu.c | 2 +- fs/proc/vmcore.c | 3 +-- fs/userfaultfd.c | 2 +- fs/xfs/xfs_file.c | 2 +- include/linux/mm.h | 2 +- kernel/bpf/ringbuf.c | 4 ++-- kernel/bpf/syscall.c | 4 ++-- kernel/events/core.c | 2 +- kernel/kcov.c | 2 +- kernel/relay.c | 2 +- mm/madvise.c | 2 +- mm/memory.c | 6 +++--- mm/mlock.c | 6 +++--- mm/mmap.c | 10 +++++----- mm/mprotect.c | 2 +- mm/mremap.c | 6 +++--- mm/nommu.c | 11 ++++++----- mm/secretmem.c | 2 +- mm/shmem.c | 2 +- mm/vmalloc.c | 2 +- net/ipv4/tcp.c | 4 ++-- security/selinux/selinuxfs.c | 6 +++--- sound/core/oss/pcm_oss.c | 2 +- sound/core/pcm_native.c | 9 +++++---- sound/soc/pxa/mmp-sspa.c | 2 +- sound/usb/usx2y/us122l.c | 4 ++-- sound/usb/usx2y/usX2Yhwdep.c | 2 +- sound/usb/usx2y/usx2yhwdeppcm.c | 2 +- 120 files changed, 188 insertions(+), 199 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c index f811733a8fc5..61c30b9a24ea 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -316,7 +316,7 @@ static int __init gate_vma_init(void) gate_vma.vm_page_prot = PAGE_READONLY_EXEC; gate_vma.vm_start = 0xffff0000; gate_vma.vm_end = 0xffff0000 + PAGE_SIZE; - gate_vma.vm_flags = VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYEXEC; + vm_flags_init(&gate_vma, VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYEXEC); return 0; } arch_initcall(gate_vma_init); diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index fc4e4217e87f..7f5353e28516 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -109,7 +109,7 @@ ia64_init_addr_space (void) vma_set_anonymous(vma); vma->vm_start = current->thread.rbs_bot & PAGE_MASK; vma->vm_end = vma->vm_start + PAGE_SIZE; - vma->vm_flags = VM_DATA_DEFAULT_FLAGS|VM_GROWSUP|VM_ACCOUNT; + vm_flags_init(vma, VM_DATA_DEFAULT_FLAGS|VM_GROWSUP|VM_ACCOUNT); vma->vm_page_prot = vm_get_page_prot(vma->vm_flags); mmap_write_lock(current->mm); if (insert_vm_struct(current->mm, vma)) { @@ -127,8 +127,8 @@ ia64_init_addr_space (void) vma_set_anonymous(vma); vma->vm_end = PAGE_SIZE; vma->vm_page_prot = __pgprot(pgprot_val(PAGE_READONLY) | _PAGE_MA_NAT); - vma->vm_flags = VM_READ | VM_MAYREAD | VM_IO | - VM_DONTEXPAND | VM_DONTDUMP; + vm_flags_init(vma, VM_READ | VM_MAYREAD | VM_IO | + VM_DONTEXPAND | VM_DONTDUMP); mmap_write_lock(current->mm); if (insert_vm_struct(current->mm, vma)) { mmap_write_unlock(current->mm); @@ -272,7 +272,7 @@ static int __init gate_vma_init(void) vma_init(&gate_vma, NULL); gate_vma.vm_start = FIXADDR_USER_START; gate_vma.vm_end = FIXADDR_USER_END; - gate_vma.vm_flags = VM_READ | VM_MAYREAD | VM_EXEC | VM_MAYEXEC; + vm_flags_init(&gate_vma, VM_READ | VM_MAYREAD | VM_EXEC | VM_MAYEXEC); gate_vma.vm_page_prot = __pgprot(__ACCESS_BITS | _PAGE_PL_3 | _PAGE_AR_RX); return 0; diff --git a/arch/loongarch/include/asm/tlb.h b/arch/loongarch/include/asm/tlb.h index dd24f5898f65..f5e4deb97402 100644 --- a/arch/loongarch/include/asm/tlb.h +++ b/arch/loongarch/include/asm/tlb.h @@ -149,7 +149,7 @@ static inline void tlb_flush(struct mmu_gather *tlb) struct vm_area_struct vma; vma.vm_mm = tlb->mm; - vma.vm_flags = 0; + vm_flags_init(&vma, 0); if (tlb->fullmm) { flush_tlb_mm(tlb->mm); return; diff --git a/arch/powerpc/kvm/book3s_xive_native.c b/arch/powerpc/kvm/book3s_xive_native.c index 4f566bea5e10..712ab91ced39 100644 --- a/arch/powerpc/kvm/book3s_xive_native.c +++ b/arch/powerpc/kvm/book3s_xive_native.c @@ -324,7 +324,7 @@ static int kvmppc_xive_native_mmap(struct kvm_device *dev, return -EINVAL; } - vma->vm_flags |= VM_IO | VM_PFNMAP; + vm_flags_set(vma, VM_IO | VM_PFNMAP); vma->vm_page_prot = pgprot_noncached_wc(vma->vm_page_prot); /* diff --git a/arch/powerpc/mm/book3s64/subpage_prot.c b/arch/powerpc/mm/book3s64/subpage_prot.c index d73b3b4176e8..b75a9fb99599 100644 --- a/arch/powerpc/mm/book3s64/subpage_prot.c +++ b/arch/powerpc/mm/book3s64/subpage_prot.c @@ -156,7 +156,7 @@ static void subpage_mark_vma_nohuge(struct mm_struct *mm, unsigned long addr, * VM_NOHUGEPAGE and split them. */ for_each_vma_range(vmi, vma, addr + len) { - vma->vm_flags |= VM_NOHUGEPAGE; + vm_flags_set(vma, VM_NOHUGEPAGE); walk_page_vma(vma, &subpage_walk_ops, NULL); } } diff --git a/arch/powerpc/platforms/book3s/vas-api.c b/arch/powerpc/platforms/book3s/vas-api.c index 9580e8e12165..36c21648d19a 100644 --- a/arch/powerpc/platforms/book3s/vas-api.c +++ b/arch/powerpc/platforms/book3s/vas-api.c @@ -525,7 +525,7 @@ static int coproc_mmap(struct file *fp, struct vm_area_struct *vma) pfn = paste_addr >> PAGE_SHIFT; /* flags, page_prot from cxl_mmap(), except we want cachable */ - vma->vm_flags |= VM_IO | VM_PFNMAP; + vm_flags_set(vma, VM_IO | VM_PFNMAP); vma->vm_page_prot = pgprot_cached(vma->vm_page_prot); prot = __pgprot(pgprot_val(vma->vm_page_prot) | _PAGE_DIRTY); diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c index 62d90a5e23d1..02a8158c469d 100644 --- a/arch/powerpc/platforms/cell/spufs/file.c +++ b/arch/powerpc/platforms/cell/spufs/file.c @@ -291,7 +291,7 @@ static int spufs_mem_mmap(struct file *file, struct vm_area_struct *vma) if (!(vma->vm_flags & VM_SHARED)) return -EINVAL; - vma->vm_flags |= VM_IO | VM_PFNMAP; + vm_flags_set(vma, VM_IO | VM_PFNMAP); vma->vm_page_prot = pgprot_noncached_wc(vma->vm_page_prot); vma->vm_ops = &spufs_mem_mmap_vmops; @@ -381,7 +381,7 @@ static int spufs_cntl_mmap(struct file *file, struct vm_area_struct *vma) if (!(vma->vm_flags & VM_SHARED)) return -EINVAL; - vma->vm_flags |= VM_IO | VM_PFNMAP; + vm_flags_set(vma, VM_IO | VM_PFNMAP); vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); vma->vm_ops = &spufs_cntl_mmap_vmops; @@ -1043,7 +1043,7 @@ static int spufs_signal1_mmap(struct file *file, struct vm_area_struct *vma) if (!(vma->vm_flags & VM_SHARED)) return -EINVAL; - vma->vm_flags |= VM_IO | VM_PFNMAP; + vm_flags_set(vma, VM_IO | VM_PFNMAP); vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); vma->vm_ops = &spufs_signal1_mmap_vmops; @@ -1179,7 +1179,7 @@ static int spufs_signal2_mmap(struct file *file, struct vm_area_struct *vma) if (!(vma->vm_flags & VM_SHARED)) return -EINVAL; - vma->vm_flags |= VM_IO | VM_PFNMAP; + vm_flags_set(vma, VM_IO | VM_PFNMAP); vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); vma->vm_ops = &spufs_signal2_mmap_vmops; @@ -1302,7 +1302,7 @@ static int spufs_mss_mmap(struct file *file, struct vm_area_struct *vma) if (!(vma->vm_flags & VM_SHARED)) return -EINVAL; - vma->vm_flags |= VM_IO | VM_PFNMAP; + vm_flags_set(vma, VM_IO | VM_PFNMAP); vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); vma->vm_ops = &spufs_mss_mmap_vmops; @@ -1364,7 +1364,7 @@ static int spufs_psmap_mmap(struct file *file, struct vm_area_struct *vma) if (!(vma->vm_flags & VM_SHARED)) return -EINVAL; - vma->vm_flags |= VM_IO | VM_PFNMAP; + vm_flags_set(vma, VM_IO | VM_PFNMAP); vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); vma->vm_ops = &spufs_psmap_mmap_vmops; @@ -1424,7 +1424,7 @@ static int spufs_mfc_mmap(struct file *file, struct vm_area_struct *vma) if (!(vma->vm_flags & VM_SHARED)) return -EINVAL; - vma->vm_flags |= VM_IO | VM_PFNMAP; + vm_flags_set(vma, VM_IO | VM_PFNMAP); vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); vma->vm_ops = &spufs_mfc_mmap_vmops; diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c index 69af6cdf1a2a..ab836597419d 100644 --- a/arch/s390/mm/gmap.c +++ b/arch/s390/mm/gmap.c @@ -2522,8 +2522,7 @@ static inline void thp_split_mm(struct mm_struct *mm) VMA_ITERATOR(vmi, mm, 0); for_each_vma(vmi, vma) { - vma->vm_flags &= ~VM_HUGEPAGE; - vma->vm_flags |= VM_NOHUGEPAGE; + vm_flags_mod(vma, VM_NOHUGEPAGE, VM_HUGEPAGE); walk_page_vma(vma, &thp_split_walk_ops, NULL); } mm->def_flags |= VM_NOHUGEPAGE; diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c index 4af81df133ee..d234ca797e4a 100644 --- a/arch/x86/entry/vsyscall/vsyscall_64.c +++ b/arch/x86/entry/vsyscall/vsyscall_64.c @@ -391,7 +391,7 @@ void __init map_vsyscall(void) } if (vsyscall_mode == XONLY) - gate_vma.vm_flags = VM_EXEC; + vm_flags_init(&gate_vma, VM_EXEC); BUILD_BUG_ON((unsigned long)__fix_to_virt(VSYSCALL_PAGE) != (unsigned long)VSYSCALL_ADDR); diff --git a/arch/x86/kernel/cpu/sgx/driver.c b/arch/x86/kernel/cpu/sgx/driver.c index aa9b8b868867..262f5fb18d74 100644 --- a/arch/x86/kernel/cpu/sgx/driver.c +++ b/arch/x86/kernel/cpu/sgx/driver.c @@ -95,7 +95,7 @@ static int sgx_mmap(struct file *file, struct vm_area_struct *vma) return ret; vma->vm_ops = &sgx_vm_ops; - vma->vm_flags |= VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP | VM_IO; + vm_flags_set(vma, VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP | VM_IO); vma->vm_private_data = encl; return 0; diff --git a/arch/x86/kernel/cpu/sgx/virt.c b/arch/x86/kernel/cpu/sgx/virt.c index 6a77a14eee38..c3e37eaec8ec 100644 --- a/arch/x86/kernel/cpu/sgx/virt.c +++ b/arch/x86/kernel/cpu/sgx/virt.c @@ -105,7 +105,7 @@ static int sgx_vepc_mmap(struct file *file, struct vm_area_struct *vma) vma->vm_ops = &sgx_vepc_vm_ops; /* Don't copy VMA in fork() */ - vma->vm_flags |= VM_PFNMAP | VM_IO | VM_DONTDUMP | VM_DONTCOPY; + vm_flags_set(vma, VM_PFNMAP | VM_IO | VM_DONTDUMP | VM_DONTCOPY); vma->vm_private_data = vepc; return 0; diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c index fb4b1b5e0dea..6ca51b1aa5d9 100644 --- a/arch/x86/mm/pat/memtype.c +++ b/arch/x86/mm/pat/memtype.c @@ -1000,7 +1000,7 @@ int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot, ret = reserve_pfn_range(paddr, size, prot, 0); if (ret == 0 && vma) - vma->vm_flags |= VM_PAT; + vm_flags_set(vma, VM_PAT); return ret; } @@ -1066,7 +1066,7 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, } free_pfn_range(paddr, size); if (vma) - vma->vm_flags &= ~VM_PAT; + vm_flags_clear(vma, VM_PAT); } /* @@ -1076,7 +1076,7 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, */ void untrack_pfn_moved(struct vm_area_struct *vma) { - vma->vm_flags &= ~VM_PAT; + vm_flags_clear(vma, VM_PAT); } pgprot_t pgprot_writecombine(pgprot_t prot) diff --git a/arch/x86/um/mem_32.c b/arch/x86/um/mem_32.c index cafd01f730da..29b2203bc82c 100644 --- a/arch/x86/um/mem_32.c +++ b/arch/x86/um/mem_32.c @@ -16,7 +16,7 @@ static int __init gate_vma_init(void) vma_init(&gate_vma, NULL); gate_vma.vm_start = FIXADDR_USER_START; gate_vma.vm_end = FIXADDR_USER_END; - gate_vma.vm_flags = VM_READ | VM_MAYREAD | VM_EXEC | VM_MAYEXEC; + vm_flags_init(&gate_vma, VM_READ | VM_MAYREAD | VM_EXEC | VM_MAYEXEC); gate_vma.vm_page_prot = PAGE_READONLY; return 0; diff --git a/drivers/acpi/pfr_telemetry.c b/drivers/acpi/pfr_telemetry.c index 27fb6cdad75f..843f678ade0c 100644 --- a/drivers/acpi/pfr_telemetry.c +++ b/drivers/acpi/pfr_telemetry.c @@ -310,7 +310,7 @@ pfrt_log_mmap(struct file *file, struct vm_area_struct *vma) return -EROFS; /* changing from read to write with mprotect is not allowed */ - vma->vm_flags &= ~VM_MAYWRITE; + vm_flags_clear(vma, VM_MAYWRITE); pfrt_log_dev = to_pfrt_log_dev(file); diff --git a/drivers/android/binder.c b/drivers/android/binder.c index 880224ec6abb..cb08982b9666 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -5572,8 +5572,7 @@ static int binder_mmap(struct file *filp, struct vm_area_struct *vma) proc->pid, vma->vm_start, vma->vm_end, "bad vm_flags", -EPERM); return -EPERM; } - vma->vm_flags |= VM_DONTCOPY | VM_MIXEDMAP; - vma->vm_flags &= ~VM_MAYWRITE; + vm_flags_mod(vma, VM_DONTCOPY | VM_MIXEDMAP, VM_MAYWRITE); vma->vm_ops = &binder_vm_ops; vma->vm_private_data = proc; diff --git a/drivers/char/mspec.c b/drivers/char/mspec.c index f8231e2e84be..b35f651837c8 100644 --- a/drivers/char/mspec.c +++ b/drivers/char/mspec.c @@ -206,7 +206,7 @@ mspec_mmap(struct file *file, struct vm_area_struct *vma, refcount_set(&vdata->refcnt, 1); vma->vm_private_data = vdata; - vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP; + vm_flags_set(vma, VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP); if (vdata->type == MSPEC_UNCACHED) vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); vma->vm_ops = &mspec_vm_ops; diff --git a/drivers/crypto/hisilicon/qm.c b/drivers/crypto/hisilicon/qm.c index 007ac7a69ce7..733fe1033910 100644 --- a/drivers/crypto/hisilicon/qm.c +++ b/drivers/crypto/hisilicon/qm.c @@ -2363,7 +2363,7 @@ static int hisi_qm_uacce_mmap(struct uacce_queue *q, return -EINVAL; } - vma->vm_flags |= VM_IO; + vm_flags_set(vma, VM_IO); return remap_pfn_range(vma, vma->vm_start, phys_base >> PAGE_SHIFT, diff --git a/drivers/dax/device.c b/drivers/dax/device.c index 5494d745ced5..223e4e233d19 100644 --- a/drivers/dax/device.c +++ b/drivers/dax/device.c @@ -308,7 +308,7 @@ static int dax_mmap(struct file *filp, struct vm_area_struct *vma) return rc; vma->vm_ops = &dax_vm_ops; - vma->vm_flags |= VM_HUGEPAGE; + vm_flags_set(vma, VM_HUGEPAGE); return 0; } diff --git a/drivers/dma/idxd/cdev.c b/drivers/dma/idxd/cdev.c index e13e92609943..674bfefca088 100644 --- a/drivers/dma/idxd/cdev.c +++ b/drivers/dma/idxd/cdev.c @@ -201,7 +201,7 @@ static int idxd_cdev_mmap(struct file *filp, struct vm_area_struct *vma) if (rc < 0) return rc; - vma->vm_flags |= VM_DONTCOPY; + vm_flags_set(vma, VM_DONTCOPY); pfn = (base + idxd_get_wq_portal_full_offset(wq->id, IDXD_PORTAL_LIMITED)) >> PAGE_SHIFT; vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index bb7350ea1d75..a69fd6fdabb4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -257,7 +257,7 @@ static int amdgpu_gem_object_mmap(struct drm_gem_object *obj, struct vm_area_str */ if (is_cow_mapping(vma->vm_flags) && !(vma->vm_flags & VM_ACCESS_FLAGS)) - vma->vm_flags &= ~VM_MAYWRITE; + vm_flags_clear(vma, VM_MAYWRITE); return drm_gem_ttm_mmap(obj, vma); } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index 6d291aa6386b..d0933dd9af06 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -2879,8 +2879,8 @@ static int kfd_mmio_mmap(struct kfd_dev *dev, struct kfd_process *process, address = dev->adev->rmmio_remap.bus_addr; - vma->vm_flags |= VM_IO | VM_DONTCOPY | VM_DONTEXPAND | VM_NORESERVE | - VM_DONTDUMP | VM_PFNMAP; + vm_flags_set(vma, VM_IO | VM_DONTCOPY | VM_DONTEXPAND | VM_NORESERVE | + VM_DONTDUMP | VM_PFNMAP); vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c b/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c index cd4e61bf0493..cbef2e147da5 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c @@ -159,8 +159,8 @@ int kfd_doorbell_mmap(struct kfd_dev *dev, struct kfd_process *process, address = kfd_get_process_doorbells(pdd); if (!address) return -ENOMEM; - vma->vm_flags |= VM_IO | VM_DONTCOPY | VM_DONTEXPAND | VM_NORESERVE | - VM_DONTDUMP | VM_PFNMAP; + vm_flags_set(vma, VM_IO | VM_DONTCOPY | VM_DONTEXPAND | VM_NORESERVE | + VM_DONTDUMP | VM_PFNMAP); vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c index 729d26d648af..dd0436bf349a 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c @@ -1052,8 +1052,8 @@ int kfd_event_mmap(struct kfd_process *p, struct vm_area_struct *vma) pfn = __pa(page->kernel_address); pfn >>= PAGE_SHIFT; - vma->vm_flags |= VM_IO | VM_DONTCOPY | VM_DONTEXPAND | VM_NORESERVE - | VM_DONTDUMP | VM_PFNMAP; + vm_flags_set(vma, VM_IO | VM_DONTCOPY | VM_DONTEXPAND | VM_NORESERVE + | VM_DONTDUMP | VM_PFNMAP); pr_debug("Mapping signal page\n"); pr_debug(" start user address == 0x%08lx\n", vma->vm_start); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c index 51b1683ac5c1..1fad0ecdfaeb 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c @@ -1978,8 +1978,8 @@ int kfd_reserved_mem_mmap(struct kfd_dev *dev, struct kfd_process *process, return -ENOMEM; } - vma->vm_flags |= VM_IO | VM_DONTCOPY | VM_DONTEXPAND - | VM_NORESERVE | VM_DONTDUMP | VM_PFNMAP; + vm_flags_set(vma, VM_IO | VM_DONTCOPY | VM_DONTEXPAND + | VM_NORESERVE | VM_DONTDUMP | VM_PFNMAP); /* Mapping pages to user process */ return remap_pfn_range(vma, vma->vm_start, PFN_DOWN(__pa(qpd->cwsr_kaddr)), diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c index b8db675e7fb5..54c76003d2cc 100644 --- a/drivers/gpu/drm/drm_gem.c +++ b/drivers/gpu/drm/drm_gem.c @@ -1047,7 +1047,7 @@ int drm_gem_mmap_obj(struct drm_gem_object *obj, unsigned long obj_size, goto err_drm_gem_object_put; } - vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP; + vm_flags_set(vma, VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP); vma->vm_page_prot = pgprot_writecombine(vm_get_page_prot(vma->vm_flags)); vma->vm_page_prot = pgprot_decrypted(vma->vm_page_prot); } diff --git a/drivers/gpu/drm/drm_gem_dma_helper.c b/drivers/gpu/drm/drm_gem_dma_helper.c index 1e658c448366..fb2c764accc6 100644 --- a/drivers/gpu/drm/drm_gem_dma_helper.c +++ b/drivers/gpu/drm/drm_gem_dma_helper.c @@ -530,8 +530,7 @@ int drm_gem_dma_mmap(struct drm_gem_dma_object *dma_obj, struct vm_area_struct * * the whole buffer. */ vma->vm_pgoff -= drm_vma_node_start(&obj->vma_node); - vma->vm_flags &= ~VM_PFNMAP; - vma->vm_flags |= VM_DONTEXPAND; + vm_flags_mod(vma, VM_DONTEXPAND, VM_PFNMAP); if (dma_obj->map_noncoherent) { vma->vm_page_prot = vm_get_page_prot(vma->vm_flags); diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c index b602cd72a120..a2c28483e010 100644 --- a/drivers/gpu/drm/drm_gem_shmem_helper.c +++ b/drivers/gpu/drm/drm_gem_shmem_helper.c @@ -633,7 +633,7 @@ int drm_gem_shmem_mmap(struct drm_gem_shmem_object *shmem, struct vm_area_struct if (ret) return ret; - vma->vm_flags |= VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP; + vm_flags_set(vma, VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP); vma->vm_page_prot = vm_get_page_prot(vma->vm_flags); if (shmem->map_wc) vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot); diff --git a/drivers/gpu/drm/drm_vm.c b/drivers/gpu/drm/drm_vm.c index f024dc93939e..87c9fe55dec7 100644 --- a/drivers/gpu/drm/drm_vm.c +++ b/drivers/gpu/drm/drm_vm.c @@ -476,7 +476,7 @@ static int drm_mmap_dma(struct file *filp, struct vm_area_struct *vma) if (!capable(CAP_SYS_ADMIN) && (dma->flags & _DRM_DMA_USE_PCI_RO)) { - vma->vm_flags &= ~(VM_WRITE | VM_MAYWRITE); + vm_flags_clear(vma, VM_WRITE | VM_MAYWRITE); #if defined(__i386__) || defined(__x86_64__) pgprot_val(vma->vm_page_prot) &= ~_PAGE_RW; #else @@ -492,7 +492,7 @@ static int drm_mmap_dma(struct file *filp, struct vm_area_struct *vma) vma->vm_ops = &drm_vm_dma_ops; - vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP; + vm_flags_set(vma, VM_DONTEXPAND | VM_DONTDUMP); drm_vm_open_locked(dev, vma); return 0; @@ -560,7 +560,7 @@ static int drm_mmap_locked(struct file *filp, struct vm_area_struct *vma) return -EINVAL; if (!capable(CAP_SYS_ADMIN) && (map->flags & _DRM_READ_ONLY)) { - vma->vm_flags &= ~(VM_WRITE | VM_MAYWRITE); + vm_flags_clear(vma, VM_WRITE | VM_MAYWRITE); #if defined(__i386__) || defined(__x86_64__) pgprot_val(vma->vm_page_prot) &= ~_PAGE_RW; #else @@ -628,7 +628,7 @@ static int drm_mmap_locked(struct file *filp, struct vm_area_struct *vma) default: return -EINVAL; /* This should never happen. */ } - vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP; + vm_flags_set(vma, VM_DONTEXPAND | VM_DONTDUMP); drm_vm_open_locked(dev, vma); return 0; diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c index c5ae5492e1af..b5f73502e3dd 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c @@ -130,7 +130,7 @@ static int etnaviv_gem_mmap_obj(struct etnaviv_gem_object *etnaviv_obj, { pgprot_t vm_page_prot; - vma->vm_flags |= VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP; + vm_flags_set(vma, VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP); vm_page_prot = vm_get_page_prot(vma->vm_flags); diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.c b/drivers/gpu/drm/exynos/exynos_drm_gem.c index 3e493f48e0d4..638ca96830e9 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_gem.c +++ b/drivers/gpu/drm/exynos/exynos_drm_gem.c @@ -274,7 +274,7 @@ static int exynos_drm_gem_mmap_buffer(struct exynos_drm_gem *exynos_gem, unsigned long vm_size; int ret; - vma->vm_flags &= ~VM_PFNMAP; + vm_flags_clear(vma, VM_PFNMAP); vma->vm_pgoff = 0; vm_size = vma->vm_end - vma->vm_start; @@ -368,7 +368,7 @@ static int exynos_drm_gem_mmap(struct drm_gem_object *obj, struct vm_area_struct if (obj->import_attach) return dma_buf_mmap(obj->dma_buf, vma, 0); - vma->vm_flags |= VM_IO | VM_DONTEXPAND | VM_DONTDUMP; + vm_flags_set(vma, VM_IO | VM_DONTEXPAND | VM_DONTDUMP); DRM_DEV_DEBUG_KMS(to_dma_dev(obj->dev), "flags = 0x%x\n", exynos_gem->flags); diff --git a/drivers/gpu/drm/gma500/framebuffer.c b/drivers/gpu/drm/gma500/framebuffer.c index 8d5a37b8f110..a9276c8a3e4e 100644 --- a/drivers/gpu/drm/gma500/framebuffer.c +++ b/drivers/gpu/drm/gma500/framebuffer.c @@ -139,7 +139,7 @@ static int psbfb_mmap(struct fb_info *info, struct vm_area_struct *vma) */ vma->vm_ops = &psbfb_vm_ops; vma->vm_private_data = (void *)fb; - vma->vm_flags |= VM_IO | VM_MIXEDMAP | VM_DONTEXPAND | VM_DONTDUMP; + vm_flags_set(vma, VM_IO | VM_MIXEDMAP | VM_DONTEXPAND | VM_DONTDUMP); return 0; } diff --git a/drivers/gpu/drm/i810/i810_dma.c b/drivers/gpu/drm/i810/i810_dma.c index 9fb4dd63342f..01967dd88762 100644 --- a/drivers/gpu/drm/i810/i810_dma.c +++ b/drivers/gpu/drm/i810/i810_dma.c @@ -102,7 +102,7 @@ static int i810_mmap_buffers(struct file *filp, struct vm_area_struct *vma) buf = dev_priv->mmap_buffer; buf_priv = buf->dev_private; - vma->vm_flags |= VM_DONTCOPY; + vm_flags_set(vma, VM_DONTCOPY); buf_priv->currently_mapped = I810_BUF_MAPPED; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c index 0ad44f3868de..e95f4c729ca5 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c @@ -979,7 +979,7 @@ int i915_gem_mmap(struct file *filp, struct vm_area_struct *vma) i915_gem_object_put(obj); return -EINVAL; } - vma->vm_flags &= ~VM_MAYWRITE; + vm_flags_clear(vma, VM_MAYWRITE); } anon = mmap_singleton(to_i915(dev)); @@ -988,7 +988,7 @@ int i915_gem_mmap(struct file *filp, struct vm_area_struct *vma) return PTR_ERR(anon); } - vma->vm_flags |= VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP | VM_IO; + vm_flags_set(vma, VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP | VM_IO); /* * We keep the ref on mmo->obj, not vm_file, but we require diff --git a/drivers/gpu/drm/mediatek/mtk_drm_gem.c b/drivers/gpu/drm/mediatek/mtk_drm_gem.c index 47e96b0289f9..28659514bf20 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_gem.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_gem.c @@ -158,7 +158,7 @@ static int mtk_drm_gem_object_mmap(struct drm_gem_object *obj, * dma_alloc_attrs() allocated a struct page table for mtk_gem, so clear * VM_PFNMAP flag that was set by drm_gem_mmap_obj()/drm_gem_mmap(). */ - vma->vm_flags |= VM_IO | VM_DONTEXPAND | VM_DONTDUMP; + vm_flags_set(vma, VM_IO | VM_DONTEXPAND | VM_DONTDUMP); vma->vm_page_prot = pgprot_writecombine(vm_get_page_prot(vma->vm_flags)); vma->vm_page_prot = pgprot_decrypted(vma->vm_page_prot); diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index 1dee0d18abbb..c2fb98a94bc3 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -1012,7 +1012,7 @@ static int msm_gem_object_mmap(struct drm_gem_object *obj, struct vm_area_struct { struct msm_gem_object *msm_obj = to_msm_bo(obj); - vma->vm_flags |= VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP; + vm_flags_set(vma, VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP); vma->vm_page_prot = msm_gem_pgprot(msm_obj, vm_get_page_prot(vma->vm_flags)); return 0; diff --git a/drivers/gpu/drm/omapdrm/omap_gem.c b/drivers/gpu/drm/omapdrm/omap_gem.c index cf571796fd26..19fef933904b 100644 --- a/drivers/gpu/drm/omapdrm/omap_gem.c +++ b/drivers/gpu/drm/omapdrm/omap_gem.c @@ -543,8 +543,7 @@ int omap_gem_mmap_obj(struct drm_gem_object *obj, { struct omap_gem_object *omap_obj = to_omap_bo(obj); - vma->vm_flags &= ~VM_PFNMAP; - vma->vm_flags |= VM_MIXEDMAP; + vm_flags_mod(vma, VM_MIXEDMAP, VM_PFNMAP); if (omap_obj->flags & OMAP_BO_WC) { vma->vm_page_prot = pgprot_writecombine(vm_get_page_prot(vma->vm_flags)); diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_gem.c b/drivers/gpu/drm/rockchip/rockchip_drm_gem.c index 6edb7c52cb3d..8ea09d915c3c 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_gem.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_gem.c @@ -251,8 +251,7 @@ static int rockchip_drm_gem_object_mmap(struct drm_gem_object *obj, * We allocated a struct page table for rk_obj, so clear * VM_PFNMAP flag that was set by drm_gem_mmap_obj()/drm_gem_mmap(). */ - vma->vm_flags |= VM_IO | VM_DONTEXPAND | VM_DONTDUMP; - vma->vm_flags &= ~VM_PFNMAP; + vm_flags_mod(vma, VM_IO | VM_DONTEXPAND | VM_DONTDUMP, VM_PFNMAP); vma->vm_page_prot = pgprot_writecombine(vm_get_page_prot(vma->vm_flags)); vma->vm_page_prot = pgprot_decrypted(vma->vm_page_prot); diff --git a/drivers/gpu/drm/tegra/gem.c b/drivers/gpu/drm/tegra/gem.c index 979e7bc902f6..bce991a2ccc0 100644 --- a/drivers/gpu/drm/tegra/gem.c +++ b/drivers/gpu/drm/tegra/gem.c @@ -574,7 +574,7 @@ int __tegra_gem_mmap(struct drm_gem_object *gem, struct vm_area_struct *vma) * and set the vm_pgoff (used as a fake buffer offset by DRM) * to 0 as we want to map the whole buffer. */ - vma->vm_flags &= ~VM_PFNMAP; + vm_flags_clear(vma, VM_PFNMAP); vma->vm_pgoff = 0; err = dma_mmap_wc(gem->dev->dev, vma, bo->vaddr, bo->iova, @@ -588,8 +588,7 @@ int __tegra_gem_mmap(struct drm_gem_object *gem, struct vm_area_struct *vma) } else { pgprot_t prot = vm_get_page_prot(vma->vm_flags); - vma->vm_flags |= VM_MIXEDMAP; - vma->vm_flags &= ~VM_PFNMAP; + vm_flags_mod(vma, VM_MIXEDMAP, VM_PFNMAP); vma->vm_page_prot = pgprot_writecombine(prot); } diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c index 5a3e4b891377..c00207582c74 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_vm.c +++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c @@ -468,8 +468,7 @@ int ttm_bo_mmap_obj(struct vm_area_struct *vma, struct ttm_buffer_object *bo) vma->vm_private_data = bo; - vma->vm_flags |= VM_PFNMAP; - vma->vm_flags |= VM_IO | VM_DONTEXPAND | VM_DONTDUMP; + vm_flags_set(vma, VM_PFNMAP | VM_IO | VM_DONTEXPAND | VM_DONTDUMP); return 0; } EXPORT_SYMBOL(ttm_bo_mmap_obj); diff --git a/drivers/gpu/drm/virtio/virtgpu_vram.c b/drivers/gpu/drm/virtio/virtgpu_vram.c index 6b45b0429fef..25df81c02783 100644 --- a/drivers/gpu/drm/virtio/virtgpu_vram.c +++ b/drivers/gpu/drm/virtio/virtgpu_vram.c @@ -46,7 +46,7 @@ static int virtio_gpu_vram_mmap(struct drm_gem_object *obj, return -EINVAL; vma->vm_pgoff -= drm_vma_node_start(&obj->vma_node); - vma->vm_flags |= VM_MIXEDMAP | VM_DONTEXPAND; + vm_flags_set(vma, VM_MIXEDMAP | VM_DONTEXPAND); vma->vm_page_prot = vm_get_page_prot(vma->vm_flags); vma->vm_page_prot = pgprot_decrypted(vma->vm_page_prot); vma->vm_ops = &virtio_gpu_vram_vm_ops; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c index 265f7c48d856..90097d04b45f 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c @@ -97,7 +97,7 @@ int vmw_mmap(struct file *filp, struct vm_area_struct *vma) /* Use VM_PFNMAP rather than VM_MIXEDMAP if not a COW mapping */ if (!is_cow_mapping(vma->vm_flags)) - vma->vm_flags = (vma->vm_flags & ~VM_MIXEDMAP) | VM_PFNMAP; + vm_flags_mod(vma, VM_PFNMAP, VM_MIXEDMAP); ttm_bo_put(bo); /* release extra ref taken by ttm_bo_mmap_obj() */ diff --git a/drivers/gpu/drm/xen/xen_drm_front_gem.c b/drivers/gpu/drm/xen/xen_drm_front_gem.c index 4c95ebcdcc2d..3ad2b4cfd1f0 100644 --- a/drivers/gpu/drm/xen/xen_drm_front_gem.c +++ b/drivers/gpu/drm/xen/xen_drm_front_gem.c @@ -69,8 +69,7 @@ static int xen_drm_front_gem_object_mmap(struct drm_gem_object *gem_obj, * vm_pgoff (used as a fake buffer offset by DRM) to 0 as we want to map * the whole buffer. */ - vma->vm_flags &= ~VM_PFNMAP; - vma->vm_flags |= VM_MIXEDMAP | VM_DONTEXPAND; + vm_flags_mod(vma, VM_MIXEDMAP | VM_DONTEXPAND, VM_PFNMAP); vma->vm_pgoff = 0; /* diff --git a/drivers/hsi/clients/cmt_speech.c b/drivers/hsi/clients/cmt_speech.c index 8069f795c864..daa8e1bff5d9 100644 --- a/drivers/hsi/clients/cmt_speech.c +++ b/drivers/hsi/clients/cmt_speech.c @@ -1264,7 +1264,7 @@ static int cs_char_mmap(struct file *file, struct vm_area_struct *vma) if (vma_pages(vma) != 1) return -EINVAL; - vma->vm_flags |= VM_IO | VM_DONTDUMP | VM_DONTEXPAND; + vm_flags_set(vma, VM_IO | VM_DONTDUMP | VM_DONTEXPAND); vma->vm_ops = &cs_char_vm_ops; vma->vm_private_data = file->private_data; diff --git a/drivers/hwtracing/intel_th/msu.c b/drivers/hwtracing/intel_th/msu.c index 6c8215a47a60..9621efe0e95c 100644 --- a/drivers/hwtracing/intel_th/msu.c +++ b/drivers/hwtracing/intel_th/msu.c @@ -1659,7 +1659,7 @@ out: atomic_dec(&msc->user_count); vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); - vma->vm_flags |= VM_DONTEXPAND | VM_DONTCOPY; + vm_flags_set(vma, VM_DONTEXPAND | VM_DONTCOPY); vma->vm_ops = &msc_mmap_ops; return ret; } diff --git a/drivers/hwtracing/stm/core.c b/drivers/hwtracing/stm/core.c index 2712e699ba08..534fbefc7f6a 100644 --- a/drivers/hwtracing/stm/core.c +++ b/drivers/hwtracing/stm/core.c @@ -715,7 +715,7 @@ static int stm_char_mmap(struct file *file, struct vm_area_struct *vma) pm_runtime_get_sync(&stm->dev); vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); - vma->vm_flags |= VM_IO | VM_DONTEXPAND | VM_DONTDUMP; + vm_flags_set(vma, VM_IO | VM_DONTEXPAND | VM_DONTDUMP); vma->vm_ops = &stm_mmap_vmops; vm_iomap_memory(vma, phys, size); diff --git a/drivers/infiniband/hw/hfi1/file_ops.c b/drivers/infiniband/hw/hfi1/file_ops.c index f5f9269fdc16..c6e59bc480f9 100644 --- a/drivers/infiniband/hw/hfi1/file_ops.c +++ b/drivers/infiniband/hw/hfi1/file_ops.c @@ -403,7 +403,7 @@ static int hfi1_file_mmap(struct file *fp, struct vm_area_struct *vma) ret = -EPERM; goto done; } - vma->vm_flags &= ~VM_MAYWRITE; + vm_flags_clear(vma, VM_MAYWRITE); addr = vma->vm_start; for (i = 0 ; i < uctxt->egrbufs.numbufs; i++) { memlen = uctxt->egrbufs.buffers[i].len; @@ -528,7 +528,7 @@ static int hfi1_file_mmap(struct file *fp, struct vm_area_struct *vma) goto done; } - vma->vm_flags = flags; + vm_flags_reset(vma, flags); hfi1_cdbg(PROC, "%u:%u type:%u io/vf:%d/%d, addr:0x%llx, len:%lu(%lu), flags:0x%lx\n", ctxt, subctxt, type, mapio, vmf, memaddr, memlen, diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index c669ef6e47e7..e3c97aa2c46c 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -2087,7 +2087,7 @@ static int mlx5_ib_mmap_clock_info_page(struct mlx5_ib_dev *dev, if (vma->vm_flags & (VM_WRITE | VM_EXEC)) return -EPERM; - vma->vm_flags &= ~VM_MAYWRITE; + vm_flags_clear(vma, VM_MAYWRITE); if (!dev->mdev->clock_info) return -EOPNOTSUPP; @@ -2311,7 +2311,7 @@ static int mlx5_ib_mmap(struct ib_ucontext *ibcontext, struct vm_area_struct *vm if (vma->vm_flags & VM_WRITE) return -EPERM; - vma->vm_flags &= ~VM_MAYWRITE; + vm_flags_clear(vma, VM_MAYWRITE); /* Don't expose to user-space information it shouldn't have */ if (PAGE_SIZE > 4096) diff --git a/drivers/infiniband/hw/qib/qib_file_ops.c b/drivers/infiniband/hw/qib/qib_file_ops.c index 3937144b2ae5..80fe92a21f96 100644 --- a/drivers/infiniband/hw/qib/qib_file_ops.c +++ b/drivers/infiniband/hw/qib/qib_file_ops.c @@ -733,7 +733,7 @@ static int qib_mmap_mem(struct vm_area_struct *vma, struct qib_ctxtdata *rcd, } /* don't allow them to later change with mprotect */ - vma->vm_flags &= ~VM_MAYWRITE; + vm_flags_clear(vma, VM_MAYWRITE); } pfn = virt_to_phys(kvaddr) >> PAGE_SHIFT; @@ -769,7 +769,7 @@ static int mmap_ureg(struct vm_area_struct *vma, struct qib_devdata *dd, phys = dd->physaddr + ureg; vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); - vma->vm_flags |= VM_DONTCOPY | VM_DONTEXPAND; + vm_flags_set(vma, VM_DONTCOPY | VM_DONTEXPAND); ret = io_remap_pfn_range(vma, vma->vm_start, phys >> PAGE_SHIFT, vma->vm_end - vma->vm_start, @@ -810,8 +810,7 @@ static int mmap_piobufs(struct vm_area_struct *vma, * don't allow them to later change to readable with mprotect (for when * not initially mapped readable, as is normally the case) */ - vma->vm_flags &= ~VM_MAYREAD; - vma->vm_flags |= VM_DONTCOPY | VM_DONTEXPAND; + vm_flags_mod(vma, VM_DONTCOPY | VM_DONTEXPAND, VM_MAYREAD); /* We used PAT if wc_cookie == 0 */ if (!dd->wc_cookie) @@ -852,7 +851,7 @@ static int mmap_rcvegrbufs(struct vm_area_struct *vma, goto bail; } /* don't allow them to later change to writable with mprotect */ - vma->vm_flags &= ~VM_MAYWRITE; + vm_flags_clear(vma, VM_MAYWRITE); start = vma->vm_start; @@ -944,7 +943,7 @@ static int mmap_kvaddr(struct vm_area_struct *vma, u64 pgaddr, * Don't allow permission to later change to writable * with mprotect. */ - vma->vm_flags &= ~VM_MAYWRITE; + vm_flags_clear(vma, VM_MAYWRITE); } else goto bail; len = vma->vm_end - vma->vm_start; @@ -955,7 +954,7 @@ static int mmap_kvaddr(struct vm_area_struct *vma, u64 pgaddr, vma->vm_pgoff = (unsigned long) addr >> PAGE_SHIFT; vma->vm_ops = &qib_file_vm_ops; - vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP; + vm_flags_set(vma, VM_DONTEXPAND | VM_DONTDUMP); ret = 1; bail: diff --git a/drivers/infiniband/hw/usnic/usnic_ib_verbs.c b/drivers/infiniband/hw/usnic/usnic_ib_verbs.c index 6e8c4fbb8083..6289238cc5af 100644 --- a/drivers/infiniband/hw/usnic/usnic_ib_verbs.c +++ b/drivers/infiniband/hw/usnic/usnic_ib_verbs.c @@ -672,7 +672,7 @@ int usnic_ib_mmap(struct ib_ucontext *context, usnic_dbg("\n"); us_ibdev = to_usdev(context->device); - vma->vm_flags |= VM_IO; + vm_flags_set(vma, VM_IO); vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); vfid = vma->vm_pgoff; usnic_dbg("Page Offset %lu PAGE_SHIFT %u VFID %u\n", diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.c index 19176583dbde..9f54aa90a35a 100644 --- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.c +++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.c @@ -408,7 +408,7 @@ int pvrdma_mmap(struct ib_ucontext *ibcontext, struct vm_area_struct *vma) } /* Map UAR to kernel space, VM_LOCKED? */ - vma->vm_flags |= VM_DONTCOPY | VM_DONTEXPAND; + vm_flags_set(vma, VM_DONTCOPY | VM_DONTEXPAND); vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); if (io_remap_pfn_range(vma, start, context->uar.pfn, size, vma->vm_page_prot)) diff --git a/drivers/media/common/videobuf2/videobuf2-dma-contig.c b/drivers/media/common/videobuf2/videobuf2-dma-contig.c index 5f1175f8b349..205d3cac425c 100644 --- a/drivers/media/common/videobuf2/videobuf2-dma-contig.c +++ b/drivers/media/common/videobuf2/videobuf2-dma-contig.c @@ -293,7 +293,7 @@ static int vb2_dc_mmap(void *buf_priv, struct vm_area_struct *vma) return ret; } - vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP; + vm_flags_set(vma, VM_DONTEXPAND | VM_DONTDUMP); vma->vm_private_data = &buf->handler; vma->vm_ops = &vb2_common_vm_ops; diff --git a/drivers/media/common/videobuf2/videobuf2-vmalloc.c b/drivers/media/common/videobuf2/videobuf2-vmalloc.c index 959b45beb1f3..a6c6d2fcaaa4 100644 --- a/drivers/media/common/videobuf2/videobuf2-vmalloc.c +++ b/drivers/media/common/videobuf2/videobuf2-vmalloc.c @@ -185,7 +185,7 @@ static int vb2_vmalloc_mmap(void *buf_priv, struct vm_area_struct *vma) /* * Make sure that vm_areas for 2 buffers won't be merged together */ - vma->vm_flags |= VM_DONTEXPAND; + vm_flags_set(vma, VM_DONTEXPAND); /* * Use common vm_area operations to track buffer refcount. diff --git a/drivers/media/v4l2-core/videobuf-dma-contig.c b/drivers/media/v4l2-core/videobuf-dma-contig.c index f2c439359557..4c2ec7a0d804 100644 --- a/drivers/media/v4l2-core/videobuf-dma-contig.c +++ b/drivers/media/v4l2-core/videobuf-dma-contig.c @@ -314,7 +314,7 @@ static int __videobuf_mmap_mapper(struct videobuf_queue *q, } vma->vm_ops = &videobuf_vm_ops; - vma->vm_flags |= VM_DONTEXPAND; + vm_flags_set(vma, VM_DONTEXPAND); vma->vm_private_data = map; dev_dbg(q->dev, "mmap %p: q=%p %08lx-%08lx (%lx) pgoff %08lx buf %d\n", diff --git a/drivers/media/v4l2-core/videobuf-dma-sg.c b/drivers/media/v4l2-core/videobuf-dma-sg.c index 234e9f647c96..53001532e8e3 100644 --- a/drivers/media/v4l2-core/videobuf-dma-sg.c +++ b/drivers/media/v4l2-core/videobuf-dma-sg.c @@ -630,8 +630,8 @@ static int __videobuf_mmap_mapper(struct videobuf_queue *q, map->count = 1; map->q = q; vma->vm_ops = &videobuf_vm_ops; - vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP; - vma->vm_flags &= ~VM_IO; /* using shared anonymous pages */ + /* using shared anonymous pages */ + vm_flags_mod(vma, VM_DONTEXPAND | VM_DONTDUMP, VM_IO); vma->vm_private_data = map; dprintk(1, "mmap %p: q=%p %08lx-%08lx pgoff %08lx bufs %d-%d\n", map, q, vma->vm_start, vma->vm_end, vma->vm_pgoff, first, last); diff --git a/drivers/media/v4l2-core/videobuf-vmalloc.c b/drivers/media/v4l2-core/videobuf-vmalloc.c index 9b2443720ab0..85c7090606d6 100644 --- a/drivers/media/v4l2-core/videobuf-vmalloc.c +++ b/drivers/media/v4l2-core/videobuf-vmalloc.c @@ -247,7 +247,7 @@ static int __videobuf_mmap_mapper(struct videobuf_queue *q, } vma->vm_ops = &videobuf_vm_ops; - vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP; + vm_flags_set(vma, VM_DONTEXPAND | VM_DONTDUMP); vma->vm_private_data = map; dprintk(1, "mmap %p: q=%p %08lx-%08lx (%lx) pgoff %08lx buf %d\n", diff --git a/drivers/misc/cxl/context.c b/drivers/misc/cxl/context.c index acaa44809c58..76b5ea66dfa1 100644 --- a/drivers/misc/cxl/context.c +++ b/drivers/misc/cxl/context.c @@ -220,7 +220,7 @@ int cxl_context_iomap(struct cxl_context *ctx, struct vm_area_struct *vma) pr_devel("%s: mmio physical: %llx pe: %i master:%i\n", __func__, ctx->psn_phys, ctx->pe , ctx->master); - vma->vm_flags |= VM_IO | VM_PFNMAP; + vm_flags_set(vma, VM_IO | VM_PFNMAP); vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); vma->vm_ops = &cxl_mmap_vmops; return 0; diff --git a/drivers/misc/habanalabs/common/memory.c b/drivers/misc/habanalabs/common/memory.c index 5e9ae7600d75..6bb44a3ad5e6 100644 --- a/drivers/misc/habanalabs/common/memory.c +++ b/drivers/misc/habanalabs/common/memory.c @@ -2082,7 +2082,7 @@ static int hl_ts_mmap(struct hl_mmap_mem_buf *buf, struct vm_area_struct *vma, v { struct hl_ts_buff *ts_buff = buf->private; - vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP | VM_DONTCOPY | VM_NORESERVE; + vm_flags_set(vma, VM_DONTEXPAND | VM_DONTDUMP | VM_DONTCOPY | VM_NORESERVE); return remap_vmalloc_range(vma, ts_buff->user_buff_address, 0); } diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c index 9f5e208701ba..3b0afdc50ff9 100644 --- a/drivers/misc/habanalabs/gaudi/gaudi.c +++ b/drivers/misc/habanalabs/gaudi/gaudi.c @@ -4236,8 +4236,8 @@ static int gaudi_mmap(struct hl_device *hdev, struct vm_area_struct *vma, { int rc; - vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP | - VM_DONTCOPY | VM_NORESERVE; + vm_flags_set(vma, VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP | + VM_DONTCOPY | VM_NORESERVE); rc = dma_mmap_coherent(hdev->dev, vma, cpu_addr, (dma_addr - HOST_PHYS_BASE), size); diff --git a/drivers/misc/habanalabs/gaudi2/gaudi2.c b/drivers/misc/habanalabs/gaudi2/gaudi2.c index e793fb2bdcbe..65502ec02bc0 100644 --- a/drivers/misc/habanalabs/gaudi2/gaudi2.c +++ b/drivers/misc/habanalabs/gaudi2/gaudi2.c @@ -5538,8 +5538,8 @@ static int gaudi2_mmap(struct hl_device *hdev, struct vm_area_struct *vma, { int rc; - vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP | - VM_DONTCOPY | VM_NORESERVE; + vm_flags_set(vma, VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP | + VM_DONTCOPY | VM_NORESERVE); #ifdef _HAS_DMA_MMAP_COHERENT @@ -10116,8 +10116,8 @@ static int gaudi2_block_mmap(struct hl_device *hdev, struct vm_area_struct *vma, address = pci_resource_start(hdev->pdev, SRAM_CFG_BAR_ID) + offset_in_bar; - vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP | - VM_DONTCOPY | VM_NORESERVE; + vm_flags_set(vma, VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP | + VM_DONTCOPY | VM_NORESERVE); rc = remap_pfn_range(vma, vma->vm_start, address >> PAGE_SHIFT, block_size, vma->vm_page_prot); diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c index 0f083fcf81a6..2a15a305d01b 100644 --- a/drivers/misc/habanalabs/goya/goya.c +++ b/drivers/misc/habanalabs/goya/goya.c @@ -2880,8 +2880,8 @@ static int goya_mmap(struct hl_device *hdev, struct vm_area_struct *vma, { int rc; - vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP | - VM_DONTCOPY | VM_NORESERVE; + vm_flags_set(vma, VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP | + VM_DONTCOPY | VM_NORESERVE); rc = dma_mmap_coherent(hdev->dev, vma, cpu_addr, (dma_addr - HOST_PHYS_BASE), size); diff --git a/drivers/misc/ocxl/context.c b/drivers/misc/ocxl/context.c index 9eb0d93b01c6..7f83116ae11a 100644 --- a/drivers/misc/ocxl/context.c +++ b/drivers/misc/ocxl/context.c @@ -180,7 +180,7 @@ static int check_mmap_afu_irq(struct ocxl_context *ctx, if ((vma->vm_flags & VM_READ) || (vma->vm_flags & VM_EXEC) || !(vma->vm_flags & VM_WRITE)) return -EINVAL; - vma->vm_flags &= ~(VM_MAYREAD | VM_MAYEXEC); + vm_flags_clear(vma, VM_MAYREAD | VM_MAYEXEC); return 0; } @@ -204,7 +204,7 @@ int ocxl_context_mmap(struct ocxl_context *ctx, struct vm_area_struct *vma) if (rc) return rc; - vma->vm_flags |= VM_IO | VM_PFNMAP; + vm_flags_set(vma, VM_IO | VM_PFNMAP); vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); vma->vm_ops = &ocxl_vmops; return 0; diff --git a/drivers/misc/ocxl/sysfs.c b/drivers/misc/ocxl/sysfs.c index 25c78df8055d..405180d47d9b 100644 --- a/drivers/misc/ocxl/sysfs.c +++ b/drivers/misc/ocxl/sysfs.c @@ -134,7 +134,7 @@ static int global_mmio_mmap(struct file *filp, struct kobject *kobj, (afu->config.global_mmio_size >> PAGE_SHIFT)) return -EINVAL; - vma->vm_flags |= VM_IO | VM_PFNMAP; + vm_flags_set(vma, VM_IO | VM_PFNMAP); vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); vma->vm_ops = &global_mmio_vmops; vma->vm_private_data = afu; diff --git a/drivers/misc/open-dice.c b/drivers/misc/open-dice.c index 9dda47b3fd70..8aea2d070a40 100644 --- a/drivers/misc/open-dice.c +++ b/drivers/misc/open-dice.c @@ -95,12 +95,12 @@ static int open_dice_mmap(struct file *filp, struct vm_area_struct *vma) if (vma->vm_flags & VM_WRITE) return -EPERM; /* Ensure userspace cannot acquire VM_WRITE later. */ - vma->vm_flags &= ~VM_MAYWRITE; + vm_flags_clear(vma, VM_MAYWRITE); } /* Create write-combine mapping so all clients observe a wipe. */ vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot); - vma->vm_flags |= VM_DONTCOPY | VM_DONTDUMP; + vm_flags_set(vma, VM_DONTCOPY | VM_DONTDUMP); return vm_iomap_memory(vma, drvdata->rmem->base, drvdata->rmem->size); } diff --git a/drivers/misc/sgi-gru/grufile.c b/drivers/misc/sgi-gru/grufile.c index 7ffcfc0bb587..a3d659c11cc4 100644 --- a/drivers/misc/sgi-gru/grufile.c +++ b/drivers/misc/sgi-gru/grufile.c @@ -101,8 +101,8 @@ static int gru_file_mmap(struct file *file, struct vm_area_struct *vma) vma->vm_end & (GRU_GSEG_PAGESIZE - 1)) return -EINVAL; - vma->vm_flags |= VM_IO | VM_PFNMAP | VM_LOCKED | - VM_DONTCOPY | VM_DONTEXPAND | VM_DONTDUMP; + vm_flags_set(vma, VM_IO | VM_PFNMAP | VM_LOCKED | + VM_DONTCOPY | VM_DONTEXPAND | VM_DONTDUMP); vma->vm_page_prot = PAGE_SHARED; vma->vm_ops = &gru_vm_ops; diff --git a/drivers/misc/uacce/uacce.c b/drivers/misc/uacce/uacce.c index 905eff1f840e..b65ab440a19e 100644 --- a/drivers/misc/uacce/uacce.c +++ b/drivers/misc/uacce/uacce.c @@ -229,7 +229,7 @@ static int uacce_fops_mmap(struct file *filep, struct vm_area_struct *vma) if (!qfr) return -ENOMEM; - vma->vm_flags |= VM_DONTCOPY | VM_DONTEXPAND | VM_WIPEONFORK; + vm_flags_set(vma, VM_DONTCOPY | VM_DONTEXPAND | VM_WIPEONFORK); vma->vm_ops = &uacce_vm_ops; vma->vm_private_data = q; qfr->type = type; diff --git a/drivers/sbus/char/oradax.c b/drivers/sbus/char/oradax.c index 21b7cb6e7e70..e300cf26bc2a 100644 --- a/drivers/sbus/char/oradax.c +++ b/drivers/sbus/char/oradax.c @@ -389,7 +389,7 @@ static int dax_devmap(struct file *f, struct vm_area_struct *vma) /* completion area is mapped read-only for user */ if (vma->vm_flags & VM_WRITE) return -EPERM; - vma->vm_flags &= ~VM_MAYWRITE; + vm_flags_clear(vma, VM_MAYWRITE); if (remap_pfn_range(vma, vma->vm_start, ctx->ca_buf_ra >> PAGE_SHIFT, len, vma->vm_page_prot)) diff --git a/drivers/scsi/cxlflash/ocxl_hw.c b/drivers/scsi/cxlflash/ocxl_hw.c index 631eda2d467e..6542818e595a 100644 --- a/drivers/scsi/cxlflash/ocxl_hw.c +++ b/drivers/scsi/cxlflash/ocxl_hw.c @@ -1167,7 +1167,7 @@ static int afu_mmap(struct file *file, struct vm_area_struct *vma) (ctx->psn_size >> PAGE_SHIFT)) return -EINVAL; - vma->vm_flags |= VM_IO | VM_PFNMAP; + vm_flags_set(vma, VM_IO | VM_PFNMAP); vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); vma->vm_ops = &ocxlflash_vmops; return 0; diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index ff9854f59964..a91049213203 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -1288,7 +1288,7 @@ sg_mmap(struct file *filp, struct vm_area_struct *vma) } sfp->mmap_called = 1; - vma->vm_flags |= VM_IO | VM_DONTEXPAND | VM_DONTDUMP; + vm_flags_set(vma, VM_IO | VM_DONTEXPAND | VM_DONTDUMP); vma->vm_private_data = sfp; vma->vm_ops = &sg_mmap_vm_ops; out: diff --git a/drivers/staging/media/atomisp/pci/hmm/hmm_bo.c b/drivers/staging/media/atomisp/pci/hmm/hmm_bo.c index 5e53eed8ae95..095cd0ba8c21 100644 --- a/drivers/staging/media/atomisp/pci/hmm/hmm_bo.c +++ b/drivers/staging/media/atomisp/pci/hmm/hmm_bo.c @@ -1072,7 +1072,7 @@ int hmm_bo_mmap(struct vm_area_struct *vma, struct hmm_buffer_object *bo) vma->vm_private_data = bo; vma->vm_ops = &hmm_bo_vm_ops; - vma->vm_flags |= VM_IO | VM_DONTEXPAND | VM_DONTDUMP; + vm_flags_set(vma, VM_IO | VM_DONTEXPAND | VM_DONTDUMP); /* * call hmm_bo_vm_open explicitly. diff --git a/drivers/staging/media/deprecated/meye/meye.c b/drivers/staging/media/deprecated/meye/meye.c index 5d87efd9b95c..746c6ea1c0a7 100644 --- a/drivers/staging/media/deprecated/meye/meye.c +++ b/drivers/staging/media/deprecated/meye/meye.c @@ -1476,8 +1476,8 @@ static int meye_mmap(struct file *file, struct vm_area_struct *vma) } vma->vm_ops = &meye_vm_ops; - vma->vm_flags &= ~VM_IO; /* not I/O memory */ - vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP; + /* not I/O memory */ + vm_flags_mod(vma, VM_DONTEXPAND | VM_DONTDUMP, VM_IO); vma->vm_private_data = (void *) (offset / gbufsize); meye_vm_open(vma); diff --git a/drivers/staging/media/deprecated/stkwebcam/stk-webcam.c b/drivers/staging/media/deprecated/stkwebcam/stk-webcam.c index 787edb3d47c2..a1b7ad350a90 100644 --- a/drivers/staging/media/deprecated/stkwebcam/stk-webcam.c +++ b/drivers/staging/media/deprecated/stkwebcam/stk-webcam.c @@ -779,7 +779,7 @@ static int v4l_stk_mmap(struct file *fp, struct vm_area_struct *vma) ret = remap_vmalloc_range(vma, sbuf->buffer, 0); if (ret) return ret; - vma->vm_flags |= VM_DONTEXPAND; + vm_flags_set(vma, VM_DONTEXPAND); vma->vm_private_data = sbuf; vma->vm_ops = &stk_v4l_vm_ops; sbuf->v4lbuf.flags |= V4L2_BUF_FLAG_MAPPED; diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c index 2940559c3086..15ffc8d2ac7b 100644 --- a/drivers/target/target_core_user.c +++ b/drivers/target/target_core_user.c @@ -1928,7 +1928,7 @@ static int tcmu_mmap(struct uio_info *info, struct vm_area_struct *vma) { struct tcmu_dev *udev = container_of(info, struct tcmu_dev, uio_info); - vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP; + vm_flags_set(vma, VM_DONTEXPAND | VM_DONTDUMP); vma->vm_ops = &tcmu_vm_ops; vma->vm_private_data = udev; diff --git a/drivers/uio/uio.c b/drivers/uio/uio.c index 43afbb7c5ab9..62082d64ece0 100644 --- a/drivers/uio/uio.c +++ b/drivers/uio/uio.c @@ -713,7 +713,7 @@ static const struct vm_operations_struct uio_logical_vm_ops = { static int uio_mmap_logical(struct vm_area_struct *vma) { - vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP; + vm_flags_set(vma, VM_DONTEXPAND | VM_DONTDUMP); vma->vm_ops = &uio_logical_vm_ops; return 0; } diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c index 837f3e57f580..e501a03d6c70 100644 --- a/drivers/usb/core/devio.c +++ b/drivers/usb/core/devio.c @@ -279,8 +279,7 @@ static int usbdev_mmap(struct file *file, struct vm_area_struct *vma) } } - vma->vm_flags |= VM_IO; - vma->vm_flags |= (VM_DONTEXPAND | VM_DONTDUMP); + vm_flags_set(vma, VM_IO | VM_DONTEXPAND | VM_DONTDUMP); vma->vm_ops = &usbdev_vm_ops; vma->vm_private_data = usbm; diff --git a/drivers/usb/mon/mon_bin.c b/drivers/usb/mon/mon_bin.c index 094e812e9e69..abb1cd35d8a6 100644 --- a/drivers/usb/mon/mon_bin.c +++ b/drivers/usb/mon/mon_bin.c @@ -1272,8 +1272,7 @@ static int mon_bin_mmap(struct file *filp, struct vm_area_struct *vma) if (vma->vm_flags & VM_WRITE) return -EPERM; - vma->vm_flags &= ~VM_MAYWRITE; - vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP; + vm_flags_mod(vma, VM_DONTEXPAND | VM_DONTDUMP, VM_MAYWRITE); vma->vm_private_data = filp->private_data; mon_bin_vma_open(vma); return 0; diff --git a/drivers/vdpa/vdpa_user/iova_domain.c b/drivers/vdpa/vdpa_user/iova_domain.c index e682bc7ee6c9..5e4a77b9bae6 100644 --- a/drivers/vdpa/vdpa_user/iova_domain.c +++ b/drivers/vdpa/vdpa_user/iova_domain.c @@ -512,7 +512,7 @@ static int vduse_domain_mmap(struct file *file, struct vm_area_struct *vma) { struct vduse_iova_domain *domain = file->private_data; - vma->vm_flags |= VM_DONTDUMP | VM_DONTEXPAND; + vm_flags_set(vma, VM_DONTDUMP | VM_DONTEXPAND); vma->vm_private_data = domain; vma->vm_ops = &vduse_domain_mmap_ops; diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c index 26a541cc64d1..c49f8f2b2865 100644 --- a/drivers/vfio/pci/vfio_pci_core.c +++ b/drivers/vfio/pci/vfio_pci_core.c @@ -1799,7 +1799,7 @@ int vfio_pci_core_mmap(struct vfio_device *core_vdev, struct vm_area_struct *vma * See remap_pfn_range(), called from vfio_pci_fault() but we can't * change vm_flags within the fault handler. Set them now. */ - vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP; + vm_flags_set(vma, VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP); vma->vm_ops = &vfio_pci_mmap_ops; return 0; diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index ec32f785dfde..9c5010ee20da 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -1315,7 +1315,7 @@ static int vhost_vdpa_mmap(struct file *file, struct vm_area_struct *vma) if (vma->vm_end - vma->vm_start != notify.size) return -ENOTSUPP; - vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP; + vm_flags_set(vma, VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP); vma->vm_ops = &vhost_vdpa_vm_ops; return 0; } diff --git a/drivers/video/fbdev/68328fb.c b/drivers/video/fbdev/68328fb.c index 7db03ed77c76..41df61b37a18 100644 --- a/drivers/video/fbdev/68328fb.c +++ b/drivers/video/fbdev/68328fb.c @@ -391,7 +391,7 @@ static int mc68x328fb_mmap(struct fb_info *info, struct vm_area_struct *vma) #ifndef MMU /* this is uClinux (no MMU) specific code */ - vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP; + vm_flags_set(vma, VM_DONTEXPAND | VM_DONTDUMP); vma->vm_start = videomemory; return 0; diff --git a/drivers/video/fbdev/core/fb_defio.c b/drivers/video/fbdev/core/fb_defio.c index c730253ab85c..dc310c7b5769 100644 --- a/drivers/video/fbdev/core/fb_defio.c +++ b/drivers/video/fbdev/core/fb_defio.c @@ -232,9 +232,9 @@ static const struct address_space_operations fb_deferred_io_aops = { int fb_deferred_io_mmap(struct fb_info *info, struct vm_area_struct *vma) { vma->vm_ops = &fb_deferred_io_vm_ops; - vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP; + vm_flags_set(vma, VM_DONTEXPAND | VM_DONTDUMP); if (!(info->flags & FBINFO_VIRTFB)) - vma->vm_flags |= VM_IO; + vm_flags_set(vma, VM_IO); vma->vm_private_data = info; return 0; } diff --git a/drivers/xen/gntalloc.c b/drivers/xen/gntalloc.c index a15729beb9d1..26ffb8755ffb 100644 --- a/drivers/xen/gntalloc.c +++ b/drivers/xen/gntalloc.c @@ -525,7 +525,7 @@ static int gntalloc_mmap(struct file *filp, struct vm_area_struct *vma) vma->vm_private_data = vm_priv; - vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP; + vm_flags_set(vma, VM_DONTEXPAND | VM_DONTDUMP); vma->vm_ops = &gntalloc_vmops; diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c index 4d9a3050de6a..61faea1f0663 100644 --- a/drivers/xen/gntdev.c +++ b/drivers/xen/gntdev.c @@ -1055,10 +1055,10 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma) vma->vm_ops = &gntdev_vmops; - vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP | VM_MIXEDMAP; + vm_flags_set(vma, VM_DONTEXPAND | VM_DONTDUMP | VM_MIXEDMAP); if (use_ptemod) - vma->vm_flags |= VM_DONTCOPY; + vm_flags_set(vma, VM_DONTCOPY); vma->vm_private_data = map; if (map->flags) { diff --git a/drivers/xen/privcmd-buf.c b/drivers/xen/privcmd-buf.c index dd5bbb6e1b6b..2fa10ca5be14 100644 --- a/drivers/xen/privcmd-buf.c +++ b/drivers/xen/privcmd-buf.c @@ -156,7 +156,7 @@ static int privcmd_buf_mmap(struct file *file, struct vm_area_struct *vma) vma_priv->file_priv = file_priv; vma_priv->users = 1; - vma->vm_flags |= VM_IO | VM_DONTEXPAND; + vm_flags_set(vma, VM_IO | VM_DONTEXPAND); vma->vm_ops = &privcmd_buf_vm_ops; vma->vm_private_data = vma_priv; diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c index 1edf45ee9890..e2f580e30a86 100644 --- a/drivers/xen/privcmd.c +++ b/drivers/xen/privcmd.c @@ -934,8 +934,8 @@ static int privcmd_mmap(struct file *file, struct vm_area_struct *vma) { /* DONTCOPY is essential for Xen because copy_page_range doesn't know * how to recreate these mappings */ - vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTCOPY | - VM_DONTEXPAND | VM_DONTDUMP; + vm_flags_set(vma, VM_IO | VM_PFNMAP | VM_DONTCOPY | + VM_DONTEXPAND | VM_DONTDUMP); vma->vm_ops = &privcmd_vm_ops; vma->vm_private_data = NULL; diff --git a/fs/aio.c b/fs/aio.c index 562916d85cba..5a88caf52be4 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -390,7 +390,7 @@ static const struct vm_operations_struct aio_ring_vm_ops = { static int aio_ring_mmap(struct file *file, struct vm_area_struct *vma) { - vma->vm_flags |= VM_DONTEXPAND; + vm_flags_set(vma, VM_DONTEXPAND); vma->vm_ops = &aio_ring_vm_ops; return 0; } diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c index 50e4e060db68..45a65c400bd0 100644 --- a/fs/cramfs/inode.c +++ b/fs/cramfs/inode.c @@ -408,7 +408,7 @@ static int cramfs_physmem_mmap(struct file *file, struct vm_area_struct *vma) * unpopulated ptes via cramfs_read_folio(). */ int i; - vma->vm_flags |= VM_MIXEDMAP; + vm_flags_set(vma, VM_MIXEDMAP); for (i = 0; i < pages && !ret; i++) { vm_fault_t vmf; unsigned long off = i * PAGE_SIZE; diff --git a/fs/erofs/data.c b/fs/erofs/data.c index f57f921683d7..f32d65987578 100644 --- a/fs/erofs/data.c +++ b/fs/erofs/data.c @@ -429,7 +429,7 @@ static int erofs_file_mmap(struct file *file, struct vm_area_struct *vma) return -EINVAL; vma->vm_ops = &erofs_dax_vm_ops; - vma->vm_flags |= VM_HUGEPAGE; + vm_flags_set(vma, VM_HUGEPAGE); return 0; } #else diff --git a/fs/exec.c b/fs/exec.c index c0df813d2b45..d2e2a15e5cfe 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -270,7 +270,7 @@ static int __bprm_mm_init(struct linux_binprm *bprm) BUILD_BUG_ON(VM_STACK_FLAGS & VM_STACK_INCOMPLETE_SETUP); vma->vm_end = STACK_TOP_MAX; vma->vm_start = vma->vm_end - PAGE_SIZE; - vma->vm_flags = VM_SOFTDIRTY | VM_STACK_FLAGS | VM_STACK_INCOMPLETE_SETUP; + vm_flags_init(vma, VM_SOFTDIRTY | VM_STACK_FLAGS | VM_STACK_INCOMPLETE_SETUP); vma->vm_page_prot = vm_get_page_prot(vma->vm_flags); err = insert_vm_struct(mm, vma); @@ -834,7 +834,7 @@ int setup_arg_pages(struct linux_binprm *bprm, } /* mprotect_fixup is overkill to remove the temporary stack flags */ - vma->vm_flags &= ~VM_STACK_INCOMPLETE_SETUP; + vm_flags_clear(vma, VM_STACK_INCOMPLETE_SETUP); stack_expand = 131072UL; /* randomly 32*4k (or 2*64k) pages */ stack_size = vma->vm_end - vma->vm_start; diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 7ac0a81bd371..6bdf61a62c79 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -801,7 +801,7 @@ static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma) file_accessed(file); if (IS_DAX(file_inode(file))) { vma->vm_ops = &ext4_dax_vm_ops; - vma->vm_flags |= VM_HUGEPAGE; + vm_flags_set(vma, VM_HUGEPAGE); } else { vma->vm_ops = &ext4_file_vm_ops; } diff --git a/fs/fuse/dax.c b/fs/fuse/dax.c index e23e802a8013..8e74f278a3f6 100644 --- a/fs/fuse/dax.c +++ b/fs/fuse/dax.c @@ -860,7 +860,7 @@ int fuse_dax_mmap(struct file *file, struct vm_area_struct *vma) { file_accessed(file); vma->vm_ops = &fuse_dax_vm_ops; - vma->vm_flags |= VM_MIXEDMAP | VM_HUGEPAGE; + vm_flags_set(vma, VM_MIXEDMAP | VM_HUGEPAGE); return 0; } diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 48f1a8ad2243..44ecdcb796cc 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -132,7 +132,7 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma) * way when do_mmap unwinds (may be important on powerpc * and ia64). */ - vma->vm_flags |= VM_HUGETLB | VM_DONTEXPAND; + vm_flags_set(vma, VM_HUGETLB | VM_DONTEXPAND); vma->vm_ops = &hugetlb_vm_ops; ret = seal_check_future_write(info->seals, vma); @@ -811,7 +811,7 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset, * as input to create an allocation policy. */ vma_init(&pseudo_vma, mm); - pseudo_vma.vm_flags = (VM_HUGETLB | VM_MAYSHARE | VM_SHARED); + vm_flags_init(&pseudo_vma, VM_HUGETLB | VM_MAYSHARE | VM_SHARED); pseudo_vma.vm_file = file; for (index = start; index < end; index++) { diff --git a/fs/orangefs/file.c b/fs/orangefs/file.c index 167fa43b24f9..a5e1ea8b7119 100644 --- a/fs/orangefs/file.c +++ b/fs/orangefs/file.c @@ -389,8 +389,7 @@ static int orangefs_file_mmap(struct file *file, struct vm_area_struct *vma) "orangefs_file_mmap: called on %pD\n", file); /* set the sequential readahead hint */ - vma->vm_flags |= VM_SEQ_READ; - vma->vm_flags &= ~VM_RAND_READ; + vm_flags_mod(vma, VM_SEQ_READ, VM_RAND_READ); file_accessed(file); vma->vm_ops = &orangefs_file_vm_ops; diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index a944e1816364..6a96e1713fd5 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1299,7 +1299,7 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, for_each_vma(vmi, vma) { if (!(vma->vm_flags & VM_SOFTDIRTY)) continue; - vma->vm_flags &= ~VM_SOFTDIRTY; + vm_flags_clear(vma, VM_SOFTDIRTY); vma_set_page_prot(vma); } diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c index 09a81e4b1273..12af614f33ce 100644 --- a/fs/proc/vmcore.c +++ b/fs/proc/vmcore.c @@ -582,8 +582,7 @@ static int mmap_vmcore(struct file *file, struct vm_area_struct *vma) if (vma->vm_flags & (VM_WRITE | VM_EXEC)) return -EPERM; - vma->vm_flags &= ~(VM_MAYWRITE | VM_MAYEXEC); - vma->vm_flags |= VM_MIXEDMAP; + vm_flags_mod(vma, VM_MIXEDMAP, VM_MAYWRITE | VM_MAYEXEC); vma->vm_ops = &vmcore_mmap_ops; len = 0; diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index f3c75c6222de..44d1ee429eb0 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -113,7 +113,7 @@ static void userfaultfd_set_vm_flags(struct vm_area_struct *vma, { const bool uffd_wp_changed = (vma->vm_flags ^ flags) & VM_UFFD_WP; - vma->vm_flags = flags; + vm_flags_reset(vma, flags); /* * For shared mappings, we want to enable writenotify while * userfaultfd-wp is enabled (see vma_wants_writenotify()). We'll simply diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 595a5bcf46b9..b0039a8fea2e 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -1429,7 +1429,7 @@ xfs_file_mmap( file_accessed(file); vma->vm_ops = &xfs_file_vm_ops; if (IS_DAX(inode)) - vma->vm_flags |= VM_HUGEPAGE; + vm_flags_set(vma, VM_HUGEPAGE); return 0; } diff --git a/include/linux/mm.h b/include/linux/mm.h index 663726ca2240..ce6d9d765aae 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3653,7 +3653,7 @@ static inline int seal_check_future_write(int seals, struct vm_area_struct *vma) * VM_MAYWRITE as we still want them to be COW-writable. */ if (vma->vm_flags & VM_SHARED) - vma->vm_flags &= ~(VM_MAYWRITE); + vm_flags_clear(vma, VM_MAYWRITE); } return 0; diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c index 80f4b4d88aaf..8732e0aadf36 100644 --- a/kernel/bpf/ringbuf.c +++ b/kernel/bpf/ringbuf.c @@ -269,7 +269,7 @@ static int ringbuf_map_mmap_kern(struct bpf_map *map, struct vm_area_struct *vma if (vma->vm_pgoff != 0 || vma->vm_end - vma->vm_start != PAGE_SIZE) return -EPERM; } else { - vma->vm_flags &= ~VM_MAYWRITE; + vm_flags_clear(vma, VM_MAYWRITE); } /* remap_vmalloc_range() checks size and offset constraints */ return remap_vmalloc_range(vma, rb_map->rb, @@ -290,7 +290,7 @@ static int ringbuf_map_mmap_user(struct bpf_map *map, struct vm_area_struct *vma */ return -EPERM; } else { - vma->vm_flags &= ~VM_MAYWRITE; + vm_flags_clear(vma, VM_MAYWRITE); } /* remap_vmalloc_range() checks size and offset constraints */ return remap_vmalloc_range(vma, rb_map->rb, vma->vm_pgoff + RINGBUF_PGOFF); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 64131f88c553..9f56b442daa9 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -882,10 +882,10 @@ static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma) /* set default open/close callbacks */ vma->vm_ops = &bpf_map_default_vmops; vma->vm_private_data = map; - vma->vm_flags &= ~VM_MAYEXEC; + vm_flags_clear(vma, VM_MAYEXEC); if (!(vma->vm_flags & VM_WRITE)) /* disallow re-mapping with PROT_WRITE */ - vma->vm_flags &= ~VM_MAYWRITE; + vm_flags_clear(vma, VM_MAYWRITE); err = map->ops->map_mmap(map, vma); if (err) diff --git a/kernel/events/core.c b/kernel/events/core.c index d56328e5080e..55a82f12a42c 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -6573,7 +6573,7 @@ aux_unlock: * Since pinned accounting is per vm we cannot allow fork() to copy our * vma. */ - vma->vm_flags |= VM_DONTCOPY | VM_DONTEXPAND | VM_DONTDUMP; + vm_flags_set(vma, VM_DONTCOPY | VM_DONTEXPAND | VM_DONTDUMP); vma->vm_ops = &perf_mmap_vmops; if (event->pmu->event_mapped) diff --git a/kernel/kcov.c b/kernel/kcov.c index e5cd09fd8a05..84c717337df0 100644 --- a/kernel/kcov.c +++ b/kernel/kcov.c @@ -489,7 +489,7 @@ static int kcov_mmap(struct file *filep, struct vm_area_struct *vma) goto exit; } spin_unlock_irqrestore(&kcov->lock, flags); - vma->vm_flags |= VM_DONTEXPAND; + vm_flags_set(vma, VM_DONTEXPAND); for (off = 0; off < size; off += PAGE_SIZE) { page = vmalloc_to_page(kcov->area + off); res = vm_insert_page(vma, vma->vm_start + off, page); diff --git a/kernel/relay.c b/kernel/relay.c index ef12532168d9..9aa70ae53d24 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -91,7 +91,7 @@ static int relay_mmap_buf(struct rchan_buf *buf, struct vm_area_struct *vma) return -EINVAL; vma->vm_ops = &relay_file_mmap_ops; - vma->vm_flags |= VM_DONTEXPAND; + vm_flags_set(vma, VM_DONTEXPAND); vma->vm_private_data = buf; return 0; diff --git a/mm/madvise.c b/mm/madvise.c index ca672e37b38c..5a5a687d03c2 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -176,7 +176,7 @@ success: /* * vm_flags is protected by the mmap_lock held in write mode. */ - vma->vm_flags = new_flags; + vm_flags_reset(vma, new_flags); if (!vma->vm_file || vma_is_anon_shmem(vma)) { error = replace_anon_vma_name(vma, anon_name); if (error) diff --git a/mm/memory.c b/mm/memory.c index 029f838587d1..4354b7987f36 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1928,7 +1928,7 @@ int vm_insert_pages(struct vm_area_struct *vma, unsigned long addr, if (!(vma->vm_flags & VM_MIXEDMAP)) { BUG_ON(mmap_read_trylock(vma->vm_mm)); BUG_ON(vma->vm_flags & VM_PFNMAP); - vma->vm_flags |= VM_MIXEDMAP; + vm_flags_set(vma, VM_MIXEDMAP); } /* Defer page refcount checking till we're about to map that page. */ return insert_pages(vma, addr, pages, num, vma->vm_page_prot); @@ -1986,7 +1986,7 @@ int vm_insert_page(struct vm_area_struct *vma, unsigned long addr, if (!(vma->vm_flags & VM_MIXEDMAP)) { BUG_ON(mmap_read_trylock(vma->vm_mm)); BUG_ON(vma->vm_flags & VM_PFNMAP); - vma->vm_flags |= VM_MIXEDMAP; + vm_flags_set(vma, VM_MIXEDMAP); } return insert_page(vma, addr, page, vma->vm_page_prot); } @@ -2452,7 +2452,7 @@ int remap_pfn_range_notrack(struct vm_area_struct *vma, unsigned long addr, vma->vm_pgoff = pfn; } - vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP; + vm_flags_set(vma, VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP); BUG_ON(addr >= end); pfn -= addr >> PAGE_SHIFT; diff --git a/mm/mlock.c b/mm/mlock.c index 5c4fff93cd6b..ed49459e343e 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -380,7 +380,7 @@ static void mlock_vma_pages_range(struct vm_area_struct *vma, */ if (newflags & VM_LOCKED) newflags |= VM_IO; - WRITE_ONCE(vma->vm_flags, newflags); + vm_flags_reset(vma, newflags); lru_add_drain(); walk_page_range(vma->vm_mm, start, end, &mlock_walk_ops, NULL); @@ -388,7 +388,7 @@ static void mlock_vma_pages_range(struct vm_area_struct *vma, if (newflags & VM_IO) { newflags &= ~VM_IO; - WRITE_ONCE(vma->vm_flags, newflags); + vm_flags_reset(vma, newflags); } } @@ -457,7 +457,7 @@ success: if ((newflags & VM_LOCKED) && (oldflags & VM_LOCKED)) { /* No work to do, and mlocking twice would be wrong */ - vma->vm_flags = newflags; + vm_flags_reset(vma, newflags); } else { mlock_vma_pages_range(vma, start, end, newflags); } diff --git a/mm/mmap.c b/mm/mmap.c index 03d7c37c5969..33c638c7ec04 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2555,7 +2555,7 @@ cannot_expand: vma_iter_set(&vmi, addr); vma->vm_start = addr; vma->vm_end = end; - vma->vm_flags = vm_flags; + vm_flags_init(vma, vm_flags); vma->vm_page_prot = vm_get_page_prot(vm_flags); vma->vm_pgoff = pgoff; @@ -2683,7 +2683,7 @@ expanded: * then new mapped in-place (which must be aimed as * a completely new data area). */ - vma->vm_flags |= VM_SOFTDIRTY; + vm_flags_set(vma, VM_SOFTDIRTY); vma_set_page_prot(vma); @@ -2909,7 +2909,7 @@ static int do_brk_flags(struct vma_iterator *vmi, struct vm_area_struct *vma, init_vma_prep(&vp, vma); vma_prepare(&vp); vma->vm_end = addr + len; - vma->vm_flags |= VM_SOFTDIRTY; + vm_flags_set(vma, VM_SOFTDIRTY); vma_iter_store(vmi, vma); vma_complete(&vp, vmi, mm); @@ -2926,7 +2926,7 @@ static int do_brk_flags(struct vma_iterator *vmi, struct vm_area_struct *vma, vma->vm_start = addr; vma->vm_end = addr + len; vma->vm_pgoff = addr >> PAGE_SHIFT; - vma->vm_flags = flags; + vm_flags_init(vma, flags); vma->vm_page_prot = vm_get_page_prot(flags); if (vma_iter_store_gfp(vmi, vma, GFP_KERNEL)) goto mas_store_fail; @@ -2938,7 +2938,7 @@ out: mm->data_vm += len >> PAGE_SHIFT; if (flags & VM_LOCKED) mm->locked_vm += (len >> PAGE_SHIFT); - vma->vm_flags |= VM_SOFTDIRTY; + vm_flags_set(vma, VM_SOFTDIRTY); validate_mm(mm); return 0; diff --git a/mm/mprotect.c b/mm/mprotect.c index cce6a0e58fb5..1d4843c97c2a 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -670,7 +670,7 @@ success: * vm_flags and vm_page_prot are protected by the mmap_lock * held in write mode. */ - vma->vm_flags = newflags; + vm_flags_reset(vma, newflags); if (vma_wants_manual_pte_write_upgrade(vma)) mm_cp_flags |= MM_CP_TRY_CHANGE_WRITABLE; vma_set_page_prot(vma); diff --git a/mm/mremap.c b/mm/mremap.c index d70d8063c6e2..411a85682b58 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -662,7 +662,7 @@ static unsigned long move_vma(struct vm_area_struct *vma, /* Conceal VM_ACCOUNT so old reservation is not undone */ if (vm_flags & VM_ACCOUNT && !(flags & MREMAP_DONTUNMAP)) { - vma->vm_flags &= ~VM_ACCOUNT; + vm_flags_clear(vma, VM_ACCOUNT); if (vma->vm_start < old_addr) account_start = vma->vm_start; if (vma->vm_end > old_addr + old_len) @@ -719,12 +719,12 @@ static unsigned long move_vma(struct vm_area_struct *vma, /* Restore VM_ACCOUNT if one or two pieces of vma left */ if (account_start) { vma = vma_prev(&vmi); - vma->vm_flags |= VM_ACCOUNT; + vm_flags_set(vma, VM_ACCOUNT); } if (account_end) { vma = vma_next(&vmi); - vma->vm_flags |= VM_ACCOUNT; + vm_flags_set(vma, VM_ACCOUNT); } return new_addr; diff --git a/mm/nommu.c b/mm/nommu.c index 9a166738909e..57ba243c6a37 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -173,7 +173,7 @@ static void *__vmalloc_user_flags(unsigned long size, gfp_t flags) mmap_write_lock(current->mm); vma = find_vma(current->mm, (unsigned long)ret); if (vma) - vma->vm_flags |= VM_USERMAP; + vm_flags_set(vma, VM_USERMAP); mmap_write_unlock(current->mm); } @@ -950,7 +950,8 @@ static int do_mmap_private(struct vm_area_struct *vma, atomic_long_add(total, &mmap_pages_allocated); - region->vm_flags = vma->vm_flags |= VM_MAPPED_COPY; + vm_flags_set(vma, VM_MAPPED_COPY); + region->vm_flags = vma->vm_flags; region->vm_start = (unsigned long) base; region->vm_end = region->vm_start + len; region->vm_top = region->vm_start + (total << PAGE_SHIFT); @@ -1047,7 +1048,7 @@ unsigned long do_mmap(struct file *file, region->vm_flags = vm_flags; region->vm_pgoff = pgoff; - vma->vm_flags = vm_flags; + vm_flags_init(vma, vm_flags); vma->vm_pgoff = pgoff; if (file) { @@ -1111,7 +1112,7 @@ unsigned long do_mmap(struct file *file, vma->vm_end = start + len; if (pregion->vm_flags & VM_MAPPED_COPY) - vma->vm_flags |= VM_MAPPED_COPY; + vm_flags_set(vma, VM_MAPPED_COPY); else { ret = do_mmap_shared_file(vma); if (ret < 0) { @@ -1601,7 +1602,7 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, if (addr != (pfn << PAGE_SHIFT)) return -EINVAL; - vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP; + vm_flags_set(vma, VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP); return 0; } EXPORT_SYMBOL(remap_pfn_range); diff --git a/mm/secretmem.c b/mm/secretmem.c index be3fff86ba00..8453ada8f41d 100644 --- a/mm/secretmem.c +++ b/mm/secretmem.c @@ -128,7 +128,7 @@ static int secretmem_mmap(struct file *file, struct vm_area_struct *vma) if (mlock_future_check(vma->vm_mm, vma->vm_flags | VM_LOCKED, len)) return -EAGAIN; - vma->vm_flags |= VM_LOCKED | VM_DONTDUMP; + vm_flags_set(vma, VM_LOCKED | VM_DONTDUMP); vma->vm_ops = &secretmem_vm_ops; return 0; diff --git a/mm/shmem.c b/mm/shmem.c index 9e1015cbad29..732969afabd1 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2304,7 +2304,7 @@ static int shmem_mmap(struct file *file, struct vm_area_struct *vma) return ret; /* arm64 - allow memory tagging on RAM-based files */ - vma->vm_flags |= VM_MTE_ALLOWED; + vm_flags_set(vma, VM_MTE_ALLOWED); file_accessed(file); /* This is anonymous shared memory if it is unlinked at the time of mmap */ diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 9b71ec3213cb..ff4d7dfdf84a 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -3596,7 +3596,7 @@ int remap_vmalloc_range_partial(struct vm_area_struct *vma, unsigned long uaddr, size -= PAGE_SIZE; } while (size > 0); - vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP; + vm_flags_set(vma, VM_DONTEXPAND | VM_DONTDUMP); return 0; } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index f713c0422f0f..7db45cdc3e1a 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1890,10 +1890,10 @@ int tcp_mmap(struct file *file, struct socket *sock, { if (vma->vm_flags & (VM_WRITE | VM_EXEC)) return -EPERM; - vma->vm_flags &= ~(VM_MAYWRITE | VM_MAYEXEC); + vm_flags_clear(vma, VM_MAYWRITE | VM_MAYEXEC); /* Instruct vm_insert_page() to not mmap_read_lock(mm) */ - vma->vm_flags |= VM_MIXEDMAP; + vm_flags_set(vma, VM_MIXEDMAP); vma->vm_ops = &tcp_vm_ops; return 0; diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c index 0a6894cdc54d..18498979a640 100644 --- a/security/selinux/selinuxfs.c +++ b/security/selinux/selinuxfs.c @@ -262,7 +262,7 @@ static int sel_mmap_handle_status(struct file *filp, if (vma->vm_flags & VM_WRITE) return -EPERM; /* disallow mprotect() turns it into writable */ - vma->vm_flags &= ~VM_MAYWRITE; + vm_flags_clear(vma, VM_MAYWRITE); return remap_pfn_range(vma, vma->vm_start, page_to_pfn(status), @@ -506,13 +506,13 @@ static int sel_mmap_policy(struct file *filp, struct vm_area_struct *vma) { if (vma->vm_flags & VM_SHARED) { /* do not allow mprotect to make mapping writable */ - vma->vm_flags &= ~VM_MAYWRITE; + vm_flags_clear(vma, VM_MAYWRITE); if (vma->vm_flags & VM_WRITE) return -EACCES; } - vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP; + vm_flags_set(vma, VM_DONTEXPAND | VM_DONTDUMP); vma->vm_ops = &sel_mmap_policy_ops; return 0; diff --git a/sound/core/oss/pcm_oss.c b/sound/core/oss/pcm_oss.c index ac2efeb63a39..728c211142d1 100644 --- a/sound/core/oss/pcm_oss.c +++ b/sound/core/oss/pcm_oss.c @@ -2910,7 +2910,7 @@ static int snd_pcm_oss_mmap(struct file *file, struct vm_area_struct *area) } /* set VM_READ access as well to fix memset() routines that do reads before writes (to improve performance) */ - area->vm_flags |= VM_READ; + vm_flags_set(area, VM_READ); if (substream == NULL) return -ENXIO; runtime = substream->runtime; diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 9c122e757efe..331380c2438b 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -3675,8 +3675,9 @@ static int snd_pcm_mmap_status(struct snd_pcm_substream *substream, struct file return -EINVAL; area->vm_ops = &snd_pcm_vm_ops_status; area->vm_private_data = substream; - area->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP; - area->vm_flags &= ~(VM_WRITE | VM_MAYWRITE); + vm_flags_mod(area, VM_DONTEXPAND | VM_DONTDUMP, + VM_WRITE | VM_MAYWRITE); + return 0; } @@ -3712,7 +3713,7 @@ static int snd_pcm_mmap_control(struct snd_pcm_substream *substream, struct file return -EINVAL; area->vm_ops = &snd_pcm_vm_ops_control; area->vm_private_data = substream; - area->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP; + vm_flags_set(area, VM_DONTEXPAND | VM_DONTDUMP); return 0; } @@ -3828,7 +3829,7 @@ static const struct vm_operations_struct snd_pcm_vm_ops_data_fault = { int snd_pcm_lib_default_mmap(struct snd_pcm_substream *substream, struct vm_area_struct *area) { - area->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP; + vm_flags_set(area, VM_DONTEXPAND | VM_DONTDUMP); if (!substream->ops->page && !snd_dma_buffer_mmap(snd_pcm_get_dma_buf(substream), area)) return 0; diff --git a/sound/soc/pxa/mmp-sspa.c b/sound/soc/pxa/mmp-sspa.c index fb5a4390443f..b3c1744eff91 100644 --- a/sound/soc/pxa/mmp-sspa.c +++ b/sound/soc/pxa/mmp-sspa.c @@ -404,7 +404,7 @@ static int mmp_pcm_mmap(struct snd_soc_component *component, struct snd_pcm_substream *substream, struct vm_area_struct *vma) { - vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP; + vm_flags_set(vma, VM_DONTEXPAND | VM_DONTDUMP); vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); return remap_pfn_range(vma, vma->vm_start, substream->dma_buffer.addr >> PAGE_SHIFT, diff --git a/sound/usb/usx2y/us122l.c b/sound/usb/usx2y/us122l.c index e558931cce16..709ccad972e2 100644 --- a/sound/usb/usx2y/us122l.c +++ b/sound/usb/usx2y/us122l.c @@ -224,9 +224,9 @@ static int usb_stream_hwdep_mmap(struct snd_hwdep *hw, } area->vm_ops = &usb_stream_hwdep_vm_ops; - area->vm_flags |= VM_DONTDUMP; + vm_flags_set(area, VM_DONTDUMP); if (!read) - area->vm_flags |= VM_DONTEXPAND; + vm_flags_set(area, VM_DONTEXPAND); area->vm_private_data = us122l; atomic_inc(&us122l->mmap_count); out: diff --git a/sound/usb/usx2y/usX2Yhwdep.c b/sound/usb/usx2y/usX2Yhwdep.c index c29da0341bc5..4937ede0b5d7 100644 --- a/sound/usb/usx2y/usX2Yhwdep.c +++ b/sound/usb/usx2y/usX2Yhwdep.c @@ -61,7 +61,7 @@ static int snd_us428ctls_mmap(struct snd_hwdep *hw, struct file *filp, struct vm } area->vm_ops = &us428ctls_vm_ops; - area->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP; + vm_flags_set(area, VM_DONTEXPAND | VM_DONTDUMP); area->vm_private_data = hw->private_data; return 0; } diff --git a/sound/usb/usx2y/usx2yhwdeppcm.c b/sound/usb/usx2y/usx2yhwdeppcm.c index 767a227d54da..36f2e31168fb 100644 --- a/sound/usb/usx2y/usx2yhwdeppcm.c +++ b/sound/usb/usx2y/usx2yhwdeppcm.c @@ -706,7 +706,7 @@ static int snd_usx2y_hwdep_pcm_mmap(struct snd_hwdep *hw, struct file *filp, str return -ENODEV; area->vm_ops = &snd_usx2y_hwdep_pcm_vm_ops; - area->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP; + vm_flags_set(area, VM_DONTEXPAND | VM_DONTDUMP); area->vm_private_data = hw->private_data; return 0; } -- cgit v1.2.3 From 68f48381d7fdd1cbb9d88c37a4dfbb98ac78226d Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Thu, 26 Jan 2023 11:37:51 -0800 Subject: mm: introduce __vm_flags_mod and use it in untrack_pfn There are scenarios when vm_flags can be modified without exclusive mmap_lock, such as: - after VMA was isolated and mmap_lock was downgraded or dropped - in exit_mmap when there are no other mm users and locking is unnecessary Introduce __vm_flags_mod to avoid assertions when the caller takes responsibility for the required locking. Pass a hint to untrack_pfn to conditionally use __vm_flags_mod for flags modification to avoid assertion. Link: https://lkml.kernel.org/r/20230126193752.297968-7-surenb@google.com Signed-off-by: Suren Baghdasaryan Acked-by: Michal Hocko Acked-by: Mike Rapoport (IBM) Cc: Andy Lutomirski Cc: Arjun Roy Cc: Axel Rasmussen Cc: David Hildenbrand Cc: David Howells Cc: Davidlohr Bueso Cc: David Rientjes Cc: Eric Dumazet Cc: Greg Thelen Cc: Hugh Dickins Cc: Ingo Molnar Cc: Jann Horn Cc: Joel Fernandes Cc: Johannes Weiner Cc: Kent Overstreet Cc: Laurent Dufour Cc: Liam R. Howlett Cc: Lorenzo Stoakes Cc: Matthew Wilcox Cc: Mel Gorman Cc: Minchan Kim Cc: Paul E. McKenney Cc: Peter Oskolkov Cc: Peter Xu Cc: Peter Zijlstra Cc: Punit Agrawal Cc: Sebastian Andrzej Siewior Cc: Sebastian Reichel Cc: Shakeel Butt Cc: Soheil Hassas Yeganeh Cc: Song Liu Cc: Vlastimil Babka Cc: Will Deacon Signed-off-by: Andrew Morton --- arch/x86/mm/pat/memtype.c | 10 +++++++--- include/linux/mm.h | 14 ++++++++++++-- include/linux/pgtable.h | 5 +++-- mm/memory.c | 13 +++++++------ mm/memremap.c | 4 ++-- mm/mmap.c | 16 ++++++++++------ 6 files changed, 41 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c index 6ca51b1aa5d9..691bf8934b6f 100644 --- a/arch/x86/mm/pat/memtype.c +++ b/arch/x86/mm/pat/memtype.c @@ -1046,7 +1046,7 @@ void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, pfn_t pfn) * can be for the entire vma (in which case pfn, size are zero). */ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, - unsigned long size) + unsigned long size, bool mm_wr_locked) { resource_size_t paddr; unsigned long prot; @@ -1065,8 +1065,12 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, size = vma->vm_end - vma->vm_start; } free_pfn_range(paddr, size); - if (vma) - vm_flags_clear(vma, VM_PAT); + if (vma) { + if (mm_wr_locked) + vm_flags_clear(vma, VM_PAT); + else + __vm_flags_mod(vma, 0, VM_PAT); + } } /* diff --git a/include/linux/mm.h b/include/linux/mm.h index ce6d9d765aae..27b34f7730e7 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -656,6 +656,16 @@ static inline void vm_flags_clear(struct vm_area_struct *vma, ACCESS_PRIVATE(vma, __vm_flags) &= ~flags; } +/* + * Use only if VMA is not part of the VMA tree or has no other users and + * therefore needs no locking. + */ +static inline void __vm_flags_mod(struct vm_area_struct *vma, + vm_flags_t set, vm_flags_t clear) +{ + vm_flags_init(vma, (vma->vm_flags | set) & ~clear); +} + /* * Use only when the order of set/clear operations is unimportant, otherwise * use vm_flags_{set|clear} explicitly. @@ -664,7 +674,7 @@ static inline void vm_flags_mod(struct vm_area_struct *vma, vm_flags_t set, vm_flags_t clear) { mmap_assert_write_locked(vma->vm_mm); - vm_flags_init(vma, (vma->vm_flags | set) & ~clear); + __vm_flags_mod(vma, set, clear); } static inline void vma_set_anonymous(struct vm_area_struct *vma) @@ -2085,7 +2095,7 @@ static inline void zap_vma_pages(struct vm_area_struct *vma) } void unmap_vmas(struct mmu_gather *tlb, struct maple_tree *mt, struct vm_area_struct *start_vma, unsigned long start, - unsigned long end); + unsigned long end, bool mm_wr_locked); struct mmu_notifier_range; diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 5fd45454c073..c63cd44777ec 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -1185,7 +1185,8 @@ static inline int track_pfn_copy(struct vm_area_struct *vma) * can be for the entire vma (in which case pfn, size are zero). */ static inline void untrack_pfn(struct vm_area_struct *vma, - unsigned long pfn, unsigned long size) + unsigned long pfn, unsigned long size, + bool mm_wr_locked) { } @@ -1203,7 +1204,7 @@ extern void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, pfn_t pfn); extern int track_pfn_copy(struct vm_area_struct *vma); extern void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, - unsigned long size); + unsigned long size, bool mm_wr_locked); extern void untrack_pfn_moved(struct vm_area_struct *vma); #endif diff --git a/mm/memory.c b/mm/memory.c index 4354b7987f36..ce1d84d022d3 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1613,7 +1613,7 @@ void unmap_page_range(struct mmu_gather *tlb, static void unmap_single_vma(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start_addr, unsigned long end_addr, - struct zap_details *details) + struct zap_details *details, bool mm_wr_locked) { unsigned long start = max(vma->vm_start, start_addr); unsigned long end; @@ -1628,7 +1628,7 @@ static void unmap_single_vma(struct mmu_gather *tlb, uprobe_munmap(vma, start, end); if (unlikely(vma->vm_flags & VM_PFNMAP)) - untrack_pfn(vma, 0, 0); + untrack_pfn(vma, 0, 0, mm_wr_locked); if (start != end) { if (unlikely(is_vm_hugetlb_page(vma))) { @@ -1675,7 +1675,7 @@ static void unmap_single_vma(struct mmu_gather *tlb, */ void unmap_vmas(struct mmu_gather *tlb, struct maple_tree *mt, struct vm_area_struct *vma, unsigned long start_addr, - unsigned long end_addr) + unsigned long end_addr, bool mm_wr_locked) { struct mmu_notifier_range range; struct zap_details details = { @@ -1689,7 +1689,8 @@ void unmap_vmas(struct mmu_gather *tlb, struct maple_tree *mt, start_addr, end_addr); mmu_notifier_invalidate_range_start(&range); do { - unmap_single_vma(tlb, vma, start_addr, end_addr, &details); + unmap_single_vma(tlb, vma, start_addr, end_addr, &details, + mm_wr_locked); } while ((vma = mas_find(&mas, end_addr - 1)) != NULL); mmu_notifier_invalidate_range_end(&range); } @@ -1723,7 +1724,7 @@ void zap_page_range_single(struct vm_area_struct *vma, unsigned long address, * unmap 'address-end' not 'range.start-range.end' as range * could have been expanded for hugetlb pmd sharing. */ - unmap_single_vma(&tlb, vma, address, end, details); + unmap_single_vma(&tlb, vma, address, end, details, false); mmu_notifier_invalidate_range_end(&range); tlb_finish_mmu(&tlb); } @@ -2492,7 +2493,7 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, err = remap_pfn_range_notrack(vma, addr, pfn, size, prot); if (err) - untrack_pfn(vma, pfn, PAGE_ALIGN(size)); + untrack_pfn(vma, pfn, PAGE_ALIGN(size), true); return err; } EXPORT_SYMBOL(remap_pfn_range); diff --git a/mm/memremap.c b/mm/memremap.c index 08cbf54fe037..2f88f43d4a01 100644 --- a/mm/memremap.c +++ b/mm/memremap.c @@ -129,7 +129,7 @@ static void pageunmap_range(struct dev_pagemap *pgmap, int range_id) } mem_hotplug_done(); - untrack_pfn(NULL, PHYS_PFN(range->start), range_len(range)); + untrack_pfn(NULL, PHYS_PFN(range->start), range_len(range), true); pgmap_array_delete(range); } @@ -276,7 +276,7 @@ err_add_memory: if (!is_private) kasan_remove_zero_shadow(__va(range->start), range_len(range)); err_kasan: - untrack_pfn(NULL, PHYS_PFN(range->start), range_len(range)); + untrack_pfn(NULL, PHYS_PFN(range->start), range_len(range), true); err_pfn_remap: pgmap_array_delete(range); return error; diff --git a/mm/mmap.c b/mm/mmap.c index 33c638c7ec04..20f21f0949dd 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -78,7 +78,7 @@ core_param(ignore_rlimit_data, ignore_rlimit_data, bool, 0644); static void unmap_region(struct mm_struct *mm, struct maple_tree *mt, struct vm_area_struct *vma, struct vm_area_struct *prev, struct vm_area_struct *next, unsigned long start, - unsigned long end); + unsigned long end, bool mm_wr_locked); static pgprot_t vm_pgprot_modify(pgprot_t oldprot, unsigned long vm_flags) { @@ -2133,14 +2133,14 @@ static inline void remove_mt(struct mm_struct *mm, struct ma_state *mas) static void unmap_region(struct mm_struct *mm, struct maple_tree *mt, struct vm_area_struct *vma, struct vm_area_struct *prev, struct vm_area_struct *next, - unsigned long start, unsigned long end) + unsigned long start, unsigned long end, bool mm_wr_locked) { struct mmu_gather tlb; lru_add_drain(); tlb_gather_mmu(&tlb, mm); update_hiwater_rss(mm); - unmap_vmas(&tlb, mt, vma, start, end); + unmap_vmas(&tlb, mt, vma, start, end, mm_wr_locked); free_pgtables(&tlb, mt, vma, prev ? prev->vm_end : FIRST_USER_ADDRESS, next ? next->vm_start : USER_PGTABLES_CEILING); tlb_finish_mmu(&tlb); @@ -2388,7 +2388,11 @@ do_vmi_align_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma, mmap_write_downgrade(mm); } - unmap_region(mm, &mt_detach, vma, prev, next, start, end); + /* + * We can free page tables without write-locking mmap_lock because VMAs + * were isolated before we downgraded mmap_lock. + */ + unmap_region(mm, &mt_detach, vma, prev, next, start, end, !downgrade); /* Statistics and freeing VMAs */ mas_set(&mas_detach, start); remove_mt(mm, &mas_detach); @@ -2701,7 +2705,7 @@ unmap_and_free_vma: /* Undo any partial mapping done by a device driver. */ unmap_region(mm, &mm->mm_mt, vma, prev, next, vma->vm_start, - vma->vm_end); + vma->vm_end, true); } if (file && (vm_flags & VM_SHARED)) mapping_unmap_writable(file->f_mapping); @@ -3029,7 +3033,7 @@ void exit_mmap(struct mm_struct *mm) tlb_gather_mmu_fullmm(&tlb, mm); /* update_hiwater_rss(mm) here? but nobody should be looking */ /* Use ULONG_MAX here to ensure all VMAs in the mm are unmapped */ - unmap_vmas(&tlb, &mm->mm_mt, vma, 0, ULONG_MAX); + unmap_vmas(&tlb, &mm->mm_mt, vma, 0, ULONG_MAX, false); mmap_read_unlock(mm); /* -- cgit v1.2.3 From 601c3c29dbeb049862faa00917f2daf094a71028 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Tue, 31 Jan 2023 16:01:16 -0800 Subject: mm: introduce vm_flags_reset_once to replace WRITE_ONCE vm_flags updates Provide vm_flags_reset_once() and replace the vm_flags updates which used WRITE_ONCE() to prevent compiler optimizations. Link: https://lkml.kernel.org/r/20230201000116.1333160-1-surenb@google.com Fixes: 0cce31a0aa0e ("mm: replace vma->vm_flags direct modifications with modifier calls") Signed-off-by: Suren Baghdasaryan Reported-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Acked-by: Michal Hocko Signed-off-by: Andrew Morton --- include/linux/mm.h | 7 +++++++ mm/mlock.c | 4 ++-- 2 files changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 27b34f7730e7..0ed0cb2401f5 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -642,6 +642,13 @@ static inline void vm_flags_reset(struct vm_area_struct *vma, vm_flags_init(vma, flags); } +static inline void vm_flags_reset_once(struct vm_area_struct *vma, + vm_flags_t flags) +{ + mmap_assert_write_locked(vma->vm_mm); + WRITE_ONCE(ACCESS_PRIVATE(vma, __vm_flags), flags); +} + static inline void vm_flags_set(struct vm_area_struct *vma, vm_flags_t flags) { diff --git a/mm/mlock.c b/mm/mlock.c index ed49459e343e..617469fce96d 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -380,7 +380,7 @@ static void mlock_vma_pages_range(struct vm_area_struct *vma, */ if (newflags & VM_LOCKED) newflags |= VM_IO; - vm_flags_reset(vma, newflags); + vm_flags_reset_once(vma, newflags); lru_add_drain(); walk_page_range(vma->vm_mm, start, end, &mlock_walk_ops, NULL); @@ -388,7 +388,7 @@ static void mlock_vma_pages_range(struct vm_area_struct *vma, if (newflags & VM_IO) { newflags &= ~VM_IO; - vm_flags_reset(vma, newflags); + vm_flags_reset_once(vma, newflags); } } -- cgit v1.2.3 From 3e629597b8477efbcc0ad14ee80558a080eebdc3 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox (Oracle) Date: Mon, 6 Feb 2023 16:25:19 +0000 Subject: filemap: add mapping_read_folio_gfp() This is like read_cache_page_gfp() except it returns the folio instead of the precise page. Link: https://lkml.kernel.org/r/20230206162520.4029022-1-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Cc: Charan Teja Kalla Cc: David Rientjes Cc: Hugh Dickins Cc: Mark Hemment Cc: Michal Hocko Cc: Pavankumar Kondeti Cc: Shakeel Butt Cc: Suren Baghdasaryan Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- include/linux/pagemap.h | 2 ++ mm/filemap.c | 24 ++++++++++++++++++++++++ 2 files changed, 26 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 9f1081683771..6a32ac170d3d 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -756,6 +756,8 @@ static inline struct page *grab_cache_page(struct address_space *mapping, struct folio *read_cache_folio(struct address_space *, pgoff_t index, filler_t *filler, struct file *file); +struct folio *mapping_read_folio_gfp(struct address_space *, pgoff_t index, + gfp_t flags); struct page *read_cache_page(struct address_space *, pgoff_t index, filler_t *filler, struct file *file); extern struct page * read_cache_page_gfp(struct address_space *mapping, diff --git a/mm/filemap.c b/mm/filemap.c index 992554c18f1f..2ebcf500871d 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -3585,6 +3585,30 @@ struct folio *read_cache_folio(struct address_space *mapping, pgoff_t index, } EXPORT_SYMBOL(read_cache_folio); +/** + * mapping_read_folio_gfp - Read into page cache, using specified allocation flags. + * @mapping: The address_space for the folio. + * @index: The index that the allocated folio will contain. + * @gfp: The page allocator flags to use if allocating. + * + * This is the same as "read_cache_folio(mapping, index, NULL, NULL)", but with + * any new memory allocations done using the specified allocation flags. + * + * The most likely error from this function is EIO, but ENOMEM is + * possible and so is EINTR. If ->read_folio returns another error, + * that will be returned to the caller. + * + * The function expects mapping->invalidate_lock to be already held. + * + * Return: Uptodate folio on success, ERR_PTR() on failure. + */ +struct folio *mapping_read_folio_gfp(struct address_space *mapping, + pgoff_t index, gfp_t gfp) +{ + return do_read_cache_folio(mapping, index, NULL, NULL, gfp); +} +EXPORT_SYMBOL(mapping_read_folio_gfp); + static struct page *do_read_cache_page(struct address_space *mapping, pgoff_t index, filler_t *filler, struct file *file, gfp_t gfp) { -- cgit v1.2.3 From f01b2b3ed8735dacd92f1da548708449525e286a Mon Sep 17 00:00:00 2001 From: Matthew Wilcox (Oracle) Date: Mon, 6 Feb 2023 16:25:20 +0000 Subject: shmem: add shmem_read_folio() and shmem_read_folio_gfp() These are the folio replacements for shmem_read_mapping_page() and shmem_read_mapping_page_gfp(). [akpm@linux-foundation.org: fix shmem_read_mapping_page_gfp(), per Matthew] Link: https://lkml.kernel.org/r/Y+QdJTuzxeBYejw2@casper.infradead.org Link: https://lkml.kernel.org/r/20230206162520.4029022-2-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Cc: Mark Hemment Cc: Charan Teja Kalla Cc: David Rientjes Cc: Hugh Dickins Cc: Michal Hocko Cc: Pavankumar Kondeti Cc: Shakeel Butt Cc: Suren Baghdasaryan Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- include/linux/shmem_fs.h | 8 ++++++++ mm/shmem.c | 36 ++++++++++++++++++++++++------------ 2 files changed, 32 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index d09d54be4ffd..103d1000a5a2 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -109,6 +109,14 @@ enum sgp_type { int shmem_get_folio(struct inode *inode, pgoff_t index, struct folio **foliop, enum sgp_type sgp); +struct folio *shmem_read_folio_gfp(struct address_space *mapping, + pgoff_t index, gfp_t gfp); + +static inline struct folio *shmem_read_folio(struct address_space *mapping, + pgoff_t index) +{ + return shmem_read_folio_gfp(mapping, index, mapping_gfp_mask(mapping)); +} static inline struct page *shmem_read_mapping_page( struct address_space *mapping, pgoff_t index) diff --git a/mm/shmem.c b/mm/shmem.c index 732969afabd1..be6bdd320d5f 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -4311,9 +4311,9 @@ int shmem_zero_setup(struct vm_area_struct *vma) } /** - * shmem_read_mapping_page_gfp - read into page cache, using specified page allocation flags. - * @mapping: the page's address_space - * @index: the page index + * shmem_read_folio_gfp - read into page cache, using specified page allocation flags. + * @mapping: the folio's address_space + * @index: the folio index * @gfp: the page allocator flags to use if allocating * * This behaves as a tmpfs "read_cache_page_gfp(mapping, index, gfp)", @@ -4325,13 +4325,12 @@ int shmem_zero_setup(struct vm_area_struct *vma) * i915_gem_object_get_pages_gtt() mixes __GFP_NORETRY | __GFP_NOWARN in * with the mapping_gfp_mask(), to avoid OOMing the machine unnecessarily. */ -struct page *shmem_read_mapping_page_gfp(struct address_space *mapping, - pgoff_t index, gfp_t gfp) +struct folio *shmem_read_folio_gfp(struct address_space *mapping, + pgoff_t index, gfp_t gfp) { #ifdef CONFIG_SHMEM struct inode *inode = mapping->host; struct folio *folio; - struct page *page; int error; BUG_ON(!shmem_mapping(mapping)); @@ -4341,6 +4340,25 @@ struct page *shmem_read_mapping_page_gfp(struct address_space *mapping, return ERR_PTR(error); folio_unlock(folio); + return folio; +#else + /* + * The tiny !SHMEM case uses ramfs without swap + */ + return mapping_read_folio_gfp(mapping, index, gfp); +#endif +} +EXPORT_SYMBOL_GPL(shmem_read_folio_gfp); + +struct page *shmem_read_mapping_page_gfp(struct address_space *mapping, + pgoff_t index, gfp_t gfp) +{ + struct folio *folio = shmem_read_folio_gfp(mapping, index, gfp); + struct page *page; + + if (IS_ERR(folio)) + return &folio->page; + page = folio_file_page(folio, index); if (PageHWPoison(page)) { folio_put(folio); @@ -4348,11 +4366,5 @@ struct page *shmem_read_mapping_page_gfp(struct address_space *mapping, } return page; -#else - /* - * The tiny !SHMEM case uses ramfs without swap - */ - return read_cache_page_gfp(mapping, index, gfp); -#endif } EXPORT_SYMBOL_GPL(shmem_read_mapping_page_gfp); -- cgit v1.2.3 From 869176a096068056b338b5cc1b0af93106007f5d Mon Sep 17 00:00:00 2001 From: Baoquan He Date: Mon, 6 Feb 2023 16:40:15 +0800 Subject: mm/vmalloc.c: add flags to mark vm_map_ram area Through vmalloc API, a virtual kernel area is reserved for physical address mapping. And vmap_area is used to track them, while vm_struct is allocated to associate with the vmap_area to store more information and passed out. However, area reserved via vm_map_ram() is an exception. It doesn't have vm_struct to associate with vmap_area. And we can't recognize the vmap_area with '->vm == NULL' as a vm_map_ram() area because the normal freeing path will set va->vm = NULL before unmapping, please see function remove_vm_area(). Meanwhile, there are two kinds of handling for vm_map_ram area. One is the whole vmap_area being reserved and mapped at one time through vm_map_area() interface; the other is the whole vmap_area with VMAP_BLOCK_SIZE size being reserved, while mapped into split regions with smaller size via vb_alloc(). To mark the area reserved through vm_map_ram(), add flags field into struct vmap_area. Bit 0 indicates this is vm_map_ram area created through vm_map_ram() interface, while bit 1 marks out the type of vm_map_ram area which makes use of vmap_block to manage split regions via vb_alloc/free(). This is a preparation for later use. Link: https://lkml.kernel.org/r/20230206084020.174506-3-bhe@redhat.com Signed-off-by: Baoquan He Reviewed-by: Lorenzo Stoakes Reviewed-by: Uladzislau Rezki (Sony) Cc: Dan Carpenter Cc: Stephen Brennan Signed-off-by: Andrew Morton --- include/linux/vmalloc.h | 1 + mm/vmalloc.c | 16 ++++++++++++---- 2 files changed, 13 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 096d48aa3437..69250efa03d1 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -76,6 +76,7 @@ struct vmap_area { unsigned long subtree_max_size; /* in "free" tree */ struct vm_struct *vm; /* in "busy" tree */ }; + unsigned long flags; /* mark type of vm_map_ram area */ }; /* archs that select HAVE_ARCH_HUGE_VMAP should override one or more of these */ diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 0f1396d6fbe6..2d0960190c42 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1578,7 +1578,8 @@ preload_this_cpu_lock(spinlock_t *lock, gfp_t gfp_mask, int node) static struct vmap_area *alloc_vmap_area(unsigned long size, unsigned long align, unsigned long vstart, unsigned long vend, - int node, gfp_t gfp_mask) + int node, gfp_t gfp_mask, + unsigned long va_flags) { struct vmap_area *va; unsigned long freed; @@ -1623,6 +1624,7 @@ retry: va->va_start = addr; va->va_end = addr + size; va->vm = NULL; + va->flags = va_flags; spin_lock(&vmap_area_lock); insert_vmap_area(va, &vmap_area_root, &vmap_area_list); @@ -1901,6 +1903,10 @@ static struct vmap_area *find_unlink_vmap_area(unsigned long addr) #define VMAP_BLOCK_SIZE (VMAP_BBMAP_BITS * PAGE_SIZE) +#define VMAP_RAM 0x1 /* indicates vm_map_ram area*/ +#define VMAP_BLOCK 0x2 /* mark out the vmap_block sub-type*/ +#define VMAP_FLAGS_MASK 0x3 + struct vmap_block_queue { spinlock_t lock; struct list_head free; @@ -1976,7 +1982,8 @@ static void *new_vmap_block(unsigned int order, gfp_t gfp_mask) va = alloc_vmap_area(VMAP_BLOCK_SIZE, VMAP_BLOCK_SIZE, VMALLOC_START, VMALLOC_END, - node, gfp_mask); + node, gfp_mask, + VMAP_RAM|VMAP_BLOCK); if (IS_ERR(va)) { kfree(vb); return ERR_CAST(va); @@ -2285,7 +2292,8 @@ void *vm_map_ram(struct page **pages, unsigned int count, int node) } else { struct vmap_area *va; va = alloc_vmap_area(size, PAGE_SIZE, - VMALLOC_START, VMALLOC_END, node, GFP_KERNEL); + VMALLOC_START, VMALLOC_END, + node, GFP_KERNEL, VMAP_RAM); if (IS_ERR(va)) return NULL; @@ -2483,7 +2491,7 @@ static struct vm_struct *__get_vm_area_node(unsigned long size, if (!(flags & VM_NO_GUARD)) size += PAGE_SIZE; - va = alloc_vmap_area(size, align, start, end, node, gfp_mask); + va = alloc_vmap_area(size, align, start, end, node, gfp_mask, 0); if (IS_ERR(va)) { kfree(area); return NULL; -- cgit v1.2.3 From 7427c30bea1449a885a1dd9baf991aaad26209ce Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Tue, 24 Jan 2023 16:34:23 -0400 Subject: mm/gup: remove obsolete FOLL_LONGTERM comment These days FOLL_LONGTERM is not allowed at all on any get_user_pages*() functions, it must be only be used with pin_user_pages*(), plus it now has universal support for all the pin_user_pages*() functions. Link: https://lkml.kernel.org/r/2-v2-987e91b59705+36b-gup_tidy_jgg@nvidia.com Signed-off-by: Jason Gunthorpe Reviewed-by: John Hubbard Cc: Alistair Popple Cc: Christoph Hellwig Cc: Claudio Imbrenda Cc: David Hildenbrand Cc: David Howells Cc: Mike Rapoport (IBM) Signed-off-by: Andrew Morton --- include/linux/mm_types.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 10a1e41f4e70..4396c7bf06d1 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -1053,12 +1053,6 @@ typedef unsigned int __bitwise zap_flags_t; * specifically failed. Filesystem pages are still subject to bugs and use of * FOLL_LONGTERM should be avoided on those pages. * - * FIXME: Also NOTE that FOLL_LONGTERM is not supported in every GUP call. - * Currently only get_user_pages() and get_user_pages_fast() support this flag - * and calls to get_user_pages_[un]locked are specifically not allowed. This - * is due to an incompatibility with the FS DAX check and - * FAULT_FLAG_ALLOW_RETRY. - * * In the CMA case: long term pins in a CMA region would unnecessarily fragment * that region. And so, CMA attempts to migrate the page before pinning, when * FOLL_LONGTERM is specified. -- cgit v1.2.3 From 7ce154fe6917e7db94d63bc4d6c73b678ad1c581 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Tue, 24 Jan 2023 16:34:25 -0400 Subject: mm/gup: move try_grab_page() to mm/internal.h This is part of the internal function of gup.c and is only non-static so that the parts of gup.c in the huge_memory.c and hugetlb.c can call it. Put it in internal.h beside the similarly purposed try_grab_folio() Link: https://lkml.kernel.org/r/4-v2-987e91b59705+36b-gup_tidy_jgg@nvidia.com Signed-off-by: Jason Gunthorpe Reviewed-by: John Hubbard Cc: Alistair Popple Cc: Christoph Hellwig Cc: Claudio Imbrenda Cc: David Hildenbrand Cc: David Howells Cc: Mike Rapoport (IBM) Signed-off-by: Andrew Morton --- include/linux/mm.h | 2 -- mm/internal.h | 1 + 2 files changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 0ed0cb2401f5..afefc166b349 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1268,8 +1268,6 @@ static inline void get_page(struct page *page) folio_get(page_folio(page)); } -int __must_check try_grab_page(struct page *page, unsigned int flags); - static inline __must_check bool try_get_page(struct page *page) { page = compound_head(page); diff --git a/mm/internal.h b/mm/internal.h index 90bb2078444c..3f75763b0fc2 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -856,6 +856,7 @@ int migrate_device_coherent_page(struct page *page); * mm/gup.c */ struct folio *try_grab_folio(struct page *page, int refs, unsigned int flags); +int __must_check try_grab_page(struct page *page, unsigned int flags); extern bool mirrored_kernelcore; -- cgit v1.2.3 From f04740f54594f85935e29a5c8ff6722f427f3dac Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Tue, 24 Jan 2023 16:34:29 -0400 Subject: mm/gup: add FOLL_UNLOCKABLE Setting FOLL_UNLOCKABLE allows GUP to lock/unlock the mmap lock on its own. It is a more explicit replacement for locked != NULL. This clears the way for passing in locked = 1, without intending that the lock can be unlocked. Set the flag in all cases where it is used, eg locked is present in the external interface or locked is used internally with locked = 0. Link: https://lkml.kernel.org/r/8-v2-987e91b59705+36b-gup_tidy_jgg@nvidia.com Signed-off-by: Jason Gunthorpe Acked-by: Mike Rapoport (IBM) Reviewed-by: John Hubbard Cc: Alistair Popple Cc: Christoph Hellwig Cc: Claudio Imbrenda Cc: David Hildenbrand Cc: David Howells Signed-off-by: Andrew Morton --- include/linux/mm_types.h | 1 + mm/gup.c | 36 +++++++++++++++++++++++------------- 2 files changed, 24 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 4396c7bf06d1..434b3ac8a351 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -1104,5 +1104,6 @@ typedef unsigned int __bitwise zap_flags_t; #define FOLL_FAST_ONLY 0x80000 /* gup_fast: prevent fall-back to slow gup */ #define FOLL_PCI_P2PDMA 0x100000 /* allow returning PCI P2PDMA pages */ #define FOLL_INTERRUPTIBLE 0x200000 /* allow interrupts from generic signals */ +#define FOLL_UNLOCKABLE 0x400000 /* allow unlocking the mmap lock (internal only) */ #endif /* _LINUX_MM_TYPES_H */ diff --git a/mm/gup.c b/mm/gup.c index 3afcd042f426..310fc6ab967e 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -896,7 +896,7 @@ static int faultin_page(struct vm_area_struct *vma, fault_flags |= FAULT_FLAG_WRITE; if (*flags & FOLL_REMOTE) fault_flags |= FAULT_FLAG_REMOTE; - if (locked) { + if (*flags & FOLL_UNLOCKABLE) { fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; /* * FAULT_FLAG_INTERRUPTIBLE is opt-in. GUP callers must set @@ -1382,9 +1382,11 @@ static __always_inline long __get_user_pages_locked(struct mm_struct *mm, for (;;) { ret = __get_user_pages(mm, start, nr_pages, flags, pages, vmas, locked); - if (!locked) + if (!(flags & FOLL_UNLOCKABLE)) { /* VM_FAULT_RETRY couldn't trigger, bypass */ - return ret; + pages_done = ret; + break; + } /* VM_FAULT_RETRY or VM_FAULT_COMPLETED cannot return errors */ if (!*locked) { @@ -1532,6 +1534,9 @@ long populate_vma_page_range(struct vm_area_struct *vma, if (vma_is_accessible(vma)) gup_flags |= FOLL_FORCE; + if (locked) + gup_flags |= FOLL_UNLOCKABLE; + /* * We made sure addr is within a VMA, so the following will * not result in a stack expansion that recurses back here. @@ -1583,7 +1588,7 @@ long faultin_vma_page_range(struct vm_area_struct *vma, unsigned long start, * a poisoned page. * !FOLL_FORCE: Require proper access permissions. */ - gup_flags = FOLL_TOUCH | FOLL_HWPOISON; + gup_flags = FOLL_TOUCH | FOLL_HWPOISON | FOLL_UNLOCKABLE; if (write) gup_flags |= FOLL_WRITE; @@ -2107,12 +2112,20 @@ static bool is_valid_gup_args(struct page **pages, struct vm_area_struct **vmas, * interfaces: * - FOLL_PIN/FOLL_TRIED/FOLL_FAST_ONLY are internal only * - FOLL_REMOTE is internal only and used on follow_page() + * - FOLL_UNLOCKABLE is internal only and used if locked is !NULL */ - if (WARN_ON_ONCE(gup_flags & (FOLL_PIN | FOLL_TRIED | + if (WARN_ON_ONCE(gup_flags & (FOLL_PIN | FOLL_TRIED | FOLL_UNLOCKABLE | FOLL_REMOTE | FOLL_FAST_ONLY))) return false; gup_flags |= to_set; + if (locked) { + /* At the external interface locked must be set */ + if (WARN_ON_ONCE(*locked != 1)) + return false; + + gup_flags |= FOLL_UNLOCKABLE; + } /* FOLL_GET and FOLL_PIN are mutually exclusive. */ if (WARN_ON_ONCE((gup_flags & (FOLL_PIN | FOLL_GET)) == @@ -2127,10 +2140,6 @@ static bool is_valid_gup_args(struct page **pages, struct vm_area_struct **vmas, if (WARN_ON_ONCE((gup_flags & (FOLL_GET | FOLL_PIN)) && !pages)) return false; - /* At the external interface locked must be set */ - if (WARN_ON_ONCE(locked && *locked != 1)) - return false; - /* We want to allow the pgmap to be hot-unplugged at all times */ if (WARN_ON_ONCE((gup_flags & FOLL_LONGTERM) && (gup_flags & FOLL_PCI_P2PDMA))) @@ -2140,7 +2149,7 @@ static bool is_valid_gup_args(struct page **pages, struct vm_area_struct **vmas, * Can't use VMAs with locked, as locked allows GUP to unlock * which invalidates the vmas array */ - if (WARN_ON_ONCE(vmas && locked)) + if (WARN_ON_ONCE(vmas && (gup_flags & FOLL_UNLOCKABLE))) return false; *gup_flags_p = gup_flags; @@ -2280,7 +2289,8 @@ long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, { int locked = 0; - if (!is_valid_gup_args(pages, NULL, NULL, &gup_flags, FOLL_TOUCH)) + if (!is_valid_gup_args(pages, NULL, NULL, &gup_flags, + FOLL_TOUCH | FOLL_UNLOCKABLE)) return -EINVAL; return __get_user_pages_locked(current->mm, start, nr_pages, pages, @@ -2968,7 +2978,7 @@ static int internal_get_user_pages_fast(unsigned long start, pages += nr_pinned; ret = __gup_longterm_locked(current->mm, start, nr_pages - nr_pinned, pages, NULL, &locked, - gup_flags | FOLL_TOUCH); + gup_flags | FOLL_TOUCH | FOLL_UNLOCKABLE); if (ret < 0) { /* * The caller has to unpin the pages we already pinned so @@ -3195,7 +3205,7 @@ long pin_user_pages_unlocked(unsigned long start, unsigned long nr_pages, int locked = 0; if (!is_valid_gup_args(pages, NULL, NULL, &gup_flags, - FOLL_PIN | FOLL_TOUCH)) + FOLL_PIN | FOLL_TOUCH | FOLL_UNLOCKABLE)) return 0; return __gup_longterm_locked(current->mm, start, nr_pages, pages, NULL, -- cgit v1.2.3 From edad1bb1fbf7e28b49bf76b2aa66bfcaba00f627 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Tue, 24 Jan 2023 16:34:31 -0400 Subject: mm/gup: remove pin_user_pages_fast_only() Commit ed29c2691188 ("drm/i915: Fix userptr so we do not have to worry about obj->mm.lock, v7.") removed the only caller, remove this dead code too. Link: https://lkml.kernel.org/r/10-v2-987e91b59705+36b-gup_tidy_jgg@nvidia.com Signed-off-by: Jason Gunthorpe Acked-by: Mike Rapoport (IBM) Reviewed-by: John Hubbard Reviewed-by: David Hildenbrand Cc: Alistair Popple Cc: Christoph Hellwig Cc: Claudio Imbrenda Cc: David Howells Signed-off-by: Andrew Morton --- include/linux/mm.h | 2 -- mm/gup.c | 33 --------------------------------- 2 files changed, 35 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index afefc166b349..a0d59645dcf9 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2261,8 +2261,6 @@ extern int mprotect_fixup(struct vma_iterator *vmi, struct mmu_gather *tlb, */ int get_user_pages_fast_only(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages); -int pin_user_pages_fast_only(unsigned long start, int nr_pages, - unsigned int gup_flags, struct page **pages); static inline bool get_user_page_fast_only(unsigned long addr, unsigned int gup_flags, struct page **pagep) diff --git a/mm/gup.c b/mm/gup.c index 4ce88e00e1c6..91c8ab53f43f 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -3102,39 +3102,6 @@ int pin_user_pages_fast(unsigned long start, int nr_pages, } EXPORT_SYMBOL_GPL(pin_user_pages_fast); -/* - * This is the FOLL_PIN equivalent of get_user_pages_fast_only(). Behavior - * is the same, except that this one sets FOLL_PIN instead of FOLL_GET. - * - * The API rules are the same, too: no negative values may be returned. - */ -int pin_user_pages_fast_only(unsigned long start, int nr_pages, - unsigned int gup_flags, struct page **pages) -{ - int nr_pinned; - - /* - * FOLL_FAST_ONLY is required in order to match the API description of - * this routine: no fall back to regular ("slow") GUP. - */ - if (!is_valid_gup_args(pages, NULL, NULL, &gup_flags, - FOLL_PIN | FOLL_FAST_ONLY)) - return 0; - - nr_pinned = internal_get_user_pages_fast(start, nr_pages, gup_flags, - pages); - /* - * This routine is not allowed to return negative values. However, - * internal_get_user_pages_fast() *can* return -errno. Therefore, - * correct for that here: - */ - if (nr_pinned < 0) - nr_pinned = 0; - - return nr_pinned; -} -EXPORT_SYMBOL_GPL(pin_user_pages_fast_only); - /** * pin_user_pages_remote() - pin pages of a remote process * -- cgit v1.2.3 From 63b605128655f2e3968d99e30b293c7e7eaa2fc2 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Tue, 24 Jan 2023 16:34:33 -0400 Subject: mm/gup: move gup_must_unshare() to mm/internal.h This function is only used in gup.c and closely related. It touches FOLL_PIN so it must be moved before the next patch. Link: https://lkml.kernel.org/r/12-v2-987e91b59705+36b-gup_tidy_jgg@nvidia.com Signed-off-by: Jason Gunthorpe Reviewed-by: John Hubbard Reviewed-by: David Hildenbrand Cc: Alistair Popple Cc: Christoph Hellwig Cc: Claudio Imbrenda Cc: David Howells Cc: Mike Rapoport (IBM) Signed-off-by: Andrew Morton --- include/linux/mm.h | 65 ------------------------------------------------------ mm/internal.h | 65 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 65 insertions(+), 65 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index a0d59645dcf9..4a0695ef969a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3180,71 +3180,6 @@ static inline int vm_fault_to_errno(vm_fault_t vm_fault, int foll_flags) return 0; } -/* - * Indicates for which pages that are write-protected in the page table, - * whether GUP has to trigger unsharing via FAULT_FLAG_UNSHARE such that the - * GUP pin will remain consistent with the pages mapped into the page tables - * of the MM. - * - * Temporary unmapping of PageAnonExclusive() pages or clearing of - * PageAnonExclusive() has to protect against concurrent GUP: - * * Ordinary GUP: Using the PT lock - * * GUP-fast and fork(): mm->write_protect_seq - * * GUP-fast and KSM or temporary unmapping (swap, migration): see - * page_try_share_anon_rmap() - * - * Must be called with the (sub)page that's actually referenced via the - * page table entry, which might not necessarily be the head page for a - * PTE-mapped THP. - * - * If the vma is NULL, we're coming from the GUP-fast path and might have - * to fallback to the slow path just to lookup the vma. - */ -static inline bool gup_must_unshare(struct vm_area_struct *vma, - unsigned int flags, struct page *page) -{ - /* - * FOLL_WRITE is implicitly handled correctly as the page table entry - * has to be writable -- and if it references (part of) an anonymous - * folio, that part is required to be marked exclusive. - */ - if ((flags & (FOLL_WRITE | FOLL_PIN)) != FOLL_PIN) - return false; - /* - * Note: PageAnon(page) is stable until the page is actually getting - * freed. - */ - if (!PageAnon(page)) { - /* - * We only care about R/O long-term pining: R/O short-term - * pinning does not have the semantics to observe successive - * changes through the process page tables. - */ - if (!(flags & FOLL_LONGTERM)) - return false; - - /* We really need the vma ... */ - if (!vma) - return true; - - /* - * ... because we only care about writable private ("COW") - * mappings where we have to break COW early. - */ - return is_cow_mapping(vma->vm_flags); - } - - /* Paired with a memory barrier in page_try_share_anon_rmap(). */ - if (IS_ENABLED(CONFIG_HAVE_FAST_GUP)) - smp_rmb(); - - /* - * Note that PageKsm() pages cannot be exclusive, and consequently, - * cannot get pinned. - */ - return !PageAnonExclusive(page); -} - /* * Indicates whether GUP can follow a PROT_NONE mapped page, or whether * a (NUMA hinting) fault is required. diff --git a/mm/internal.h b/mm/internal.h index 3f75763b0fc2..4f5ca3401b05 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -858,6 +858,71 @@ int migrate_device_coherent_page(struct page *page); struct folio *try_grab_folio(struct page *page, int refs, unsigned int flags); int __must_check try_grab_page(struct page *page, unsigned int flags); +/* + * Indicates for which pages that are write-protected in the page table, + * whether GUP has to trigger unsharing via FAULT_FLAG_UNSHARE such that the + * GUP pin will remain consistent with the pages mapped into the page tables + * of the MM. + * + * Temporary unmapping of PageAnonExclusive() pages or clearing of + * PageAnonExclusive() has to protect against concurrent GUP: + * * Ordinary GUP: Using the PT lock + * * GUP-fast and fork(): mm->write_protect_seq + * * GUP-fast and KSM or temporary unmapping (swap, migration): see + * page_try_share_anon_rmap() + * + * Must be called with the (sub)page that's actually referenced via the + * page table entry, which might not necessarily be the head page for a + * PTE-mapped THP. + * + * If the vma is NULL, we're coming from the GUP-fast path and might have + * to fallback to the slow path just to lookup the vma. + */ +static inline bool gup_must_unshare(struct vm_area_struct *vma, + unsigned int flags, struct page *page) +{ + /* + * FOLL_WRITE is implicitly handled correctly as the page table entry + * has to be writable -- and if it references (part of) an anonymous + * folio, that part is required to be marked exclusive. + */ + if ((flags & (FOLL_WRITE | FOLL_PIN)) != FOLL_PIN) + return false; + /* + * Note: PageAnon(page) is stable until the page is actually getting + * freed. + */ + if (!PageAnon(page)) { + /* + * We only care about R/O long-term pining: R/O short-term + * pinning does not have the semantics to observe successive + * changes through the process page tables. + */ + if (!(flags & FOLL_LONGTERM)) + return false; + + /* We really need the vma ... */ + if (!vma) + return true; + + /* + * ... because we only care about writable private ("COW") + * mappings where we have to break COW early. + */ + return is_cow_mapping(vma->vm_flags); + } + + /* Paired with a memory barrier in page_try_share_anon_rmap(). */ + if (IS_ENABLED(CONFIG_HAVE_FAST_GUP)) + smp_rmb(); + + /* + * Note that PageKsm() pages cannot be exclusive, and consequently, + * cannot get pinned. + */ + return !PageAnonExclusive(page); +} + extern bool mirrored_kernelcore; static inline bool vma_soft_dirty_enabled(struct vm_area_struct *vma) -- cgit v1.2.3 From 2c2241081f7dec878331fdc3a3f2361e99556bca Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Tue, 24 Jan 2023 16:34:34 -0400 Subject: mm/gup: move private gup FOLL_ flags to internal.h Move the flags that should not/are not used outside gup.c and related into mm/internal.h to discourage driver abuse. To make this more maintainable going forward compact the two FOLL ranges with new bit numbers from 0 to 11 and 16 to 21, using shifts so it is explicit. Switch to an enum so the whole thing is easier to read. Link: https://lkml.kernel.org/r/13-v2-987e91b59705+36b-gup_tidy_jgg@nvidia.com Signed-off-by: Jason Gunthorpe Reviewed-by: John Hubbard Acked-by: David Hildenbrand Cc: David Howells Cc: Christoph Hellwig Cc: Claudio Imbrenda Cc: Alistair Popple Cc: Mike Rapoport (IBM) Signed-off-by: Andrew Morton --- include/linux/mm_types.h | 57 +++++++++++++++++++++++++++++------------------- mm/internal.h | 15 +++++++++++++ 2 files changed, 50 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 434b3ac8a351..56753d0f096d 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -1040,9 +1040,6 @@ typedef unsigned int __bitwise zap_flags_t; * FOLL_PIN and FOLL_LONGTERM may be used in various combinations with each * other. Here is what they mean, and how to use them: * - * FOLL_LONGTERM indicates that the page will be held for an indefinite time - * period _often_ under userspace control. This is in contrast to - * iov_iter_get_pages(), whose usages are transient. * * FIXME: For pages which are part of a filesystem, mappings are subject to the * lifetime enforced by the filesystem and we need guarantees that longterm @@ -1086,24 +1083,40 @@ typedef unsigned int __bitwise zap_flags_t; * Please see Documentation/core-api/pin_user_pages.rst for more information. */ -#define FOLL_WRITE 0x01 /* check pte is writable */ -#define FOLL_TOUCH 0x02 /* mark page accessed */ -#define FOLL_GET 0x04 /* do get_page on page */ -#define FOLL_DUMP 0x08 /* give error on hole if it would be zero */ -#define FOLL_FORCE 0x10 /* get_user_pages read/write w/o permission */ -#define FOLL_NOWAIT 0x20 /* if a disk transfer is needed, start the IO - * and return without waiting upon it */ -#define FOLL_NOFAULT 0x80 /* do not fault in pages */ -#define FOLL_HWPOISON 0x100 /* check page is hwpoisoned */ -#define FOLL_TRIED 0x800 /* a retry, previous pass started an IO */ -#define FOLL_REMOTE 0x2000 /* we are working on non-current tsk/mm */ -#define FOLL_ANON 0x8000 /* don't do file mappings */ -#define FOLL_LONGTERM 0x10000 /* mapping lifetime is indefinite: see below */ -#define FOLL_SPLIT_PMD 0x20000 /* split huge pmd before returning */ -#define FOLL_PIN 0x40000 /* pages must be released via unpin_user_page */ -#define FOLL_FAST_ONLY 0x80000 /* gup_fast: prevent fall-back to slow gup */ -#define FOLL_PCI_P2PDMA 0x100000 /* allow returning PCI P2PDMA pages */ -#define FOLL_INTERRUPTIBLE 0x200000 /* allow interrupts from generic signals */ -#define FOLL_UNLOCKABLE 0x400000 /* allow unlocking the mmap lock (internal only) */ +enum { + /* check pte is writable */ + FOLL_WRITE = 1 << 0, + /* do get_page on page */ + FOLL_GET = 1 << 1, + /* give error on hole if it would be zero */ + FOLL_DUMP = 1 << 2, + /* get_user_pages read/write w/o permission */ + FOLL_FORCE = 1 << 3, + /* + * if a disk transfer is needed, start the IO and return without waiting + * upon it + */ + FOLL_NOWAIT = 1 << 4, + /* do not fault in pages */ + FOLL_NOFAULT = 1 << 5, + /* check page is hwpoisoned */ + FOLL_HWPOISON = 1 << 6, + /* don't do file mappings */ + FOLL_ANON = 1 << 7, + /* + * FOLL_LONGTERM indicates that the page will be held for an indefinite + * time period _often_ under userspace control. This is in contrast to + * iov_iter_get_pages(), whose usages are transient. + */ + FOLL_LONGTERM = 1 << 8, + /* split huge pmd before returning */ + FOLL_SPLIT_PMD = 1 << 9, + /* allow returning PCI P2PDMA pages */ + FOLL_PCI_P2PDMA = 1 << 10, + /* allow interrupts from generic signals */ + FOLL_INTERRUPTIBLE = 1 << 11, + + /* See also internal only FOLL flags in mm/internal.h */ +}; #endif /* _LINUX_MM_TYPES_H */ diff --git a/mm/internal.h b/mm/internal.h index 4f5ca3401b05..dfb37e94e140 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -858,6 +858,21 @@ int migrate_device_coherent_page(struct page *page); struct folio *try_grab_folio(struct page *page, int refs, unsigned int flags); int __must_check try_grab_page(struct page *page, unsigned int flags); +enum { + /* mark page accessed */ + FOLL_TOUCH = 1 << 16, + /* a retry, previous pass started an IO */ + FOLL_TRIED = 1 << 17, + /* we are working on non-current tsk/mm */ + FOLL_REMOTE = 1 << 18, + /* pages must be released via unpin_user_page */ + FOLL_PIN = 1 << 19, + /* gup_fast: prevent fall-back to slow gup */ + FOLL_FAST_ONLY = 1 << 20, + /* allow unlocking the mmap lock */ + FOLL_UNLOCKABLE = 1 << 21, +}; + /* * Indicates for which pages that are write-protected in the page table, * whether GUP has to trigger unsharing via FAULT_FLAG_UNSHARE such that the -- cgit v1.2.3 From 17ce252266c7f016ece026492c45838f852ddc79 Mon Sep 17 00:00:00 2001 From: Lizhi Hou Date: Thu, 19 Jan 2023 08:32:05 -0800 Subject: dmaengine: xilinx: xdma: Add xilinx xdma driver Add driver to enable PCIe board which uses XDMA (the DMA/Bridge Subsystem for PCI Express). For example, Xilinx Alveo PCIe devices. https://www.xilinx.com/products/boards-and-kits/alveo.html The XDMA engine support up to 4 Host to Card (H2C) and 4 Card to Host (C2H) channels. Memory transfers are specified on a per-channel basis in descriptor linked lists, which the DMA fetches from host memory and processes. Events such as descriptor completion and errors are signaled using interrupts. The hardware detail is provided by https://docs.xilinx.com/r/en-US/pg195-pcie-dma/Introduction This driver implements dmaengine APIs. - probe the available DMA channels - use dma_slave_map for channel lookup - use virtual channel to manage dmaengine tx descriptors - implement device_prep_slave_sg callback to handle host scatter gather list - implement device_config to config device address for DMA transfer Signed-off-by: Lizhi Hou Signed-off-by: Sonal Santan Signed-off-by: Max Zhen Signed-off-by: Brian Xu Tested-by: Martin Tuma Link: https://lore.kernel.org/r/1674145926-29449-2-git-send-email-lizhi.hou@amd.com Signed-off-by: Vinod Koul --- MAINTAINERS | 10 + drivers/dma/Kconfig | 14 + drivers/dma/xilinx/Makefile | 1 + drivers/dma/xilinx/xdma-regs.h | 166 ++++++ drivers/dma/xilinx/xdma.c | 893 +++++++++++++++++++++++++++++++++ include/linux/platform_data/amd_xdma.h | 34 ++ 6 files changed, 1118 insertions(+) create mode 100644 drivers/dma/xilinx/xdma-regs.h create mode 100644 drivers/dma/xilinx/xdma.c create mode 100644 include/linux/platform_data/amd_xdma.h (limited to 'include/linux') diff --git a/MAINTAINERS b/MAINTAINERS index f61eb221415b..b768ad4e901b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -22889,6 +22889,16 @@ F: Documentation/devicetree/bindings/media/xilinx/ F: drivers/media/platform/xilinx/ F: include/uapi/linux/xilinx-v4l2-controls.h +XILINX XDMA DRIVER +M: Lizhi Hou +M: Brian Xu +M: Raj Kumar Rampelli +L: dmaengine@vger.kernel.org +S: Supported +F: drivers/dma/xilinx/xdma-regs.h +F: drivers/dma/xilinx/xdma.c +F: include/linux/platform_data/amd_xdma.h + XILINX ZYNQMP DPDMA DRIVER M: Hyun Kwon M: Laurent Pinchart diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig index 7b95f07c6f1a..472dc315b889 100644 --- a/drivers/dma/Kconfig +++ b/drivers/dma/Kconfig @@ -728,6 +728,20 @@ config XILINX_DMA the scatter gather interface with multiple channels independent configuration support. +config XILINX_XDMA + tristate "Xilinx DMA/Bridge Subsystem DMA Engine" + depends on HAS_IOMEM + select DMA_ENGINE + select DMA_VIRTUAL_CHANNELS + select REGMAP_MMIO + help + Enable support for Xilinx DMA/Bridge Subsystem DMA engine. The DMA + provides high performance block data movement between Host memory + and the DMA subsystem. These direct memory transfers can be both in + the Host to Card (H2C) and Card to Host (C2H) transfers. + The core also provides up to 16 user interrupt wires that generate + interrupts to the host. + config XILINX_ZYNQMP_DMA tristate "Xilinx ZynqMP DMA Engine" depends on ARCH_ZYNQ || MICROBLAZE || ARM64 || COMPILE_TEST diff --git a/drivers/dma/xilinx/Makefile b/drivers/dma/xilinx/Makefile index 767bb45f641f..ebaa93644c94 100644 --- a/drivers/dma/xilinx/Makefile +++ b/drivers/dma/xilinx/Makefile @@ -1,4 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only obj-$(CONFIG_XILINX_DMA) += xilinx_dma.o +obj-$(CONFIG_XILINX_XDMA) += xdma.o obj-$(CONFIG_XILINX_ZYNQMP_DMA) += zynqmp_dma.o obj-$(CONFIG_XILINX_ZYNQMP_DPDMA) += xilinx_dpdma.o diff --git a/drivers/dma/xilinx/xdma-regs.h b/drivers/dma/xilinx/xdma-regs.h new file mode 100644 index 000000000000..dd98b4526b90 --- /dev/null +++ b/drivers/dma/xilinx/xdma-regs.h @@ -0,0 +1,166 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2017-2020 Xilinx, Inc. All rights reserved. + * Copyright (C) 2022, Advanced Micro Devices, Inc. + */ + +#ifndef __DMA_XDMA_REGS_H +#define __DMA_XDMA_REGS_H + +/* The length of register space exposed to host */ +#define XDMA_REG_SPACE_LEN 65536 + +/* + * maximum number of DMA channels for each direction: + * Host to Card (H2C) or Card to Host (C2H) + */ +#define XDMA_MAX_CHANNELS 4 + +/* + * macros to define the number of descriptor blocks can be used in one + * DMA transfer request. + * the DMA engine uses a linked list of descriptor blocks that specify the + * source, destination, and length of the DMA transfers. + */ +#define XDMA_DESC_BLOCK_NUM BIT(7) +#define XDMA_DESC_BLOCK_MASK (XDMA_DESC_BLOCK_NUM - 1) + +/* descriptor definitions */ +#define XDMA_DESC_ADJACENT 32 +#define XDMA_DESC_ADJACENT_MASK (XDMA_DESC_ADJACENT - 1) +#define XDMA_DESC_ADJACENT_BITS GENMASK(13, 8) +#define XDMA_DESC_MAGIC 0xad4bUL +#define XDMA_DESC_MAGIC_BITS GENMASK(31, 16) +#define XDMA_DESC_FLAGS_BITS GENMASK(7, 0) +#define XDMA_DESC_STOPPED BIT(0) +#define XDMA_DESC_COMPLETED BIT(1) +#define XDMA_DESC_BLEN_BITS 28 +#define XDMA_DESC_BLEN_MAX (BIT(XDMA_DESC_BLEN_BITS) - PAGE_SIZE) + +/* macros to construct the descriptor control word */ +#define XDMA_DESC_CONTROL(adjacent, flag) \ + (FIELD_PREP(XDMA_DESC_MAGIC_BITS, XDMA_DESC_MAGIC) | \ + FIELD_PREP(XDMA_DESC_ADJACENT_BITS, (adjacent) - 1) | \ + FIELD_PREP(XDMA_DESC_FLAGS_BITS, (flag))) +#define XDMA_DESC_CONTROL_LAST \ + XDMA_DESC_CONTROL(1, XDMA_DESC_STOPPED | XDMA_DESC_COMPLETED) + +/* + * Descriptor for a single contiguous memory block transfer. + * + * Multiple descriptors are linked by means of the next pointer. An additional + * extra adjacent number gives the amount of extra contiguous descriptors. + * + * The descriptors are in root complex memory, and the bytes in the 32-bit + * words must be in little-endian byte ordering. + */ +struct xdma_hw_desc { + __le32 control; + __le32 bytes; + __le64 src_addr; + __le64 dst_addr; + __le64 next_desc; +}; + +#define XDMA_DESC_SIZE sizeof(struct xdma_hw_desc) +#define XDMA_DESC_BLOCK_SIZE (XDMA_DESC_SIZE * XDMA_DESC_ADJACENT) +#define XDMA_DESC_BLOCK_ALIGN 4096 + +/* + * Channel registers + */ +#define XDMA_CHAN_IDENTIFIER 0x0 +#define XDMA_CHAN_CONTROL 0x4 +#define XDMA_CHAN_CONTROL_W1S 0x8 +#define XDMA_CHAN_CONTROL_W1C 0xc +#define XDMA_CHAN_STATUS 0x40 +#define XDMA_CHAN_COMPLETED_DESC 0x48 +#define XDMA_CHAN_ALIGNMENTS 0x4c +#define XDMA_CHAN_INTR_ENABLE 0x90 +#define XDMA_CHAN_INTR_ENABLE_W1S 0x94 +#define XDMA_CHAN_INTR_ENABLE_W1C 0x9c + +#define XDMA_CHAN_STRIDE 0x100 +#define XDMA_CHAN_H2C_OFFSET 0x0 +#define XDMA_CHAN_C2H_OFFSET 0x1000 +#define XDMA_CHAN_H2C_TARGET 0x0 +#define XDMA_CHAN_C2H_TARGET 0x1 + +/* macro to check if channel is available */ +#define XDMA_CHAN_MAGIC 0x1fc0 +#define XDMA_CHAN_CHECK_TARGET(id, target) \ + (((u32)(id) >> 16) == XDMA_CHAN_MAGIC + (target)) + +/* bits of the channel control register */ +#define CHAN_CTRL_RUN_STOP BIT(0) +#define CHAN_CTRL_IE_DESC_STOPPED BIT(1) +#define CHAN_CTRL_IE_DESC_COMPLETED BIT(2) +#define CHAN_CTRL_IE_DESC_ALIGN_MISMATCH BIT(3) +#define CHAN_CTRL_IE_MAGIC_STOPPED BIT(4) +#define CHAN_CTRL_IE_IDLE_STOPPED BIT(6) +#define CHAN_CTRL_IE_READ_ERROR GENMASK(13, 9) +#define CHAN_CTRL_IE_DESC_ERROR GENMASK(23, 19) +#define CHAN_CTRL_NON_INCR_ADDR BIT(25) +#define CHAN_CTRL_POLL_MODE_WB BIT(26) + +#define CHAN_CTRL_START (CHAN_CTRL_RUN_STOP | \ + CHAN_CTRL_IE_DESC_STOPPED | \ + CHAN_CTRL_IE_DESC_COMPLETED | \ + CHAN_CTRL_IE_DESC_ALIGN_MISMATCH | \ + CHAN_CTRL_IE_MAGIC_STOPPED | \ + CHAN_CTRL_IE_READ_ERROR | \ + CHAN_CTRL_IE_DESC_ERROR) + +/* bits of the channel interrupt enable mask */ +#define CHAN_IM_DESC_ERROR BIT(19) +#define CHAN_IM_READ_ERROR BIT(9) +#define CHAN_IM_IDLE_STOPPED BIT(6) +#define CHAN_IM_MAGIC_STOPPED BIT(4) +#define CHAN_IM_DESC_COMPLETED BIT(2) +#define CHAN_IM_DESC_STOPPED BIT(1) + +#define CHAN_IM_ALL (CHAN_IM_DESC_ERROR | CHAN_IM_READ_ERROR | \ + CHAN_IM_IDLE_STOPPED | CHAN_IM_MAGIC_STOPPED | \ + CHAN_IM_DESC_COMPLETED | CHAN_IM_DESC_STOPPED) + +/* + * Channel SGDMA registers + */ +#define XDMA_SGDMA_IDENTIFIER 0x4000 +#define XDMA_SGDMA_DESC_LO 0x4080 +#define XDMA_SGDMA_DESC_HI 0x4084 +#define XDMA_SGDMA_DESC_ADJ 0x4088 +#define XDMA_SGDMA_DESC_CREDIT 0x408c + +/* bits of the SG DMA control register */ +#define XDMA_CTRL_RUN_STOP BIT(0) +#define XDMA_CTRL_IE_DESC_STOPPED BIT(1) +#define XDMA_CTRL_IE_DESC_COMPLETED BIT(2) +#define XDMA_CTRL_IE_DESC_ALIGN_MISMATCH BIT(3) +#define XDMA_CTRL_IE_MAGIC_STOPPED BIT(4) +#define XDMA_CTRL_IE_IDLE_STOPPED BIT(6) +#define XDMA_CTRL_IE_READ_ERROR GENMASK(13, 9) +#define XDMA_CTRL_IE_DESC_ERROR GENMASK(23, 19) +#define XDMA_CTRL_NON_INCR_ADDR BIT(25) +#define XDMA_CTRL_POLL_MODE_WB BIT(26) + +/* + * interrupt registers + */ +#define XDMA_IRQ_IDENTIFIER 0x2000 +#define XDMA_IRQ_USER_INT_EN 0x2004 +#define XDMA_IRQ_USER_INT_EN_W1S 0x2008 +#define XDMA_IRQ_USER_INT_EN_W1C 0x200c +#define XDMA_IRQ_CHAN_INT_EN 0x2010 +#define XDMA_IRQ_CHAN_INT_EN_W1S 0x2014 +#define XDMA_IRQ_CHAN_INT_EN_W1C 0x2018 +#define XDMA_IRQ_USER_INT_REQ 0x2040 +#define XDMA_IRQ_CHAN_INT_REQ 0x2044 +#define XDMA_IRQ_USER_INT_PEND 0x2048 +#define XDMA_IRQ_CHAN_INT_PEND 0x204c +#define XDMA_IRQ_USER_VEC_NUM 0x2080 +#define XDMA_IRQ_CHAN_VEC_NUM 0x20a0 + +#define XDMA_IRQ_VEC_SHIFT 8 + +#endif /* __DMA_XDMA_REGS_H */ diff --git a/drivers/dma/xilinx/xdma.c b/drivers/dma/xilinx/xdma.c new file mode 100644 index 000000000000..48efb75ef9b4 --- /dev/null +++ b/drivers/dma/xilinx/xdma.c @@ -0,0 +1,893 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * DMA driver for Xilinx DMA/Bridge Subsystem + * + * Copyright (C) 2017-2020 Xilinx, Inc. All rights reserved. + * Copyright (C) 2022, Advanced Micro Devices, Inc. + */ + +/* + * The DMA/Bridge Subsystem for PCI Express allows for the movement of data + * between Host memory and the DMA subsystem. It does this by operating on + * 'descriptors' that contain information about the source, destination and + * amount of data to transfer. These direct memory transfers can be both in + * the Host to Card (H2C) and Card to Host (C2H) transfers. The DMA can be + * configured to have a single AXI4 Master interface shared by all channels + * or one AXI4-Stream interface for each channel enabled. Memory transfers are + * specified on a per-channel basis in descriptor linked lists, which the DMA + * fetches from host memory and processes. Events such as descriptor completion + * and errors are signaled using interrupts. The core also provides up to 16 + * user interrupt wires that generate interrupts to the host. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "../virt-dma.h" +#include "xdma-regs.h" + +/* mmio regmap config for all XDMA registers */ +static const struct regmap_config xdma_regmap_config = { + .reg_bits = 32, + .val_bits = 32, + .reg_stride = 4, + .max_register = XDMA_REG_SPACE_LEN, +}; + +/** + * struct xdma_desc_block - Descriptor block + * @virt_addr: Virtual address of block start + * @dma_addr: DMA address of block start + */ +struct xdma_desc_block { + void *virt_addr; + dma_addr_t dma_addr; +}; + +/** + * struct xdma_chan - Driver specific DMA channel structure + * @vchan: Virtual channel + * @xdev_hdl: Pointer to DMA device structure + * @base: Offset of channel registers + * @desc_pool: Descriptor pool + * @busy: Busy flag of the channel + * @dir: Transferring direction of the channel + * @cfg: Transferring config of the channel + * @irq: IRQ assigned to the channel + */ +struct xdma_chan { + struct virt_dma_chan vchan; + void *xdev_hdl; + u32 base; + struct dma_pool *desc_pool; + bool busy; + enum dma_transfer_direction dir; + struct dma_slave_config cfg; + u32 irq; +}; + +/** + * struct xdma_desc - DMA desc structure + * @vdesc: Virtual DMA descriptor + * @chan: DMA channel pointer + * @dir: Transferring direction of the request + * @dev_addr: Physical address on DMA device side + * @desc_blocks: Hardware descriptor blocks + * @dblk_num: Number of hardware descriptor blocks + * @desc_num: Number of hardware descriptors + * @completed_desc_num: Completed hardware descriptors + */ +struct xdma_desc { + struct virt_dma_desc vdesc; + struct xdma_chan *chan; + enum dma_transfer_direction dir; + u64 dev_addr; + struct xdma_desc_block *desc_blocks; + u32 dblk_num; + u32 desc_num; + u32 completed_desc_num; +}; + +#define XDMA_DEV_STATUS_REG_DMA BIT(0) +#define XDMA_DEV_STATUS_INIT_MSIX BIT(1) + +/** + * struct xdma_device - DMA device structure + * @pdev: Platform device pointer + * @dma_dev: DMA device structure + * @rmap: MMIO regmap for DMA registers + * @h2c_chans: Host to Card channels + * @c2h_chans: Card to Host channels + * @h2c_chan_num: Number of H2C channels + * @c2h_chan_num: Number of C2H channels + * @irq_start: Start IRQ assigned to device + * @irq_num: Number of IRQ assigned to device + * @status: Initialization status + */ +struct xdma_device { + struct platform_device *pdev; + struct dma_device dma_dev; + struct regmap *rmap; + struct xdma_chan *h2c_chans; + struct xdma_chan *c2h_chans; + u32 h2c_chan_num; + u32 c2h_chan_num; + u32 irq_start; + u32 irq_num; + u32 status; +}; + +#define xdma_err(xdev, fmt, args...) \ + dev_err(&(xdev)->pdev->dev, fmt, ##args) +#define XDMA_CHAN_NUM(_xd) ({ \ + typeof(_xd) (xd) = (_xd); \ + ((xd)->h2c_chan_num + (xd)->c2h_chan_num); }) + +/* Get the last desc in a desc block */ +static inline void *xdma_blk_last_desc(struct xdma_desc_block *block) +{ + return block->virt_addr + (XDMA_DESC_ADJACENT - 1) * XDMA_DESC_SIZE; +} + +/** + * xdma_link_desc_blocks - Link descriptor blocks for DMA transfer + * @sw_desc: Tx descriptor pointer + */ +static void xdma_link_desc_blocks(struct xdma_desc *sw_desc) +{ + struct xdma_desc_block *block; + u32 last_blk_desc, desc_control; + struct xdma_hw_desc *desc; + int i; + + desc_control = XDMA_DESC_CONTROL(XDMA_DESC_ADJACENT, 0); + for (i = 1; i < sw_desc->dblk_num; i++) { + block = &sw_desc->desc_blocks[i - 1]; + desc = xdma_blk_last_desc(block); + + if (!(i & XDMA_DESC_BLOCK_MASK)) { + desc->control = cpu_to_le32(XDMA_DESC_CONTROL_LAST); + continue; + } + desc->control = cpu_to_le32(desc_control); + desc->next_desc = cpu_to_le64(block[1].dma_addr); + } + + /* update the last block */ + last_blk_desc = (sw_desc->desc_num - 1) & XDMA_DESC_ADJACENT_MASK; + if (((sw_desc->dblk_num - 1) & XDMA_DESC_BLOCK_MASK) > 0) { + block = &sw_desc->desc_blocks[sw_desc->dblk_num - 2]; + desc = xdma_blk_last_desc(block); + desc_control = XDMA_DESC_CONTROL(last_blk_desc + 1, 0); + desc->control = cpu_to_le32(desc_control); + } + + block = &sw_desc->desc_blocks[sw_desc->dblk_num - 1]; + desc = block->virt_addr + last_blk_desc * XDMA_DESC_SIZE; + desc->control = cpu_to_le32(XDMA_DESC_CONTROL_LAST); +} + +static inline struct xdma_chan *to_xdma_chan(struct dma_chan *chan) +{ + return container_of(chan, struct xdma_chan, vchan.chan); +} + +static inline struct xdma_desc *to_xdma_desc(struct virt_dma_desc *vdesc) +{ + return container_of(vdesc, struct xdma_desc, vdesc); +} + +/** + * xdma_channel_init - Initialize DMA channel registers + * @chan: DMA channel pointer + */ +static int xdma_channel_init(struct xdma_chan *chan) +{ + struct xdma_device *xdev = chan->xdev_hdl; + int ret; + + ret = regmap_write(xdev->rmap, chan->base + XDMA_CHAN_CONTROL_W1C, + CHAN_CTRL_NON_INCR_ADDR); + if (ret) + return ret; + + ret = regmap_write(xdev->rmap, chan->base + XDMA_CHAN_INTR_ENABLE, + CHAN_IM_ALL); + if (ret) + return ret; + + return 0; +} + +/** + * xdma_free_desc - Free descriptor + * @vdesc: Virtual DMA descriptor + */ +static void xdma_free_desc(struct virt_dma_desc *vdesc) +{ + struct xdma_desc *sw_desc; + int i; + + sw_desc = to_xdma_desc(vdesc); + for (i = 0; i < sw_desc->dblk_num; i++) { + if (!sw_desc->desc_blocks[i].virt_addr) + break; + dma_pool_free(sw_desc->chan->desc_pool, + sw_desc->desc_blocks[i].virt_addr, + sw_desc->desc_blocks[i].dma_addr); + } + kfree(sw_desc->desc_blocks); + kfree(sw_desc); +} + +/** + * xdma_alloc_desc - Allocate descriptor + * @chan: DMA channel pointer + * @desc_num: Number of hardware descriptors + */ +static struct xdma_desc * +xdma_alloc_desc(struct xdma_chan *chan, u32 desc_num) +{ + struct xdma_desc *sw_desc; + struct xdma_hw_desc *desc; + dma_addr_t dma_addr; + u32 dblk_num; + void *addr; + int i, j; + + sw_desc = kzalloc(sizeof(*sw_desc), GFP_NOWAIT); + if (!sw_desc) + return NULL; + + sw_desc->chan = chan; + sw_desc->desc_num = desc_num; + dblk_num = DIV_ROUND_UP(desc_num, XDMA_DESC_ADJACENT); + sw_desc->desc_blocks = kcalloc(dblk_num, sizeof(*sw_desc->desc_blocks), + GFP_NOWAIT); + if (!sw_desc->desc_blocks) + goto failed; + + sw_desc->dblk_num = dblk_num; + for (i = 0; i < sw_desc->dblk_num; i++) { + addr = dma_pool_alloc(chan->desc_pool, GFP_NOWAIT, &dma_addr); + if (!addr) + goto failed; + + sw_desc->desc_blocks[i].virt_addr = addr; + sw_desc->desc_blocks[i].dma_addr = dma_addr; + for (j = 0, desc = addr; j < XDMA_DESC_ADJACENT; j++) + desc[j].control = cpu_to_le32(XDMA_DESC_CONTROL(1, 0)); + } + + xdma_link_desc_blocks(sw_desc); + + return sw_desc; + +failed: + xdma_free_desc(&sw_desc->vdesc); + return NULL; +} + +/** + * xdma_xfer_start - Start DMA transfer + * @xdma_chan: DMA channel pointer + */ +static int xdma_xfer_start(struct xdma_chan *xchan) +{ + struct virt_dma_desc *vd = vchan_next_desc(&xchan->vchan); + struct xdma_device *xdev = xchan->xdev_hdl; + struct xdma_desc_block *block; + u32 val, completed_blocks; + struct xdma_desc *desc; + int ret; + + /* + * check if there is not any submitted descriptor or channel is busy. + * vchan lock should be held where this function is called. + */ + if (!vd || xchan->busy) + return -EINVAL; + + /* clear run stop bit to get ready for transfer */ + ret = regmap_write(xdev->rmap, xchan->base + XDMA_CHAN_CONTROL_W1C, + CHAN_CTRL_RUN_STOP); + if (ret) + return ret; + + desc = to_xdma_desc(vd); + if (desc->dir != xchan->dir) { + xdma_err(xdev, "incorrect request direction"); + return -EINVAL; + } + + /* set DMA engine to the first descriptor block */ + completed_blocks = desc->completed_desc_num / XDMA_DESC_ADJACENT; + block = &desc->desc_blocks[completed_blocks]; + val = lower_32_bits(block->dma_addr); + ret = regmap_write(xdev->rmap, xchan->base + XDMA_SGDMA_DESC_LO, val); + if (ret) + return ret; + + val = upper_32_bits(block->dma_addr); + ret = regmap_write(xdev->rmap, xchan->base + XDMA_SGDMA_DESC_HI, val); + if (ret) + return ret; + + if (completed_blocks + 1 == desc->dblk_num) + val = (desc->desc_num - 1) & XDMA_DESC_ADJACENT_MASK; + else + val = XDMA_DESC_ADJACENT - 1; + ret = regmap_write(xdev->rmap, xchan->base + XDMA_SGDMA_DESC_ADJ, val); + if (ret) + return ret; + + /* kick off DMA transfer */ + ret = regmap_write(xdev->rmap, xchan->base + XDMA_CHAN_CONTROL, + CHAN_CTRL_START); + if (ret) + return ret; + + xchan->busy = true; + return 0; +} + +/** + * xdma_alloc_channels - Detect and allocate DMA channels + * @xdev: DMA device pointer + * @dir: Channel direction + */ +static int xdma_alloc_channels(struct xdma_device *xdev, + enum dma_transfer_direction dir) +{ + struct xdma_platdata *pdata = dev_get_platdata(&xdev->pdev->dev); + struct xdma_chan **chans, *xchan; + u32 base, identifier, target; + u32 *chan_num; + int i, j, ret; + + if (dir == DMA_MEM_TO_DEV) { + base = XDMA_CHAN_H2C_OFFSET; + target = XDMA_CHAN_H2C_TARGET; + chans = &xdev->h2c_chans; + chan_num = &xdev->h2c_chan_num; + } else if (dir == DMA_DEV_TO_MEM) { + base = XDMA_CHAN_C2H_OFFSET; + target = XDMA_CHAN_C2H_TARGET; + chans = &xdev->c2h_chans; + chan_num = &xdev->c2h_chan_num; + } else { + xdma_err(xdev, "invalid direction specified"); + return -EINVAL; + } + + /* detect number of available DMA channels */ + for (i = 0, *chan_num = 0; i < pdata->max_dma_channels; i++) { + ret = regmap_read(xdev->rmap, base + i * XDMA_CHAN_STRIDE, + &identifier); + if (ret) + return ret; + + /* check if it is available DMA channel */ + if (XDMA_CHAN_CHECK_TARGET(identifier, target)) + (*chan_num)++; + } + + if (!*chan_num) { + xdma_err(xdev, "does not probe any channel"); + return -EINVAL; + } + + *chans = devm_kcalloc(&xdev->pdev->dev, *chan_num, sizeof(**chans), + GFP_KERNEL); + if (!*chans) + return -ENOMEM; + + for (i = 0, j = 0; i < pdata->max_dma_channels; i++) { + ret = regmap_read(xdev->rmap, base + i * XDMA_CHAN_STRIDE, + &identifier); + if (ret) + return ret; + + if (!XDMA_CHAN_CHECK_TARGET(identifier, target)) + continue; + + if (j == *chan_num) { + xdma_err(xdev, "invalid channel number"); + return -EIO; + } + + /* init channel structure and hardware */ + xchan = &(*chans)[j]; + xchan->xdev_hdl = xdev; + xchan->base = base + i * XDMA_CHAN_STRIDE; + xchan->dir = dir; + + ret = xdma_channel_init(xchan); + if (ret) + return ret; + xchan->vchan.desc_free = xdma_free_desc; + vchan_init(&xchan->vchan, &xdev->dma_dev); + + j++; + } + + dev_info(&xdev->pdev->dev, "configured %d %s channels", j, + (dir == DMA_MEM_TO_DEV) ? "H2C" : "C2H"); + + return 0; +} + +/** + * xdma_issue_pending - Issue pending transactions + * @chan: DMA channel pointer + */ +static void xdma_issue_pending(struct dma_chan *chan) +{ + struct xdma_chan *xdma_chan = to_xdma_chan(chan); + unsigned long flags; + + spin_lock_irqsave(&xdma_chan->vchan.lock, flags); + if (vchan_issue_pending(&xdma_chan->vchan)) + xdma_xfer_start(xdma_chan); + spin_unlock_irqrestore(&xdma_chan->vchan.lock, flags); +} + +/** + * xdma_prep_device_sg - prepare a descriptor for a DMA transaction + * @chan: DMA channel pointer + * @sgl: Transfer scatter gather list + * @sg_len: Length of scatter gather list + * @dir: Transfer direction + * @flags: transfer ack flags + * @context: APP words of the descriptor + */ +static struct dma_async_tx_descriptor * +xdma_prep_device_sg(struct dma_chan *chan, struct scatterlist *sgl, + unsigned int sg_len, enum dma_transfer_direction dir, + unsigned long flags, void *context) +{ + struct xdma_chan *xdma_chan = to_xdma_chan(chan); + struct dma_async_tx_descriptor *tx_desc; + u32 desc_num = 0, i, len, rest; + struct xdma_desc_block *dblk; + struct xdma_hw_desc *desc; + struct xdma_desc *sw_desc; + u64 dev_addr, *src, *dst; + struct scatterlist *sg; + u64 addr; + + for_each_sg(sgl, sg, sg_len, i) + desc_num += DIV_ROUND_UP(sg_dma_len(sg), XDMA_DESC_BLEN_MAX); + + sw_desc = xdma_alloc_desc(xdma_chan, desc_num); + if (!sw_desc) + return NULL; + sw_desc->dir = dir; + + if (dir == DMA_MEM_TO_DEV) { + dev_addr = xdma_chan->cfg.dst_addr; + src = &addr; + dst = &dev_addr; + } else { + dev_addr = xdma_chan->cfg.src_addr; + src = &dev_addr; + dst = &addr; + } + + dblk = sw_desc->desc_blocks; + desc = dblk->virt_addr; + desc_num = 1; + for_each_sg(sgl, sg, sg_len, i) { + addr = sg_dma_address(sg); + rest = sg_dma_len(sg); + + do { + len = min_t(u32, rest, XDMA_DESC_BLEN_MAX); + /* set hardware descriptor */ + desc->bytes = cpu_to_le32(len); + desc->src_addr = cpu_to_le64(*src); + desc->dst_addr = cpu_to_le64(*dst); + + if (!(desc_num & XDMA_DESC_ADJACENT_MASK)) { + dblk++; + desc = dblk->virt_addr; + } else { + desc++; + } + + desc_num++; + dev_addr += len; + addr += len; + rest -= len; + } while (rest); + } + + tx_desc = vchan_tx_prep(&xdma_chan->vchan, &sw_desc->vdesc, flags); + if (!tx_desc) + goto failed; + + return tx_desc; + +failed: + xdma_free_desc(&sw_desc->vdesc); + + return NULL; +} + +/** + * xdma_device_config - Configure the DMA channel + * @chan: DMA channel + * @cfg: channel configuration + */ +static int xdma_device_config(struct dma_chan *chan, + struct dma_slave_config *cfg) +{ + struct xdma_chan *xdma_chan = to_xdma_chan(chan); + + memcpy(&xdma_chan->cfg, cfg, sizeof(*cfg)); + + return 0; +} + +/** + * xdma_free_chan_resources - Free channel resources + * @chan: DMA channel + */ +static void xdma_free_chan_resources(struct dma_chan *chan) +{ + struct xdma_chan *xdma_chan = to_xdma_chan(chan); + + vchan_free_chan_resources(&xdma_chan->vchan); + dma_pool_destroy(xdma_chan->desc_pool); + xdma_chan->desc_pool = NULL; +} + +/** + * xdma_alloc_chan_resources - Allocate channel resources + * @chan: DMA channel + */ +static int xdma_alloc_chan_resources(struct dma_chan *chan) +{ + struct xdma_chan *xdma_chan = to_xdma_chan(chan); + struct xdma_device *xdev = xdma_chan->xdev_hdl; + struct device *dev = xdev->dma_dev.dev; + + while (dev && !dev_is_pci(dev)) + dev = dev->parent; + if (!dev) { + xdma_err(xdev, "unable to find pci device"); + return -EINVAL; + } + + xdma_chan->desc_pool = dma_pool_create(dma_chan_name(chan), + dev, XDMA_DESC_BLOCK_SIZE, + XDMA_DESC_BLOCK_ALIGN, 0); + if (!xdma_chan->desc_pool) { + xdma_err(xdev, "unable to allocate descriptor pool"); + return -ENOMEM; + } + + return 0; +} + +/** + * xdma_channel_isr - XDMA channel interrupt handler + * @irq: IRQ number + * @dev_id: Pointer to the DMA channel structure + */ +static irqreturn_t xdma_channel_isr(int irq, void *dev_id) +{ + struct xdma_chan *xchan = dev_id; + u32 complete_desc_num = 0; + struct xdma_device *xdev; + struct virt_dma_desc *vd; + struct xdma_desc *desc; + int ret; + + spin_lock(&xchan->vchan.lock); + + /* get submitted request */ + vd = vchan_next_desc(&xchan->vchan); + if (!vd) + goto out; + + xchan->busy = false; + desc = to_xdma_desc(vd); + xdev = xchan->xdev_hdl; + + ret = regmap_read(xdev->rmap, xchan->base + XDMA_CHAN_COMPLETED_DESC, + &complete_desc_num); + if (ret) + goto out; + + desc->completed_desc_num += complete_desc_num; + /* + * if all data blocks are transferred, remove and complete the request + */ + if (desc->completed_desc_num == desc->desc_num) { + list_del(&vd->node); + vchan_cookie_complete(vd); + goto out; + } + + if (desc->completed_desc_num > desc->desc_num || + complete_desc_num != XDMA_DESC_BLOCK_NUM * XDMA_DESC_ADJACENT) + goto out; + + /* transfer the rest of data */ + xdma_xfer_start(xchan); + +out: + spin_unlock(&xchan->vchan.lock); + return IRQ_HANDLED; +} + +/** + * xdma_irq_fini - Uninitialize IRQ + * @xdev: DMA device pointer + */ +static void xdma_irq_fini(struct xdma_device *xdev) +{ + int i; + + /* disable interrupt */ + regmap_write(xdev->rmap, XDMA_IRQ_CHAN_INT_EN_W1C, ~0); + + /* free irq handler */ + for (i = 0; i < xdev->h2c_chan_num; i++) + free_irq(xdev->h2c_chans[i].irq, &xdev->h2c_chans[i]); + + for (i = 0; i < xdev->c2h_chan_num; i++) + free_irq(xdev->c2h_chans[i].irq, &xdev->c2h_chans[i]); +} + +/** + * xdma_set_vector_reg - configure hardware IRQ registers + * @xdev: DMA device pointer + * @vec_tbl_start: Start of IRQ registers + * @irq_start: Start of IRQ + * @irq_num: Number of IRQ + */ +static int xdma_set_vector_reg(struct xdma_device *xdev, u32 vec_tbl_start, + u32 irq_start, u32 irq_num) +{ + u32 shift, i, val = 0; + int ret; + + /* Each IRQ register is 32 bit and contains 4 IRQs */ + while (irq_num > 0) { + for (i = 0; i < 4; i++) { + shift = XDMA_IRQ_VEC_SHIFT * i; + val |= irq_start << shift; + irq_start++; + irq_num--; + } + + /* write IRQ register */ + ret = regmap_write(xdev->rmap, vec_tbl_start, val); + if (ret) + return ret; + vec_tbl_start += sizeof(u32); + val = 0; + } + + return 0; +} + +/** + * xdma_irq_init - initialize IRQs + * @xdev: DMA device pointer + */ +static int xdma_irq_init(struct xdma_device *xdev) +{ + u32 irq = xdev->irq_start; + int i, j, ret; + + /* return failure if there are not enough IRQs */ + if (xdev->irq_num < XDMA_CHAN_NUM(xdev)) { + xdma_err(xdev, "not enough irq"); + return -EINVAL; + } + + /* setup H2C interrupt handler */ + for (i = 0; i < xdev->h2c_chan_num; i++) { + ret = request_irq(irq, xdma_channel_isr, 0, + "xdma-h2c-channel", &xdev->h2c_chans[i]); + if (ret) { + xdma_err(xdev, "H2C channel%d request irq%d failed: %d", + i, irq, ret); + goto failed_init_h2c; + } + xdev->h2c_chans[i].irq = irq; + irq++; + } + + /* setup C2H interrupt handler */ + for (j = 0; j < xdev->c2h_chan_num; j++) { + ret = request_irq(irq, xdma_channel_isr, 0, + "xdma-c2h-channel", &xdev->c2h_chans[j]); + if (ret) { + xdma_err(xdev, "H2C channel%d request irq%d failed: %d", + j, irq, ret); + goto failed_init_c2h; + } + xdev->c2h_chans[j].irq = irq; + irq++; + } + + /* config hardware IRQ registers */ + ret = xdma_set_vector_reg(xdev, XDMA_IRQ_CHAN_VEC_NUM, 0, + XDMA_CHAN_NUM(xdev)); + if (ret) { + xdma_err(xdev, "failed to set channel vectors: %d", ret); + goto failed_init_c2h; + } + + /* enable interrupt */ + ret = regmap_write(xdev->rmap, XDMA_IRQ_CHAN_INT_EN_W1S, ~0); + if (ret) + goto failed_init_c2h; + + return 0; + +failed_init_c2h: + while (j--) + free_irq(xdev->c2h_chans[j].irq, &xdev->c2h_chans[j]); +failed_init_h2c: + while (i--) + free_irq(xdev->h2c_chans[i].irq, &xdev->h2c_chans[i]); + + return ret; +} + +static bool xdma_filter_fn(struct dma_chan *chan, void *param) +{ + struct xdma_chan *xdma_chan = to_xdma_chan(chan); + struct xdma_chan_info *chan_info = param; + + return chan_info->dir == xdma_chan->dir; +} + +/** + * xdma_remove - Driver remove function + * @pdev: Pointer to the platform_device structure + */ +static int xdma_remove(struct platform_device *pdev) +{ + struct xdma_device *xdev = platform_get_drvdata(pdev); + + if (xdev->status & XDMA_DEV_STATUS_INIT_MSIX) + xdma_irq_fini(xdev); + + if (xdev->status & XDMA_DEV_STATUS_REG_DMA) + dma_async_device_unregister(&xdev->dma_dev); + + return 0; +} + +/** + * xdma_probe - Driver probe function + * @pdev: Pointer to the platform_device structure + */ +static int xdma_probe(struct platform_device *pdev) +{ + struct xdma_platdata *pdata = dev_get_platdata(&pdev->dev); + struct xdma_device *xdev; + void __iomem *reg_base; + struct resource *res; + int ret = -ENODEV; + + if (pdata->max_dma_channels > XDMA_MAX_CHANNELS) { + dev_err(&pdev->dev, "invalid max dma channels %d", + pdata->max_dma_channels); + return -EINVAL; + } + + xdev = devm_kzalloc(&pdev->dev, sizeof(*xdev), GFP_KERNEL); + if (!xdev) + return -ENOMEM; + + platform_set_drvdata(pdev, xdev); + xdev->pdev = pdev; + + res = platform_get_resource(pdev, IORESOURCE_IRQ, 0); + if (!res) { + xdma_err(xdev, "failed to get irq resource"); + goto failed; + } + xdev->irq_start = res->start; + xdev->irq_num = res->end - res->start + 1; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!res) { + xdma_err(xdev, "failed to get io resource"); + goto failed; + } + + reg_base = devm_ioremap_resource(&pdev->dev, res); + if (!reg_base) { + xdma_err(xdev, "ioremap failed"); + goto failed; + } + + xdev->rmap = devm_regmap_init_mmio(&pdev->dev, reg_base, + &xdma_regmap_config); + if (!xdev->rmap) { + xdma_err(xdev, "config regmap failed: %d", ret); + goto failed; + } + INIT_LIST_HEAD(&xdev->dma_dev.channels); + + ret = xdma_alloc_channels(xdev, DMA_MEM_TO_DEV); + if (ret) { + xdma_err(xdev, "config H2C channels failed: %d", ret); + goto failed; + } + + ret = xdma_alloc_channels(xdev, DMA_DEV_TO_MEM); + if (ret) { + xdma_err(xdev, "config C2H channels failed: %d", ret); + goto failed; + } + + dma_cap_set(DMA_SLAVE, xdev->dma_dev.cap_mask); + dma_cap_set(DMA_PRIVATE, xdev->dma_dev.cap_mask); + + xdev->dma_dev.dev = &pdev->dev; + xdev->dma_dev.device_free_chan_resources = xdma_free_chan_resources; + xdev->dma_dev.device_alloc_chan_resources = xdma_alloc_chan_resources; + xdev->dma_dev.device_tx_status = dma_cookie_status; + xdev->dma_dev.device_prep_slave_sg = xdma_prep_device_sg; + xdev->dma_dev.device_config = xdma_device_config; + xdev->dma_dev.device_issue_pending = xdma_issue_pending; + xdev->dma_dev.filter.map = pdata->device_map; + xdev->dma_dev.filter.mapcnt = pdata->device_map_cnt; + xdev->dma_dev.filter.fn = xdma_filter_fn; + + ret = dma_async_device_register(&xdev->dma_dev); + if (ret) { + xdma_err(xdev, "failed to register Xilinx XDMA: %d", ret); + goto failed; + } + xdev->status |= XDMA_DEV_STATUS_REG_DMA; + + ret = xdma_irq_init(xdev); + if (ret) { + xdma_err(xdev, "failed to init msix: %d", ret); + goto failed; + } + xdev->status |= XDMA_DEV_STATUS_INIT_MSIX; + + return 0; + +failed: + xdma_remove(pdev); + + return ret; +} + +static const struct platform_device_id xdma_id_table[] = { + { "xdma", 0}, + { }, +}; + +static struct platform_driver xdma_driver = { + .driver = { + .name = "xdma", + }, + .id_table = xdma_id_table, + .probe = xdma_probe, + .remove = xdma_remove, +}; + +module_platform_driver(xdma_driver); + +MODULE_DESCRIPTION("AMD XDMA driver"); +MODULE_AUTHOR("XRT Team "); +MODULE_LICENSE("GPL"); diff --git a/include/linux/platform_data/amd_xdma.h b/include/linux/platform_data/amd_xdma.h new file mode 100644 index 000000000000..b5e23e14bac8 --- /dev/null +++ b/include/linux/platform_data/amd_xdma.h @@ -0,0 +1,34 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2022, Advanced Micro Devices, Inc. + */ + +#ifndef _PLATDATA_AMD_XDMA_H +#define _PLATDATA_AMD_XDMA_H + +#include + +/** + * struct xdma_chan_info - DMA channel information + * This information is used to match channel when request dma channel + * @dir: Channel transfer direction + */ +struct xdma_chan_info { + enum dma_transfer_direction dir; +}; + +#define XDMA_FILTER_PARAM(chan_info) ((void *)(chan_info)) + +struct dma_slave_map; + +/** + * struct xdma_platdata - platform specific data for XDMA engine + * @max_dma_channels: Maximum dma channels in each direction + */ +struct xdma_platdata { + u32 max_dma_channels; + u32 device_map_cnt; + struct dma_slave_map *device_map; +}; + +#endif /* _PLATDATA_AMD_XDMA_H */ -- cgit v1.2.3 From ecf294a6f63f882319485f807754dacaeae96e9d Mon Sep 17 00:00:00 2001 From: Lizhi Hou Date: Thu, 19 Jan 2023 08:32:06 -0800 Subject: dmaengine: xilinx: xdma: Add user logic interrupt support The Xilinx DMA/Bridge Subsystem for PCIe (XDMA) provides up to 16 user interrupt wires to user logic that generate interrupts to the host. This patch adds APIs to enable/disable user logic interrupt for a given interrupt wire index. Signed-off-by: Lizhi Hou Signed-off-by: Sonal Santan Signed-off-by: Max Zhen Signed-off-by: Brian Xu Tested-by: Martin Tuma Link: https://lore.kernel.org/r/1674145926-29449-3-git-send-email-lizhi.hou@amd.com Signed-off-by: Vinod Koul --- MAINTAINERS | 1 + drivers/dma/xilinx/xdma.c | 81 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/dma/amd_xdma.h | 16 +++++++++ 3 files changed, 98 insertions(+) create mode 100644 include/linux/dma/amd_xdma.h (limited to 'include/linux') diff --git a/MAINTAINERS b/MAINTAINERS index b768ad4e901b..7fdeab4c4baa 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -22897,6 +22897,7 @@ L: dmaengine@vger.kernel.org S: Supported F: drivers/dma/xilinx/xdma-regs.h F: drivers/dma/xilinx/xdma.c +F: include/linux/dma/amd_xdma.h F: include/linux/platform_data/amd_xdma.h XILINX ZYNQMP DPDMA DRIVER diff --git a/drivers/dma/xilinx/xdma.c b/drivers/dma/xilinx/xdma.c index 48efb75ef9b4..462109c61653 100644 --- a/drivers/dma/xilinx/xdma.c +++ b/drivers/dma/xilinx/xdma.c @@ -25,6 +25,7 @@ #include #include #include +#include #include #include #include @@ -687,6 +688,7 @@ static int xdma_set_vector_reg(struct xdma_device *xdev, u32 vec_tbl_start, static int xdma_irq_init(struct xdma_device *xdev) { u32 irq = xdev->irq_start; + u32 user_irq_start; int i, j, ret; /* return failure if there are not enough IRQs */ @@ -729,6 +731,18 @@ static int xdma_irq_init(struct xdma_device *xdev) goto failed_init_c2h; } + /* config user IRQ registers if needed */ + user_irq_start = XDMA_CHAN_NUM(xdev); + if (xdev->irq_num > user_irq_start) { + ret = xdma_set_vector_reg(xdev, XDMA_IRQ_USER_VEC_NUM, + user_irq_start, + xdev->irq_num - user_irq_start); + if (ret) { + xdma_err(xdev, "failed to set user vectors: %d", ret); + goto failed_init_c2h; + } + } + /* enable interrupt */ ret = regmap_write(xdev->rmap, XDMA_IRQ_CHAN_INT_EN_W1S, ~0); if (ret) @@ -754,6 +768,73 @@ static bool xdma_filter_fn(struct dma_chan *chan, void *param) return chan_info->dir == xdma_chan->dir; } +/** + * xdma_disable_user_irq - Disable user interrupt + * @pdev: Pointer to the platform_device structure + * @irq_num: System IRQ number + */ +void xdma_disable_user_irq(struct platform_device *pdev, u32 irq_num) +{ + struct xdma_device *xdev = platform_get_drvdata(pdev); + u32 index; + + index = irq_num - xdev->irq_start; + if (index < XDMA_CHAN_NUM(xdev) || index >= xdev->irq_num) { + xdma_err(xdev, "invalid user irq number"); + return; + } + index -= XDMA_CHAN_NUM(xdev); + + regmap_write(xdev->rmap, XDMA_IRQ_USER_INT_EN_W1C, 1 << index); +} +EXPORT_SYMBOL(xdma_disable_user_irq); + +/** + * xdma_enable_user_irq - Enable user logic interrupt + * @pdev: Pointer to the platform_device structure + * @irq_num: System IRQ number + */ +int xdma_enable_user_irq(struct platform_device *pdev, u32 irq_num) +{ + struct xdma_device *xdev = platform_get_drvdata(pdev); + u32 index; + int ret; + + index = irq_num - xdev->irq_start; + if (index < XDMA_CHAN_NUM(xdev) || index >= xdev->irq_num) { + xdma_err(xdev, "invalid user irq number"); + return -EINVAL; + } + index -= XDMA_CHAN_NUM(xdev); + + ret = regmap_write(xdev->rmap, XDMA_IRQ_USER_INT_EN_W1S, 1 << index); + if (ret) + return ret; + + return 0; +} +EXPORT_SYMBOL(xdma_enable_user_irq); + +/** + * xdma_get_user_irq - Get system IRQ number + * @pdev: Pointer to the platform_device structure + * @user_irq_index: User logic IRQ wire index + * + * Return: The system IRQ number allocated for the given wire index. + */ +int xdma_get_user_irq(struct platform_device *pdev, u32 user_irq_index) +{ + struct xdma_device *xdev = platform_get_drvdata(pdev); + + if (XDMA_CHAN_NUM(xdev) + user_irq_index >= xdev->irq_num) { + xdma_err(xdev, "invalid user irq index"); + return -EINVAL; + } + + return xdev->irq_start + XDMA_CHAN_NUM(xdev) + user_irq_index; +} +EXPORT_SYMBOL(xdma_get_user_irq); + /** * xdma_remove - Driver remove function * @pdev: Pointer to the platform_device structure diff --git a/include/linux/dma/amd_xdma.h b/include/linux/dma/amd_xdma.h new file mode 100644 index 000000000000..ceba69ed7cb4 --- /dev/null +++ b/include/linux/dma/amd_xdma.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2022, Advanced Micro Devices, Inc. + */ + +#ifndef _DMAENGINE_AMD_XDMA_H +#define _DMAENGINE_AMD_XDMA_H + +#include +#include + +int xdma_enable_user_irq(struct platform_device *pdev, u32 irq_num); +void xdma_disable_user_irq(struct platform_device *pdev, u32 irq_num); +int xdma_get_user_irq(struct platform_device *pdev, u32 user_irq_index); + +#endif /* _DMAENGINE_AMD_XDMA_H */ -- cgit v1.2.3 From 8b5443102cfca7a4346a50918f8ecc8a1644ea2e Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 30 Jan 2023 13:05:03 +0200 Subject: dmaengine: Make an order in struct dma_device definition Make an order in struct dma_device: - added missing kernel doc descriptions - put descriptions in the order of appearance in the code - updated indentation where it makes sense Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20230130110503.52250-1-andriy.shevchenko@linux.intel.com Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index c923f4e60f24..bcfece892812 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -773,6 +773,7 @@ struct dma_filter { /** * struct dma_device - info on the entity supplying DMA services + * @ref: reference is taken and put every time a channel is allocated or freed * @chancnt: how many DMA channels are supported * @privatecnt: how many DMA channels are requested by dma_request_channel * @channels: the list of struct dma_chan @@ -789,6 +790,7 @@ struct dma_filter { * @dev_id: unique device ID * @dev: struct device reference for dma mapping api * @owner: owner module (automatically set based on the provided dev) + * @chan_ida: unique channel ID * @src_addr_widths: bit mask of src addr widths the device supports * Width is specified in bytes, e.g. for a device supporting * a width of 4 the mask should have BIT(4) set. @@ -802,6 +804,7 @@ struct dma_filter { * @max_sg_burst: max number of SG list entries executed in a single burst * DMA tansaction with no software intervention for reinitialization. * Zero value means unlimited number of entries. + * @descriptor_reuse: a submitted transfer can be resubmitted after completion * @residue_granularity: granularity of the transfer residue reported * by tx_status * @device_alloc_chan_resources: allocate resources and return the @@ -839,7 +842,6 @@ struct dma_filter { * struct with auxiliary transfer status information, otherwise the call * will just return a simple status code * @device_issue_pending: push pending transactions to hardware - * @descriptor_reuse: a submitted transfer can be resubmitted after completion * @device_release: called sometime atfer dma_async_device_unregister() is * called and there are no further references to this structure. This * must be implemented to free resources however many existing drivers @@ -847,6 +849,7 @@ struct dma_filter { * @dbg_summary_show: optional routine to show contents in debugfs; default code * will be used when this is omitted, but custom code can show extra, * controller specific information. + * @dbg_dev_root: the root folder in debugfs for this device */ struct dma_device { struct kref ref; @@ -855,7 +858,7 @@ struct dma_device { struct list_head channels; struct list_head global_node; struct dma_filter filter; - dma_cap_mask_t cap_mask; + dma_cap_mask_t cap_mask; enum dma_desc_metadata_mode desc_metadata_modes; unsigned short max_xor; unsigned short max_pq; @@ -924,10 +927,8 @@ struct dma_device { struct dma_chan *chan, dma_addr_t dst, u64 data, unsigned long flags); - void (*device_caps)(struct dma_chan *chan, - struct dma_slave_caps *caps); - int (*device_config)(struct dma_chan *chan, - struct dma_slave_config *config); + void (*device_caps)(struct dma_chan *chan, struct dma_slave_caps *caps); + int (*device_config)(struct dma_chan *chan, struct dma_slave_config *config); int (*device_pause)(struct dma_chan *chan); int (*device_resume)(struct dma_chan *chan); int (*device_terminate_all)(struct dma_chan *chan); -- cgit v1.2.3 From 8c99377e614f8abfd881c34611002b2af5ab1ee8 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 9 Feb 2023 10:35:56 +0100 Subject: driver core: bus: add bus_get_dev_root() function Instead of poking around in the struct bus_type directly for the dev_root pointer, provide a function to return it properly reference counted, if it is present in the bus. This will be needed to move the pointer out of struct bus_type in the future. Use the function in the driver core code at the same time it is introduced to verify that it works properly. Cc: "Rafael J. Wysocki" Link: https://lore.kernel.org/r/20230209093556.19132-1-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/base/bus.c | 20 ++++++++++++++++++++ drivers/base/core.c | 14 +++++++++++--- drivers/base/cpu.c | 10 +++++++--- include/linux/device/bus.h | 1 + 4 files changed, 39 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/bus.c b/drivers/base/bus.c index 301b9c6ece86..def1e009ad9d 100644 --- a/drivers/base/bus.c +++ b/drivers/base/bus.c @@ -1334,6 +1334,26 @@ bool bus_is_registered(const struct bus_type *bus) return is_initialized; } +/** + * bus_get_dev_root - return a pointer to the "device root" of a bus + * @bus: bus to return the device root of. + * + * If a bus has a "device root" structure, return it, WITH THE REFERENCE + * COUNT INCREMENTED. + * + * Note, when finished with the device, a call to put_device() is required. + * + * If the device root is not present (or bus is not a valid pointer), NULL + * will be returned. + */ +struct device *bus_get_dev_root(const struct bus_type *bus) +{ + if (bus) + return get_device(bus->dev_root); + return NULL; +} +EXPORT_SYMBOL_GPL(bus_get_dev_root); + int __init buses_init(void) { bus_kset = kset_create_and_add("bus", &bus_uevent_ops, NULL); diff --git a/drivers/base/core.c b/drivers/base/core.c index 2712a1a1e959..f9297c68214a 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -3173,8 +3173,9 @@ static DEFINE_MUTEX(gdp_mutex); static struct kobject *get_device_parent(struct device *dev, struct device *parent) { + struct kobject *kobj = NULL; + if (dev->class) { - struct kobject *kobj = NULL; struct kobject *parent_kobj; struct kobject *k; @@ -3222,8 +3223,15 @@ static struct kobject *get_device_parent(struct device *dev, } /* subsystems can specify a default root directory for their devices */ - if (!parent && dev->bus && dev->bus->dev_root) - return &dev->bus->dev_root->kobj; + if (!parent && dev->bus) { + struct device *dev_root = bus_get_dev_root(dev->bus); + + if (dev_root) { + kobj = &dev_root->kobj; + put_device(dev_root); + return kobj; + } + } if (parent) return &parent->kobj; diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index 441eb5bdec7d..8bb623039bb2 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -610,9 +610,13 @@ static const struct attribute_group cpu_root_vulnerabilities_group = { static void __init cpu_register_vulnerabilities(void) { - if (sysfs_create_group(&cpu_subsys.dev_root->kobj, - &cpu_root_vulnerabilities_group)) - pr_err("Unable to register CPU vulnerabilities\n"); + struct device *dev = bus_get_dev_root(&cpu_subsys); + + if (dev) { + if (sysfs_create_group(&dev->kobj, &cpu_root_vulnerabilities_group)) + pr_err("Unable to register CPU vulnerabilities\n"); + put_device(dev); + } } #else diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h index 31be18608f83..6ce32ef4b8fd 100644 --- a/include/linux/device/bus.h +++ b/include/linux/device/bus.h @@ -282,5 +282,6 @@ enum bus_notifier_event { }; extern struct kset *bus_get_kset(const struct bus_type *bus); +struct device *bus_get_dev_root(const struct bus_type *bus); #endif -- cgit v1.2.3 From 53c0e2f9b808fafaea7bec91eeec48046bcaaba0 Mon Sep 17 00:00:00 2001 From: Serge Semin Date: Fri, 13 Jan 2023 20:14:03 +0300 Subject: dmaengine: dw-edma: Replace chip ID number with device name Using an abstract number as the DW eDMA chip identifier isn't practical because there can be more than one DW eDMA controller on the platform. Some may be detected as the PCIe Endpoints, and others may be embedded in DW PCIe Root Port/Endpoint controllers. An abstract number in, for instance, the IRQ handlers list, doesn't give a notion regarding their reference to the particular DMA controller. To preserve the code simplicity and support multi-eDMA platforms, use the parental device name to create the DW eDMA controller name. Link: https://lore.kernel.org/r/20230113171409.30470-22-Sergey.Semin@baikalelectronics.ru Tested-by: Manivannan Sadhasivam Signed-off-by: Serge Semin Signed-off-by: Lorenzo Pieralisi Signed-off-by: Bjorn Helgaas Reviewed-by: Manivannan Sadhasivam Acked-by: Vinod Koul --- drivers/dma/dw-edma/dw-edma-core.c | 3 ++- drivers/dma/dw-edma/dw-edma-core.h | 2 +- drivers/dma/dw-edma/dw-edma-pcie.c | 1 - include/linux/dma/edma.h | 1 - 4 files changed, 3 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/dma/dw-edma/dw-edma-core.c b/drivers/dma/dw-edma/dw-edma-core.c index 040a88cfe070..e3671bfbe186 100644 --- a/drivers/dma/dw-edma/dw-edma-core.c +++ b/drivers/dma/dw-edma/dw-edma-core.c @@ -973,7 +973,8 @@ int dw_edma_probe(struct dw_edma_chip *chip) if (!dw->chan) return -ENOMEM; - snprintf(dw->name, sizeof(dw->name), "dw-edma-core:%d", chip->id); + snprintf(dw->name, sizeof(dw->name), "dw-edma-core:%s", + dev_name(chip->dev)); /* Disable eDMA, only to establish the ideal initial conditions */ dw_edma_v0_core_off(dw); diff --git a/drivers/dma/dw-edma/dw-edma-core.h b/drivers/dma/dw-edma/dw-edma-core.h index e3ad3e372b55..0ab2b6dba880 100644 --- a/drivers/dma/dw-edma/dw-edma-core.h +++ b/drivers/dma/dw-edma/dw-edma-core.h @@ -96,7 +96,7 @@ struct dw_edma_irq { }; struct dw_edma { - char name[20]; + char name[32]; struct dma_device dma; diff --git a/drivers/dma/dw-edma/dw-edma-pcie.c b/drivers/dma/dw-edma/dw-edma-pcie.c index f530bacfd716..3f9dadc73854 100644 --- a/drivers/dma/dw-edma/dw-edma-pcie.c +++ b/drivers/dma/dw-edma/dw-edma-pcie.c @@ -222,7 +222,6 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev, /* Data structure initialization */ chip->dev = dev; - chip->id = pdev->devfn; chip->mf = vsec_data.mf; chip->nr_irqs = nr_irqs; diff --git a/include/linux/dma/edma.h b/include/linux/dma/edma.h index 07a23ecc834f..96bfd0173f3a 100644 --- a/include/linux/dma/edma.h +++ b/include/linux/dma/edma.h @@ -76,7 +76,6 @@ enum dw_edma_chip_flags { */ struct dw_edma_chip { struct device *dev; - int id; int nr_irqs; const struct dw_edma_core_ops *ops; u32 flags; -- cgit v1.2.3 From 93c177fd6ff0655a5fa43ec945a57d7b0200ad80 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 10 Feb 2023 01:06:21 -0800 Subject: kernel/range: Uplevel the cxl subsystem's range_contains() helper In support of the CXL subsystem's use of 'struct range' to track decode address ranges, add a common range_contains() implementation with identical semantics as resource_contains(); The existing 'range_contains()' in lib/stackinit_kunit.c is namespaced with a 'stackinit_' prefix. Cc: Kees Cook Reviewed-by: Vishal Verma Reviewed-by: Jonathan Cameron Reviewed-by: Dave Jiang Reviewed-by: Gregory Price Reviewed-by: Ira Weiny Tested-by: Fan Ni Link: https://lore.kernel.org/r/167601998163.1924368.6067392174077323935.stgit@dwillia2-xfh.jf.intel.com Signed-off-by: Dan Williams --- drivers/cxl/core/pci.c | 5 ----- include/linux/range.h | 5 +++++ lib/stackinit_kunit.c | 6 +++--- 3 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c index 1d1492440287..9ed2120dbf8a 100644 --- a/drivers/cxl/core/pci.c +++ b/drivers/cxl/core/pci.c @@ -214,11 +214,6 @@ static int devm_cxl_enable_mem(struct device *host, struct cxl_dev_state *cxlds) return devm_add_action_or_reset(host, clear_mem_enable, cxlds); } -static bool range_contains(struct range *r1, struct range *r2) -{ - return r1->start <= r2->start && r1->end >= r2->end; -} - /* require dvsec ranges to be covered by a locked platform window */ static int dvsec_range_allowed(struct device *dev, void *arg) { diff --git a/include/linux/range.h b/include/linux/range.h index 274681cc3154..7efb6a9b069b 100644 --- a/include/linux/range.h +++ b/include/linux/range.h @@ -13,6 +13,11 @@ static inline u64 range_len(const struct range *range) return range->end - range->start + 1; } +static inline bool range_contains(struct range *r1, struct range *r2) +{ + return r1->start <= r2->start && r1->end >= r2->end; +} + int add_range(struct range *range, int az, int nr_range, u64 start, u64 end); diff --git a/lib/stackinit_kunit.c b/lib/stackinit_kunit.c index 4591d6cf5e01..05947a2feb93 100644 --- a/lib/stackinit_kunit.c +++ b/lib/stackinit_kunit.c @@ -31,8 +31,8 @@ static volatile u8 forced_mask = 0xff; static void *fill_start, *target_start; static size_t fill_size, target_size; -static bool range_contains(char *haystack_start, size_t haystack_size, - char *needle_start, size_t needle_size) +static bool stackinit_range_contains(char *haystack_start, size_t haystack_size, + char *needle_start, size_t needle_size) { if (needle_start >= haystack_start && needle_start + needle_size <= haystack_start + haystack_size) @@ -175,7 +175,7 @@ static noinline void test_ ## name (struct kunit *test) \ \ /* Validate that compiler lined up fill and target. */ \ KUNIT_ASSERT_TRUE_MSG(test, \ - range_contains(fill_start, fill_size, \ + stackinit_range_contains(fill_start, fill_size, \ target_start, target_size), \ "stack fill missed target!? " \ "(fill %zu wide, target offset by %d)\n", \ -- cgit v1.2.3 From fe098574a93b4e2acb046b583e9857337d807f38 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 10 Feb 2023 01:07:02 -0800 Subject: dax/hmem: Convey the dax range via memregion_info() In preparation for hmem platform devices to be unregistered, stop using platform_device_add_resources() to convey the address range. The platform_device_add_resources() API causes an existing "Soft Reserved" iomem resource to be re-parented under an inserted platform device resource. When that platform device is deleted it removes the platform device resource and all children. Instead, it is sufficient to convey just the address range and let request_mem_region() insert resources to indicate the devices active in the range. This allows the "Soft Reserved" resource to be re-enumerated upon the next probe event. Reviewed-by: Jonathan Cameron Tested-by: Fan Ni Reviewed-by: Dave Jiang Link: https://lore.kernel.org/r/167602002217.1924368.7036275892522551624.stgit@dwillia2-xfh.jf.intel.com Signed-off-by: Dan Williams --- drivers/dax/hmem/device.c | 37 ++++++++++++++----------------------- drivers/dax/hmem/hmem.c | 14 +++----------- include/linux/memregion.h | 2 ++ 3 files changed, 19 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/drivers/dax/hmem/device.c b/drivers/dax/hmem/device.c index 20749c7fab81..b1b339bccfe5 100644 --- a/drivers/dax/hmem/device.c +++ b/drivers/dax/hmem/device.c @@ -15,15 +15,8 @@ static struct resource hmem_active = { .flags = IORESOURCE_MEM, }; -void hmem_register_device(int target_nid, struct resource *r) +void hmem_register_device(int target_nid, struct resource *res) { - /* define a clean / non-busy resource for the platform device */ - struct resource res = { - .start = r->start, - .end = r->end, - .flags = IORESOURCE_MEM, - .desc = IORES_DESC_SOFT_RESERVED, - }; struct platform_device *pdev; struct memregion_info info; int rc, id; @@ -31,55 +24,53 @@ void hmem_register_device(int target_nid, struct resource *r) if (nohmem) return; - rc = region_intersects(res.start, resource_size(&res), IORESOURCE_MEM, - IORES_DESC_SOFT_RESERVED); + rc = region_intersects(res->start, resource_size(res), IORESOURCE_MEM, + IORES_DESC_SOFT_RESERVED); if (rc != REGION_INTERSECTS) return; id = memregion_alloc(GFP_KERNEL); if (id < 0) { - pr_err("memregion allocation failure for %pr\n", &res); + pr_err("memregion allocation failure for %pr\n", res); return; } pdev = platform_device_alloc("hmem", id); if (!pdev) { - pr_err("hmem device allocation failure for %pr\n", &res); + pr_err("hmem device allocation failure for %pr\n", res); goto out_pdev; } - if (!__request_region(&hmem_active, res.start, resource_size(&res), + if (!__request_region(&hmem_active, res->start, resource_size(res), dev_name(&pdev->dev), 0)) { - dev_dbg(&pdev->dev, "hmem range %pr already active\n", &res); + dev_dbg(&pdev->dev, "hmem range %pr already active\n", res); goto out_active; } pdev->dev.numa_node = numa_map_to_online_node(target_nid); info = (struct memregion_info) { .target_node = target_nid, + .range = { + .start = res->start, + .end = res->end, + }, }; rc = platform_device_add_data(pdev, &info, sizeof(info)); if (rc < 0) { - pr_err("hmem memregion_info allocation failure for %pr\n", &res); - goto out_resource; - } - - rc = platform_device_add_resources(pdev, &res, 1); - if (rc < 0) { - pr_err("hmem resource allocation failure for %pr\n", &res); + pr_err("hmem memregion_info allocation failure for %pr\n", res); goto out_resource; } rc = platform_device_add(pdev); if (rc < 0) { - dev_err(&pdev->dev, "device add failed for %pr\n", &res); + dev_err(&pdev->dev, "device add failed for %pr\n", res); goto out_resource; } return; out_resource: - __release_region(&hmem_active, res.start, resource_size(&res)); + __release_region(&hmem_active, res->start, resource_size(res)); out_active: platform_device_put(pdev); out_pdev: diff --git a/drivers/dax/hmem/hmem.c b/drivers/dax/hmem/hmem.c index c7351e0dc8ff..5025a8c9850b 100644 --- a/drivers/dax/hmem/hmem.c +++ b/drivers/dax/hmem/hmem.c @@ -15,25 +15,17 @@ static int dax_hmem_probe(struct platform_device *pdev) struct memregion_info *mri; struct dev_dax_data data; struct dev_dax *dev_dax; - struct resource *res; - struct range range; - - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (!res) - return -ENOMEM; mri = dev->platform_data; - range.start = res->start; - range.end = res->end; - dax_region = alloc_dax_region(dev, pdev->id, &range, mri->target_node, - PMD_SIZE, 0); + dax_region = alloc_dax_region(dev, pdev->id, &mri->range, + mri->target_node, PMD_SIZE, 0); if (!dax_region) return -ENOMEM; data = (struct dev_dax_data) { .dax_region = dax_region, .id = -1, - .size = region_idle ? 0 : resource_size(res), + .size = region_idle ? 0 : range_len(&mri->range), }; dev_dax = devm_create_dev_dax(&data); if (IS_ERR(dev_dax)) diff --git a/include/linux/memregion.h b/include/linux/memregion.h index bf83363807ac..c01321467789 100644 --- a/include/linux/memregion.h +++ b/include/linux/memregion.h @@ -3,10 +3,12 @@ #define _MEMREGION_H_ #include #include +#include #include struct memregion_info { int target_node; + struct range range; }; #ifdef CONFIG_MEMREGION -- cgit v1.2.3 From 7dab174e2e27eeaf10273e597ffbef4f8ea032bb Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 10 Feb 2023 01:07:07 -0800 Subject: dax/hmem: Move hmem device registration to dax_hmem.ko In preparation for the CXL region driver to take over the responsibility of registering device-dax instances for CXL regions, move the registration of "hmem" devices to dax_hmem.ko. Previously the builtin component of this enabling (drivers/dax/hmem/device.o) would register platform devices for each address range and trigger the dax_hmem.ko module to load and attach device-dax instances to those devices. Now, the ranges are collected from the HMAT and EFI memory map walking, but the device creation is deferred. A new "hmem_platform" device is created which triggers dax_hmem.ko to load and register the platform devices. Tested-by: Fan Ni Reviewed-by: Dave Jiang Reviewed-by: Jonathan Cameron Link: https://lore.kernel.org/r/167602002771.1924368.5653558226424530127.stgit@dwillia2-xfh.jf.intel.com Signed-off-by: Dan Williams --- drivers/acpi/numa/hmat.c | 2 +- drivers/dax/Kconfig | 2 +- drivers/dax/hmem/device.c | 91 +++++++++++++++++++--------------------- drivers/dax/hmem/hmem.c | 105 +++++++++++++++++++++++++++++++++++++++++++++- include/linux/dax.h | 7 +++- 5 files changed, 155 insertions(+), 52 deletions(-) (limited to 'include/linux') diff --git a/drivers/acpi/numa/hmat.c b/drivers/acpi/numa/hmat.c index ff24282301ab..bba268ecd802 100644 --- a/drivers/acpi/numa/hmat.c +++ b/drivers/acpi/numa/hmat.c @@ -718,7 +718,7 @@ static void hmat_register_target_devices(struct memory_target *target) for (res = target->memregions.child; res; res = res->sibling) { int target_nid = pxm_to_node(target->memory_pxm); - hmem_register_device(target_nid, res); + hmem_register_resource(target_nid, res); } } diff --git a/drivers/dax/Kconfig b/drivers/dax/Kconfig index 5fdf269a822e..d13c889c2a64 100644 --- a/drivers/dax/Kconfig +++ b/drivers/dax/Kconfig @@ -46,7 +46,7 @@ config DEV_DAX_HMEM Say M if unsure. config DEV_DAX_HMEM_DEVICES - depends on DEV_DAX_HMEM && DAX=y + depends on DEV_DAX_HMEM && DAX def_bool y config DEV_DAX_KMEM diff --git a/drivers/dax/hmem/device.c b/drivers/dax/hmem/device.c index b1b339bccfe5..f9e1a76a04a9 100644 --- a/drivers/dax/hmem/device.c +++ b/drivers/dax/hmem/device.c @@ -8,6 +8,8 @@ static bool nohmem; module_param_named(disable, nohmem, bool, 0444); +static bool platform_initialized; +static DEFINE_MUTEX(hmem_resource_lock); static struct resource hmem_active = { .name = "HMEM devices", .start = 0, @@ -15,71 +17,66 @@ static struct resource hmem_active = { .flags = IORESOURCE_MEM, }; -void hmem_register_device(int target_nid, struct resource *res) +int walk_hmem_resources(struct device *host, walk_hmem_fn fn) +{ + struct resource *res; + int rc = 0; + + mutex_lock(&hmem_resource_lock); + for (res = hmem_active.child; res; res = res->sibling) { + rc = fn(host, (int) res->desc, res); + if (rc) + break; + } + mutex_unlock(&hmem_resource_lock); + return rc; +} +EXPORT_SYMBOL_GPL(walk_hmem_resources); + +static void __hmem_register_resource(int target_nid, struct resource *res) { struct platform_device *pdev; - struct memregion_info info; - int rc, id; + struct resource *new; + int rc; - if (nohmem) + new = __request_region(&hmem_active, res->start, resource_size(res), "", + 0); + if (!new) { + pr_debug("hmem range %pr already active\n", res); return; + } - rc = region_intersects(res->start, resource_size(res), IORESOURCE_MEM, - IORES_DESC_SOFT_RESERVED); - if (rc != REGION_INTERSECTS) - return; + new->desc = target_nid; - id = memregion_alloc(GFP_KERNEL); - if (id < 0) { - pr_err("memregion allocation failure for %pr\n", res); + if (platform_initialized) return; - } - pdev = platform_device_alloc("hmem", id); + pdev = platform_device_alloc("hmem_platform", 0); if (!pdev) { - pr_err("hmem device allocation failure for %pr\n", res); - goto out_pdev; - } - - if (!__request_region(&hmem_active, res->start, resource_size(res), - dev_name(&pdev->dev), 0)) { - dev_dbg(&pdev->dev, "hmem range %pr already active\n", res); - goto out_active; - } - - pdev->dev.numa_node = numa_map_to_online_node(target_nid); - info = (struct memregion_info) { - .target_node = target_nid, - .range = { - .start = res->start, - .end = res->end, - }, - }; - rc = platform_device_add_data(pdev, &info, sizeof(info)); - if (rc < 0) { - pr_err("hmem memregion_info allocation failure for %pr\n", res); - goto out_resource; + pr_err_once("failed to register device-dax hmem_platform device\n"); + return; } rc = platform_device_add(pdev); - if (rc < 0) { - dev_err(&pdev->dev, "device add failed for %pr\n", res); - goto out_resource; - } + if (rc) + platform_device_put(pdev); + else + platform_initialized = true; +} - return; +void hmem_register_resource(int target_nid, struct resource *res) +{ + if (nohmem) + return; -out_resource: - __release_region(&hmem_active, res->start, resource_size(res)); -out_active: - platform_device_put(pdev); -out_pdev: - memregion_free(id); + mutex_lock(&hmem_resource_lock); + __hmem_register_resource(target_nid, res); + mutex_unlock(&hmem_resource_lock); } static __init int hmem_register_one(struct resource *res, void *data) { - hmem_register_device(phys_to_target_node(res->start), res); + hmem_register_resource(phys_to_target_node(res->start), res); return 0; } diff --git a/drivers/dax/hmem/hmem.c b/drivers/dax/hmem/hmem.c index 5025a8c9850b..e7bdff3132fa 100644 --- a/drivers/dax/hmem/hmem.c +++ b/drivers/dax/hmem/hmem.c @@ -3,6 +3,7 @@ #include #include #include +#include #include "../bus.h" static bool region_idle; @@ -43,8 +44,110 @@ static struct platform_driver dax_hmem_driver = { }, }; -module_platform_driver(dax_hmem_driver); +static void release_memregion(void *data) +{ + memregion_free((long) data); +} + +static void release_hmem(void *pdev) +{ + platform_device_unregister(pdev); +} + +static int hmem_register_device(struct device *host, int target_nid, + const struct resource *res) +{ + struct platform_device *pdev; + struct memregion_info info; + long id; + int rc; + + rc = region_intersects(res->start, resource_size(res), IORESOURCE_MEM, + IORES_DESC_SOFT_RESERVED); + if (rc != REGION_INTERSECTS) + return 0; + + id = memregion_alloc(GFP_KERNEL); + if (id < 0) { + dev_err(host, "memregion allocation failure for %pr\n", res); + return -ENOMEM; + } + rc = devm_add_action_or_reset(host, release_memregion, (void *) id); + if (rc) + return rc; + + pdev = platform_device_alloc("hmem", id); + if (!pdev) { + dev_err(host, "device allocation failure for %pr\n", res); + return -ENOMEM; + } + + pdev->dev.numa_node = numa_map_to_online_node(target_nid); + info = (struct memregion_info) { + .target_node = target_nid, + .range = { + .start = res->start, + .end = res->end, + }, + }; + rc = platform_device_add_data(pdev, &info, sizeof(info)); + if (rc < 0) { + dev_err(host, "memregion_info allocation failure for %pr\n", + res); + goto out_put; + } + + rc = platform_device_add(pdev); + if (rc < 0) { + dev_err(host, "%s add failed for %pr\n", dev_name(&pdev->dev), + res); + goto out_put; + } + + return devm_add_action_or_reset(host, release_hmem, pdev); + +out_put: + platform_device_put(pdev); + return rc; +} + +static int dax_hmem_platform_probe(struct platform_device *pdev) +{ + return walk_hmem_resources(&pdev->dev, hmem_register_device); +} + +static struct platform_driver dax_hmem_platform_driver = { + .probe = dax_hmem_platform_probe, + .driver = { + .name = "hmem_platform", + }, +}; + +static __init int dax_hmem_init(void) +{ + int rc; + + rc = platform_driver_register(&dax_hmem_platform_driver); + if (rc) + return rc; + + rc = platform_driver_register(&dax_hmem_driver); + if (rc) + platform_driver_unregister(&dax_hmem_platform_driver); + + return rc; +} + +static __exit void dax_hmem_exit(void) +{ + platform_driver_unregister(&dax_hmem_driver); + platform_driver_unregister(&dax_hmem_platform_driver); +} + +module_init(dax_hmem_init); +module_exit(dax_hmem_exit); MODULE_ALIAS("platform:hmem*"); +MODULE_ALIAS("platform:hmem_platform*"); MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Intel Corporation"); diff --git a/include/linux/dax.h b/include/linux/dax.h index 2b5ecb591059..bf6258472e49 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -262,11 +262,14 @@ static inline bool dax_mapping(struct address_space *mapping) } #ifdef CONFIG_DEV_DAX_HMEM_DEVICES -void hmem_register_device(int target_nid, struct resource *r); +void hmem_register_resource(int target_nid, struct resource *r); #else -static inline void hmem_register_device(int target_nid, struct resource *r) +static inline void hmem_register_resource(int target_nid, struct resource *r) { } #endif +typedef int (*walk_hmem_fn)(struct device *dev, int target_nid, + const struct resource *res); +int walk_hmem_resources(struct device *dev, walk_hmem_fn fn); #endif -- cgit v1.2.3 From ffb1b4a41016295e298409c9dbcacd55680bd6d4 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Fri, 10 Feb 2023 14:42:01 -0800 Subject: x86/unwind/orc: Add 'signal' field to ORC metadata Add a 'signal' field which allows unwind hints to specify whether the instruction pointer should be taken literally (like for most interrupts and exceptions) rather than decremented (like for call stack return addresses) when used to find the next ORC entry. Signed-off-by: Josh Poimboeuf Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/d2c5ec4d83a45b513d8fd72fab59f1a8cfa46871.1676068346.git.jpoimboe@kernel.org --- arch/x86/include/asm/orc_types.h | 4 +++- arch/x86/include/asm/unwind_hints.h | 10 +++++----- arch/x86/kernel/unwind_orc.c | 5 ++--- include/linux/objtool.h | 11 +++++++---- tools/arch/x86/include/asm/orc_types.h | 4 +++- tools/include/linux/objtool.h | 11 +++++++---- tools/objtool/orc_dump.c | 4 ++-- 7 files changed, 29 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/include/asm/orc_types.h b/arch/x86/include/asm/orc_types.h index 5a2baf28a1dc..1343a62106de 100644 --- a/arch/x86/include/asm/orc_types.h +++ b/arch/x86/include/asm/orc_types.h @@ -57,12 +57,14 @@ struct orc_entry { unsigned sp_reg:4; unsigned bp_reg:4; unsigned type:2; + unsigned signal:1; unsigned end:1; #elif defined(__BIG_ENDIAN_BITFIELD) unsigned bp_reg:4; unsigned sp_reg:4; - unsigned unused:5; + unsigned unused:4; unsigned end:1; + unsigned signal:1; unsigned type:2; #endif } __packed; diff --git a/arch/x86/include/asm/unwind_hints.h b/arch/x86/include/asm/unwind_hints.h index f66fbe6537dd..e7c71750b309 100644 --- a/arch/x86/include/asm/unwind_hints.h +++ b/arch/x86/include/asm/unwind_hints.h @@ -15,7 +15,7 @@ UNWIND_HINT type=UNWIND_HINT_TYPE_ENTRY end=1 .endm -.macro UNWIND_HINT_REGS base=%rsp offset=0 indirect=0 extra=1 partial=0 +.macro UNWIND_HINT_REGS base=%rsp offset=0 indirect=0 extra=1 partial=0 signal=1 .if \base == %rsp .if \indirect .set sp_reg, ORC_REG_SP_INDIRECT @@ -45,11 +45,11 @@ .set type, UNWIND_HINT_TYPE_REGS .endif - UNWIND_HINT sp_reg=sp_reg sp_offset=sp_offset type=type + UNWIND_HINT sp_reg=sp_reg sp_offset=sp_offset type=type signal=\signal .endm -.macro UNWIND_HINT_IRET_REGS base=%rsp offset=0 - UNWIND_HINT_REGS base=\base offset=\offset partial=1 +.macro UNWIND_HINT_IRET_REGS base=%rsp offset=0 signal=1 + UNWIND_HINT_REGS base=\base offset=\offset partial=1 signal=\signal .endm .macro UNWIND_HINT_FUNC @@ -67,7 +67,7 @@ #else #define UNWIND_HINT_FUNC \ - UNWIND_HINT(ORC_REG_SP, 8, UNWIND_HINT_TYPE_FUNC, 0) + UNWIND_HINT(ORC_REG_SP, 8, UNWIND_HINT_TYPE_FUNC, 0, 0) #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index cdf6c6060170..37307b40f8da 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -484,6 +484,8 @@ bool unwind_next_frame(struct unwind_state *state) goto the_end; } + state->signal = orc->signal; + /* Find the previous frame's stack: */ switch (orc->sp_reg) { case ORC_REG_SP: @@ -563,7 +565,6 @@ bool unwind_next_frame(struct unwind_state *state) state->sp = sp; state->regs = NULL; state->prev_regs = NULL; - state->signal = false; break; case UNWIND_HINT_TYPE_REGS: @@ -587,7 +588,6 @@ bool unwind_next_frame(struct unwind_state *state) state->regs = (struct pt_regs *)sp; state->prev_regs = NULL; state->full_regs = true; - state->signal = true; break; case UNWIND_HINT_TYPE_REGS_PARTIAL: @@ -604,7 +604,6 @@ bool unwind_next_frame(struct unwind_state *state) state->prev_regs = state->regs; state->regs = (void *)sp - IRET_FRAME_OFFSET; state->full_regs = false; - state->signal = true; break; default: diff --git a/include/linux/objtool.h b/include/linux/objtool.h index 62c54ffbeeaa..9ac3df3fccf0 100644 --- a/include/linux/objtool.h +++ b/include/linux/objtool.h @@ -15,6 +15,7 @@ struct unwind_hint { s16 sp_offset; u8 sp_reg; u8 type; + u8 signal; u8 end; }; #endif @@ -49,7 +50,7 @@ struct unwind_hint { #ifndef __ASSEMBLY__ -#define UNWIND_HINT(sp_reg, sp_offset, type, end) \ +#define UNWIND_HINT(sp_reg, sp_offset, type, signal, end) \ "987: \n\t" \ ".pushsection .discard.unwind_hints\n\t" \ /* struct unwind_hint */ \ @@ -57,6 +58,7 @@ struct unwind_hint { ".short " __stringify(sp_offset) "\n\t" \ ".byte " __stringify(sp_reg) "\n\t" \ ".byte " __stringify(type) "\n\t" \ + ".byte " __stringify(signal) "\n\t" \ ".byte " __stringify(end) "\n\t" \ ".balign 4 \n\t" \ ".popsection\n\t" @@ -129,7 +131,7 @@ struct unwind_hint { * the debuginfo as necessary. It will also warn if it sees any * inconsistencies. */ -.macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 end=0 +.macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 signal=0 end=0 .Lunwind_hint_ip_\@: .pushsection .discard.unwind_hints /* struct unwind_hint */ @@ -137,6 +139,7 @@ struct unwind_hint { .short \sp_offset .byte \sp_reg .byte \type + .byte \signal .byte \end .balign 4 .popsection @@ -174,7 +177,7 @@ struct unwind_hint { #ifndef __ASSEMBLY__ -#define UNWIND_HINT(sp_reg, sp_offset, type, end) \ +#define UNWIND_HINT(sp_reg, sp_offset, type, signal, end) \ "\n\t" #define STACK_FRAME_NON_STANDARD(func) #define STACK_FRAME_NON_STANDARD_FP(func) @@ -182,7 +185,7 @@ struct unwind_hint { #define ASM_REACHABLE #else #define ANNOTATE_INTRA_FUNCTION_CALL -.macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 end=0 +.macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 signal=0 end=0 .endm .macro STACK_FRAME_NON_STANDARD func:req .endm diff --git a/tools/arch/x86/include/asm/orc_types.h b/tools/arch/x86/include/asm/orc_types.h index 5a2baf28a1dc..1343a62106de 100644 --- a/tools/arch/x86/include/asm/orc_types.h +++ b/tools/arch/x86/include/asm/orc_types.h @@ -57,12 +57,14 @@ struct orc_entry { unsigned sp_reg:4; unsigned bp_reg:4; unsigned type:2; + unsigned signal:1; unsigned end:1; #elif defined(__BIG_ENDIAN_BITFIELD) unsigned bp_reg:4; unsigned sp_reg:4; - unsigned unused:5; + unsigned unused:4; unsigned end:1; + unsigned signal:1; unsigned type:2; #endif } __packed; diff --git a/tools/include/linux/objtool.h b/tools/include/linux/objtool.h index 62c54ffbeeaa..9ac3df3fccf0 100644 --- a/tools/include/linux/objtool.h +++ b/tools/include/linux/objtool.h @@ -15,6 +15,7 @@ struct unwind_hint { s16 sp_offset; u8 sp_reg; u8 type; + u8 signal; u8 end; }; #endif @@ -49,7 +50,7 @@ struct unwind_hint { #ifndef __ASSEMBLY__ -#define UNWIND_HINT(sp_reg, sp_offset, type, end) \ +#define UNWIND_HINT(sp_reg, sp_offset, type, signal, end) \ "987: \n\t" \ ".pushsection .discard.unwind_hints\n\t" \ /* struct unwind_hint */ \ @@ -57,6 +58,7 @@ struct unwind_hint { ".short " __stringify(sp_offset) "\n\t" \ ".byte " __stringify(sp_reg) "\n\t" \ ".byte " __stringify(type) "\n\t" \ + ".byte " __stringify(signal) "\n\t" \ ".byte " __stringify(end) "\n\t" \ ".balign 4 \n\t" \ ".popsection\n\t" @@ -129,7 +131,7 @@ struct unwind_hint { * the debuginfo as necessary. It will also warn if it sees any * inconsistencies. */ -.macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 end=0 +.macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 signal=0 end=0 .Lunwind_hint_ip_\@: .pushsection .discard.unwind_hints /* struct unwind_hint */ @@ -137,6 +139,7 @@ struct unwind_hint { .short \sp_offset .byte \sp_reg .byte \type + .byte \signal .byte \end .balign 4 .popsection @@ -174,7 +177,7 @@ struct unwind_hint { #ifndef __ASSEMBLY__ -#define UNWIND_HINT(sp_reg, sp_offset, type, end) \ +#define UNWIND_HINT(sp_reg, sp_offset, type, signal, end) \ "\n\t" #define STACK_FRAME_NON_STANDARD(func) #define STACK_FRAME_NON_STANDARD_FP(func) @@ -182,7 +185,7 @@ struct unwind_hint { #define ASM_REACHABLE #else #define ANNOTATE_INTRA_FUNCTION_CALL -.macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 end=0 +.macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 signal=0 end=0 .endm .macro STACK_FRAME_NON_STANDARD func:req .endm diff --git a/tools/objtool/orc_dump.c b/tools/objtool/orc_dump.c index 4f1211fec82c..2d8ebdcd1db3 100644 --- a/tools/objtool/orc_dump.c +++ b/tools/objtool/orc_dump.c @@ -211,8 +211,8 @@ int orc_dump(const char *_objname) print_reg(orc[i].bp_reg, bswap_if_needed(&dummy_elf, orc[i].bp_offset)); - printf(" type:%s end:%d\n", - orc_type_name(orc[i].type), orc[i].end); + printf(" type:%s signal:%d end:%d\n", + orc_type_name(orc[i].type), orc[i].signal, orc[i].end); } elf_end(elf); -- cgit v1.2.3 From 05b8773ca33253ea562be145cf3145b05ef19f86 Mon Sep 17 00:00:00 2001 From: Daniel Golle Date: Thu, 22 Dec 2022 19:33:31 +0000 Subject: mtd: ubi: block: wire-up device parent ubiblock devices were previously only identifyable by their name, but not connected to their parent UBI volume device e.g. in sysfs. Properly parent ubiblock device as descendant of a UBI volume device to reflect device model hierachy. Signed-off-by: Daniel Golle Signed-off-by: Richard Weinberger --- drivers/mtd/ubi/block.c | 2 +- drivers/mtd/ubi/kapi.c | 1 + include/linux/mtd/ubi.h | 1 + 3 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/mtd/ubi/block.c b/drivers/mtd/ubi/block.c index f5d036203fe7..6a9eb2c860b5 100644 --- a/drivers/mtd/ubi/block.c +++ b/drivers/mtd/ubi/block.c @@ -419,7 +419,7 @@ int ubiblock_create(struct ubi_volume_info *vi) list_add_tail(&dev->list, &ubiblock_devices); /* Must be the last step: anyone can call file ops from now on */ - ret = add_disk(dev->gd); + ret = device_add_disk(vi->dev, dev->gd, NULL); if (ret) goto out_remove_minor; diff --git a/drivers/mtd/ubi/kapi.c b/drivers/mtd/ubi/kapi.c index 0fce99ff29b5..5db653eacbd4 100644 --- a/drivers/mtd/ubi/kapi.c +++ b/drivers/mtd/ubi/kapi.c @@ -79,6 +79,7 @@ void ubi_do_get_volume_info(struct ubi_device *ubi, struct ubi_volume *vol, vi->name_len = vol->name_len; vi->name = vol->name; vi->cdev = vol->cdev.dev; + vi->dev = &vol->dev; } /** diff --git a/include/linux/mtd/ubi.h b/include/linux/mtd/ubi.h index 7d48ea368c5e..a529347fd75b 100644 --- a/include/linux/mtd/ubi.h +++ b/include/linux/mtd/ubi.h @@ -110,6 +110,7 @@ struct ubi_volume_info { int name_len; const char *name; dev_t cdev; + struct device *dev; }; /** -- cgit v1.2.3 From d6dd5bafaabf98a99a76227ab8dc9a89e76a198f Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Tue, 24 Jan 2023 12:41:56 +0530 Subject: PCI: endpoint: Use a separate lock for protecting epc->pci_epf list The EPC controller maintains a list of EPF drivers added to it. For protecting this list against the concurrent accesses, the epc->lock (used for protecting epc_ops) has been used so far. Since there were no users trying to use epc_ops and modify the pci_epf list simultaneously, this was not an issue. But with the addition of callback mechanism for passing the events, this will be a problem. Because the pci_epf list needs to be iterated first for getting hold of the EPF driver and then the relevant event specific callback needs to be called for the driver. If the same epc->lock is used, then it will result in a deadlock scenario. For instance, ... mutex_lock(&epc->lock); list_for_each_entry(epf, &epc->pci_epf, list) { epf->event_ops->core_init(epf); | |-> pci_epc_set_bar(); | |-> mutex_lock(&epc->lock) # DEADLOCK ... So to fix this issue, use a separate lock called "list_lock" for protecting the pci_epf list against the concurrent accesses. This lock will also be used by the callback mechanism. Link: https://lore.kernel.org/linux-pci/20230124071158.5503-4-manivannan.sadhasivam@linaro.org Signed-off-by: Manivannan Sadhasivam Signed-off-by: Krzysztof Wilczyński Acked-by: Kishon Vijay Abraham I --- drivers/pci/endpoint/pci-epc-core.c | 9 +++++---- include/linux/pci-epc.h | 2 ++ 2 files changed, 7 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/endpoint/pci-epc-core.c b/drivers/pci/endpoint/pci-epc-core.c index 2542196e8c3d..2c023db8f51c 100644 --- a/drivers/pci/endpoint/pci-epc-core.c +++ b/drivers/pci/endpoint/pci-epc-core.c @@ -613,7 +613,7 @@ int pci_epc_add_epf(struct pci_epc *epc, struct pci_epf *epf, if (type == SECONDARY_INTERFACE && epf->sec_epc) return -EBUSY; - mutex_lock(&epc->lock); + mutex_lock(&epc->list_lock); func_no = find_first_zero_bit(&epc->function_num_map, BITS_PER_LONG); if (func_no >= BITS_PER_LONG) { @@ -640,7 +640,7 @@ int pci_epc_add_epf(struct pci_epc *epc, struct pci_epf *epf, list_add_tail(list, &epc->pci_epf); ret: - mutex_unlock(&epc->lock); + mutex_unlock(&epc->list_lock); return ret; } @@ -672,11 +672,11 @@ void pci_epc_remove_epf(struct pci_epc *epc, struct pci_epf *epf, list = &epf->sec_epc_list; } - mutex_lock(&epc->lock); + mutex_lock(&epc->list_lock); clear_bit(func_no, &epc->function_num_map); list_del(list); epf->epc = NULL; - mutex_unlock(&epc->lock); + mutex_unlock(&epc->list_lock); } EXPORT_SYMBOL_GPL(pci_epc_remove_epf); @@ -777,6 +777,7 @@ __pci_epc_create(struct device *dev, const struct pci_epc_ops *ops, } mutex_init(&epc->lock); + mutex_init(&epc->list_lock); INIT_LIST_HEAD(&epc->pci_epf); ATOMIC_INIT_NOTIFIER_HEAD(&epc->notifier); diff --git a/include/linux/pci-epc.h b/include/linux/pci-epc.h index a48778e1a4ee..fe729dfe509b 100644 --- a/include/linux/pci-epc.h +++ b/include/linux/pci-epc.h @@ -122,6 +122,7 @@ struct pci_epc_mem { * struct pci_epc - represents the PCI EPC device * @dev: PCI EPC device * @pci_epf: list of endpoint functions present in this EPC device + * list_lock: Mutex for protecting pci_epf list * @ops: function pointers for performing endpoint operations * @windows: array of address space of the endpoint controller * @mem: first window of the endpoint controller, which corresponds to @@ -139,6 +140,7 @@ struct pci_epc_mem { struct pci_epc { struct device dev; struct list_head pci_epf; + struct mutex list_lock; const struct pci_epc_ops *ops; struct pci_epc_mem **windows; struct pci_epc_mem *mem; -- cgit v1.2.3 From 838125b07e7706b1a9069079a73507fd3df244f7 Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Tue, 24 Jan 2023 12:41:57 +0530 Subject: PCI: endpoint: Use callback mechanism for passing events from EPC to EPF Instead of using the notifiers for passing the events from EPC to EPF, let's introduce a callback based mechanism where the EPF drivers can populate relevant callbacks for EPC events they want to subscribe. The use of notifiers in kernel is not recommended if there is a real link between the sender and receiver, like in this case. Also, the existing atomic notifier forces the notification functions to be in atomic context while the caller may be in non-atomic context. For instance, the two in-kernel users of the notifiers, pcie-qcom and pcie-tegra194, both are calling the notifier functions in non-atomic context (from threaded IRQ handlers). This creates a sleeping in atomic context issue with the existing EPF_TEST driver that calls the EPC APIs that may sleep. For all these reasons, let's get rid of the notifier chains and use the simple callback mechanism for signalling the events from EPC to EPF drivers. This preserves the context of the caller and avoids the latency of going through a separate interface for triggering the notifications. As a first step of the transition, the core_init() callback is introduced in this commit, that'll replace the existing CORE_INIT notifier used for signalling the init complete event from EPC. During the occurrence of the event, EPC will go over the list of EPF drivers attached to it and will call the core_init() callback if available. Link: https://lore.kernel.org/linux-pci/20230124071158.5503-5-manivannan.sadhasivam@linaro.org Signed-off-by: Manivannan Sadhasivam Signed-off-by: Krzysztof Wilczyński Acked-by: Kishon Vijay Abraham I --- drivers/pci/endpoint/functions/pci-epf-test.c | 13 ++++++------- drivers/pci/endpoint/pci-epc-core.c | 11 ++++++++++- include/linux/pci-epf.h | 11 ++++++++++- 3 files changed, 26 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/endpoint/functions/pci-epf-test.c b/drivers/pci/endpoint/functions/pci-epf-test.c index 55283d2379a6..2fe161747e51 100644 --- a/drivers/pci/endpoint/functions/pci-epf-test.c +++ b/drivers/pci/endpoint/functions/pci-epf-test.c @@ -826,20 +826,17 @@ static int pci_epf_test_core_init(struct pci_epf *epf) return 0; } +static const struct pci_epc_event_ops pci_epf_test_event_ops = { + .core_init = pci_epf_test_core_init, +}; + static int pci_epf_test_notifier(struct notifier_block *nb, unsigned long val, void *data) { struct pci_epf *epf = container_of(nb, struct pci_epf, nb); struct pci_epf_test *epf_test = epf_get_drvdata(epf); - int ret; switch (val) { - case CORE_INIT: - ret = pci_epf_test_core_init(epf); - if (ret) - return NOTIFY_BAD; - break; - case LINK_UP: queue_delayed_work(kpcitest_workqueue, &epf_test->cmd_handler, msecs_to_jiffies(1)); @@ -1010,6 +1007,8 @@ static int pci_epf_test_probe(struct pci_epf *epf) INIT_DELAYED_WORK(&epf_test->cmd_handler, pci_epf_test_cmd_handler); + epf->event_ops = &pci_epf_test_event_ops; + epf_set_drvdata(epf, epf_test); return 0; } diff --git a/drivers/pci/endpoint/pci-epc-core.c b/drivers/pci/endpoint/pci-epc-core.c index 2c023db8f51c..7cb9587c6548 100644 --- a/drivers/pci/endpoint/pci-epc-core.c +++ b/drivers/pci/endpoint/pci-epc-core.c @@ -707,10 +707,19 @@ EXPORT_SYMBOL_GPL(pci_epc_linkup); */ void pci_epc_init_notify(struct pci_epc *epc) { + struct pci_epf *epf; + if (!epc || IS_ERR(epc)) return; - atomic_notifier_call_chain(&epc->notifier, CORE_INIT, NULL); + mutex_lock(&epc->list_lock); + list_for_each_entry(epf, &epc->pci_epf, list) { + mutex_lock(&epf->lock); + if (epf->event_ops && epf->event_ops->core_init) + epf->event_ops->core_init(epf); + mutex_unlock(&epf->lock); + } + mutex_unlock(&epc->list_lock); } EXPORT_SYMBOL_GPL(pci_epc_init_notify); diff --git a/include/linux/pci-epf.h b/include/linux/pci-epf.h index 009a07147c61..fa629c191f00 100644 --- a/include/linux/pci-epf.h +++ b/include/linux/pci-epf.h @@ -18,7 +18,6 @@ struct pci_epf; enum pci_epc_interface_type; enum pci_notify_event { - CORE_INIT, LINK_UP, }; @@ -72,6 +71,14 @@ struct pci_epf_ops { struct config_group *group); }; +/** + * struct pci_epf_event_ops - Callbacks for capturing the EPC events + * @core_init: Callback for the EPC initialization complete event + */ +struct pci_epc_event_ops { + int (*core_init)(struct pci_epf *epf); +}; + /** * struct pci_epf_driver - represents the PCI EPF driver * @probe: ops to perform when a new EPF device has been bound to the EPF driver @@ -139,6 +146,7 @@ struct pci_epf_bar { * @is_vf: true - virtual function, false - physical function * @vfunction_num_map: bitmap to manage virtual function number * @pci_vepf: list of virtual endpoint functions associated with this function + * @event_ops: Callbacks for capturing the EPC events */ struct pci_epf { struct device dev; @@ -168,6 +176,7 @@ struct pci_epf { unsigned int is_vf; unsigned long vfunction_num_map; struct list_head pci_vepf; + const struct pci_epc_event_ops *event_ops; }; /** -- cgit v1.2.3 From f5edd8715e2ea672e6119c3764041743761fb178 Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Tue, 24 Jan 2023 12:41:58 +0530 Subject: PCI: endpoint: Use link_up() callback in place of LINK_UP notifier As a part of the transition towards callback mechanism for signalling the events from EPC to EPF, let's use the link_up() callback in the place of the LINK_UP notifier. This also removes the notifier support completely from the PCI endpoint framework. Link: https://lore.kernel.org/linux-pci/20230124071158.5503-6-manivannan.sadhasivam@linaro.org Signed-off-by: Manivannan Sadhasivam Signed-off-by: Krzysztof Wilczyński Acked-by: Kishon Vijay Abraham I --- drivers/pci/endpoint/functions/pci-epf-test.c | 33 ++++++++------------------- drivers/pci/endpoint/pci-epc-core.c | 12 ++++++++-- include/linux/pci-epc.h | 8 ------- include/linux/pci-epf.h | 8 ++----- 4 files changed, 22 insertions(+), 39 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/endpoint/functions/pci-epf-test.c b/drivers/pci/endpoint/functions/pci-epf-test.c index 2fe161747e51..0f9d2ec822ac 100644 --- a/drivers/pci/endpoint/functions/pci-epf-test.c +++ b/drivers/pci/endpoint/functions/pci-epf-test.c @@ -826,30 +826,21 @@ static int pci_epf_test_core_init(struct pci_epf *epf) return 0; } -static const struct pci_epc_event_ops pci_epf_test_event_ops = { - .core_init = pci_epf_test_core_init, -}; - -static int pci_epf_test_notifier(struct notifier_block *nb, unsigned long val, - void *data) +static int pci_epf_test_link_up(struct pci_epf *epf) { - struct pci_epf *epf = container_of(nb, struct pci_epf, nb); struct pci_epf_test *epf_test = epf_get_drvdata(epf); - switch (val) { - case LINK_UP: - queue_delayed_work(kpcitest_workqueue, &epf_test->cmd_handler, - msecs_to_jiffies(1)); - break; - - default: - dev_err(&epf->dev, "Invalid EPF test notifier event\n"); - return NOTIFY_BAD; - } + queue_delayed_work(kpcitest_workqueue, &epf_test->cmd_handler, + msecs_to_jiffies(1)); - return NOTIFY_OK; + return 0; } +static const struct pci_epc_event_ops pci_epf_test_event_ops = { + .core_init = pci_epf_test_core_init, + .link_up = pci_epf_test_link_up, +}; + static int pci_epf_test_alloc_space(struct pci_epf *epf) { struct pci_epf_test *epf_test = epf_get_drvdata(epf); @@ -976,12 +967,8 @@ static int pci_epf_test_bind(struct pci_epf *epf) if (ret) epf_test->dma_supported = false; - if (linkup_notifier || core_init_notifier) { - epf->nb.notifier_call = pci_epf_test_notifier; - pci_epc_register_notifier(epc, &epf->nb); - } else { + if (!linkup_notifier && !core_init_notifier) queue_work(kpcitest_workqueue, &epf_test->cmd_handler.work); - } return 0; } diff --git a/drivers/pci/endpoint/pci-epc-core.c b/drivers/pci/endpoint/pci-epc-core.c index 7cb9587c6548..c9c3c6b58a9f 100644 --- a/drivers/pci/endpoint/pci-epc-core.c +++ b/drivers/pci/endpoint/pci-epc-core.c @@ -690,10 +690,19 @@ EXPORT_SYMBOL_GPL(pci_epc_remove_epf); */ void pci_epc_linkup(struct pci_epc *epc) { + struct pci_epf *epf; + if (!epc || IS_ERR(epc)) return; - atomic_notifier_call_chain(&epc->notifier, LINK_UP, NULL); + mutex_lock(&epc->list_lock); + list_for_each_entry(epf, &epc->pci_epf, list) { + mutex_lock(&epf->lock); + if (epf->event_ops && epf->event_ops->link_up) + epf->event_ops->link_up(epf); + mutex_unlock(&epf->lock); + } + mutex_unlock(&epc->list_lock); } EXPORT_SYMBOL_GPL(pci_epc_linkup); @@ -788,7 +797,6 @@ __pci_epc_create(struct device *dev, const struct pci_epc_ops *ops, mutex_init(&epc->lock); mutex_init(&epc->list_lock); INIT_LIST_HEAD(&epc->pci_epf); - ATOMIC_INIT_NOTIFIER_HEAD(&epc->notifier); device_initialize(&epc->dev); epc->dev.class = pci_epc_class; diff --git a/include/linux/pci-epc.h b/include/linux/pci-epc.h index fe729dfe509b..301bb0e53707 100644 --- a/include/linux/pci-epc.h +++ b/include/linux/pci-epc.h @@ -135,7 +135,6 @@ struct pci_epc_mem { * @group: configfs group representing the PCI EPC device * @lock: mutex to protect pci_epc ops * @function_num_map: bitmap to manage physical function number - * @notifier: used to notify EPF of any EPC events (like linkup) */ struct pci_epc { struct device dev; @@ -151,7 +150,6 @@ struct pci_epc { /* mutex to protect against concurrent access of EP controller */ struct mutex lock; unsigned long function_num_map; - struct atomic_notifier_head notifier; }; /** @@ -194,12 +192,6 @@ static inline void *epc_get_drvdata(struct pci_epc *epc) return dev_get_drvdata(&epc->dev); } -static inline int -pci_epc_register_notifier(struct pci_epc *epc, struct notifier_block *nb) -{ - return atomic_notifier_chain_register(&epc->notifier, nb); -} - struct pci_epc * __devm_pci_epc_create(struct device *dev, const struct pci_epc_ops *ops, struct module *owner); diff --git a/include/linux/pci-epf.h b/include/linux/pci-epf.h index fa629c191f00..a215dc8ce693 100644 --- a/include/linux/pci-epf.h +++ b/include/linux/pci-epf.h @@ -17,10 +17,6 @@ struct pci_epf; enum pci_epc_interface_type; -enum pci_notify_event { - LINK_UP, -}; - enum pci_barno { NO_BAR = -1, BAR_0, @@ -74,9 +70,11 @@ struct pci_epf_ops { /** * struct pci_epf_event_ops - Callbacks for capturing the EPC events * @core_init: Callback for the EPC initialization complete event + * @link_up: Callback for the EPC link up event */ struct pci_epc_event_ops { int (*core_init)(struct pci_epf *epf); + int (*link_up)(struct pci_epf *epf); }; /** @@ -134,7 +132,6 @@ struct pci_epf_bar { * @epf_pf: the physical EPF device to which this virtual EPF device is bound * @driver: the EPF driver to which this EPF device is bound * @list: to add pci_epf as a list of PCI endpoint functions to pci_epc - * @nb: notifier block to notify EPF of any EPC events (like linkup) * @lock: mutex to protect pci_epf_ops * @sec_epc: the secondary EPC device to which this EPF device is bound * @sec_epc_list: to add pci_epf as list of PCI endpoint functions to secondary @@ -162,7 +159,6 @@ struct pci_epf { struct pci_epf *epf_pf; struct pci_epf_driver *driver; struct list_head list; - struct notifier_block nb; /* mutex to protect against concurrent access of pci_epf_ops */ struct mutex lock; -- cgit v1.2.3 From 80df83c2c57e75cb482ccf0c639ce84703ab41a2 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Sat, 4 Feb 2023 00:53:35 +0100 Subject: mmc: core: add devm_mmc_alloc_host Add a device-managed version of mmc_alloc_host(). The argument order is reversed compared to mmc_alloc_host() because device-managed functions typically have the device argument first. Signed-off-by: Heiner Kallweit Link: https://lore.kernel.org/r/6d8f9fdc-7c9e-8e4f-e6ef-5470b971c74e@gmail.com Signed-off-by: Ulf Hansson --- drivers/mmc/core/host.c | 26 ++++++++++++++++++++++++++ include/linux/mmc/host.h | 1 + 2 files changed, 27 insertions(+) (limited to 'include/linux') diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c index d17eda753b7e..6a7475ad7685 100644 --- a/drivers/mmc/core/host.c +++ b/drivers/mmc/core/host.c @@ -588,6 +588,32 @@ struct mmc_host *mmc_alloc_host(int extra, struct device *dev) EXPORT_SYMBOL(mmc_alloc_host); +static void devm_mmc_host_release(struct device *dev, void *res) +{ + mmc_free_host(*(struct mmc_host **)res); +} + +struct mmc_host *devm_mmc_alloc_host(struct device *dev, int extra) +{ + struct mmc_host **dr, *host; + + dr = devres_alloc(devm_mmc_host_release, sizeof(*dr), GFP_KERNEL); + if (!dr) + return ERR_PTR(-ENOMEM); + + host = mmc_alloc_host(extra, dev); + if (IS_ERR(host)) { + devres_free(dr); + return host; + } + + *dr = host; + devres_add(dev, dr); + + return host; +} +EXPORT_SYMBOL(devm_mmc_alloc_host); + static int mmc_validate_host_caps(struct mmc_host *host) { struct device *dev = host->parent; diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 8fdd3cf971a3..812e6b583b25 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -527,6 +527,7 @@ struct mmc_host { struct device_node; struct mmc_host *mmc_alloc_host(int extra, struct device *); +struct mmc_host *devm_mmc_alloc_host(struct device *dev, int extra); int mmc_add_host(struct mmc_host *); void mmc_remove_host(struct mmc_host *); void mmc_free_host(struct mmc_host *); -- cgit v1.2.3 From 6aa3a920125e9f58891e2b5dc2efd4d0c1ff05a6 Mon Sep 17 00:00:00 2001 From: Sidhartha Kumar Date: Fri, 13 Jan 2023 16:30:50 -0600 Subject: mm/hugetlb: convert isolate_hugetlb to folios Patch series "continue hugetlb folio conversion", v3. This series continues the conversion of core hugetlb functions to use folios. This series converts many helper funtions in the hugetlb fault path. This is in preparation for another series to convert the hugetlb fault code paths to operate on folios. This patch (of 8): Convert isolate_hugetlb() to take in a folio and convert its callers to pass a folio. Use page_folio() to convert the callers to use a folio is safe as isolate_hugetlb() operates on a head page. Link: https://lkml.kernel.org/r/20230113223057.173292-1-sidhartha.kumar@oracle.com Link: https://lkml.kernel.org/r/20230113223057.173292-2-sidhartha.kumar@oracle.com Signed-off-by: Sidhartha Kumar Reviewed-by: Mike Kravetz Cc: John Hubbard Cc: Matthew Wilcox Cc: Mike Kravetz Cc: Muchun Song Signed-off-by: Andrew Morton --- include/linux/hugetlb.h | 4 ++-- mm/gup.c | 2 +- mm/hugetlb.c | 16 ++++++++-------- mm/memory-failure.c | 2 +- mm/memory_hotplug.c | 2 +- mm/mempolicy.c | 2 +- mm/migrate.c | 2 +- 7 files changed, 15 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index a51e6daacac6..6e38a019f654 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -171,7 +171,7 @@ bool hugetlb_reserve_pages(struct inode *inode, long from, long to, vm_flags_t vm_flags); long hugetlb_unreserve_pages(struct inode *inode, long start, long end, long freed); -int isolate_hugetlb(struct page *page, struct list_head *list); +int isolate_hugetlb(struct folio *folio, struct list_head *list); int get_hwpoison_hugetlb_folio(struct folio *folio, bool *hugetlb, bool unpoison); int get_huge_page_for_hwpoison(unsigned long pfn, int flags, bool *migratable_cleared); @@ -413,7 +413,7 @@ static inline pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, return NULL; } -static inline int isolate_hugetlb(struct page *page, struct list_head *list) +static inline int isolate_hugetlb(struct folio *folio, struct list_head *list) { return -EBUSY; } diff --git a/mm/gup.c b/mm/gup.c index 25e4a3d923d6..b0885f70579c 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -1930,7 +1930,7 @@ static unsigned long collect_longterm_unpinnable_pages( continue; if (folio_test_hugetlb(folio)) { - isolate_hugetlb(&folio->page, movable_page_list); + isolate_hugetlb(folio, movable_page_list); continue; } diff --git a/mm/hugetlb.c b/mm/hugetlb.c index ab35b1cc9927..0c1e1ce113c8 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2925,7 +2925,7 @@ retry: * Fail with -EBUSY if not possible. */ spin_unlock_irq(&hugetlb_lock); - ret = isolate_hugetlb(&old_folio->page, list); + ret = isolate_hugetlb(old_folio, list); spin_lock_irq(&hugetlb_lock); goto free_new; } else if (!folio_test_hugetlb_freed(old_folio)) { @@ -3000,7 +3000,7 @@ int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list) if (hstate_is_gigantic(h)) return -ENOMEM; - if (folio_ref_count(folio) && !isolate_hugetlb(&folio->page, list)) + if (folio_ref_count(folio) && !isolate_hugetlb(folio, list)) ret = 0; else if (!folio_ref_count(folio)) ret = alloc_and_dissolve_hugetlb_folio(h, folio, list); @@ -7250,19 +7250,19 @@ __weak unsigned long hugetlb_mask_last_page(struct hstate *h) * These functions are overwritable if your architecture needs its own * behavior. */ -int isolate_hugetlb(struct page *page, struct list_head *list) +int isolate_hugetlb(struct folio *folio, struct list_head *list) { int ret = 0; spin_lock_irq(&hugetlb_lock); - if (!PageHeadHuge(page) || - !HPageMigratable(page) || - !get_page_unless_zero(page)) { + if (!folio_test_hugetlb(folio) || + !folio_test_hugetlb_migratable(folio) || + !folio_try_get(folio)) { ret = -EBUSY; goto unlock; } - ClearHPageMigratable(page); - list_move_tail(&page->lru, list); + folio_clear_hugetlb_migratable(folio); + list_move_tail(&folio->lru, list); unlock: spin_unlock_irq(&hugetlb_lock); return ret; diff --git a/mm/memory-failure.c b/mm/memory-failure.c index b4b30d9b0782..db85c2d37f70 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -2508,7 +2508,7 @@ static bool isolate_page(struct page *page, struct list_head *pagelist) bool isolated = false; if (PageHuge(page)) { - isolated = !isolate_hugetlb(page, pagelist); + isolated = !isolate_hugetlb(page_folio(page), pagelist); } else { bool lru = !__PageMovable(page); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index fd40f7e9f176..a1e8c3e9ab08 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1641,7 +1641,7 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) if (PageHuge(page)) { pfn = page_to_pfn(head) + compound_nr(head) - 1; - isolate_hugetlb(head, &source); + isolate_hugetlb(folio, &source); continue; } else if (PageTransHuge(page)) pfn = page_to_pfn(head) + thp_nr_pages(page) - 1; diff --git a/mm/mempolicy.c b/mm/mempolicy.c index dd5ca942256f..fc034b070645 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -602,7 +602,7 @@ static int queue_pages_hugetlb(pte_t *pte, unsigned long hmask, if (flags & (MPOL_MF_MOVE_ALL) || (flags & MPOL_MF_MOVE && page_mapcount(page) == 1 && !hugetlb_pmd_shared(pte))) { - if (isolate_hugetlb(page, qp->pagelist) && + if (isolate_hugetlb(page_folio(page), qp->pagelist) && (flags & MPOL_MF_STRICT)) /* * Failed to isolate page but allow migrating pages diff --git a/mm/migrate.c b/mm/migrate.c index 206fcdbe67f3..f6464bce7678 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1773,7 +1773,7 @@ static int add_page_for_migration(struct mm_struct *mm, unsigned long addr, if (PageHuge(page)) { if (PageHead(page)) { - err = isolate_hugetlb(page, pagelist); + err = isolate_hugetlb(page_folio(page), pagelist); if (!err) err = 1; } -- cgit v1.2.3 From ff7d853b031302376a0d3640fa1c463d94079637 Mon Sep 17 00:00:00 2001 From: Sidhartha Kumar Date: Fri, 13 Jan 2023 16:30:54 -0600 Subject: mm/hugetlb: increase use of folios in alloc_huge_page() Change hugetlb_cgroup_commit_charge{,_rsvd}(), dequeue_huge_page_vma() and alloc_buddy_huge_page_with_mpol() to use folios so alloc_huge_page() is cleaned by operating on folios until its return. Link: https://lkml.kernel.org/r/20230113223057.173292-6-sidhartha.kumar@oracle.com Signed-off-by: Sidhartha Kumar Reviewed-by: Mike Kravetz Cc: John Hubbard Cc: Matthew Wilcox Cc: Muchun Song Signed-off-by: Andrew Morton --- include/linux/hugetlb_cgroup.h | 8 ++++---- mm/hugetlb.c | 33 ++++++++++++++++----------------- mm/hugetlb_cgroup.c | 8 ++------ 3 files changed, 22 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb_cgroup.h b/include/linux/hugetlb_cgroup.h index f706626a8063..3d82d91f49ac 100644 --- a/include/linux/hugetlb_cgroup.h +++ b/include/linux/hugetlb_cgroup.h @@ -141,10 +141,10 @@ extern int hugetlb_cgroup_charge_cgroup_rsvd(int idx, unsigned long nr_pages, struct hugetlb_cgroup **ptr); extern void hugetlb_cgroup_commit_charge(int idx, unsigned long nr_pages, struct hugetlb_cgroup *h_cg, - struct page *page); + struct folio *folio); extern void hugetlb_cgroup_commit_charge_rsvd(int idx, unsigned long nr_pages, struct hugetlb_cgroup *h_cg, - struct page *page); + struct folio *folio); extern void hugetlb_cgroup_uncharge_folio(int idx, unsigned long nr_pages, struct folio *folio); extern void hugetlb_cgroup_uncharge_folio_rsvd(int idx, unsigned long nr_pages, @@ -230,14 +230,14 @@ static inline int hugetlb_cgroup_charge_cgroup_rsvd(int idx, static inline void hugetlb_cgroup_commit_charge(int idx, unsigned long nr_pages, struct hugetlb_cgroup *h_cg, - struct page *page) + struct folio *folio) { } static inline void hugetlb_cgroup_commit_charge_rsvd(int idx, unsigned long nr_pages, struct hugetlb_cgroup *h_cg, - struct page *page) + struct folio *folio) { } diff --git a/mm/hugetlb.c b/mm/hugetlb.c index fa61b4aa68ca..5d0d1efbe590 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1348,7 +1348,7 @@ static unsigned long available_huge_pages(struct hstate *h) return h->free_huge_pages - h->resv_huge_pages; } -static struct page *dequeue_huge_page_vma(struct hstate *h, +static struct folio *dequeue_hugetlb_folio_vma(struct hstate *h, struct vm_area_struct *vma, unsigned long address, int avoid_reserve, long chg) @@ -1392,7 +1392,7 @@ static struct page *dequeue_huge_page_vma(struct hstate *h, } mpol_cond_put(mpol); - return &folio->page; + return folio; err: return NULL; @@ -2446,7 +2446,7 @@ static struct page *alloc_migrate_huge_page(struct hstate *h, gfp_t gfp_mask, * Use the VMA's mpolicy to allocate a huge page from the buddy. */ static -struct page *alloc_buddy_huge_page_with_mpol(struct hstate *h, +struct folio *alloc_buddy_hugetlb_folio_with_mpol(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) { struct folio *folio = NULL; @@ -2469,7 +2469,7 @@ struct page *alloc_buddy_huge_page_with_mpol(struct hstate *h, if (!folio) folio = alloc_surplus_hugetlb_folio(h, gfp_mask, nid, nodemask); mpol_cond_put(mpol); - return &folio->page; + return folio; } /* page migration callback function */ @@ -3018,7 +3018,6 @@ struct page *alloc_huge_page(struct vm_area_struct *vma, { struct hugepage_subpool *spool = subpool_vma(vma); struct hstate *h = hstate_vma(vma); - struct page *page; struct folio *folio; long map_chg, map_commit; long gbl_chg; @@ -3082,34 +3081,34 @@ struct page *alloc_huge_page(struct vm_area_struct *vma, * from the global free pool (global change). gbl_chg == 0 indicates * a reservation exists for the allocation. */ - page = dequeue_huge_page_vma(h, vma, addr, avoid_reserve, gbl_chg); - if (!page) { + folio = dequeue_hugetlb_folio_vma(h, vma, addr, avoid_reserve, gbl_chg); + if (!folio) { spin_unlock_irq(&hugetlb_lock); - page = alloc_buddy_huge_page_with_mpol(h, vma, addr); - if (!page) + folio = alloc_buddy_hugetlb_folio_with_mpol(h, vma, addr); + if (!folio) goto out_uncharge_cgroup; spin_lock_irq(&hugetlb_lock); if (!avoid_reserve && vma_has_reserves(vma, gbl_chg)) { - SetHPageRestoreReserve(page); + folio_set_hugetlb_restore_reserve(folio); h->resv_huge_pages--; } - list_add(&page->lru, &h->hugepage_activelist); - set_page_refcounted(page); + list_add(&folio->lru, &h->hugepage_activelist); + folio_ref_unfreeze(folio, 1); /* Fall through */ } - folio = page_folio(page); - hugetlb_cgroup_commit_charge(idx, pages_per_huge_page(h), h_cg, page); + + hugetlb_cgroup_commit_charge(idx, pages_per_huge_page(h), h_cg, folio); /* If allocation is not consuming a reservation, also store the * hugetlb_cgroup pointer on the page. */ if (deferred_reserve) { hugetlb_cgroup_commit_charge_rsvd(idx, pages_per_huge_page(h), - h_cg, page); + h_cg, folio); } spin_unlock_irq(&hugetlb_lock); - hugetlb_set_page_subpool(page, spool); + hugetlb_set_folio_subpool(folio, spool); map_commit = vma_commit_reservation(h, vma, addr); if (unlikely(map_chg > map_commit)) { @@ -3130,7 +3129,7 @@ struct page *alloc_huge_page(struct vm_area_struct *vma, hugetlb_cgroup_uncharge_folio_rsvd(hstate_index(h), pages_per_huge_page(h), folio); } - return page; + return &folio->page; out_uncharge_cgroup: hugetlb_cgroup_uncharge_cgroup(idx, pages_per_huge_page(h), h_cg); diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c index d9e4425d81ac..dedd2edb076e 100644 --- a/mm/hugetlb_cgroup.c +++ b/mm/hugetlb_cgroup.c @@ -331,19 +331,15 @@ static void __hugetlb_cgroup_commit_charge(int idx, unsigned long nr_pages, void hugetlb_cgroup_commit_charge(int idx, unsigned long nr_pages, struct hugetlb_cgroup *h_cg, - struct page *page) + struct folio *folio) { - struct folio *folio = page_folio(page); - __hugetlb_cgroup_commit_charge(idx, nr_pages, h_cg, folio, false); } void hugetlb_cgroup_commit_charge_rsvd(int idx, unsigned long nr_pages, struct hugetlb_cgroup *h_cg, - struct page *page) + struct folio *folio) { - struct folio *folio = page_folio(page); - __hugetlb_cgroup_commit_charge(idx, nr_pages, h_cg, folio, true); } -- cgit v1.2.3 From e37d3e838d9078538f920957d1e89682b6764977 Mon Sep 17 00:00:00 2001 From: Sidhartha Kumar Date: Fri, 13 Jan 2023 16:30:55 -0600 Subject: mm/hugetlb: convert alloc_migrate_huge_page to folios Change alloc_huge_page_nodemask() to alloc_hugetlb_folio_nodemask() and alloc_migrate_huge_page() to alloc_migrate_hugetlb_folio(). Both functions now return a folio rather than a page. Link: https://lkml.kernel.org/r/20230113223057.173292-7-sidhartha.kumar@oracle.com Signed-off-by: Sidhartha Kumar Reviewed-by: Mike Kravetz Cc: John Hubbard Cc: Matthew Wilcox Cc: Muchun Song Signed-off-by: Andrew Morton --- include/linux/hugetlb.h | 6 +++--- mm/hugetlb.c | 18 +++++++++--------- mm/migrate.c | 5 ++++- 3 files changed, 16 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 6e38a019f654..2375c62c61a4 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -719,7 +719,7 @@ struct huge_bootmem_page { int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list); struct page *alloc_huge_page(struct vm_area_struct *vma, unsigned long addr, int avoid_reserve); -struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid, +struct folio *alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid, nodemask_t *nmask, gfp_t gfp_mask); struct page *alloc_huge_page_vma(struct hstate *h, struct vm_area_struct *vma, unsigned long address); @@ -1040,8 +1040,8 @@ static inline struct page *alloc_huge_page(struct vm_area_struct *vma, return NULL; } -static inline struct page * -alloc_huge_page_nodemask(struct hstate *h, int preferred_nid, +static inline struct folio * +alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid, nodemask_t *nmask, gfp_t gfp_mask) { return NULL; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 5d0d1efbe590..57894beb3382 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2419,7 +2419,7 @@ out_unlock: return folio; } -static struct page *alloc_migrate_huge_page(struct hstate *h, gfp_t gfp_mask, +static struct folio *alloc_migrate_hugetlb_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask) { struct folio *folio; @@ -2439,7 +2439,7 @@ static struct page *alloc_migrate_huge_page(struct hstate *h, gfp_t gfp_mask, */ folio_set_hugetlb_temporary(folio); - return &folio->page; + return folio; } /* @@ -2472,8 +2472,8 @@ struct folio *alloc_buddy_hugetlb_folio_with_mpol(struct hstate *h, return folio; } -/* page migration callback function */ -struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid, +/* folio migration callback function */ +struct folio *alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid, nodemask_t *nmask, gfp_t gfp_mask) { spin_lock_irq(&hugetlb_lock); @@ -2484,12 +2484,12 @@ struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid, preferred_nid, nmask); if (folio) { spin_unlock_irq(&hugetlb_lock); - return &folio->page; + return folio; } } spin_unlock_irq(&hugetlb_lock); - return alloc_migrate_huge_page(h, gfp_mask, preferred_nid, nmask); + return alloc_migrate_hugetlb_folio(h, gfp_mask, preferred_nid, nmask); } /* mempolicy aware migration callback */ @@ -2498,16 +2498,16 @@ struct page *alloc_huge_page_vma(struct hstate *h, struct vm_area_struct *vma, { struct mempolicy *mpol; nodemask_t *nodemask; - struct page *page; + struct folio *folio; gfp_t gfp_mask; int node; gfp_mask = htlb_alloc_mask(h); node = huge_node(vma, address, gfp_mask, &mpol, &nodemask); - page = alloc_huge_page_nodemask(h, node, nodemask, gfp_mask); + folio = alloc_hugetlb_folio_nodemask(h, node, nodemask, gfp_mask); mpol_cond_put(mpol); - return page; + return &folio->page; } /* diff --git a/mm/migrate.c b/mm/migrate.c index f6464bce7678..811e76c6fac1 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1663,6 +1663,7 @@ struct page *alloc_migration_target(struct page *page, unsigned long private) struct migration_target_control *mtc; gfp_t gfp_mask; unsigned int order = 0; + struct folio *hugetlb_folio = NULL; struct folio *new_folio = NULL; int nid; int zidx; @@ -1677,7 +1678,9 @@ struct page *alloc_migration_target(struct page *page, unsigned long private) struct hstate *h = folio_hstate(folio); gfp_mask = htlb_modify_alloc_mask(h, gfp_mask); - return alloc_huge_page_nodemask(h, nid, mtc->nmask, gfp_mask); + hugetlb_folio = alloc_hugetlb_folio_nodemask(h, nid, + mtc->nmask, gfp_mask); + return &hugetlb_folio->page; } if (folio_test_large(folio)) { -- cgit v1.2.3 From ea8e72f4116a995c2aba3fb738ac372c4115375a Mon Sep 17 00:00:00 2001 From: Sidhartha Kumar Date: Wed, 25 Jan 2023 09:05:32 -0800 Subject: mm/hugetlb: convert putback_active_hugepage to take in a folio Convert putback_active_hugepage() to folio_putback_active_hugetlb(), this removes one user of the Huge Page macros which take in a page. The callers in migrate.c are also cleaned up by being able to directly use the src and dst folio variables. Link: https://lkml.kernel.org/r/20230125170537.96973-4-sidhartha.kumar@oracle.com Signed-off-by: Sidhartha Kumar Reviewed-by: Mike Kravetz Cc: Gerald Schaefer Cc: John Hubbard Cc: Matthew Wilcox Cc: Muchun Song Signed-off-by: Andrew Morton --- include/linux/hugetlb.h | 4 ++-- mm/hugetlb.c | 8 ++++---- mm/migrate.c | 8 ++++---- 3 files changed, 10 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 2375c62c61a4..067906c5778e 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -175,7 +175,7 @@ int isolate_hugetlb(struct folio *folio, struct list_head *list); int get_hwpoison_hugetlb_folio(struct folio *folio, bool *hugetlb, bool unpoison); int get_huge_page_for_hwpoison(unsigned long pfn, int flags, bool *migratable_cleared); -void putback_active_hugepage(struct page *page); +void folio_putback_active_hugetlb(struct folio *folio); void move_hugetlb_state(struct folio *old_folio, struct folio *new_folio, int reason); void free_huge_page(struct page *page); void hugetlb_fix_reserve_counts(struct inode *inode); @@ -429,7 +429,7 @@ static inline int get_huge_page_for_hwpoison(unsigned long pfn, int flags, return 0; } -static inline void putback_active_hugepage(struct page *page) +static inline void folio_putback_active_hugetlb(struct folio *folio) { } diff --git a/mm/hugetlb.c b/mm/hugetlb.c index a0d486ed5411..fd1ce61b8f3f 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -7300,13 +7300,13 @@ int get_huge_page_for_hwpoison(unsigned long pfn, int flags, return ret; } -void putback_active_hugepage(struct page *page) +void folio_putback_active_hugetlb(struct folio *folio) { spin_lock_irq(&hugetlb_lock); - SetHPageMigratable(page); - list_move_tail(&page->lru, &(page_hstate(page))->hugepage_activelist); + folio_set_hugetlb_migratable(folio); + list_move_tail(&folio->lru, &(folio_hstate(folio))->hugepage_activelist); spin_unlock_irq(&hugetlb_lock); - put_page(page); + folio_put(folio); } void move_hugetlb_state(struct folio *old_folio, struct folio *new_folio, int reason) diff --git a/mm/migrate.c b/mm/migrate.c index 811e76c6fac1..c09872cf41b7 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -151,7 +151,7 @@ void putback_movable_pages(struct list_head *l) list_for_each_entry_safe(page, page2, l, lru) { if (unlikely(PageHuge(page))) { - putback_active_hugepage(page); + folio_putback_active_hugetlb(page_folio(page)); continue; } list_del(&page->lru); @@ -1298,7 +1298,7 @@ static int unmap_and_move_huge_page(new_page_t get_new_page, if (folio_ref_count(src) == 1) { /* page was freed from under us. So we are done. */ - putback_active_hugepage(hpage); + folio_putback_active_hugetlb(src); return MIGRATEPAGE_SUCCESS; } @@ -1383,7 +1383,7 @@ out_unlock: folio_unlock(src); out: if (rc == MIGRATEPAGE_SUCCESS) - putback_active_hugepage(hpage); + folio_putback_active_hugetlb(src); else if (rc != -EAGAIN) list_move_tail(&src->lru, ret); @@ -1395,7 +1395,7 @@ out: if (put_new_page) put_new_page(new_hpage, private); else - putback_active_hugepage(new_hpage); + folio_putback_active_hugetlb(dst); return rc; } -- cgit v1.2.3 From d0ce0e47b323a8d7fb5dc3314ce56afa650ade2d Mon Sep 17 00:00:00 2001 From: Sidhartha Kumar Date: Wed, 25 Jan 2023 09:05:33 -0800 Subject: mm/hugetlb: convert hugetlb fault paths to use alloc_hugetlb_folio() Change alloc_huge_page() to alloc_hugetlb_folio() by changing all callers to handle the now folio return type of the function. In this conversion, alloc_huge_page_vma() is also changed to alloc_hugetlb_folio_vma() and hugepage_add_new_anon_rmap() is changed to take in a folio directly. Many additions of '&folio->page' are cleaned up in subsequent patches. hugetlbfs_fallocate() is also refactored to use the RCU + page_cache_next_miss() API. Link: https://lkml.kernel.org/r/20230125170537.96973-5-sidhartha.kumar@oracle.com Suggested-by: Mike Kravetz Reported-by: kernel test robot Signed-off-by: Sidhartha Kumar Cc: Gerald Schaefer Cc: John Hubbard Cc: Matthew Wilcox Cc: Muchun Song Signed-off-by: Andrew Morton --- fs/hugetlbfs/inode.c | 40 +++++----- include/linux/hugetlb.h | 8 +- include/linux/rmap.h | 2 +- mm/hugetlb.c | 201 ++++++++++++++++++++++++------------------------ mm/mempolicy.c | 6 +- mm/rmap.c | 6 +- 6 files changed, 133 insertions(+), 130 deletions(-) (limited to 'include/linux') diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 44ecdcb796cc..f89e12106e8a 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -819,8 +819,9 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset, * This is supposed to be the vaddr where the page is being * faulted in, but we have no vaddr here. */ - struct page *page; + struct folio *folio; unsigned long addr; + bool present; cond_resched(); @@ -844,48 +845,49 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset, mutex_lock(&hugetlb_fault_mutex_table[hash]); /* See if already present in mapping to avoid alloc/free */ - page = find_get_page(mapping, index); - if (page) { - put_page(page); + rcu_read_lock(); + present = page_cache_next_miss(mapping, index, 1) != index; + rcu_read_unlock(); + if (present) { mutex_unlock(&hugetlb_fault_mutex_table[hash]); hugetlb_drop_vma_policy(&pseudo_vma); continue; } /* - * Allocate page without setting the avoid_reserve argument. + * Allocate folio without setting the avoid_reserve argument. * There certainly are no reserves associated with the * pseudo_vma. However, there could be shared mappings with * reserves for the file at the inode level. If we fallocate - * pages in these areas, we need to consume the reserves + * folios in these areas, we need to consume the reserves * to keep reservation accounting consistent. */ - page = alloc_huge_page(&pseudo_vma, addr, 0); + folio = alloc_hugetlb_folio(&pseudo_vma, addr, 0); hugetlb_drop_vma_policy(&pseudo_vma); - if (IS_ERR(page)) { + if (IS_ERR(folio)) { mutex_unlock(&hugetlb_fault_mutex_table[hash]); - error = PTR_ERR(page); + error = PTR_ERR(folio); goto out; } - clear_huge_page(page, addr, pages_per_huge_page(h)); - __SetPageUptodate(page); - error = hugetlb_add_to_page_cache(page, mapping, index); + clear_huge_page(&folio->page, addr, pages_per_huge_page(h)); + __folio_mark_uptodate(folio); + error = hugetlb_add_to_page_cache(&folio->page, mapping, index); if (unlikely(error)) { - restore_reserve_on_error(h, &pseudo_vma, addr, page); - put_page(page); + restore_reserve_on_error(h, &pseudo_vma, addr, &folio->page); + folio_put(folio); mutex_unlock(&hugetlb_fault_mutex_table[hash]); goto out; } mutex_unlock(&hugetlb_fault_mutex_table[hash]); - SetHPageMigratable(page); + folio_set_hugetlb_migratable(folio); /* - * unlock_page because locked by hugetlb_add_to_page_cache() - * put_page() due to reference from alloc_huge_page() + * folio_unlock because locked by hugetlb_add_to_page_cache() + * folio_put() due to reference from alloc_hugetlb_folio() */ - unlock_page(page); - put_page(page); + folio_unlock(folio); + folio_put(folio); } if (!(mode & FALLOC_FL_KEEP_SIZE) && offset + len > inode->i_size) diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 067906c5778e..6408f85e5754 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -717,11 +717,11 @@ struct huge_bootmem_page { }; int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list); -struct page *alloc_huge_page(struct vm_area_struct *vma, +struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, unsigned long addr, int avoid_reserve); struct folio *alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid, nodemask_t *nmask, gfp_t gfp_mask); -struct page *alloc_huge_page_vma(struct hstate *h, struct vm_area_struct *vma, +struct folio *alloc_hugetlb_folio_vma(struct hstate *h, struct vm_area_struct *vma, unsigned long address); int hugetlb_add_to_page_cache(struct page *page, struct address_space *mapping, pgoff_t idx); @@ -1033,7 +1033,7 @@ static inline int isolate_or_dissolve_huge_page(struct page *page, return -ENOMEM; } -static inline struct page *alloc_huge_page(struct vm_area_struct *vma, +static inline struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, unsigned long addr, int avoid_reserve) { @@ -1047,7 +1047,7 @@ alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid, return NULL; } -static inline struct page *alloc_huge_page_vma(struct hstate *h, +static inline struct folio *alloc_hugetlb_folio_vma(struct hstate *h, struct vm_area_struct *vma, unsigned long address) { diff --git a/include/linux/rmap.h b/include/linux/rmap.h index a6bd1f0a183d..a4570da03e58 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -203,7 +203,7 @@ void page_remove_rmap(struct page *, struct vm_area_struct *, void hugepage_add_anon_rmap(struct page *, struct vm_area_struct *, unsigned long address, rmap_t flags); -void hugepage_add_new_anon_rmap(struct page *, struct vm_area_struct *, +void hugepage_add_new_anon_rmap(struct folio *, struct vm_area_struct *, unsigned long address); static inline void __page_dup_rmap(struct page *page, bool compound) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index fd1ce61b8f3f..ea8d4611779b 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2493,7 +2493,7 @@ struct folio *alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid, } /* mempolicy aware migration callback */ -struct page *alloc_huge_page_vma(struct hstate *h, struct vm_area_struct *vma, +struct folio *alloc_hugetlb_folio_vma(struct hstate *h, struct vm_area_struct *vma, unsigned long address) { struct mempolicy *mpol; @@ -2507,7 +2507,7 @@ struct page *alloc_huge_page_vma(struct hstate *h, struct vm_area_struct *vma, folio = alloc_hugetlb_folio_nodemask(h, node, nodemask, gfp_mask); mpol_cond_put(mpol); - return &folio->page; + return folio; } /* @@ -2798,14 +2798,14 @@ static long vma_del_reservation(struct hstate *h, /* * This routine is called to restore reservation information on error paths. - * It should ONLY be called for pages allocated via alloc_huge_page(), and - * the hugetlb mutex should remain held when calling this routine. + * It should ONLY be called for folios allocated via alloc_hugetlb_folio(), + * and the hugetlb mutex should remain held when calling this routine. * * It handles two specific cases: * 1) A reservation was in place and the page consumed the reservation. * HPageRestoreReserve is set in the page. * 2) No reservation was in place for the page, so HPageRestoreReserve is - * not set. However, alloc_huge_page always updates the reserve map. + * not set. However, alloc_hugetlb_folio always updates the reserve map. * * In case 1, free_huge_page later in the error path will increment the * global reserve count. But, free_huge_page does not have enough context @@ -2814,7 +2814,7 @@ static long vma_del_reservation(struct hstate *h, * reserve count adjustments to be made by free_huge_page. Make sure the * reserve map indicates there is a reservation present. * - * In case 2, simply undo reserve map modifications done by alloc_huge_page. + * In case 2, simply undo reserve map modifications done by alloc_hugetlb_folio. */ void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma, unsigned long address, struct page *page) @@ -2844,8 +2844,8 @@ void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma, if (!rc) { /* * This indicates there is an entry in the reserve map - * not added by alloc_huge_page. We know it was added - * before the alloc_huge_page call, otherwise + * not added by alloc_hugetlb_folio. We know it was added + * before the alloc_hugetlb_folio call, otherwise * hugetlb_restore_reserve would be set on the folio. * Remove the entry so that a subsequent allocation * does not consume a reservation. @@ -3014,7 +3014,7 @@ int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list) return ret; } -struct page *alloc_huge_page(struct vm_area_struct *vma, +struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, unsigned long addr, int avoid_reserve) { struct hugepage_subpool *spool = subpool_vma(vma); @@ -3023,7 +3023,7 @@ struct page *alloc_huge_page(struct vm_area_struct *vma, long map_chg, map_commit; long gbl_chg; int ret, idx; - struct hugetlb_cgroup *h_cg; + struct hugetlb_cgroup *h_cg = NULL; bool deferred_reserve; idx = hstate_index(h); @@ -3130,7 +3130,7 @@ struct page *alloc_huge_page(struct vm_area_struct *vma, hugetlb_cgroup_uncharge_folio_rsvd(hstate_index(h), pages_per_huge_page(h), folio); } - return &folio->page; + return folio; out_uncharge_cgroup: hugetlb_cgroup_uncharge_cgroup(idx, pages_per_huge_page(h), h_cg); @@ -4950,7 +4950,7 @@ hugetlb_install_folio(struct vm_area_struct *vma, pte_t *ptep, unsigned long add struct folio *new_folio) { __folio_mark_uptodate(new_folio); - hugepage_add_new_anon_rmap(&new_folio->page, vma, addr); + hugepage_add_new_anon_rmap(new_folio, vma, addr); set_huge_pte_at(vma->vm_mm, addr, ptep, make_huge_pte(vma, &new_folio->page, 1)); hugetlb_count_add(pages_per_huge_page(hstate_vma(vma)), vma->vm_mm); folio_set_hugetlb_migratable(new_folio); @@ -5080,34 +5080,34 @@ again: } else if (page_try_dup_anon_rmap(ptepage, true, src_vma)) { pte_t src_pte_old = entry; - struct page *new; + struct folio *new_folio; spin_unlock(src_ptl); spin_unlock(dst_ptl); /* Do not use reserve as it's private owned */ - new = alloc_huge_page(dst_vma, addr, 1); - if (IS_ERR(new)) { + new_folio = alloc_hugetlb_folio(dst_vma, addr, 1); + if (IS_ERR(new_folio)) { put_page(ptepage); - ret = PTR_ERR(new); + ret = PTR_ERR(new_folio); break; } - copy_user_huge_page(new, ptepage, addr, dst_vma, + copy_user_huge_page(&new_folio->page, ptepage, addr, dst_vma, npages); put_page(ptepage); - /* Install the new huge page if src pte stable */ + /* Install the new hugetlb folio if src pte stable */ dst_ptl = huge_pte_lock(h, dst, dst_pte); src_ptl = huge_pte_lockptr(h, src, src_pte); spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); entry = huge_ptep_get(src_pte); if (!pte_same(src_pte_old, entry)) { restore_reserve_on_error(h, dst_vma, addr, - new); - put_page(new); + &new_folio->page); + folio_put(new_folio); /* huge_ptep of dst_pte won't change as in child */ goto again; } - hugetlb_install_folio(dst_vma, dst_pte, addr, page_folio(new)); + hugetlb_install_folio(dst_vma, dst_pte, addr, new_folio); spin_unlock(src_ptl); spin_unlock(dst_ptl); continue; @@ -5478,7 +5478,8 @@ static vm_fault_t hugetlb_wp(struct mm_struct *mm, struct vm_area_struct *vma, const bool unshare = flags & FAULT_FLAG_UNSHARE; pte_t pte; struct hstate *h = hstate_vma(vma); - struct page *old_page, *new_page; + struct page *old_page; + struct folio *new_folio; int outside_reserve = 0; vm_fault_t ret = 0; unsigned long haddr = address & huge_page_mask(h); @@ -5539,9 +5540,9 @@ retry_avoidcopy: * be acquired again before returning to the caller, as expected. */ spin_unlock(ptl); - new_page = alloc_huge_page(vma, haddr, outside_reserve); + new_folio = alloc_hugetlb_folio(vma, haddr, outside_reserve); - if (IS_ERR(new_page)) { + if (IS_ERR(new_folio)) { /* * If a process owning a MAP_PRIVATE mapping fails to COW, * it is due to references held by a child and an insufficient @@ -5586,7 +5587,7 @@ retry_avoidcopy: return 0; } - ret = vmf_error(PTR_ERR(new_page)); + ret = vmf_error(PTR_ERR(new_folio)); goto out_release_old; } @@ -5599,9 +5600,9 @@ retry_avoidcopy: goto out_release_all; } - copy_user_huge_page(new_page, old_page, address, vma, + copy_user_huge_page(&new_folio->page, old_page, address, vma, pages_per_huge_page(h)); - __SetPageUptodate(new_page); + __folio_mark_uptodate(new_folio); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, haddr, haddr + huge_page_size(h)); @@ -5618,12 +5619,12 @@ retry_avoidcopy: huge_ptep_clear_flush(vma, haddr, ptep); mmu_notifier_invalidate_range(mm, range.start, range.end); page_remove_rmap(old_page, vma, true); - hugepage_add_new_anon_rmap(new_page, vma, haddr); + hugepage_add_new_anon_rmap(new_folio, vma, haddr); set_huge_pte_at(mm, haddr, ptep, - make_huge_pte(vma, new_page, !unshare)); - SetHPageMigratable(new_page); + make_huge_pte(vma, &new_folio->page, !unshare)); + folio_set_hugetlb_migratable(new_folio); /* Make the old page be freed below */ - new_page = old_page; + new_folio = page_folio(old_page); } spin_unlock(ptl); mmu_notifier_invalidate_range_end(&range); @@ -5632,9 +5633,9 @@ out_release_all: * No restore in case of successful pagetable update (Break COW or * unshare) */ - if (new_page != old_page) - restore_reserve_on_error(h, vma, haddr, new_page); - put_page(new_page); + if (new_folio != page_folio(old_page)) + restore_reserve_on_error(h, vma, haddr, &new_folio->page); + folio_put(new_folio); out_release_old: put_page(old_page); @@ -5753,11 +5754,11 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, vm_fault_t ret = VM_FAULT_SIGBUS; int anon_rmap = 0; unsigned long size; - struct page *page; + struct folio *folio; pte_t new_pte; spinlock_t *ptl; unsigned long haddr = address & huge_page_mask(h); - bool new_page, new_pagecache_page = false; + bool new_folio, new_pagecache_folio = false; u32 hash = hugetlb_fault_mutex_hash(mapping, idx); /* @@ -5776,9 +5777,9 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, * Use page lock to guard against racing truncation * before we get page_table_lock. */ - new_page = false; - page = find_lock_page(mapping, idx); - if (!page) { + new_folio = false; + folio = filemap_lock_folio(mapping, idx); + if (!folio) { size = i_size_read(mapping->host) >> huge_page_shift(h); if (idx >= size) goto out; @@ -5811,8 +5812,8 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, VM_UFFD_MISSING); } - page = alloc_huge_page(vma, haddr, 0); - if (IS_ERR(page)) { + folio = alloc_hugetlb_folio(vma, haddr, 0); + if (IS_ERR(folio)) { /* * Returning error will result in faulting task being * sent SIGBUS. The hugetlb fault mutex prevents two @@ -5826,17 +5827,17 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, * sure there really is no pte entry. */ if (hugetlb_pte_stable(h, mm, ptep, old_pte)) - ret = vmf_error(PTR_ERR(page)); + ret = vmf_error(PTR_ERR(folio)); else ret = 0; goto out; } - clear_huge_page(page, address, pages_per_huge_page(h)); - __SetPageUptodate(page); - new_page = true; + clear_huge_page(&folio->page, address, pages_per_huge_page(h)); + __folio_mark_uptodate(folio); + new_folio = true; if (vma->vm_flags & VM_MAYSHARE) { - int err = hugetlb_add_to_page_cache(page, mapping, idx); + int err = hugetlb_add_to_page_cache(&folio->page, mapping, idx); if (err) { /* * err can't be -EEXIST which implies someone @@ -5845,13 +5846,13 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, * to the page cache. So it's safe to call * restore_reserve_on_error() here. */ - restore_reserve_on_error(h, vma, haddr, page); - put_page(page); + restore_reserve_on_error(h, vma, haddr, &folio->page); + folio_put(folio); goto out; } - new_pagecache_page = true; + new_pagecache_folio = true; } else { - lock_page(page); + folio_lock(folio); if (unlikely(anon_vma_prepare(vma))) { ret = VM_FAULT_OOM; goto backout_unlocked; @@ -5864,7 +5865,7 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, * don't have hwpoisoned swap entry for errored virtual address. * So we need to block hugepage fault by PG_hwpoison bit check. */ - if (unlikely(PageHWPoison(page))) { + if (unlikely(folio_test_hwpoison(folio))) { ret = VM_FAULT_HWPOISON_LARGE | VM_FAULT_SET_HINDEX(hstate_index(h)); goto backout_unlocked; @@ -5872,8 +5873,8 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, /* Check for page in userfault range. */ if (userfaultfd_minor(vma)) { - unlock_page(page); - put_page(page); + folio_unlock(folio); + folio_put(folio); /* See comment in userfaultfd_missing() block above */ if (!hugetlb_pte_stable(h, mm, ptep, old_pte)) { ret = 0; @@ -5907,10 +5908,10 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, goto backout; if (anon_rmap) - hugepage_add_new_anon_rmap(page, vma, haddr); + hugepage_add_new_anon_rmap(folio, vma, haddr); else - page_dup_file_rmap(page, true); - new_pte = make_huge_pte(vma, page, ((vma->vm_flags & VM_WRITE) + page_dup_file_rmap(&folio->page, true); + new_pte = make_huge_pte(vma, &folio->page, ((vma->vm_flags & VM_WRITE) && (vma->vm_flags & VM_SHARED))); /* * If this pte was previously wr-protected, keep it wr-protected even @@ -5923,20 +5924,20 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, hugetlb_count_add(pages_per_huge_page(h), mm); if ((flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) { /* Optimization, do the COW without a second fault */ - ret = hugetlb_wp(mm, vma, address, ptep, flags, page, ptl); + ret = hugetlb_wp(mm, vma, address, ptep, flags, &folio->page, ptl); } spin_unlock(ptl); /* - * Only set HPageMigratable in newly allocated pages. Existing pages - * found in the pagecache may not have HPageMigratableset if they have + * Only set hugetlb_migratable in newly allocated pages. Existing pages + * found in the pagecache may not have hugetlb_migratable if they have * been isolated for migration. */ - if (new_page) - SetHPageMigratable(page); + if (new_folio) + folio_set_hugetlb_migratable(folio); - unlock_page(page); + folio_unlock(folio); out: hugetlb_vma_unlock_read(vma); mutex_unlock(&hugetlb_fault_mutex_table[hash]); @@ -5945,11 +5946,11 @@ out: backout: spin_unlock(ptl); backout_unlocked: - if (new_page && !new_pagecache_page) - restore_reserve_on_error(h, vma, haddr, page); + if (new_folio && !new_pagecache_folio) + restore_reserve_on_error(h, vma, haddr, &folio->page); - unlock_page(page); - put_page(page); + folio_unlock(folio); + folio_put(folio); goto out; } @@ -6173,16 +6174,16 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, pte_t _dst_pte; spinlock_t *ptl; int ret = -ENOMEM; - struct page *page; + struct folio *folio; int writable; - bool page_in_pagecache = false; + bool folio_in_pagecache = false; if (is_continue) { ret = -EFAULT; - page = find_lock_page(mapping, idx); - if (!page) + folio = filemap_lock_folio(mapping, idx); + if (!folio) goto out; - page_in_pagecache = true; + folio_in_pagecache = true; } else if (!*pagep) { /* If a page already exists, then it's UFFDIO_COPY for * a non-missing case. Return -EEXIST. @@ -6193,34 +6194,34 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, goto out; } - page = alloc_huge_page(dst_vma, dst_addr, 0); - if (IS_ERR(page)) { + folio = alloc_hugetlb_folio(dst_vma, dst_addr, 0); + if (IS_ERR(folio)) { ret = -ENOMEM; goto out; } - ret = copy_huge_page_from_user(page, + ret = copy_huge_page_from_user(&folio->page, (const void __user *) src_addr, pages_per_huge_page(h), false); /* fallback to copy_from_user outside mmap_lock */ if (unlikely(ret)) { ret = -ENOENT; - /* Free the allocated page which may have + /* Free the allocated folio which may have * consumed a reservation. */ - restore_reserve_on_error(h, dst_vma, dst_addr, page); - put_page(page); + restore_reserve_on_error(h, dst_vma, dst_addr, &folio->page); + folio_put(folio); - /* Allocate a temporary page to hold the copied + /* Allocate a temporary folio to hold the copied * contents. */ - page = alloc_huge_page_vma(h, dst_vma, dst_addr); - if (!page) { + folio = alloc_hugetlb_folio_vma(h, dst_vma, dst_addr); + if (!folio) { ret = -ENOMEM; goto out; } - *pagep = page; + *pagep = &folio->page; /* Set the outparam pagep and return to the caller to * copy the contents outside the lock. Don't free the * page. @@ -6236,25 +6237,25 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, goto out; } - page = alloc_huge_page(dst_vma, dst_addr, 0); - if (IS_ERR(page)) { + folio = alloc_hugetlb_folio(dst_vma, dst_addr, 0); + if (IS_ERR(folio)) { put_page(*pagep); ret = -ENOMEM; *pagep = NULL; goto out; } - copy_user_huge_page(page, *pagep, dst_addr, dst_vma, + copy_user_huge_page(&folio->page, *pagep, dst_addr, dst_vma, pages_per_huge_page(h)); put_page(*pagep); *pagep = NULL; } /* - * The memory barrier inside __SetPageUptodate makes sure that + * The memory barrier inside __folio_mark_uptodate makes sure that * preceding stores to the page contents become visible before * the set_pte_at() write. */ - __SetPageUptodate(page); + __folio_mark_uptodate(folio); /* Add shared, newly allocated pages to the page cache. */ if (vm_shared && !is_continue) { @@ -6269,16 +6270,16 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, * hugetlb_fault_mutex_table that here must be hold by * the caller. */ - ret = hugetlb_add_to_page_cache(page, mapping, idx); + ret = hugetlb_add_to_page_cache(&folio->page, mapping, idx); if (ret) goto out_release_nounlock; - page_in_pagecache = true; + folio_in_pagecache = true; } ptl = huge_pte_lock(h, dst_mm, dst_pte); ret = -EIO; - if (PageHWPoison(page)) + if (folio_test_hwpoison(folio)) goto out_release_unlock; /* @@ -6290,10 +6291,10 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, if (!huge_pte_none_mostly(huge_ptep_get(dst_pte))) goto out_release_unlock; - if (page_in_pagecache) - page_dup_file_rmap(page, true); + if (folio_in_pagecache) + page_dup_file_rmap(&folio->page, true); else - hugepage_add_new_anon_rmap(page, dst_vma, dst_addr); + hugepage_add_new_anon_rmap(folio, dst_vma, dst_addr); /* * For either: (1) CONTINUE on a non-shared VMA, or (2) UFFDIO_COPY @@ -6304,7 +6305,7 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, else writable = dst_vma->vm_flags & VM_WRITE; - _dst_pte = make_huge_pte(dst_vma, page, writable); + _dst_pte = make_huge_pte(dst_vma, &folio->page, writable); /* * Always mark UFFDIO_COPY page dirty; note that this may not be * extremely important for hugetlbfs for now since swapping is not @@ -6326,20 +6327,20 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, spin_unlock(ptl); if (!is_continue) - SetHPageMigratable(page); + folio_set_hugetlb_migratable(folio); if (vm_shared || is_continue) - unlock_page(page); + folio_unlock(folio); ret = 0; out: return ret; out_release_unlock: spin_unlock(ptl); if (vm_shared || is_continue) - unlock_page(page); + folio_unlock(folio); out_release_nounlock: - if (!page_in_pagecache) - restore_reserve_on_error(h, dst_vma, dst_addr, page); - put_page(page); + if (!folio_in_pagecache) + restore_reserve_on_error(h, dst_vma, dst_addr, &folio->page); + folio_put(folio); goto out; } #endif /* CONFIG_USERFAULTFD */ @@ -6871,7 +6872,7 @@ bool hugetlb_reserve_pages(struct inode *inode, /* * pages in this range were added to the reserve * map between region_chg and region_add. This - * indicates a race with alloc_huge_page. Adjust + * indicates a race with alloc_hugetlb_folio. Adjust * the subpool and reserve counts modified above * based on the difference. */ diff --git a/mm/mempolicy.c b/mm/mempolicy.c index fc034b070645..7686f40c9750 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1210,9 +1210,11 @@ static struct page *new_page(struct page *page, unsigned long start) break; } - if (folio_test_hugetlb(src)) - return alloc_huge_page_vma(page_hstate(&src->page), + if (folio_test_hugetlb(src)) { + dst = alloc_hugetlb_folio_vma(folio_hstate(src), vma, address); + return &dst->page; + } if (folio_test_large(src)) gfp = GFP_TRANSHUGE; diff --git a/mm/rmap.c b/mm/rmap.c index 86fccc2b9fc9..8287f2cc327d 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -2534,15 +2534,13 @@ void hugepage_add_anon_rmap(struct page *page, struct vm_area_struct *vma, !!(flags & RMAP_EXCLUSIVE)); } -void hugepage_add_new_anon_rmap(struct page *page, +void hugepage_add_new_anon_rmap(struct folio *folio, struct vm_area_struct *vma, unsigned long address) { - struct folio *folio = page_folio(page); - BUG_ON(address < vma->vm_start || address >= vma->vm_end); /* increment count (starts at -1) */ atomic_set(&folio->_entire_mapcount, 0); folio_clear_hugetlb_restore_reserve(folio); - __page_set_anon_rmap(folio, page, vma, address, 1); + __page_set_anon_rmap(folio, &folio->page, vma, address, 1); } #endif /* CONFIG_HUGETLB_PAGE */ -- cgit v1.2.3 From d2d7bb44bfbd29200426ba17741550d36e081f91 Mon Sep 17 00:00:00 2001 From: Sidhartha Kumar Date: Wed, 25 Jan 2023 09:05:34 -0800 Subject: mm/hugetlb: convert restore_reserve_on_error to take in a folio Every caller of restore_reserve_on_error() is now passing in &folio->page, change the function to take in a folio directly and clean up the call sites. Link: https://lkml.kernel.org/r/20230125170537.96973-6-sidhartha.kumar@oracle.com Signed-off-by: Sidhartha Kumar Cc: Gerald Schaefer Cc: John Hubbard Cc: Matthew Wilcox Cc: Mike Kravetz Cc: Muchun Song Signed-off-by: Andrew Morton --- fs/hugetlbfs/inode.c | 2 +- include/linux/hugetlb.h | 2 +- mm/hugetlb.c | 21 ++++++++++----------- 3 files changed, 12 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index f89e12106e8a..c736947e73da 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -873,7 +873,7 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset, __folio_mark_uptodate(folio); error = hugetlb_add_to_page_cache(&folio->page, mapping, index); if (unlikely(error)) { - restore_reserve_on_error(h, &pseudo_vma, addr, &folio->page); + restore_reserve_on_error(h, &pseudo_vma, addr, folio); folio_put(folio); mutex_unlock(&hugetlb_fault_mutex_table[hash]); goto out; diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 6408f85e5754..20ceaaea1697 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -726,7 +726,7 @@ struct folio *alloc_hugetlb_folio_vma(struct hstate *h, struct vm_area_struct *v int hugetlb_add_to_page_cache(struct page *page, struct address_space *mapping, pgoff_t idx); void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma, - unsigned long address, struct page *page); + unsigned long address, struct folio *folio); /* arch callback */ int __init __alloc_bootmem_huge_page(struct hstate *h, int nid); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index ea8d4611779b..1f6270c586c0 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2802,9 +2802,9 @@ static long vma_del_reservation(struct hstate *h, * and the hugetlb mutex should remain held when calling this routine. * * It handles two specific cases: - * 1) A reservation was in place and the page consumed the reservation. - * HPageRestoreReserve is set in the page. - * 2) No reservation was in place for the page, so HPageRestoreReserve is + * 1) A reservation was in place and the folio consumed the reservation. + * hugetlb_restore_reserve is set in the folio. + * 2) No reservation was in place for the page, so hugetlb_restore_reserve is * not set. However, alloc_hugetlb_folio always updates the reserve map. * * In case 1, free_huge_page later in the error path will increment the @@ -2817,9 +2817,8 @@ static long vma_del_reservation(struct hstate *h, * In case 2, simply undo reserve map modifications done by alloc_hugetlb_folio. */ void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma, - unsigned long address, struct page *page) + unsigned long address, struct folio *folio) { - struct folio *folio = page_folio(page); long rc = vma_needs_reservation(h, vma, address); if (folio_test_hugetlb_restore_reserve(folio)) { @@ -5102,7 +5101,7 @@ again: entry = huge_ptep_get(src_pte); if (!pte_same(src_pte_old, entry)) { restore_reserve_on_error(h, dst_vma, addr, - &new_folio->page); + new_folio); folio_put(new_folio); /* huge_ptep of dst_pte won't change as in child */ goto again; @@ -5634,7 +5633,7 @@ out_release_all: * unshare) */ if (new_folio != page_folio(old_page)) - restore_reserve_on_error(h, vma, haddr, &new_folio->page); + restore_reserve_on_error(h, vma, haddr, new_folio); folio_put(new_folio); out_release_old: put_page(old_page); @@ -5846,7 +5845,7 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, * to the page cache. So it's safe to call * restore_reserve_on_error() here. */ - restore_reserve_on_error(h, vma, haddr, &folio->page); + restore_reserve_on_error(h, vma, haddr, folio); folio_put(folio); goto out; } @@ -5947,7 +5946,7 @@ backout: spin_unlock(ptl); backout_unlocked: if (new_folio && !new_pagecache_folio) - restore_reserve_on_error(h, vma, haddr, &folio->page); + restore_reserve_on_error(h, vma, haddr, folio); folio_unlock(folio); folio_put(folio); @@ -6210,7 +6209,7 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, /* Free the allocated folio which may have * consumed a reservation. */ - restore_reserve_on_error(h, dst_vma, dst_addr, &folio->page); + restore_reserve_on_error(h, dst_vma, dst_addr, folio); folio_put(folio); /* Allocate a temporary folio to hold the copied @@ -6339,7 +6338,7 @@ out_release_unlock: folio_unlock(folio); out_release_nounlock: if (!folio_in_pagecache) - restore_reserve_on_error(h, dst_vma, dst_addr, &folio->page); + restore_reserve_on_error(h, dst_vma, dst_addr, folio); folio_put(folio); goto out; } -- cgit v1.2.3 From 9b91c0e277a3dbb165c2e4301be7a231dc2f76f7 Mon Sep 17 00:00:00 2001 From: Sidhartha Kumar Date: Wed, 25 Jan 2023 09:05:35 -0800 Subject: mm/hugetlb: convert hugetlb_add_to_page_cache to take in a folio Every caller of hugetlb_add_to_page_cache() is now passing in &folio->page, change the function to take in a folio directly and clean up the call sites. Link: https://lkml.kernel.org/r/20230125170537.96973-7-sidhartha.kumar@oracle.com Signed-off-by: Sidhartha Kumar Cc: Gerald Schaefer Cc: John Hubbard Cc: Matthew Wilcox Cc: Mike Kravetz Cc: Muchun Song Signed-off-by: Andrew Morton --- fs/hugetlbfs/inode.c | 2 +- include/linux/hugetlb.h | 2 +- mm/hugetlb.c | 9 ++++----- 3 files changed, 6 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index c736947e73da..cfd09f95551b 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -871,7 +871,7 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset, } clear_huge_page(&folio->page, addr, pages_per_huge_page(h)); __folio_mark_uptodate(folio); - error = hugetlb_add_to_page_cache(&folio->page, mapping, index); + error = hugetlb_add_to_page_cache(folio, mapping, index); if (unlikely(error)) { restore_reserve_on_error(h, &pseudo_vma, addr, folio); folio_put(folio); diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 20ceaaea1697..df6dd624ccfe 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -723,7 +723,7 @@ struct folio *alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid, nodemask_t *nmask, gfp_t gfp_mask); struct folio *alloc_hugetlb_folio_vma(struct hstate *h, struct vm_area_struct *vma, unsigned long address); -int hugetlb_add_to_page_cache(struct page *page, struct address_space *mapping, +int hugetlb_add_to_page_cache(struct folio *folio, struct address_space *mapping, pgoff_t idx); void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma, unsigned long address, struct folio *folio); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 1f6270c586c0..de1f73e5e200 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5662,10 +5662,9 @@ static bool hugetlbfs_pagecache_present(struct hstate *h, return present; } -int hugetlb_add_to_page_cache(struct page *page, struct address_space *mapping, +int hugetlb_add_to_page_cache(struct folio *folio, struct address_space *mapping, pgoff_t idx) { - struct folio *folio = page_folio(page); struct inode *inode = mapping->host; struct hstate *h = hstate_inode(inode); int err; @@ -5677,7 +5676,7 @@ int hugetlb_add_to_page_cache(struct page *page, struct address_space *mapping, __folio_clear_locked(folio); return err; } - ClearHPageRestoreReserve(page); + folio_clear_hugetlb_restore_reserve(folio); /* * mark folio dirty so that it will not be removed from cache/file @@ -5836,7 +5835,7 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, new_folio = true; if (vma->vm_flags & VM_MAYSHARE) { - int err = hugetlb_add_to_page_cache(&folio->page, mapping, idx); + int err = hugetlb_add_to_page_cache(folio, mapping, idx); if (err) { /* * err can't be -EEXIST which implies someone @@ -6269,7 +6268,7 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, * hugetlb_fault_mutex_table that here must be hold by * the caller. */ - ret = hugetlb_add_to_page_cache(&folio->page, mapping, idx); + ret = hugetlb_add_to_page_cache(folio, mapping, idx); if (ret) goto out_release_nounlock; folio_in_pagecache = true; -- cgit v1.2.3 From fa4e3f5ffa5e6e22f751d289c9afa502dda30b8d Mon Sep 17 00:00:00 2001 From: Vishal Moola (Oracle) Date: Mon, 30 Jan 2023 12:18:28 -0800 Subject: mm: add folio_estimated_sharers() Patch series "Convert various mempolicy.c functions to use folios", v4. This patch series converts migrate_page_add() and queue_pages_required() to migrate_folio_add() and queue_page_required(). It also converts the callers of the functions to use folios as well, and introduces a helper function to estimate the number of sharers of a folio. This patch (of 6): folio_estimated_sharers() takes in a folio and returns the precise number of times the first subpage of the folio is mapped. This function aims to provide an estimate for the number of sharers of a folio. This is necessary for folio conversions where we care about the number of processes that share a folio, but don't necessarily want to check every single page within that folio. This is in contrast to folio_mapcount() which calculates the total number of the times a folio and all its subpages are mapped. Link: https://lkml.kernel.org/r/20230130201833.27042-1-vishal.moola@gmail.com Link: https://lkml.kernel.org/r/20230130201833.27042-2-vishal.moola@gmail.com Signed-off-by: Vishal Moola (Oracle) Reviewed-by: Yin Fengwei Acked-by: David Hildenbrand Cc: Jane Chu Signed-off-by: Andrew Morton --- include/linux/mm.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 9454b7eb055b..89c118ad4a44 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1916,6 +1916,24 @@ static inline size_t folio_size(struct folio *folio) return PAGE_SIZE << folio_order(folio); } +/** + * folio_estimated_sharers - Estimate the number of sharers of a folio. + * @folio: The folio. + * + * folio_estimated_sharers() aims to serve as a function to efficiently + * estimate the number of processes sharing a folio. This is done by + * looking at the precise mapcount of the first subpage in the folio, and + * assuming the other subpages are the same. This may not be true for large + * folios. If you want exact mapcounts for exact calculations, look at + * page_mapcount() or folio_total_mapcount(). + * + * Return: The estimated number of processes sharing a folio. + */ +static inline int folio_estimated_sharers(struct folio *folio) +{ + return page_mapcount(folio_page(folio, 0)); +} + #ifndef HAVE_ARCH_MAKE_PAGE_ACCESSIBLE static inline int arch_make_page_accessible(struct page *page) { -- cgit v1.2.3 From 3c1ea2c729ef8ef07bcb80d01ab2ead45b3406dd Mon Sep 17 00:00:00 2001 From: Vishal Moola (Oracle) Date: Mon, 30 Jan 2023 13:43:49 -0800 Subject: mm: add folio_get_nontail_page() Patch series "Convert a couple migrate functions to use folios", v2. This patchset introduces folio_movable_ops() and converts 3 functions in mm/migrate.c to use folios. It also introduces folio_get_nontail_page() for folio conversions which may want to distinguish between head and tail pages. This patch (of 4): folio_get_nontail_page() returns the folio associated with a head page. This is necessary for folio conversions where the behavior of that function differs between head pages and tail pages. Link: https://lkml.kernel.org/r/20230130214352.40538-1-vishal.moola@gmail.com Link: https://lkml.kernel.org/r/20230130214352.40538-2-vishal.moola@gmail.com Signed-off-by: Vishal Moola (Oracle) Cc: Matthew Wilcox Signed-off-by: Andrew Morton --- include/linux/mm.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 89c118ad4a44..2992a2d55aee 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -892,6 +892,13 @@ static inline bool get_page_unless_zero(struct page *page) return page_ref_add_unless(page, 1, 0); } +static inline struct folio *folio_get_nontail_page(struct page *page) +{ + if (unlikely(!get_page_unless_zero(page))) + return NULL; + return (struct folio *)page; +} + extern int page_is_ram(unsigned long pfn); enum { -- cgit v1.2.3 From da707a6d184a8a6ef0b756c3ba49888fec223793 Mon Sep 17 00:00:00 2001 From: Vishal Moola (Oracle) Date: Mon, 30 Jan 2023 13:43:50 -0800 Subject: mm/migrate: add folio_movable_ops() folio_movable_ops() does the same as page_movable_ops() except uses folios instead of pages. This function will help make folio conversions in migrate.c more readable. Link: https://lkml.kernel.org/r/20230130214352.40538-3-vishal.moola@gmail.com Signed-off-by: Vishal Moola (Oracle) Cc: Matthew Wilcox Signed-off-by: Andrew Morton --- include/linux/migrate.h | 9 +++++++++ mm/migrate.c | 2 +- 2 files changed, 10 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 3ef77f52a4f0..bdff950a8bb4 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -122,6 +122,15 @@ static inline bool folio_test_movable(struct folio *folio) return PageMovable(&folio->page); } +static inline +const struct movable_operations *folio_movable_ops(struct folio *folio) +{ + VM_BUG_ON(!__folio_test_movable(folio)); + + return (const struct movable_operations *) + ((unsigned long)folio->mapping - PAGE_MAPPING_MOVABLE); +} + static inline const struct movable_operations *page_movable_ops(struct page *page) { diff --git a/mm/migrate.c b/mm/migrate.c index c09872cf41b7..d2b1167329b9 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -990,7 +990,7 @@ static int move_to_new_folio(struct folio *dst, struct folio *src, goto out; } - mops = page_movable_ops(&src->page); + mops = folio_movable_ops(src); rc = mops->migrate_page(&dst->page, &src->page, mode); WARN_ON_ONCE(rc == MIGRATEPAGE_SUCCESS && !folio_test_isolated(src)); -- cgit v1.2.3 From a2b9b123ccac913e9f9b80337d687a2fe786a634 Mon Sep 17 00:00:00 2001 From: Mengyuan Lou Date: Tue, 7 Feb 2023 18:24:19 +0800 Subject: PCI: Add ACS quirk for Wangxun NICs Wangxun has verified there is no peer-to-peer between functions for the below selection of SFxxx, RP1000 and RP2000 NICS. They may be multi-function devices, but the hardware does not advertise ACS capability. Add an ACS quirk for these devices so the functions can be in independent IOMMU groups. Link: https://lore.kernel.org/r/20230207102419.44326-1-mengyuanlou@net-swift.com Signed-off-by: Mengyuan Lou Signed-off-by: Bjorn Helgaas --- drivers/pci/quirks.c | 22 ++++++++++++++++++++++ include/linux/pci_ids.h | 2 ++ 2 files changed, 24 insertions(+) (limited to 'include/linux') diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 20ac67d59034..494fa46f5767 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -4835,6 +4835,26 @@ static int pci_quirk_brcm_acs(struct pci_dev *dev, u16 acs_flags) PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF); } +/* + * Wangxun 10G/1G NICs have no ACS capability, and on multi-function + * devices, peer-to-peer transactions are not be used between the functions. + * So add an ACS quirk for below devices to isolate functions. + * SFxxx 1G NICs(em). + * RP1000/RP2000 10G NICs(sp). + */ +static int pci_quirk_wangxun_nic_acs(struct pci_dev *dev, u16 acs_flags) +{ + switch (dev->device) { + case 0x0100 ... 0x010F: + case 0x1001: + case 0x2001: + return pci_acs_ctrl_enabled(acs_flags, + PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF); + } + + return false; +} + static const struct pci_dev_acs_enabled { u16 vendor; u16 device; @@ -4980,6 +5000,8 @@ static const struct pci_dev_acs_enabled { { PCI_VENDOR_ID_NXP, 0x8d9b, pci_quirk_nxp_rp_acs }, /* Zhaoxin Root/Downstream Ports */ { PCI_VENDOR_ID_ZHAOXIN, PCI_ANY_ID, pci_quirk_zhaoxin_pcie_ports_acs }, + /* Wangxun nics */ + { PCI_VENDOR_ID_WANGXUN, PCI_ANY_ID, pci_quirk_wangxun_nic_acs }, { 0 } }; diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index b362d90eb9b0..bc8f484cdcf3 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -3012,6 +3012,8 @@ #define PCI_DEVICE_ID_INTEL_VMD_9A0B 0x9a0b #define PCI_DEVICE_ID_INTEL_S21152BB 0xb152 +#define PCI_VENDOR_ID_WANGXUN 0x8088 + #define PCI_VENDOR_ID_SCALEMP 0x8686 #define PCI_DEVICE_ID_SCALEMP_VSMP_CTL 0x1010 -- cgit v1.2.3 From f57aec443c24d2e8e1f3b5b4856aea12ddda4254 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Mon, 13 Feb 2023 17:01:05 -0800 Subject: cxl/pmem: Fix nvdimm registration races A loop of the form: while true; do modprobe cxl_pci; modprobe -r cxl_pci; done ...fails with the following crash signature: BUG: kernel NULL pointer dereference, address: 0000000000000040 [..] RIP: 0010:cxl_internal_send_cmd+0x5/0xb0 [cxl_core] [..] Call Trace: cxl_pmem_ctl+0x121/0x240 [cxl_pmem] nvdimm_get_config_data+0xd6/0x1a0 [libnvdimm] nd_label_data_init+0x135/0x7e0 [libnvdimm] nvdimm_probe+0xd6/0x1c0 [libnvdimm] nvdimm_bus_probe+0x7a/0x1e0 [libnvdimm] really_probe+0xde/0x380 __driver_probe_device+0x78/0x170 driver_probe_device+0x1f/0x90 __device_attach_driver+0x85/0x110 bus_for_each_drv+0x7d/0xc0 __device_attach+0xb4/0x1e0 bus_probe_device+0x9f/0xc0 device_add+0x445/0x9c0 nd_async_device_register+0xe/0x40 [libnvdimm] async_run_entry_fn+0x30/0x130 ...namely that the bottom half of async nvdimm device registration runs after the CXL has already torn down the context that cxl_pmem_ctl() needs. Unlike the ACPI NFIT case that benefits from launching multiple nvdimm device registrations in parallel from those listed in the table, CXL is already marked PROBE_PREFER_ASYNCHRONOUS. So provide for a synchronous registration path to preclude this scenario. Fixes: 21083f51521f ("cxl/pmem: Register 'pmem' / cxl_nvdimm devices") Cc: Reported-by: Dave Jiang Signed-off-by: Dan Williams --- drivers/cxl/pmem.c | 1 + drivers/nvdimm/bus.c | 19 ++++++++++++++++--- drivers/nvdimm/dimm_devs.c | 5 ++++- drivers/nvdimm/nd-core.h | 1 + include/linux/libnvdimm.h | 3 +++ 5 files changed, 25 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/cxl/pmem.c b/drivers/cxl/pmem.c index 08bbbac9a6d0..71cfa1fdf902 100644 --- a/drivers/cxl/pmem.c +++ b/drivers/cxl/pmem.c @@ -76,6 +76,7 @@ static int cxl_nvdimm_probe(struct device *dev) return rc; set_bit(NDD_LABELING, &flags); + set_bit(NDD_REGISTER_SYNC, &flags); set_bit(ND_CMD_GET_CONFIG_SIZE, &cmd_mask); set_bit(ND_CMD_GET_CONFIG_DATA, &cmd_mask); set_bit(ND_CMD_SET_CONFIG_DATA, &cmd_mask); diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c index b38d0355b0ac..5ad49056921b 100644 --- a/drivers/nvdimm/bus.c +++ b/drivers/nvdimm/bus.c @@ -508,7 +508,7 @@ static void nd_async_device_unregister(void *d, async_cookie_t cookie) put_device(dev); } -void nd_device_register(struct device *dev) +static void __nd_device_register(struct device *dev, bool sync) { if (!dev) return; @@ -531,11 +531,24 @@ void nd_device_register(struct device *dev) } get_device(dev); - async_schedule_dev_domain(nd_async_device_register, dev, - &nd_async_domain); + if (sync) + nd_async_device_register(dev, 0); + else + async_schedule_dev_domain(nd_async_device_register, dev, + &nd_async_domain); +} + +void nd_device_register(struct device *dev) +{ + __nd_device_register(dev, false); } EXPORT_SYMBOL(nd_device_register); +void nd_device_register_sync(struct device *dev) +{ + __nd_device_register(dev, true); +} + void nd_device_unregister(struct device *dev, enum nd_async_mode mode) { bool killed; diff --git a/drivers/nvdimm/dimm_devs.c b/drivers/nvdimm/dimm_devs.c index 1fc081dcf631..6d3b03a9fa02 100644 --- a/drivers/nvdimm/dimm_devs.c +++ b/drivers/nvdimm/dimm_devs.c @@ -624,7 +624,10 @@ struct nvdimm *__nvdimm_create(struct nvdimm_bus *nvdimm_bus, nvdimm->sec.ext_flags = nvdimm_security_flags(nvdimm, NVDIMM_MASTER); device_initialize(dev); lockdep_set_class(&dev->mutex, &nvdimm_key); - nd_device_register(dev); + if (test_bit(NDD_REGISTER_SYNC, &flags)) + nd_device_register_sync(dev); + else + nd_device_register(dev); return nvdimm; } diff --git a/drivers/nvdimm/nd-core.h b/drivers/nvdimm/nd-core.h index cc86ee09d7c0..845408f10655 100644 --- a/drivers/nvdimm/nd-core.h +++ b/drivers/nvdimm/nd-core.h @@ -107,6 +107,7 @@ int nvdimm_bus_create_ndctl(struct nvdimm_bus *nvdimm_bus); void nvdimm_bus_destroy_ndctl(struct nvdimm_bus *nvdimm_bus); void nd_synchronize(void); void nd_device_register(struct device *dev); +void nd_device_register_sync(struct device *dev); struct nd_label_id; char *nd_label_gen_id(struct nd_label_id *label_id, const uuid_t *uuid, u32 flags); diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index af38252ad704..e772aae71843 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -41,6 +41,9 @@ enum { */ NDD_INCOHERENT = 7, + /* dimm provider wants synchronous registration by __nvdimm_create() */ + NDD_REGISTER_SYNC = 8, + /* need to set a limit somewhere, but yes, this is likely overkill */ ND_IOCTL_MAX_BUFLEN = SZ_4M, ND_CMD_MAX_ELEM = 5, -- cgit v1.2.3 From ab9fdd41d970c38ddc0fd59e5f8f37e8d966d454 Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Mon, 13 Feb 2023 07:52:11 -0800 Subject: rpmsg: glink: smem: Wrap driver context The Glink SMEM driver allocates a struct device and hangs two devres-allocated pipe objects thereon. To facilitate the move of interrupt and mailbox handling to the driver, introduce a wrapper object capturing the device, glink reference and remote processor id. The type of the remoteproc reference is updated, as these are specifically targeting the SMEM implementation. Signed-off-by: Bjorn Andersson Reviewed-by: Chris Lew Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230213155215.1237059-3-quic_bjorande@quicinc.com --- drivers/remoteproc/qcom_common.h | 3 ++- drivers/rpmsg/qcom_glink_smem.c | 43 ++++++++++++++++++++++++++++++---------- include/linux/rpmsg/qcom_glink.h | 12 +++++------ 3 files changed, 40 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/drivers/remoteproc/qcom_common.h b/drivers/remoteproc/qcom_common.h index c35adf730be0..2747c7d9ba44 100644 --- a/drivers/remoteproc/qcom_common.h +++ b/drivers/remoteproc/qcom_common.h @@ -6,6 +6,7 @@ #include "remoteproc_internal.h" #include +struct qcom_glink_smem; struct qcom_sysmon; struct qcom_rproc_glink { @@ -15,7 +16,7 @@ struct qcom_rproc_glink { struct device *dev; struct device_node *node; - struct qcom_glink *edge; + struct qcom_glink_smem *edge; }; struct qcom_rproc_subdev { diff --git a/drivers/rpmsg/qcom_glink_smem.c b/drivers/rpmsg/qcom_glink_smem.c index 579bc4443f6d..a9c477df4d68 100644 --- a/drivers/rpmsg/qcom_glink_smem.c +++ b/drivers/rpmsg/qcom_glink_smem.c @@ -33,6 +33,14 @@ #define SMEM_GLINK_NATIVE_XPRT_FIFO_0 479 #define SMEM_GLINK_NATIVE_XPRT_FIFO_1 480 +struct qcom_glink_smem { + struct device dev; + + struct qcom_glink *glink; + + u32 remote_pid; +}; + struct glink_smem_pipe { struct qcom_glink_pipe native; @@ -41,7 +49,7 @@ struct glink_smem_pipe { void *fifo; - int remote_pid; + struct qcom_glink_smem *smem; }; #define to_smem_pipe(p) container_of(p, struct glink_smem_pipe, native) @@ -49,13 +57,14 @@ struct glink_smem_pipe { static size_t glink_smem_rx_avail(struct qcom_glink_pipe *np) { struct glink_smem_pipe *pipe = to_smem_pipe(np); + struct qcom_glink_smem *smem = pipe->smem; size_t len; void *fifo; u32 head; u32 tail; if (!pipe->fifo) { - fifo = qcom_smem_get(pipe->remote_pid, + fifo = qcom_smem_get(smem->remote_pid, SMEM_GLINK_NATIVE_XPRT_FIFO_1, &len); if (IS_ERR(fifo)) { pr_err("failed to acquire RX fifo handle: %ld\n", @@ -179,14 +188,17 @@ static void glink_smem_tx_write(struct qcom_glink_pipe *glink_pipe, static void qcom_glink_smem_release(struct device *dev) { - kfree(dev); + struct qcom_glink_smem *smem = container_of(dev, struct qcom_glink_smem, dev); + + kfree(smem); } -struct qcom_glink *qcom_glink_smem_register(struct device *parent, - struct device_node *node) +struct qcom_glink_smem *qcom_glink_smem_register(struct device *parent, + struct device_node *node) { struct glink_smem_pipe *rx_pipe; struct glink_smem_pipe *tx_pipe; + struct qcom_glink_smem *smem; struct qcom_glink *glink; struct device *dev; u32 remote_pid; @@ -194,10 +206,12 @@ struct qcom_glink *qcom_glink_smem_register(struct device *parent, size_t size; int ret; - dev = kzalloc(sizeof(*dev), GFP_KERNEL); - if (!dev) + smem = kzalloc(sizeof(*smem), GFP_KERNEL); + if (!smem) return ERR_PTR(-ENOMEM); + dev = &smem->dev; + dev->parent = parent; dev->of_node = node; dev->release = qcom_glink_smem_release; @@ -216,6 +230,8 @@ struct qcom_glink *qcom_glink_smem_register(struct device *parent, goto err_put_dev; } + smem->remote_pid = remote_pid; + rx_pipe = devm_kzalloc(dev, sizeof(*rx_pipe), GFP_KERNEL); tx_pipe = devm_kzalloc(dev, sizeof(*tx_pipe), GFP_KERNEL); if (!rx_pipe || !tx_pipe) { @@ -264,14 +280,14 @@ struct qcom_glink *qcom_glink_smem_register(struct device *parent, goto err_put_dev; } + rx_pipe->smem = smem; rx_pipe->native.avail = glink_smem_rx_avail; rx_pipe->native.peak = glink_smem_rx_peak; rx_pipe->native.advance = glink_smem_rx_advance; - rx_pipe->remote_pid = remote_pid; + tx_pipe->smem = smem; tx_pipe->native.avail = glink_smem_tx_avail; tx_pipe->native.write = glink_smem_tx_write; - tx_pipe->remote_pid = remote_pid; *rx_pipe->tail = 0; *tx_pipe->head = 0; @@ -285,7 +301,10 @@ struct qcom_glink *qcom_glink_smem_register(struct device *parent, goto err_put_dev; } - return glink; + smem->glink = glink; + + return smem; + err_put_dev: device_unregister(dev); @@ -294,8 +313,10 @@ err_put_dev: } EXPORT_SYMBOL_GPL(qcom_glink_smem_register); -void qcom_glink_smem_unregister(struct qcom_glink *glink) +void qcom_glink_smem_unregister(struct qcom_glink_smem *smem) { + struct qcom_glink *glink = smem->glink; + qcom_glink_native_remove(glink); qcom_glink_native_unregister(glink); } diff --git a/include/linux/rpmsg/qcom_glink.h b/include/linux/rpmsg/qcom_glink.h index 22fc3a69b683..bfbd48f435fa 100644 --- a/include/linux/rpmsg/qcom_glink.h +++ b/include/linux/rpmsg/qcom_glink.h @@ -5,7 +5,7 @@ #include -struct qcom_glink; +struct qcom_glink_smem; #if IS_ENABLED(CONFIG_RPMSG_QCOM_GLINK) void qcom_glink_ssr_notify(const char *ssr_name); @@ -15,20 +15,20 @@ static inline void qcom_glink_ssr_notify(const char *ssr_name) {} #if IS_ENABLED(CONFIG_RPMSG_QCOM_GLINK_SMEM) -struct qcom_glink *qcom_glink_smem_register(struct device *parent, - struct device_node *node); -void qcom_glink_smem_unregister(struct qcom_glink *glink); +struct qcom_glink_smem *qcom_glink_smem_register(struct device *parent, + struct device_node *node); +void qcom_glink_smem_unregister(struct qcom_glink_smem *glink); #else -static inline struct qcom_glink * +static inline struct qcom_glink_smem * qcom_glink_smem_register(struct device *parent, struct device_node *node) { return NULL; } -static inline void qcom_glink_smem_unregister(struct qcom_glink *glink) {} +static inline void qcom_glink_smem_unregister(struct qcom_glink_smem *glink) {} #endif #endif -- cgit v1.2.3 From 35c5db0ec49f073e6a2d5236b5fcfb0a134a215a Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 19 Jan 2023 16:33:35 -0500 Subject: NFS: Add basic functionality for tracking folios in struct nfs_page Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- fs/nfs/pagelist.c | 5 +++-- include/linux/nfs_page.h | 38 +++++++++++++++++++++++++++++++++++++- 2 files changed, 40 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 369e4553399a..315e58d73718 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -500,9 +500,10 @@ nfs_create_subreq(struct nfs_page *req, { struct nfs_page *last; struct nfs_page *ret; + struct page *page = nfs_page_to_page(req, pgbase); - ret = __nfs_create_request(req->wb_lock_context, req->wb_page, - pgbase, offset, count); + ret = __nfs_create_request(req->wb_lock_context, page, pgbase, offset, + count); if (!IS_ERR(ret)) { /* find the last request */ for (last = req->wb_head; diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index ba7e2e4b0926..d2ddc9a594c5 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -25,6 +25,7 @@ enum { PG_BUSY = 0, /* nfs_{un}lock_request */ PG_MAPPED, /* page private set for buffered io */ + PG_FOLIO, /* Tracking a folio (unset for O_DIRECT) */ PG_CLEAN, /* write succeeded */ PG_COMMIT_TO_DS, /* used by pnfs layouts */ PG_INODE_REF, /* extra ref held by inode when in writeback */ @@ -41,7 +42,10 @@ enum { struct nfs_inode; struct nfs_page { struct list_head wb_list; /* Defines state of page: */ - struct page *wb_page; /* page to read in/write out */ + union { + struct page *wb_page; /* page to read in/write out */ + struct folio *wb_folio; + }; struct nfs_lock_context *wb_lock_context; /* lock context info */ pgoff_t wb_index; /* Offset >> PAGE_SHIFT */ unsigned int wb_offset, /* Offset & ~PAGE_MASK */ @@ -153,6 +157,38 @@ extern int nfs_page_set_headlock(struct nfs_page *req); extern void nfs_page_clear_headlock(struct nfs_page *req); extern bool nfs_async_iocounter_wait(struct rpc_task *, struct nfs_lock_context *); +/** + * nfs_page_to_folio - Retrieve a struct folio for the request + * @req: pointer to a struct nfs_page + * + * If a folio was assigned to @req, then return it, otherwise return NULL. + */ +static inline struct folio *nfs_page_to_folio(const struct nfs_page *req) +{ + if (test_bit(PG_FOLIO, &req->wb_flags)) + return req->wb_folio; + return NULL; +} + +/** + * nfs_page_to_page - Retrieve a struct page for the request + * @req: pointer to a struct nfs_page + * @pgbase: folio byte offset + * + * Return the page containing the byte that is at offset @pgbase relative + * to the start of the folio. + * Note: The request starts at offset @req->wb_pgbase. + */ +static inline struct page *nfs_page_to_page(const struct nfs_page *req, + size_t pgbase) +{ + struct folio *folio = nfs_page_to_folio(req); + + if (folio == NULL) + return req->wb_page; + return folio_page(folio, pgbase >> PAGE_SHIFT); +} + /* * Lock the page of an asynchronous request */ -- cgit v1.2.3 From 8e0bdc7021f713fdf3b985cda3ce715e41b06698 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 19 Jan 2023 16:33:37 -0500 Subject: NFS: Fix nfs_coalesce_size() to work with folios Use the helper folio_size() where appropriate. Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- fs/nfs/pagelist.c | 28 +++++++++++++++++++--------- include/linux/nfs_page.h | 15 +++++++++++++++ 2 files changed, 34 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 174462722266..16c146ca7ffc 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -1084,6 +1084,24 @@ static bool nfs_match_lock_context(const struct nfs_lock_context *l1, return l1->lockowner == l2->lockowner; } +static bool nfs_page_is_contiguous(const struct nfs_page *prev, + const struct nfs_page *req) +{ + size_t prev_end = prev->wb_pgbase + prev->wb_bytes; + + if (req_offset(req) != req_offset(prev) + prev->wb_bytes) + return false; + if (req->wb_pgbase == 0) + return prev_end == nfs_page_max_length(prev); + if (req->wb_pgbase == prev_end) { + struct folio *folio = nfs_page_to_folio(req); + if (folio) + return folio == nfs_page_to_folio(prev); + return req->wb_page == prev->wb_page; + } + return false; +} + /** * nfs_coalesce_size - test two requests for compatibility * @prev: pointer to nfs_page @@ -1112,16 +1130,8 @@ static unsigned int nfs_coalesce_size(struct nfs_page *prev, !nfs_match_lock_context(req->wb_lock_context, prev->wb_lock_context)) return 0; - if (req_offset(req) != req_offset(prev) + prev->wb_bytes) + if (!nfs_page_is_contiguous(prev, req)) return 0; - if (req->wb_page == prev->wb_page) { - if (req->wb_pgbase != prev->wb_pgbase + prev->wb_bytes) - return 0; - } else { - if (req->wb_pgbase != 0 || - prev->wb_pgbase + prev->wb_bytes != PAGE_SIZE) - return 0; - } } return pgio->pg_ops->pg_test(pgio, prev, req); } diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index d2ddc9a594c5..192071a6e5f6 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -189,6 +189,21 @@ static inline struct page *nfs_page_to_page(const struct nfs_page *req, return folio_page(folio, pgbase >> PAGE_SHIFT); } +/** + * nfs_page_max_length - Retrieve the maximum possible length for a request + * @req: pointer to a struct nfs_page + * + * Returns the maximum possible length of a request + */ +static inline size_t nfs_page_max_length(const struct nfs_page *req) +{ + struct folio *folio = nfs_page_to_folio(req); + + if (folio == NULL) + return PAGE_SIZE; + return folio_size(folio); +} + /* * Lock the page of an asynchronous request */ -- cgit v1.2.3 From 6dd85e83f3f182b56770f8bb6dbed1f0dafb9117 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 19 Jan 2023 16:33:38 -0500 Subject: NFS: Add a helper to convert a struct nfs_page into an inode Replace all the open coded calls to page_file_mapping(req->wb_page)->host. Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- fs/nfs/pagelist.c | 2 +- fs/nfs/write.c | 7 +++---- include/linux/nfs_page.h | 13 +++++++++++++ 3 files changed, 17 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 16c146ca7ffc..4bdb570184f7 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -426,7 +426,7 @@ nfs_page_group_init(struct nfs_page *req, struct nfs_page *prev) * has extra ref from the write/commit path to handle handoff * between write and commit lists. */ if (test_bit(PG_INODE_REF, &prev->wb_head->wb_flags)) { - inode = page_file_mapping(req->wb_page)->host; + inode = nfs_page_to_inode(req); set_bit(PG_INODE_REF, &req->wb_flags); kref_get(&req->wb_kref); atomic_long_inc(&NFS_I(inode)->nrequests); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 80c240e50952..1cbb92824791 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -421,7 +421,7 @@ static void nfs_set_page_writeback(struct page *page) static void nfs_end_page_writeback(struct nfs_page *req) { - struct inode *inode = page_file_mapping(req->wb_page)->host; + struct inode *inode = nfs_page_to_inode(req); struct nfs_server *nfss = NFS_SERVER(inode); bool is_done; @@ -592,8 +592,7 @@ nfs_lock_and_join_requests(struct page *page) static void nfs_write_error(struct nfs_page *req, int error) { - trace_nfs_write_error(page_file_mapping(req->wb_page)->host, req, - error); + trace_nfs_write_error(nfs_page_to_inode(req), req, error); nfs_mapping_set_error(req->wb_page, error); nfs_inode_remove_request(req); nfs_end_page_writeback(req); @@ -1420,7 +1419,7 @@ static void nfs_initiate_write(struct nfs_pgio_header *hdr, */ static void nfs_redirty_request(struct nfs_page *req) { - struct nfs_inode *nfsi = NFS_I(page_file_mapping(req->wb_page)->host); + struct nfs_inode *nfsi = NFS_I(nfs_page_to_inode(req)); /* Bump the transmission count */ req->wb_nio++; diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index 192071a6e5f6..b0b03ec4a209 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -189,6 +189,19 @@ static inline struct page *nfs_page_to_page(const struct nfs_page *req, return folio_page(folio, pgbase >> PAGE_SHIFT); } +/** + * nfs_page_to_inode - Retrieve an inode for the request + * @req: pointer to a struct nfs_page + */ +static inline struct inode *nfs_page_to_inode(const struct nfs_page *req) +{ + struct folio *folio = nfs_page_to_folio(req); + + if (folio == NULL) + return page_file_mapping(req->wb_page)->host; + return folio_file_mapping(folio)->host; +} + /** * nfs_page_max_length - Retrieve the maximum possible length for a request * @req: pointer to a struct nfs_page -- cgit v1.2.3 From 4b27232a6e064f3d779cfa76cd251d6023949d22 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 19 Jan 2023 16:33:40 -0500 Subject: NFS: Add a helper nfs_wb_folio() ...and use it in nfs_launder_folio(). Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- fs/nfs/file.c | 2 +- fs/nfs/write.c | 13 +++++++++++++ include/linux/nfs_fs.h | 1 + 3 files changed, 15 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/fs/nfs/file.c b/fs/nfs/file.c index d8ec889a4b3f..8704bd071d3a 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -469,7 +469,7 @@ static int nfs_launder_folio(struct folio *folio) inode->i_ino, folio_pos(folio)); folio_wait_fscache(folio); - return nfs_wb_page(inode, &folio->page); + return nfs_wb_folio(inode, folio); } static int nfs_swap_activate(struct swap_info_struct *sis, struct file *file, diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 1cbb92824791..c80a57801b2e 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -2106,6 +2106,19 @@ out_error: return ret; } +/** + * nfs_wb_folio - Write back all requests on one page + * @inode: pointer to page + * @folio: pointer to folio + * + * Assumes that the folio has been locked by the caller, and will + * not unlock it. + */ +int nfs_wb_folio(struct inode *inode, struct folio *folio) +{ + return nfs_wb_page(inode, &folio->page); +} + #ifdef CONFIG_MIGRATION int nfs_migrate_folio(struct address_space *mapping, struct folio *dst, struct folio *src, enum migrate_mode mode) diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index d92fdfd2444c..66b5de42f6b8 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -578,6 +578,7 @@ extern int nfs_updatepage(struct file *, struct page *, unsigned int, unsigned */ extern int nfs_sync_inode(struct inode *inode); extern int nfs_wb_all(struct inode *inode); +extern int nfs_wb_folio(struct inode *inode, struct folio *folio); extern int nfs_wb_page(struct inode *inode, struct page *page); int nfs_wb_folio_cancel(struct inode *inode, struct folio *folio); extern int nfs_commit_inode(struct inode *, int); -- cgit v1.2.3 From ab75bff1140733f1b43e81f055acd7d27af7ac05 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 19 Jan 2023 16:33:41 -0500 Subject: NFS: Convert buffered reads to use folios Perform a largely mechanical conversion of references to struct page and page-specific functions to use the folio equivalents. Note that the fscache functionality remains untouched. Instead we just pass in the folio page. This should be OK, as long as we use order 0 folios together with fscache. Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- fs/nfs/internal.h | 18 ++++++++++ fs/nfs/nfstrace.h | 12 +++---- fs/nfs/pagelist.c | 30 +++++++++++++++++ fs/nfs/read.c | 86 +++++++++++++++++++++++------------------------- include/linux/nfs_page.h | 4 +++ 5 files changed, 100 insertions(+), 50 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 6197b165c8c8..529b87336ffa 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -794,6 +794,24 @@ unsigned int nfs_page_length(struct page *page) return 0; } +/* + * Determine the number of bytes of data the page contains + */ +static inline size_t nfs_folio_length(struct folio *folio) +{ + loff_t i_size = i_size_read(folio_file_mapping(folio)->host); + + if (i_size > 0) { + pgoff_t index = folio_index(folio) >> folio_order(folio); + pgoff_t end_index = (i_size - 1) >> folio_shift(folio); + if (index < end_index) + return folio_size(folio); + if (index == end_index) + return offset_in_folio(folio, i_size - 1) + 1; + } + return 0; +} + /* * Convert a umode to a dirent->d_type */ diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h index 642f6921852f..b686b615586e 100644 --- a/fs/nfs/nfstrace.h +++ b/fs/nfs/nfstrace.h @@ -936,10 +936,10 @@ TRACE_EVENT(nfs_sillyrename_unlink, TRACE_EVENT(nfs_aop_readpage, TP_PROTO( const struct inode *inode, - struct page *page + struct folio *folio ), - TP_ARGS(inode, page), + TP_ARGS(inode, folio), TP_STRUCT__entry( __field(dev_t, dev) @@ -956,7 +956,7 @@ TRACE_EVENT(nfs_aop_readpage, __entry->fileid = nfsi->fileid; __entry->fhandle = nfs_fhandle_hash(&nfsi->fh); __entry->version = inode_peek_iversion_raw(inode); - __entry->offset = page_index(page) << PAGE_SHIFT; + __entry->offset = folio_file_pos(folio); ), TP_printk( @@ -971,11 +971,11 @@ TRACE_EVENT(nfs_aop_readpage, TRACE_EVENT(nfs_aop_readpage_done, TP_PROTO( const struct inode *inode, - struct page *page, + struct folio *folio, int ret ), - TP_ARGS(inode, page, ret), + TP_ARGS(inode, folio, ret), TP_STRUCT__entry( __field(dev_t, dev) @@ -993,7 +993,7 @@ TRACE_EVENT(nfs_aop_readpage_done, __entry->fileid = nfsi->fileid; __entry->fhandle = nfs_fhandle_hash(&nfsi->fh); __entry->version = inode_peek_iversion_raw(inode); - __entry->offset = page_index(page) << PAGE_SHIFT; + __entry->offset = folio_file_pos(folio); __entry->ret = ret; ), diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index dd99a5d381b3..7a622263a9fc 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -542,6 +542,36 @@ nfs_create_request(struct nfs_open_context *ctx, struct page *page, return ret; } +/** + * nfs_page_create_from_folio - Create an NFS read/write request. + * @ctx: open context to use + * @folio: folio to write + * @offset: starting offset within the folio for the write + * @count: number of bytes to read/write + * + * The page must be locked by the caller. This makes sure we never + * create two different requests for the same page. + * User should ensure it is safe to sleep in this function. + */ +struct nfs_page *nfs_page_create_from_folio(struct nfs_open_context *ctx, + struct folio *folio, + unsigned int offset, + unsigned int count) +{ + struct nfs_lock_context *l_ctx = nfs_get_lock_context(ctx); + struct nfs_page *ret; + + if (IS_ERR(l_ctx)) + return ERR_CAST(l_ctx); + ret = nfs_page_create(l_ctx, offset, folio_index(folio), offset, count); + if (!IS_ERR(ret)) { + nfs_page_assign_folio(ret, folio); + nfs_page_group_init(ret, NULL); + } + nfs_put_lock_context(l_ctx); + return ret; +} + static struct nfs_page * nfs_create_subreq(struct nfs_page *req, unsigned int pgbase, diff --git a/fs/nfs/read.c b/fs/nfs/read.c index 8ae2c8d1219d..bf4154f9b48c 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -49,12 +49,11 @@ static void nfs_readhdr_free(struct nfs_pgio_header *rhdr) kmem_cache_free(nfs_rdata_cachep, rhdr); } -static -int nfs_return_empty_page(struct page *page) +static int nfs_return_empty_folio(struct folio *folio) { - zero_user(page, 0, PAGE_SIZE); - SetPageUptodate(page); - unlock_page(page); + folio_zero_segment(folio, 0, folio_size(folio)); + folio_mark_uptodate(folio); + folio_unlock(folio); return 0; } @@ -111,18 +110,18 @@ EXPORT_SYMBOL_GPL(nfs_pageio_reset_read_mds); static void nfs_readpage_release(struct nfs_page *req, int error) { struct inode *inode = d_inode(nfs_req_openctx(req)->dentry); - struct page *page = req->wb_page; + struct folio *folio = nfs_page_to_folio(req); dprintk("NFS: read done (%s/%llu %d@%lld)\n", inode->i_sb->s_id, (unsigned long long)NFS_FILEID(inode), req->wb_bytes, (long long)req_offset(req)); if (nfs_error_is_fatal_on_server(error) && error != -ETIMEDOUT) - SetPageError(page); + folio_set_error(folio); if (nfs_page_group_sync_on_bit(req, PG_UNLOCKPAGE)) { - if (PageUptodate(page)) - nfs_fscache_write_page(inode, page); - unlock_page(page); + if (folio_test_uptodate(folio)) + nfs_fscache_write_page(inode, &folio->page); + folio_unlock(folio); } nfs_release_request(req); } @@ -135,7 +134,7 @@ struct nfs_readdesc { static void nfs_page_group_set_uptodate(struct nfs_page *req) { if (nfs_page_group_sync_on_bit(req, PG_UPTODATE)) - SetPageUptodate(req->wb_page); + folio_mark_uptodate(nfs_page_to_folio(req)); } static void nfs_read_completion(struct nfs_pgio_header *hdr) @@ -147,7 +146,7 @@ static void nfs_read_completion(struct nfs_pgio_header *hdr) goto out; while (!list_empty(&hdr->pages)) { struct nfs_page *req = nfs_list_entry(hdr->pages.next); - struct page *page = req->wb_page; + struct folio *folio = nfs_page_to_folio(req); unsigned long start = req->wb_pgbase; unsigned long end = req->wb_pgbase + req->wb_bytes; @@ -157,14 +156,14 @@ static void nfs_read_completion(struct nfs_pgio_header *hdr) if (bytes > hdr->good_bytes) { /* nothing in this request was good, so zero * the full extent of the request */ - zero_user_segment(page, start, end); + folio_zero_segment(folio, start, end); } else if (hdr->good_bytes - bytes < req->wb_bytes) { /* part of this request has good bytes, but * not all. zero the bad bytes */ start += hdr->good_bytes - bytes; WARN_ON(start < req->wb_pgbase); - zero_user_segment(page, start, end); + folio_zero_segment(folio, start, end); } } error = 0; @@ -281,33 +280,34 @@ static void nfs_readpage_result(struct rpc_task *task, nfs_readpage_retry(task, hdr); } -static int -readpage_async_filler(struct nfs_readdesc *desc, struct page *page) +static int readpage_async_filler(struct nfs_readdesc *desc, struct folio *folio) { - struct inode *inode = page_file_mapping(page)->host; - unsigned int rsize = NFS_SERVER(inode)->rsize; + struct inode *inode = folio_file_mapping(folio)->host; + struct nfs_server *server = NFS_SERVER(inode); + size_t fsize = folio_size(folio); + unsigned int rsize = server->rsize; struct nfs_page *new; unsigned int len, aligned_len; int error; - len = nfs_page_length(page); + len = nfs_folio_length(folio); if (len == 0) - return nfs_return_empty_page(page); + return nfs_return_empty_folio(folio); - aligned_len = min_t(unsigned int, ALIGN(len, rsize), PAGE_SIZE); + aligned_len = min_t(unsigned int, ALIGN(len, rsize), fsize); - if (!IS_SYNC(page->mapping->host)) { - error = nfs_fscache_read_page(page->mapping->host, page); + if (!IS_SYNC(inode)) { + error = nfs_fscache_read_page(inode, &folio->page); if (error == 0) goto out_unlock; } - new = nfs_create_request(desc->ctx, page, 0, aligned_len); + new = nfs_page_create_from_folio(desc->ctx, folio, 0, aligned_len); if (IS_ERR(new)) goto out_error; - if (len < PAGE_SIZE) - zero_user_segment(page, len, PAGE_SIZE); + if (len < fsize) + folio_zero_segment(folio, len, fsize); if (!nfs_pageio_add_request(&desc->pgio, new)) { nfs_list_remove_request(new); error = desc->pgio.pg_error; @@ -318,7 +318,7 @@ readpage_async_filler(struct nfs_readdesc *desc, struct page *page) out_error: error = PTR_ERR(new); out_unlock: - unlock_page(page); + folio_unlock(folio); out: return error; } @@ -331,25 +331,24 @@ out: */ int nfs_read_folio(struct file *file, struct folio *folio) { - struct page *page = &folio->page; struct nfs_readdesc desc; - struct inode *inode = page_file_mapping(page)->host; + struct inode *inode = file_inode(file); int ret; - trace_nfs_aop_readpage(inode, page); + trace_nfs_aop_readpage(inode, folio); nfs_inc_stats(inode, NFSIOS_VFSREADPAGE); /* * Try to flush any pending writes to the file.. * - * NOTE! Because we own the page lock, there cannot + * NOTE! Because we own the folio lock, there cannot * be any new pending writes generated at this point - * for this page (other pages can be written to). + * for this folio (other folios can be written to). */ - ret = nfs_wb_page(inode, page); + ret = nfs_wb_folio(inode, folio); if (ret) goto out_unlock; - if (PageUptodate(page)) + if (folio_test_uptodate(folio)) goto out_unlock; ret = -ESTALE; @@ -368,24 +367,24 @@ int nfs_read_folio(struct file *file, struct folio *folio) nfs_pageio_init_read(&desc.pgio, inode, false, &nfs_async_read_completion_ops); - ret = readpage_async_filler(&desc, page); + ret = readpage_async_filler(&desc, folio); if (ret) goto out; nfs_pageio_complete_read(&desc.pgio); ret = desc.pgio.pg_error < 0 ? desc.pgio.pg_error : 0; if (!ret) { - ret = wait_on_page_locked_killable(page); - if (!PageUptodate(page) && !ret) + ret = folio_wait_locked_killable(folio); + if (!folio_test_uptodate(folio) && !ret) ret = xchg(&desc.ctx->error, 0); } out: put_nfs_open_context(desc.ctx); - trace_nfs_aop_readpage_done(inode, page, ret); + trace_nfs_aop_readpage_done(inode, folio, ret); return ret; out_unlock: - unlock_page(page); - trace_nfs_aop_readpage_done(inode, page, ret); + folio_unlock(folio); + trace_nfs_aop_readpage_done(inode, folio, ret); return ret; } @@ -395,7 +394,7 @@ void nfs_readahead(struct readahead_control *ractl) struct file *file = ractl->file; struct nfs_readdesc desc; struct inode *inode = ractl->mapping->host; - struct page *page; + struct folio *folio; int ret; trace_nfs_aop_readahead(inode, readahead_pos(ractl), nr_pages); @@ -416,9 +415,8 @@ void nfs_readahead(struct readahead_control *ractl) nfs_pageio_init_read(&desc.pgio, inode, false, &nfs_async_read_completion_ops); - while ((page = readahead_page(ractl)) != NULL) { - ret = readpage_async_filler(&desc, page); - put_page(page); + while ((folio = readahead_folio(ractl)) != NULL) { + ret = readpage_async_filler(&desc, folio); if (ret) break; } diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index b0b03ec4a209..3c71493d5cc3 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -125,6 +125,10 @@ extern struct nfs_page *nfs_create_request(struct nfs_open_context *ctx, struct page *page, unsigned int offset, unsigned int count); +extern struct nfs_page *nfs_page_create_from_folio(struct nfs_open_context *ctx, + struct folio *folio, + unsigned int offset, + unsigned int count); extern void nfs_release_request(struct nfs_page *); -- cgit v1.2.3 From 0c493b5cf16e28d761b6e77c7c32aa0e7af70813 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 19 Jan 2023 16:33:43 -0500 Subject: NFS: Convert buffered writes to use folios Mostly mechanical conversion of struct page and functions into struct folio equivalents. The lack of support for folios in write_cache_pages(), means we still only support order 0 folio allocations. However the rest of the writeback code should now be ready for order n > 0. Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- fs/nfs/file.c | 14 +- fs/nfs/internal.h | 13 +- fs/nfs/pnfs.h | 10 +- fs/nfs/pnfs_nfs.c | 18 +-- fs/nfs/write.c | 350 +++++++++++++++++++++++++------------------------ include/linux/nfs_fs.h | 5 +- 6 files changed, 210 insertions(+), 200 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 8704bd071d3a..9fbe27214da0 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -319,6 +319,7 @@ static int nfs_write_begin(struct file *file, struct address_space *mapping, int ret; pgoff_t index = pos >> PAGE_SHIFT; struct page *page; + struct folio *folio; int once_thru = 0; dfprintk(PAGECACHE, "NFS: write_begin(%pD2(%lu), %u@%lld)\n", @@ -329,15 +330,16 @@ start: if (!page) return -ENOMEM; *pagep = page; + folio = page_folio(page); - ret = nfs_flush_incompatible(file, page); + ret = nfs_flush_incompatible(file, folio); if (ret) { unlock_page(page); put_page(page); } else if (!once_thru && nfs_want_read_modify_write(file, page, pos, len)) { once_thru = 1; - ret = nfs_read_folio(file, page_folio(page)); + ret = nfs_read_folio(file, folio); put_page(page); if (!ret) goto start; @@ -351,6 +353,7 @@ static int nfs_write_end(struct file *file, struct address_space *mapping, { unsigned offset = pos & (PAGE_SIZE - 1); struct nfs_open_context *ctx = nfs_file_open_context(file); + struct folio *folio = page_folio(page); int status; dfprintk(PAGECACHE, "NFS: write_end(%pD2(%lu), %u@%lld)\n", @@ -376,7 +379,7 @@ static int nfs_write_end(struct file *file, struct address_space *mapping, zero_user_segment(page, pglen, PAGE_SIZE); } - status = nfs_updatepage(file, page, offset, copied); + status = nfs_update_folio(file, folio, offset, copied); unlock_page(page); put_page(page); @@ -552,6 +555,7 @@ static vm_fault_t nfs_vm_page_mkwrite(struct vm_fault *vmf) unsigned pagelen; vm_fault_t ret = VM_FAULT_NOPAGE; struct address_space *mapping; + struct folio *folio = page_folio(page); dfprintk(PAGECACHE, "NFS: vm_page_mkwrite(%pD2(%lu), offset %lld)\n", filp, filp->f_mapping->host->i_ino, @@ -582,8 +586,8 @@ static vm_fault_t nfs_vm_page_mkwrite(struct vm_fault *vmf) goto out_unlock; ret = VM_FAULT_LOCKED; - if (nfs_flush_incompatible(filp, page) == 0 && - nfs_updatepage(filp, page, 0, pagelen) == 0) + if (nfs_flush_incompatible(filp, folio) == 0 && + nfs_update_folio(filp, folio, 0, pagelen) == 0) goto out; ret = VM_FAULT_SIGBUS; diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 529b87336ffa..239ae5084774 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -760,17 +760,18 @@ void nfs_super_set_maxbytes(struct super_block *sb, __u64 maxfilesize) * Record the page as unstable (an extra writeback period) and mark its * inode as dirty. */ -static inline -void nfs_mark_page_unstable(struct page *page, struct nfs_commit_info *cinfo) +static inline void nfs_folio_mark_unstable(struct folio *folio, + struct nfs_commit_info *cinfo) { - if (!cinfo->dreq) { - struct inode *inode = page_file_mapping(page)->host; + if (folio && !cinfo->dreq) { + struct inode *inode = folio_file_mapping(folio)->host; + long nr = folio_nr_pages(folio); /* This page is really still in write-back - just that the * writeback is happening on the server now. */ - inc_node_page_state(page, NR_WRITEBACK); - inc_wb_stat(&inode_to_bdi(inode)->wb, WB_WRITEBACK); + node_stat_mod_folio(folio, NR_WRITEBACK, nr); + wb_stat_mod(&inode_to_bdi(inode)->wb, WB_WRITEBACK, nr); __mark_inode_dirty(inode, I_DIRTY_DATASYNC); } } diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index e3e6a41f19de..d886c8226d8f 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -193,7 +193,7 @@ struct pnfs_commit_ops { void (*recover_commit_reqs) (struct list_head *list, struct nfs_commit_info *cinfo); struct nfs_page * (*search_commit_reqs)(struct nfs_commit_info *cinfo, - struct page *page); + struct folio *folio); }; struct pnfs_layout_hdr { @@ -395,7 +395,7 @@ void pnfs_generic_rw_release(void *data); void pnfs_generic_recover_commit_reqs(struct list_head *dst, struct nfs_commit_info *cinfo); struct nfs_page *pnfs_generic_search_commit_reqs(struct nfs_commit_info *cinfo, - struct page *page); + struct folio *folio); int pnfs_generic_commit_pagelist(struct inode *inode, struct list_head *mds_pages, int how, @@ -557,13 +557,13 @@ pnfs_recover_commit_reqs(struct list_head *head, struct nfs_commit_info *cinfo) static inline struct nfs_page * pnfs_search_commit_reqs(struct inode *inode, struct nfs_commit_info *cinfo, - struct page *page) + struct folio *folio) { struct pnfs_ds_commit_info *fl_cinfo = cinfo->ds; if (!fl_cinfo->ops || !fl_cinfo->ops->search_commit_reqs) return NULL; - return fl_cinfo->ops->search_commit_reqs(cinfo, page); + return fl_cinfo->ops->search_commit_reqs(cinfo, folio); } /* Should the pNFS client commit and return the layout upon a setattr */ @@ -864,7 +864,7 @@ pnfs_recover_commit_reqs(struct list_head *head, struct nfs_commit_info *cinfo) static inline struct nfs_page * pnfs_search_commit_reqs(struct inode *inode, struct nfs_commit_info *cinfo, - struct page *page) + struct folio *folio) { return NULL; } diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c index 5d035dd2d7bf..a0112ad4937a 100644 --- a/fs/nfs/pnfs_nfs.c +++ b/fs/nfs/pnfs_nfs.c @@ -353,7 +353,7 @@ EXPORT_SYMBOL_GPL(pnfs_generic_recover_commit_reqs); static struct nfs_page * pnfs_bucket_search_commit_reqs(struct pnfs_commit_bucket *buckets, - unsigned int nbuckets, struct page *page) + unsigned int nbuckets, struct folio *folio) { struct nfs_page *req; struct pnfs_commit_bucket *b; @@ -363,11 +363,11 @@ pnfs_bucket_search_commit_reqs(struct pnfs_commit_bucket *buckets, * request is found */ for (i = 0, b = buckets; i < nbuckets; i++, b++) { list_for_each_entry(req, &b->written, wb_list) { - if (req->wb_page == page) + if (nfs_page_to_folio(req) == folio) return req->wb_head; } list_for_each_entry(req, &b->committing, wb_list) { - if (req->wb_page == page) + if (nfs_page_to_folio(req) == folio) return req->wb_head; } } @@ -375,14 +375,14 @@ pnfs_bucket_search_commit_reqs(struct pnfs_commit_bucket *buckets, } /* pnfs_generic_search_commit_reqs - Search lists in @cinfo for the head request - * for @page + * for @folio * @cinfo - commit info for current inode - * @page - page to search for matching head request + * @folio - page to search for matching head request * * Return: the head request if one is found, otherwise %NULL. */ -struct nfs_page * -pnfs_generic_search_commit_reqs(struct nfs_commit_info *cinfo, struct page *page) +struct nfs_page *pnfs_generic_search_commit_reqs(struct nfs_commit_info *cinfo, + struct folio *folio) { struct pnfs_ds_commit_info *fl_cinfo = cinfo->ds; struct pnfs_commit_array *array; @@ -390,7 +390,7 @@ pnfs_generic_search_commit_reqs(struct nfs_commit_info *cinfo, struct page *page list_for_each_entry(array, &fl_cinfo->commits, cinfo_list) { req = pnfs_bucket_search_commit_reqs(array->buckets, - array->nbuckets, page); + array->nbuckets, folio); if (req) return req; } @@ -1180,7 +1180,7 @@ pnfs_layout_mark_request_commit(struct nfs_page *req, nfs_request_add_commit_list_locked(req, list, cinfo); mutex_unlock(&NFS_I(cinfo->inode)->commit_mutex); - nfs_mark_page_unstable(req->wb_page, cinfo); + nfs_folio_mark_unstable(nfs_page_to_folio(req), cinfo); return; out_resched: mutex_unlock(&NFS_I(cinfo->inode)->commit_mutex); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 0d63f03436d3..442aee011871 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -63,7 +63,7 @@ static void nfs_init_cinfo_from_inode(struct nfs_commit_info *cinfo, struct inode *inode); static struct nfs_page * nfs_page_search_commits_for_head_request_locked(struct nfs_inode *nfsi, - struct page *page); + struct folio *folio); static struct kmem_cache *nfs_wdata_cachep; static mempool_t *nfs_wdata_mempool; @@ -170,31 +170,28 @@ nfs_cancel_remove_inode(struct nfs_page *req, struct inode *inode) return 0; } -static struct nfs_page * -nfs_page_private_request(struct page *page) +static struct nfs_page *nfs_folio_private_request(struct folio *folio) { - if (!PagePrivate(page)) - return NULL; - return (struct nfs_page *)page_private(page); + return folio_get_private(folio); } -/* - * nfs_page_find_head_request_locked - find head request associated with @page +/** + * nfs_folio_find_private_request - find head request associated with a folio + * @folio: pointer to folio * * must be called while holding the inode lock. * * returns matching head request with reference held, or NULL if not found. */ -static struct nfs_page * -nfs_page_find_private_request(struct page *page) +static struct nfs_page *nfs_folio_find_private_request(struct folio *folio) { - struct address_space *mapping = page_file_mapping(page); + struct address_space *mapping = folio_file_mapping(folio); struct nfs_page *req; - if (!PagePrivate(page)) + if (!folio_test_private(folio)) return NULL; spin_lock(&mapping->private_lock); - req = nfs_page_private_request(page); + req = nfs_folio_private_request(folio); if (req) { WARN_ON_ONCE(req->wb_head != req); kref_get(&req->wb_kref); @@ -203,18 +200,17 @@ nfs_page_find_private_request(struct page *page) return req; } -static struct nfs_page * -nfs_page_find_swap_request(struct page *page) +static struct nfs_page *nfs_folio_find_swap_request(struct folio *folio) { - struct inode *inode = page_file_mapping(page)->host; + struct inode *inode = folio_file_mapping(folio)->host; struct nfs_inode *nfsi = NFS_I(inode); struct nfs_page *req = NULL; - if (!PageSwapCache(page)) + if (!folio_test_swapcache(folio)) return NULL; mutex_lock(&nfsi->commit_mutex); - if (PageSwapCache(page)) { + if (folio_test_swapcache(folio)) { req = nfs_page_search_commits_for_head_request_locked(nfsi, - page); + folio); if (req) { WARN_ON_ONCE(req->wb_head != req); kref_get(&req->wb_kref); @@ -224,29 +220,30 @@ nfs_page_find_swap_request(struct page *page) return req; } -/* - * nfs_page_find_head_request - find head request associated with @page +/** + * nfs_folio_find_head_request - find head request associated with a folio + * @folio: pointer to folio * * returns matching head request with reference held, or NULL if not found. */ -static struct nfs_page *nfs_page_find_head_request(struct page *page) +static struct nfs_page *nfs_folio_find_head_request(struct folio *folio) { struct nfs_page *req; - req = nfs_page_find_private_request(page); + req = nfs_folio_find_private_request(folio); if (!req) - req = nfs_page_find_swap_request(page); + req = nfs_folio_find_swap_request(folio); return req; } -static struct nfs_page *nfs_find_and_lock_page_request(struct page *page) +static struct nfs_page *nfs_folio_find_and_lock_request(struct folio *folio) { - struct inode *inode = page_file_mapping(page)->host; + struct inode *inode = folio_file_mapping(folio)->host; struct nfs_page *req, *head; int ret; for (;;) { - req = nfs_page_find_head_request(page); + req = nfs_folio_find_head_request(folio); if (!req) return req; head = nfs_page_group_lock_head(req); @@ -260,9 +257,9 @@ static struct nfs_page *nfs_find_and_lock_page_request(struct page *page) return ERR_PTR(ret); } /* Ensure that nobody removed the request before we locked it */ - if (head == nfs_page_private_request(page)) + if (head == nfs_folio_private_request(folio)) break; - if (PageSwapCache(page)) + if (folio_test_swapcache(folio)) break; nfs_unlock_and_release_request(head); } @@ -270,18 +267,19 @@ static struct nfs_page *nfs_find_and_lock_page_request(struct page *page) } /* Adjust the file length if we're writing beyond the end */ -static void nfs_grow_file(struct page *page, unsigned int offset, unsigned int count) +static void nfs_grow_file(struct folio *folio, unsigned int offset, + unsigned int count) { - struct inode *inode = page_file_mapping(page)->host; + struct inode *inode = folio_file_mapping(folio)->host; loff_t end, i_size; pgoff_t end_index; spin_lock(&inode->i_lock); i_size = i_size_read(inode); - end_index = (i_size - 1) >> PAGE_SHIFT; - if (i_size > 0 && page_index(page) < end_index) + end_index = ((i_size - 1) >> folio_shift(folio)) << folio_order(folio); + if (i_size > 0 && folio_index(folio) < end_index) goto out; - end = page_file_offset(page) + ((loff_t)offset+count); + end = folio_file_pos(folio) + (loff_t)offset + (loff_t)count; if (i_size >= end) goto out; trace_nfs_size_grow(inode, end); @@ -307,11 +305,11 @@ static void nfs_set_pageerror(struct address_space *mapping) spin_unlock(&inode->i_lock); } -static void nfs_mapping_set_error(struct page *page, int error) +static void nfs_mapping_set_error(struct folio *folio, int error) { - struct address_space *mapping = page_file_mapping(page); + struct address_space *mapping = folio_file_mapping(folio); - SetPageError(page); + folio_set_error(folio); filemap_set_wb_err(mapping, error); if (mapping->host) errseq_set(&mapping->host->i_sb->s_wb_err, @@ -358,9 +356,9 @@ nfs_page_group_search_locked(struct nfs_page *head, unsigned int page_offset) */ static bool nfs_page_group_covers_page(struct nfs_page *req) { + unsigned int len = nfs_folio_length(nfs_page_to_folio(req)); struct nfs_page *tmp; unsigned int pos = 0; - unsigned int len = nfs_page_length(req->wb_page); nfs_page_group_lock(req); @@ -380,11 +378,13 @@ static bool nfs_page_group_covers_page(struct nfs_page *req) */ static void nfs_mark_uptodate(struct nfs_page *req) { - if (PageUptodate(req->wb_page)) + struct folio *folio = nfs_page_to_folio(req); + + if (folio_test_uptodate(folio)) return; if (!nfs_page_group_covers_page(req)) return; - SetPageUptodate(req->wb_page); + folio_mark_uptodate(folio); } static int wb_priority(struct writeback_control *wbc) @@ -406,35 +406,34 @@ int nfs_congestion_kb; #define NFS_CONGESTION_OFF_THRESH \ (NFS_CONGESTION_ON_THRESH - (NFS_CONGESTION_ON_THRESH >> 2)) -static void nfs_set_page_writeback(struct page *page) +static void nfs_folio_set_writeback(struct folio *folio) { - struct inode *inode = page_file_mapping(page)->host; - struct nfs_server *nfss = NFS_SERVER(inode); - int ret = test_set_page_writeback(page); - - WARN_ON_ONCE(ret != 0); + struct nfs_server *nfss = NFS_SERVER(folio_file_mapping(folio)->host); - if (atomic_long_inc_return(&nfss->writeback) > - NFS_CONGESTION_ON_THRESH) + folio_start_writeback(folio); + if (atomic_long_inc_return(&nfss->writeback) > NFS_CONGESTION_ON_THRESH) nfss->write_congested = 1; } -static void nfs_end_page_writeback(struct nfs_page *req) +static void nfs_folio_end_writeback(struct folio *folio) { - struct inode *inode = nfs_page_to_inode(req); - struct nfs_server *nfss = NFS_SERVER(inode); - bool is_done; + struct nfs_server *nfss = NFS_SERVER(folio_file_mapping(folio)->host); - is_done = nfs_page_group_sync_on_bit(req, PG_WB_END); - nfs_unlock_request(req); - if (!is_done) - return; - - end_page_writeback(req->wb_page); - if (atomic_long_dec_return(&nfss->writeback) < NFS_CONGESTION_OFF_THRESH) + folio_end_writeback(folio); + if (atomic_long_dec_return(&nfss->writeback) < + NFS_CONGESTION_OFF_THRESH) nfss->write_congested = 0; } +static void nfs_page_end_writeback(struct nfs_page *req) +{ + if (nfs_page_group_sync_on_bit(req, PG_WB_END)) { + nfs_unlock_request(req); + nfs_folio_end_writeback(nfs_page_to_folio(req)); + } else + nfs_unlock_request(req); +} + /* * nfs_destroy_unlinked_subrequests - destroy recently unlinked subrequests * @@ -549,7 +548,7 @@ nfs_join_page_group(struct nfs_page *head, struct inode *inode) /* * nfs_lock_and_join_requests - join all subreqs to the head req - * @page: the page used to lookup the "page group" of nfs_page structures + * @folio: the folio used to lookup the "page group" of nfs_page structures * * This function joins all sub requests to the head request by first * locking all requests in the group, cancelling any pending operations @@ -559,13 +558,12 @@ nfs_join_page_group(struct nfs_page *head, struct inode *inode) * * Returns a locked, referenced pointer to the head request - which after * this call is guaranteed to be the only request associated with the page. - * Returns NULL if no requests are found for @page, or a ERR_PTR if an + * Returns NULL if no requests are found for @folio, or a ERR_PTR if an * error was encountered. */ -static struct nfs_page * -nfs_lock_and_join_requests(struct page *page) +static struct nfs_page *nfs_lock_and_join_requests(struct folio *folio) { - struct inode *inode = page_file_mapping(page)->host; + struct inode *inode = folio_file_mapping(folio)->host; struct nfs_page *head; int ret; @@ -574,7 +572,7 @@ nfs_lock_and_join_requests(struct page *page) * reference to the whole page group - the group will not be destroyed * until the head reference is released. */ - head = nfs_find_and_lock_page_request(page); + head = nfs_folio_find_and_lock_request(folio); if (IS_ERR_OR_NULL(head)) return head; @@ -593,9 +591,9 @@ nfs_lock_and_join_requests(struct page *page) static void nfs_write_error(struct nfs_page *req, int error) { trace_nfs_write_error(nfs_page_to_inode(req), req, error); - nfs_mapping_set_error(req->wb_page, error); + nfs_mapping_set_error(nfs_page_to_folio(req), error); nfs_inode_remove_request(req); - nfs_end_page_writeback(req); + nfs_page_end_writeback(req); nfs_release_request(req); } @@ -603,21 +601,21 @@ static void nfs_write_error(struct nfs_page *req, int error) * Find an associated nfs write request, and prepare to flush it out * May return an error if the user signalled nfs_wait_on_request(). */ -static int nfs_page_async_flush(struct page *page, +static int nfs_page_async_flush(struct folio *folio, struct writeback_control *wbc, struct nfs_pageio_descriptor *pgio) { struct nfs_page *req; int ret = 0; - req = nfs_lock_and_join_requests(page); + req = nfs_lock_and_join_requests(folio); if (!req) goto out; ret = PTR_ERR(req); if (IS_ERR(req)) goto out; - nfs_set_page_writeback(page); + nfs_folio_set_writeback(folio); WARN_ON_ONCE(test_bit(PG_CLEAN, &req->wb_flags)); /* If there is a fatal error that covers this write, just exit */ @@ -635,12 +633,12 @@ static int nfs_page_async_flush(struct page *page, goto out_launder; if (wbc->sync_mode == WB_SYNC_NONE) ret = AOP_WRITEPAGE_ACTIVATE; - redirty_page_for_writepage(wbc, page); + folio_redirty_for_writepage(wbc, folio); nfs_redirty_request(req); pgio->pg_error = 0; } else - nfs_add_stats(page_file_mapping(page)->host, - NFSIOS_WRITEPAGES, 1); + nfs_add_stats(folio_file_mapping(folio)->host, + NFSIOS_WRITEPAGES, 1); out: return ret; out_launder: @@ -648,21 +646,21 @@ out_launder: return 0; } -static int nfs_do_writepage(struct page *page, struct writeback_control *wbc, +static int nfs_do_writepage(struct folio *folio, struct writeback_control *wbc, struct nfs_pageio_descriptor *pgio) { - nfs_pageio_cond_complete(pgio, page_index(page)); - return nfs_page_async_flush(page, wbc, pgio); + nfs_pageio_cond_complete(pgio, folio_index(folio)); + return nfs_page_async_flush(folio, wbc, pgio); } /* * Write an mmapped page to the server. */ -static int nfs_writepage_locked(struct page *page, +static int nfs_writepage_locked(struct folio *folio, struct writeback_control *wbc) { struct nfs_pageio_descriptor pgio; - struct inode *inode = page_file_mapping(page)->host; + struct inode *inode = folio_file_mapping(folio)->host; int err; if (wbc->sync_mode == WB_SYNC_NONE && @@ -670,9 +668,9 @@ static int nfs_writepage_locked(struct page *page, return AOP_WRITEPAGE_ACTIVATE; nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGE); - nfs_pageio_init_write(&pgio, inode, 0, - false, &nfs_async_write_completion_ops); - err = nfs_do_writepage(page, wbc, &pgio); + nfs_pageio_init_write(&pgio, inode, 0, false, + &nfs_async_write_completion_ops); + err = nfs_do_writepage(folio, wbc, &pgio); pgio.pg_error = 0; nfs_pageio_complete(&pgio); return err; @@ -680,19 +678,22 @@ static int nfs_writepage_locked(struct page *page, int nfs_writepage(struct page *page, struct writeback_control *wbc) { + struct folio *folio = page_folio(page); int ret; - ret = nfs_writepage_locked(page, wbc); + ret = nfs_writepage_locked(folio, wbc); if (ret != AOP_WRITEPAGE_ACTIVATE) unlock_page(page); return ret; } -static int nfs_writepages_callback(struct page *page, struct writeback_control *wbc, void *data) +static int nfs_writepages_callback(struct page *page, + struct writeback_control *wbc, void *data) { + struct folio *folio = page_folio(page); int ret; - ret = nfs_do_writepage(page, wbc, data); + ret = nfs_do_writepage(folio, wbc, data); if (ret != AOP_WRITEPAGE_ACTIVATE) unlock_page(page); return ret; @@ -748,10 +749,11 @@ out_err: /* * Insert a write request into an inode */ -static void nfs_inode_add_request(struct inode *inode, struct nfs_page *req) +static void nfs_inode_add_request(struct nfs_page *req) { - struct address_space *mapping = page_file_mapping(req->wb_page); - struct nfs_inode *nfsi = NFS_I(inode); + struct folio *folio = nfs_page_to_folio(req); + struct address_space *mapping = folio_file_mapping(folio); + struct nfs_inode *nfsi = NFS_I(mapping->host); WARN_ON_ONCE(req->wb_this_page != req); @@ -763,10 +765,10 @@ static void nfs_inode_add_request(struct inode *inode, struct nfs_page *req) * with invalidate/truncate. */ spin_lock(&mapping->private_lock); - if (likely(!PageSwapCache(req->wb_page))) { + if (likely(!folio_test_swapcache(folio))) { set_bit(PG_MAPPED, &req->wb_flags); - SetPagePrivate(req->wb_page); - set_page_private(req->wb_page, (unsigned long)req); + folio_set_private(folio); + folio->private = req; } spin_unlock(&mapping->private_lock); atomic_long_inc(&nfsi->nrequests); @@ -783,47 +785,43 @@ static void nfs_inode_add_request(struct inode *inode, struct nfs_page *req) */ static void nfs_inode_remove_request(struct nfs_page *req) { - struct address_space *mapping = page_file_mapping(req->wb_page); - struct inode *inode = mapping->host; - struct nfs_inode *nfsi = NFS_I(inode); - struct nfs_page *head; - if (nfs_page_group_sync_on_bit(req, PG_REMOVE)) { - head = req->wb_head; + struct folio *folio = nfs_page_to_folio(req->wb_head); + struct address_space *mapping = folio_file_mapping(folio); spin_lock(&mapping->private_lock); - if (likely(head->wb_page && !PageSwapCache(head->wb_page))) { - set_page_private(head->wb_page, 0); - ClearPagePrivate(head->wb_page); - clear_bit(PG_MAPPED, &head->wb_flags); + if (likely(folio && !folio_test_swapcache(folio))) { + folio->private = NULL; + folio_clear_private(folio); + clear_bit(PG_MAPPED, &req->wb_head->wb_flags); } spin_unlock(&mapping->private_lock); } if (test_and_clear_bit(PG_INODE_REF, &req->wb_flags)) { nfs_release_request(req); - atomic_long_dec(&nfsi->nrequests); + atomic_long_dec(&NFS_I(nfs_page_to_inode(req))->nrequests); } } -static void -nfs_mark_request_dirty(struct nfs_page *req) +static void nfs_mark_request_dirty(struct nfs_page *req) { - if (req->wb_page) - __set_page_dirty_nobuffers(req->wb_page); + struct folio *folio = nfs_page_to_folio(req); + if (folio) + filemap_dirty_folio(folio_mapping(folio), folio); } /* * nfs_page_search_commits_for_head_request_locked * - * Search through commit lists on @inode for the head request for @page. + * Search through commit lists on @inode for the head request for @folio. * Must be called while holding the inode (which is cinfo) lock. * * Returns the head request if found, or NULL if not found. */ static struct nfs_page * nfs_page_search_commits_for_head_request_locked(struct nfs_inode *nfsi, - struct page *page) + struct folio *folio) { struct nfs_page *freq, *t; struct nfs_commit_info cinfo; @@ -832,13 +830,13 @@ nfs_page_search_commits_for_head_request_locked(struct nfs_inode *nfsi, nfs_init_cinfo_from_inode(&cinfo, inode); /* search through pnfs commit lists */ - freq = pnfs_search_commit_reqs(inode, &cinfo, page); + freq = pnfs_search_commit_reqs(inode, &cinfo, folio); if (freq) return freq->wb_head; /* Linearly search the commit list for the correct request */ list_for_each_entry_safe(freq, t, &cinfo.mds->list, wb_list) { - if (freq->wb_page == page) + if (nfs_page_to_folio(freq) == folio) return freq->wb_head; } @@ -886,8 +884,7 @@ nfs_request_add_commit_list(struct nfs_page *req, struct nfs_commit_info *cinfo) mutex_lock(&NFS_I(cinfo->inode)->commit_mutex); nfs_request_add_commit_list_locked(req, &cinfo->mds->list, cinfo); mutex_unlock(&NFS_I(cinfo->inode)->commit_mutex); - if (req->wb_page) - nfs_mark_page_unstable(req->wb_page, cinfo); + nfs_folio_mark_unstable(nfs_page_to_folio(req), cinfo); } EXPORT_SYMBOL_GPL(nfs_request_add_commit_list); @@ -946,12 +943,15 @@ nfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg, nfs_request_add_commit_list(req, cinfo); } -static void -nfs_clear_page_commit(struct page *page) +static void nfs_folio_clear_commit(struct folio *folio) { - dec_node_page_state(page, NR_WRITEBACK); - dec_wb_stat(&inode_to_bdi(page_file_mapping(page)->host)->wb, - WB_WRITEBACK); + if (folio) { + long nr = folio_nr_pages(folio); + + node_stat_mod_folio(folio, NR_WRITEBACK, -nr); + wb_stat_mod(&inode_to_bdi(folio_file_mapping(folio)->host)->wb, + WB_WRITEBACK, -nr); + } } /* Called holding the request lock on @req */ @@ -969,7 +969,7 @@ nfs_clear_request_commit(struct nfs_page *req) nfs_request_remove_commit_list(req, &cinfo); } mutex_unlock(&NFS_I(inode)->commit_mutex); - nfs_clear_page_commit(req->wb_page); + nfs_folio_clear_commit(nfs_page_to_folio(req)); } } @@ -1001,7 +1001,8 @@ static void nfs_write_completion(struct nfs_pgio_header *hdr) if (test_bit(NFS_IOHDR_ERROR, &hdr->flags) && (hdr->good_bytes < bytes)) { trace_nfs_comp_error(hdr->inode, req, hdr->error); - nfs_mapping_set_error(req->wb_page, hdr->error); + nfs_mapping_set_error(nfs_page_to_folio(req), + hdr->error); goto remove_req; } if (nfs_write_need_commit(hdr)) { @@ -1015,7 +1016,7 @@ static void nfs_write_completion(struct nfs_pgio_header *hdr) remove_req: nfs_inode_remove_request(req); next: - nfs_end_page_writeback(req); + nfs_page_end_writeback(req); nfs_release_request(req); } out: @@ -1091,10 +1092,9 @@ nfs_scan_commit(struct inode *inode, struct list_head *dst, * If the attempt fails, then the existing request is flushed out * to disk. */ -static struct nfs_page *nfs_try_to_update_request(struct inode *inode, - struct page *page, - unsigned int offset, - unsigned int bytes) +static struct nfs_page *nfs_try_to_update_request(struct folio *folio, + unsigned int offset, + unsigned int bytes) { struct nfs_page *req; unsigned int rqend; @@ -1103,7 +1103,7 @@ static struct nfs_page *nfs_try_to_update_request(struct inode *inode, end = offset + bytes; - req = nfs_lock_and_join_requests(page); + req = nfs_lock_and_join_requests(folio); if (IS_ERR_OR_NULL(req)) return req; @@ -1136,7 +1136,7 @@ out_flushme: */ nfs_mark_request_dirty(req); nfs_unlock_and_release_request(req); - error = nfs_wb_page(inode, page); + error = nfs_wb_folio(folio_file_mapping(folio)->host, folio); return (error < 0) ? ERR_PTR(error) : NULL; } @@ -1147,40 +1147,42 @@ out_flushme: * if we have to add a new request. Also assumes that the caller has * already called nfs_flush_incompatible() if necessary. */ -static struct nfs_page * nfs_setup_write_request(struct nfs_open_context* ctx, - struct page *page, unsigned int offset, unsigned int bytes) +static struct nfs_page *nfs_setup_write_request(struct nfs_open_context *ctx, + struct folio *folio, + unsigned int offset, + unsigned int bytes) { - struct inode *inode = page_file_mapping(page)->host; - struct nfs_page *req; + struct nfs_page *req; - req = nfs_try_to_update_request(inode, page, offset, bytes); + req = nfs_try_to_update_request(folio, offset, bytes); if (req != NULL) goto out; - req = nfs_create_request(ctx, page, offset, bytes); + req = nfs_page_create_from_folio(ctx, folio, offset, bytes); if (IS_ERR(req)) goto out; - nfs_inode_add_request(inode, req); + nfs_inode_add_request(req); out: return req; } -static int nfs_writepage_setup(struct nfs_open_context *ctx, struct page *page, - unsigned int offset, unsigned int count) +static int nfs_writepage_setup(struct nfs_open_context *ctx, + struct folio *folio, unsigned int offset, + unsigned int count) { - struct nfs_page *req; + struct nfs_page *req; - req = nfs_setup_write_request(ctx, page, offset, count); + req = nfs_setup_write_request(ctx, folio, offset, count); if (IS_ERR(req)) return PTR_ERR(req); /* Update file length */ - nfs_grow_file(page, offset, count); + nfs_grow_file(folio, offset, count); nfs_mark_uptodate(req); nfs_mark_request_dirty(req); nfs_unlock_and_release_request(req); return 0; } -int nfs_flush_incompatible(struct file *file, struct page *page) +int nfs_flush_incompatible(struct file *file, struct folio *folio) { struct nfs_open_context *ctx = nfs_file_open_context(file); struct nfs_lock_context *l_ctx; @@ -1196,12 +1198,12 @@ int nfs_flush_incompatible(struct file *file, struct page *page) * dropped page. */ do { - req = nfs_page_find_head_request(page); + req = nfs_folio_find_head_request(folio); if (req == NULL) return 0; l_ctx = req->wb_lock_context; - do_flush = req->wb_page != page || - !nfs_match_open_context(nfs_req_openctx(req), ctx); + do_flush = nfs_page_to_folio(req) != folio || + !nfs_match_open_context(nfs_req_openctx(req), ctx); if (l_ctx && flctx && !(list_empty_careful(&flctx->flc_posix) && list_empty_careful(&flctx->flc_flock))) { @@ -1210,7 +1212,7 @@ int nfs_flush_incompatible(struct file *file, struct page *page) nfs_release_request(req); if (!do_flush) return 0; - status = nfs_wb_page(page_file_mapping(page)->host, page); + status = nfs_wb_folio(folio_file_mapping(folio)->host, folio); } while (status == 0); return status; } @@ -1282,9 +1284,9 @@ out: * the PageUptodate() flag. In this case, we will need to turn off * write optimisations that depend on the page contents being correct. */ -static bool nfs_write_pageuptodate(struct page *page, struct inode *inode, - unsigned int pagelen) +static bool nfs_folio_write_uptodate(struct folio *folio, unsigned int pagelen) { + struct inode *inode = folio_file_mapping(folio)->host; struct nfs_inode *nfsi = NFS_I(inode); if (nfs_have_delegated_attributes(inode)) @@ -1298,7 +1300,7 @@ static bool nfs_write_pageuptodate(struct page *page, struct inode *inode, out: if (nfsi->cache_validity & NFS_INO_INVALID_DATA && pagelen != 0) return false; - return PageUptodate(page) != 0; + return folio_test_uptodate(folio) != 0; } static bool @@ -1316,16 +1318,17 @@ is_whole_file_wrlock(struct file_lock *fl) * If the file is opened for synchronous writes then we can just skip the rest * of the checks. */ -static int nfs_can_extend_write(struct file *file, struct page *page, - struct inode *inode, unsigned int pagelen) +static int nfs_can_extend_write(struct file *file, struct folio *folio, + unsigned int pagelen) { - int ret; + struct inode *inode = file_inode(file); struct file_lock_context *flctx = locks_inode_context(inode); struct file_lock *fl; + int ret; if (file->f_flags & O_DSYNC) return 0; - if (!nfs_write_pageuptodate(page, inode, pagelen)) + if (!nfs_folio_write_uptodate(folio, pagelen)) return 0; if (NFS_PROTO(inode)->have_delegation(inode, FMODE_WRITE)) return 1; @@ -1357,33 +1360,33 @@ static int nfs_can_extend_write(struct file *file, struct page *page, * XXX: Keep an eye on generic_file_read to make sure it doesn't do bad * things with a page scheduled for an RPC call (e.g. invalidate it). */ -int nfs_updatepage(struct file *file, struct page *page, - unsigned int offset, unsigned int count) +int nfs_update_folio(struct file *file, struct folio *folio, + unsigned int offset, unsigned int count) { struct nfs_open_context *ctx = nfs_file_open_context(file); - struct address_space *mapping = page_file_mapping(page); - struct inode *inode = mapping->host; - unsigned int pagelen = nfs_page_length(page); + struct address_space *mapping = folio_file_mapping(folio); + struct inode *inode = mapping->host; + unsigned int pagelen = nfs_folio_length(folio); int status = 0; nfs_inc_stats(inode, NFSIOS_VFSUPDATEPAGE); - dprintk("NFS: nfs_updatepage(%pD2 %d@%lld)\n", - file, count, (long long)(page_file_offset(page) + offset)); + dprintk("NFS: nfs_update_folio(%pD2 %d@%lld)\n", file, count, + (long long)(folio_file_pos(folio) + offset)); if (!count) goto out; - if (nfs_can_extend_write(file, page, inode, pagelen)) { + if (nfs_can_extend_write(file, folio, pagelen)) { count = max(count + offset, pagelen); offset = 0; } - status = nfs_writepage_setup(ctx, page, offset, count); + status = nfs_writepage_setup(ctx, folio, offset, count); if (status < 0) nfs_set_pageerror(mapping); out: - dprintk("NFS: nfs_updatepage returns %d (isize %lld)\n", + dprintk("NFS: nfs_update_folio returns %d (isize %lld)\n", status, (long long)i_size_read(inode)); return status; } @@ -1425,7 +1428,7 @@ static void nfs_redirty_request(struct nfs_page *req) req->wb_nio++; nfs_mark_request_dirty(req); atomic_long_inc(&nfsi->redirtied_pages); - nfs_end_page_writeback(req); + nfs_page_end_writeback(req); nfs_release_request(req); } @@ -1783,18 +1786,18 @@ void nfs_retry_commit(struct list_head *page_list, req = nfs_list_entry(page_list->next); nfs_list_remove_request(req); nfs_mark_request_commit(req, lseg, cinfo, ds_commit_idx); - if (!cinfo->dreq) - nfs_clear_page_commit(req->wb_page); + nfs_folio_clear_commit(nfs_page_to_folio(req)); nfs_unlock_and_release_request(req); } } EXPORT_SYMBOL_GPL(nfs_retry_commit); -static void -nfs_commit_resched_write(struct nfs_commit_info *cinfo, - struct nfs_page *req) +static void nfs_commit_resched_write(struct nfs_commit_info *cinfo, + struct nfs_page *req) { - __set_page_dirty_nobuffers(req->wb_page); + struct folio *folio = nfs_page_to_folio(req); + + filemap_dirty_folio(folio_mapping(folio), folio); } /* @@ -1845,12 +1848,13 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data) int status = data->task.tk_status; struct nfs_commit_info cinfo; struct nfs_server *nfss; + struct folio *folio; while (!list_empty(&data->pages)) { req = nfs_list_entry(data->pages.next); nfs_list_remove_request(req); - if (req->wb_page) - nfs_clear_page_commit(req->wb_page); + folio = nfs_page_to_folio(req); + nfs_folio_clear_commit(folio); dprintk("NFS: commit (%s/%llu %d@%lld)", nfs_req_openctx(req)->dentry->d_sb->s_id, @@ -1858,10 +1862,10 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data) req->wb_bytes, (long long)req_offset(req)); if (status < 0) { - if (req->wb_page) { + if (folio) { trace_nfs_commit_error(data->inode, req, status); - nfs_mapping_set_error(req->wb_page, status); + nfs_mapping_set_error(folio, status); nfs_inode_remove_request(req); } dprintk_cont(", error = %d\n", status); @@ -1872,7 +1876,7 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data) * returned by the server against all stored verfs. */ if (nfs_write_match_verf(verf, req)) { /* We have a match */ - if (req->wb_page) + if (folio) nfs_inode_remove_request(req); dprintk_cont(" OK\n"); goto next; @@ -2053,7 +2057,7 @@ int nfs_wb_folio_cancel(struct inode *inode, struct folio *folio) /* blocking call to cancel all requests and join to a single (head) * request */ - req = nfs_lock_and_join_requests(&folio->page); + req = nfs_lock_and_join_requests(folio); if (IS_ERR(req)) { ret = PTR_ERR(req); @@ -2094,7 +2098,7 @@ int nfs_wb_folio(struct inode *inode, struct folio *folio) for (;;) { folio_wait_writeback(folio); if (folio_clear_dirty_for_io(folio)) { - ret = nfs_writepage_locked(&folio->page, &wbc); + ret = nfs_writepage_locked(folio, &wbc); if (ret < 0) goto out_error; continue; diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 66b5de42f6b8..a61bfd52d551 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -569,8 +569,9 @@ extern void nfs_complete_unlink(struct dentry *dentry, struct inode *); extern int nfs_congestion_kb; extern int nfs_writepage(struct page *page, struct writeback_control *wbc); extern int nfs_writepages(struct address_space *, struct writeback_control *); -extern int nfs_flush_incompatible(struct file *file, struct page *page); -extern int nfs_updatepage(struct file *, struct page *, unsigned int, unsigned int); +extern int nfs_flush_incompatible(struct file *file, struct folio *folio); +extern int nfs_update_folio(struct file *file, struct folio *folio, + unsigned int offset, unsigned int count); /* * Try to write back everything synchronously (but check the -- cgit v1.2.3 From 4cbf76948c457f0beb9f184ebb21341c8235846a Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 19 Jan 2023 16:33:44 -0500 Subject: NFS: Remove unused function nfs_wb_page() Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- fs/nfs/write.c | 5 ----- include/linux/nfs_fs.h | 1 - 2 files changed, 6 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 442aee011871..77e6c033ca95 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -2115,11 +2115,6 @@ out_error: return ret; } -int nfs_wb_page(struct inode *inode, struct page *page) -{ - return nfs_wb_folio(inode, page_folio(page)); -} - #ifdef CONFIG_MIGRATION int nfs_migrate_folio(struct address_space *mapping, struct folio *dst, struct folio *src, enum migrate_mode mode) diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index a61bfd52d551..45c44211e50e 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -580,7 +580,6 @@ extern int nfs_update_folio(struct file *file, struct folio *folio, extern int nfs_sync_inode(struct inode *inode); extern int nfs_wb_all(struct inode *inode); extern int nfs_wb_folio(struct inode *inode, struct folio *folio); -extern int nfs_wb_page(struct inode *inode, struct page *page); int nfs_wb_folio_cancel(struct inode *inode, struct folio *folio); extern int nfs_commit_inode(struct inode *, int); extern struct nfs_commit_data *nfs_commitdata_alloc(void); -- cgit v1.2.3 From 70e9db69f927bb378db9aaa807cc83ae550779a9 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 19 Jan 2023 16:33:47 -0500 Subject: NFS: Clean up O_DIRECT request allocation Rather than adjusting the index+offset after the call to nfs_create_request(), add a function nfs_page_create_from_page() that takes an offset. Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- fs/nfs/direct.c | 12 ++++-------- fs/nfs/pagelist.c | 15 +++++++++------ include/linux/nfs_page.h | 9 +++++---- 3 files changed, 18 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 1707f46b1335..9a18c5a69ace 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -343,14 +343,12 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq, struct nfs_page *req; unsigned int req_len = min_t(size_t, bytes, PAGE_SIZE - pgbase); /* XXX do we need to do the eof zeroing found in async_filler? */ - req = nfs_create_request(dreq->ctx, pagevec[i], - pgbase, req_len); + req = nfs_page_create_from_page(dreq->ctx, pagevec[i], + pgbase, pos, req_len); if (IS_ERR(req)) { result = PTR_ERR(req); break; } - req->wb_index = pos >> PAGE_SHIFT; - req->wb_offset = pos & ~PAGE_MASK; if (!nfs_pageio_add_request(&desc, req)) { result = desc.pg_error; nfs_release_request(req); @@ -802,8 +800,8 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, struct nfs_page *req; unsigned int req_len = min_t(size_t, bytes, PAGE_SIZE - pgbase); - req = nfs_create_request(dreq->ctx, pagevec[i], - pgbase, req_len); + req = nfs_page_create_from_page(dreq->ctx, pagevec[i], + pgbase, pos, req_len); if (IS_ERR(req)) { result = PTR_ERR(req); break; @@ -816,8 +814,6 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, } nfs_lock_request(req); - req->wb_index = pos >> PAGE_SHIFT; - req->wb_offset = pos & ~PAGE_MASK; if (!nfs_pageio_add_request(&desc, req)) { result = desc.pg_error; nfs_unlock_and_release_request(req); diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 7a622263a9fc..0b4c07c93a52 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -514,26 +514,29 @@ static void nfs_page_assign_page(struct nfs_page *req, struct page *page) } /** - * nfs_create_request - Create an NFS read/write request. + * nfs_page_create_from_page - Create an NFS read/write request. * @ctx: open context to use * @page: page to write - * @offset: starting offset within the page for the write + * @pgbase: starting offset within the page for the write + * @offset: file offset for the write * @count: number of bytes to read/write * * The page must be locked by the caller. This makes sure we never * create two different requests for the same page. * User should ensure it is safe to sleep in this function. */ -struct nfs_page * -nfs_create_request(struct nfs_open_context *ctx, struct page *page, - unsigned int offset, unsigned int count) +struct nfs_page *nfs_page_create_from_page(struct nfs_open_context *ctx, + struct page *page, + unsigned int pgbase, loff_t offset, + unsigned int count) { struct nfs_lock_context *l_ctx = nfs_get_lock_context(ctx); struct nfs_page *ret; if (IS_ERR(l_ctx)) return ERR_CAST(l_ctx); - ret = nfs_page_create(l_ctx, offset, page_index(page), offset, count); + ret = nfs_page_create(l_ctx, pgbase, offset >> PAGE_SHIFT, + offset_in_page(offset), count); if (!IS_ERR(ret)) { nfs_page_assign_page(ret, page); nfs_page_group_init(ret, NULL); diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index 3c71493d5cc3..a2f1ca657623 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -121,10 +121,11 @@ struct nfs_pageio_descriptor { #define NFS_WBACK_BUSY(req) (test_bit(PG_BUSY,&(req)->wb_flags)) -extern struct nfs_page *nfs_create_request(struct nfs_open_context *ctx, - struct page *page, - unsigned int offset, - unsigned int count); +extern struct nfs_page *nfs_page_create_from_page(struct nfs_open_context *ctx, + struct page *page, + unsigned int pgbase, + loff_t offset, + unsigned int count); extern struct nfs_page *nfs_page_create_from_folio(struct nfs_open_context *ctx, struct folio *folio, unsigned int offset, -- cgit v1.2.3 From 3bd940030752a33ff665eefdd74a1cdb74a4f9b0 Mon Sep 17 00:00:00 2001 From: Heinz Mauelshagen Date: Wed, 25 Jan 2023 21:00:44 +0100 Subject: dm: add missing SPDX-License-Indentifiers 'GPL-2.0-only' is used instead of 'GPL-2.0' because SPDX has deprecated its use. Suggested-by: John Wiele Signed-off-by: Heinz Mauelshagen Signed-off-by: Mike Snitzer --- drivers/md/dm-audit.c | 2 +- drivers/md/dm-bio-prison-v1.c | 1 + drivers/md/dm-bio-prison-v1.h | 1 + drivers/md/dm-bio-prison-v2.c | 1 + drivers/md/dm-bio-prison-v2.h | 1 + drivers/md/dm-bio-record.h | 1 + drivers/md/dm-bufio.c | 1 + drivers/md/dm-builtin.c | 2 +- drivers/md/dm-cache-background-tracker.c | 1 + drivers/md/dm-cache-background-tracker.h | 1 + drivers/md/dm-cache-block-types.h | 1 + drivers/md/dm-cache-metadata.c | 1 + drivers/md/dm-cache-metadata.h | 1 + drivers/md/dm-cache-policy-internal.h | 1 + drivers/md/dm-cache-policy-smq.c | 1 + drivers/md/dm-cache-policy.c | 1 + drivers/md/dm-cache-policy.h | 1 + drivers/md/dm-cache-target.c | 1 + drivers/md/dm-core.h | 1 + drivers/md/dm-crypt.c | 1 + drivers/md/dm-delay.c | 1 + drivers/md/dm-dust.c | 2 +- drivers/md/dm-ebs-target.c | 1 + drivers/md/dm-exception-store.c | 1 + drivers/md/dm-exception-store.h | 1 + drivers/md/dm-flakey.c | 1 + drivers/md/dm-ima.c | 2 +- drivers/md/dm-ima.h | 4 ++-- drivers/md/dm-init.c | 2 +- drivers/md/dm-integrity.c | 1 + drivers/md/dm-io-rewind.c | 2 +- drivers/md/dm-io-tracker.h | 1 + drivers/md/dm-io.c | 1 + drivers/md/dm-ioctl.c | 1 + drivers/md/dm-kcopyd.c | 1 + drivers/md/dm-linear.c | 1 + drivers/md/dm-log-userspace-base.c | 1 + drivers/md/dm-log-userspace-transfer.c | 1 + drivers/md/dm-log-userspace-transfer.h | 1 + drivers/md/dm-log-writes.c | 1 + drivers/md/dm-log.c | 1 + drivers/md/dm-mpath.c | 1 + drivers/md/dm-mpath.h | 1 + drivers/md/dm-path-selector.c | 1 + drivers/md/dm-path-selector.h | 1 + drivers/md/dm-ps-historical-service-time.c | 2 +- drivers/md/dm-ps-queue-length.c | 1 + drivers/md/dm-ps-round-robin.c | 1 + drivers/md/dm-ps-service-time.c | 1 + drivers/md/dm-raid.c | 1 + drivers/md/dm-raid1.c | 1 + drivers/md/dm-region-hash.c | 1 + drivers/md/dm-rq.c | 1 + drivers/md/dm-rq.h | 1 + drivers/md/dm-snap-persistent.c | 1 + drivers/md/dm-snap-transient.c | 1 + drivers/md/dm-snap.c | 1 + drivers/md/dm-stats.c | 2 +- drivers/md/dm-stripe.c | 1 + drivers/md/dm-switch.c | 1 + drivers/md/dm-sysfs.c | 1 + drivers/md/dm-table.c | 1 + drivers/md/dm-target.c | 1 + drivers/md/dm-thin-metadata.c | 1 + drivers/md/dm-thin-metadata.h | 1 + drivers/md/dm-thin.c | 1 + drivers/md/dm-unstripe.c | 1 + drivers/md/dm-verity-verify-sig.c | 2 +- drivers/md/dm-verity-verify-sig.h | 2 +- drivers/md/dm-writecache.c | 2 +- drivers/md/dm-zero.c | 1 + drivers/md/dm-zone.c | 2 +- drivers/md/dm.c | 1 + drivers/md/persistent-data/dm-array.c | 1 + drivers/md/persistent-data/dm-array.h | 1 + drivers/md/persistent-data/dm-bitset.c | 1 + drivers/md/persistent-data/dm-bitset.h | 1 + drivers/md/persistent-data/dm-block-manager.c | 1 + drivers/md/persistent-data/dm-block-manager.h | 1 + drivers/md/persistent-data/dm-btree-internal.h | 1 + drivers/md/persistent-data/dm-btree-remove.c | 1 + drivers/md/persistent-data/dm-btree-spine.c | 1 + drivers/md/persistent-data/dm-btree.c | 1 + drivers/md/persistent-data/dm-btree.h | 1 + drivers/md/persistent-data/dm-persistent-data-internal.h | 1 + drivers/md/persistent-data/dm-space-map-common.c | 1 + drivers/md/persistent-data/dm-space-map-common.h | 1 + drivers/md/persistent-data/dm-space-map-disk.c | 1 + drivers/md/persistent-data/dm-space-map-disk.h | 1 + drivers/md/persistent-data/dm-space-map-metadata.c | 1 + drivers/md/persistent-data/dm-space-map-metadata.h | 1 + drivers/md/persistent-data/dm-space-map.h | 1 + drivers/md/persistent-data/dm-transaction-manager.c | 1 + drivers/md/persistent-data/dm-transaction-manager.h | 1 + include/linux/device-mapper.h | 1 + include/linux/dm-bufio.h | 1 + include/linux/dm-dirty-log.h | 1 + include/linux/dm-io.h | 1 + include/linux/dm-kcopyd.h | 1 + include/linux/dm-region-hash.h | 1 + 100 files changed, 101 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/drivers/md/dm-audit.c b/drivers/md/dm-audit.c index 3049dfe67e50..2e979eeb1116 100644 --- a/drivers/md/dm-audit.c +++ b/drivers/md/dm-audit.c @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 +// SPDX-License-Identifier: GPL-2.0-only /* * Creating audit records for mapped devices. * diff --git a/drivers/md/dm-bio-prison-v1.c b/drivers/md/dm-bio-prison-v1.c index 1f8f98efd97a..6b172fd6bd53 100644 --- a/drivers/md/dm-bio-prison-v1.c +++ b/drivers/md/dm-bio-prison-v1.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2012 Red Hat, Inc. * diff --git a/drivers/md/dm-bio-prison-v1.h b/drivers/md/dm-bio-prison-v1.h index cec52ac5e1ae..dfbf1e94cb75 100644 --- a/drivers/md/dm-bio-prison-v1.h +++ b/drivers/md/dm-bio-prison-v1.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2011-2017 Red Hat, Inc. * diff --git a/drivers/md/dm-bio-prison-v2.c b/drivers/md/dm-bio-prison-v2.c index 9dec3b61cf70..e25baed524ee 100644 --- a/drivers/md/dm-bio-prison-v2.c +++ b/drivers/md/dm-bio-prison-v2.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2012-2017 Red Hat, Inc. * diff --git a/drivers/md/dm-bio-prison-v2.h b/drivers/md/dm-bio-prison-v2.h index 6e04234268db..8742f180f5e8 100644 --- a/drivers/md/dm-bio-prison-v2.h +++ b/drivers/md/dm-bio-prison-v2.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2011-2017 Red Hat, Inc. * diff --git a/drivers/md/dm-bio-record.h b/drivers/md/dm-bio-record.h index 745e3ab4aa0a..04d2f0cda324 100644 --- a/drivers/md/dm-bio-record.h +++ b/drivers/md/dm-bio-record.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2004-2005 Red Hat, Inc. All rights reserved. * diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index 19caaf684ee3..50e932951d09 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2009-2011 Red Hat, Inc. * diff --git a/drivers/md/dm-builtin.c b/drivers/md/dm-builtin.c index 8eb52e425141..1fb7b91f1949 100644 --- a/drivers/md/dm-builtin.c +++ b/drivers/md/dm-builtin.c @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 +// SPDX-License-Identifier: GPL-2.0-only #include "dm-core.h" /* diff --git a/drivers/md/dm-cache-background-tracker.c b/drivers/md/dm-cache-background-tracker.c index 7887f99b82bd..716c6ea4febb 100644 --- a/drivers/md/dm-cache-background-tracker.c +++ b/drivers/md/dm-cache-background-tracker.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2017 Red Hat. All rights reserved. * diff --git a/drivers/md/dm-cache-background-tracker.h b/drivers/md/dm-cache-background-tracker.h index b5056e8275c1..001439a8514c 100644 --- a/drivers/md/dm-cache-background-tracker.h +++ b/drivers/md/dm-cache-background-tracker.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2017 Red Hat. All rights reserved. * diff --git a/drivers/md/dm-cache-block-types.h b/drivers/md/dm-cache-block-types.h index 389c9e8ac785..57d2534c59ce 100644 --- a/drivers/md/dm-cache-block-types.h +++ b/drivers/md/dm-cache-block-types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2012 Red Hat, Inc. * diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c index 83a5975bcc72..dd51c298f8d6 100644 --- a/drivers/md/dm-cache-metadata.c +++ b/drivers/md/dm-cache-metadata.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2012 Red Hat, Inc. * diff --git a/drivers/md/dm-cache-metadata.h b/drivers/md/dm-cache-metadata.h index 0905f2c1615e..2789f9e3ff26 100644 --- a/drivers/md/dm-cache-metadata.h +++ b/drivers/md/dm-cache-metadata.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2012 Red Hat, Inc. * diff --git a/drivers/md/dm-cache-policy-internal.h b/drivers/md/dm-cache-policy-internal.h index 56f0a23f698c..44fc8b701441 100644 --- a/drivers/md/dm-cache-policy-internal.h +++ b/drivers/md/dm-cache-policy-internal.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2012 Red Hat. All rights reserved. * diff --git a/drivers/md/dm-cache-policy-smq.c b/drivers/md/dm-cache-policy-smq.c index a3d281fc14c3..e05977ae2923 100644 --- a/drivers/md/dm-cache-policy-smq.c +++ b/drivers/md/dm-cache-policy-smq.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2015 Red Hat. All rights reserved. * diff --git a/drivers/md/dm-cache-policy.c b/drivers/md/dm-cache-policy.c index c1a3cee99b44..e1046ad50aca 100644 --- a/drivers/md/dm-cache-policy.c +++ b/drivers/md/dm-cache-policy.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2012 Red Hat. All rights reserved. * diff --git a/drivers/md/dm-cache-policy.h b/drivers/md/dm-cache-policy.h index 06eb31af626f..f8013a8a5a0f 100644 --- a/drivers/md/dm-cache-policy.h +++ b/drivers/md/dm-cache-policy.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2012 Red Hat. All rights reserved. * diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index 5e92fac90b67..f242a860efbd 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2012 Red Hat. All rights reserved. * diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h index 6c6bd24774f2..9d1c658da468 100644 --- a/drivers/md/dm-core.h +++ b/drivers/md/dm-core.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Internal header file _only_ for device mapper core * diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index b9c41fd42e8a..7f48256db9b2 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2003 Jana Saout * Copyright (C) 2004 Clemens Fruhwirth diff --git a/drivers/md/dm-delay.c b/drivers/md/dm-delay.c index 869afef5654a..19ece841750a 100644 --- a/drivers/md/dm-delay.c +++ b/drivers/md/dm-delay.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2005-2007 Red Hat GmbH * diff --git a/drivers/md/dm-dust.c b/drivers/md/dm-dust.c index 03672204b0e3..7ae9936752de 100644 --- a/drivers/md/dm-dust.c +++ b/drivers/md/dm-dust.c @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2018 Red Hat, Inc. * diff --git a/drivers/md/dm-ebs-target.c b/drivers/md/dm-ebs-target.c index 512cc6cea095..23f9d868e20c 100644 --- a/drivers/md/dm-ebs-target.c +++ b/drivers/md/dm-ebs-target.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2020 Red Hat GmbH * diff --git a/drivers/md/dm-exception-store.c b/drivers/md/dm-exception-store.c index 3997f34cfebc..b96e312d8d59 100644 --- a/drivers/md/dm-exception-store.c +++ b/drivers/md/dm-exception-store.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2001-2002 Sistina Software (UK) Limited. * Copyright (C) 2006-2008 Red Hat GmbH diff --git a/drivers/md/dm-exception-store.h b/drivers/md/dm-exception-store.h index b5f20eba3641..1773ecf942eb 100644 --- a/drivers/md/dm-exception-store.h +++ b/drivers/md/dm-exception-store.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2001-2002 Sistina Software (UK) Limited. * Copyright (C) 2008 Red Hat, Inc. All rights reserved. diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c index 335684a1aeaa..f3be0911a95b 100644 --- a/drivers/md/dm-flakey.c +++ b/drivers/md/dm-flakey.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2003 Sistina Software (UK) Limited. * Copyright (C) 2004, 2010-2011 Red Hat, Inc. All rights reserved. diff --git a/drivers/md/dm-ima.c b/drivers/md/dm-ima.c index a1bd7cd52b1b..4e9c0e9c7a8b 100644 --- a/drivers/md/dm-ima.c +++ b/drivers/md/dm-ima.c @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2021 Microsoft Corporation * diff --git a/drivers/md/dm-ima.h b/drivers/md/dm-ima.h index b8c3b614670b..1ed96400b8d4 100644 --- a/drivers/md/dm-ima.h +++ b/drivers/md/dm-ima.h @@ -1,5 +1,5 @@ -/* SPDX-License-Identifier: GPL-2.0 - * +/* SPDX-License-Identifier: GPL-2.0-only */ +/* * Copyright (C) 2021 Microsoft Corporation * * Author: Tushar Sugandhi diff --git a/drivers/md/dm-init.c b/drivers/md/dm-init.c index dc4381d68313..5ca15528e5be 100644 --- a/drivers/md/dm-init.c +++ b/drivers/md/dm-init.c @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 +// SPDX-License-Identifier: GPL-2.0-only /* * dm-init.c diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index c62c21aadf32..b4b62b79229f 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2016-2017 Red Hat, Inc. All rights reserved. * Copyright (C) 2016-2017 Milan Broz diff --git a/drivers/md/dm-io-rewind.c b/drivers/md/dm-io-rewind.c index 0db53ccb94ba..412e63ce3b60 100644 --- a/drivers/md/dm-io-rewind.c +++ b/drivers/md/dm-io-rewind.c @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright 2022 Red Hat, Inc. */ diff --git a/drivers/md/dm-io-tracker.h b/drivers/md/dm-io-tracker.h index bdcc6273ebf0..bea1ca11855e 100644 --- a/drivers/md/dm-io-tracker.h +++ b/drivers/md/dm-io-tracker.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2021 Red Hat, Inc. All rights reserved. * diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c index 783564533459..83903255ee57 100644 --- a/drivers/md/dm-io.c +++ b/drivers/md/dm-io.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2003 Sistina Software * Copyright (C) 2006 Red Hat GmbH diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c index a3b86716f606..1c27b23c98f9 100644 --- a/drivers/md/dm-ioctl.c +++ b/drivers/md/dm-ioctl.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2001, 2002 Sistina Software (UK) Limited. * Copyright (C) 2004 - 2006 Red Hat, Inc. All rights reserved. diff --git a/drivers/md/dm-kcopyd.c b/drivers/md/dm-kcopyd.c index 4d3bbbea2e9a..387ca7daf8fd 100644 --- a/drivers/md/dm-kcopyd.c +++ b/drivers/md/dm-kcopyd.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2002 Sistina Software (UK) Limited. * Copyright (C) 2006 Red Hat GmbH diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c index 3212ef6aa81b..b0a644bff294 100644 --- a/drivers/md/dm-linear.c +++ b/drivers/md/dm-linear.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2001-2003 Sistina Software (UK) Limited. * diff --git a/drivers/md/dm-log-userspace-base.c b/drivers/md/dm-log-userspace-base.c index 9ab93ebea889..1aed04c855f9 100644 --- a/drivers/md/dm-log-userspace-base.c +++ b/drivers/md/dm-log-userspace-base.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2006-2009 Red Hat, Inc. * diff --git a/drivers/md/dm-log-userspace-transfer.c b/drivers/md/dm-log-userspace-transfer.c index fdf8ec304f8d..8037fb0dc03c 100644 --- a/drivers/md/dm-log-userspace-transfer.c +++ b/drivers/md/dm-log-userspace-transfer.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2006-2009 Red Hat, Inc. * diff --git a/drivers/md/dm-log-userspace-transfer.h b/drivers/md/dm-log-userspace-transfer.h index 04ee874f9153..f2f970af906f 100644 --- a/drivers/md/dm-log-userspace-transfer.h +++ b/drivers/md/dm-log-userspace-transfer.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2006-2009 Red Hat, Inc. * diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c index 178e13a5b059..7c3b83536481 100644 --- a/drivers/md/dm-log-writes.c +++ b/drivers/md/dm-log-writes.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2014 Facebook. All rights reserved. * diff --git a/drivers/md/dm-log.c b/drivers/md/dm-log.c index cf10fa667797..aefd977f8340 100644 --- a/drivers/md/dm-log.c +++ b/drivers/md/dm-log.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2003 Sistina Software * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved. diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index 0e325469a252..a922794b2b40 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2003 Sistina Software Limited. * Copyright (C) 2004-2005 Red Hat, Inc. All rights reserved. diff --git a/drivers/md/dm-mpath.h b/drivers/md/dm-mpath.h index e230f7196259..61aa8e49cf59 100644 --- a/drivers/md/dm-mpath.h +++ b/drivers/md/dm-mpath.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2004 Red Hat, Inc. All rights reserved. * diff --git a/drivers/md/dm-path-selector.c b/drivers/md/dm-path-selector.c index fa0ccc585cb4..93115b99bd7c 100644 --- a/drivers/md/dm-path-selector.c +++ b/drivers/md/dm-path-selector.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2003 Sistina Software. * Copyright (C) 2004 Red Hat, Inc. All rights reserved. diff --git a/drivers/md/dm-path-selector.h b/drivers/md/dm-path-selector.h index 83cac2b04b66..2e3ae9a1f687 100644 --- a/drivers/md/dm-path-selector.h +++ b/drivers/md/dm-path-selector.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2003 Sistina Software. * Copyright (C) 2004 Red Hat, Inc. All rights reserved. diff --git a/drivers/md/dm-ps-historical-service-time.c b/drivers/md/dm-ps-historical-service-time.c index 1d82c95d323d..b49e10d76d03 100644 --- a/drivers/md/dm-ps-historical-service-time.c +++ b/drivers/md/dm-ps-historical-service-time.c @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 +// SPDX-License-Identifier: GPL-2.0-only /* * Historical Service Time * diff --git a/drivers/md/dm-ps-queue-length.c b/drivers/md/dm-ps-queue-length.c index cef70657bbbc..2a24eadfe772 100644 --- a/drivers/md/dm-ps-queue-length.c +++ b/drivers/md/dm-ps-queue-length.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2004-2005 IBM Corp. All Rights Reserved. * Copyright (C) 2006-2009 NEC Corporation. diff --git a/drivers/md/dm-ps-round-robin.c b/drivers/md/dm-ps-round-robin.c index 27f44c5fa04e..e7b99a8c12a6 100644 --- a/drivers/md/dm-ps-round-robin.c +++ b/drivers/md/dm-ps-round-robin.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2003 Sistina Software. * Copyright (C) 2004-2005 Red Hat, Inc. All rights reserved. diff --git a/drivers/md/dm-ps-service-time.c b/drivers/md/dm-ps-service-time.c index 3ec9c33265c5..debc88498784 100644 --- a/drivers/md/dm-ps-service-time.c +++ b/drivers/md/dm-ps-service-time.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2007-2009 NEC Corporation. All Rights Reserved. * diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 8c66a986d647..cac781ecee5a 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2010-2011 Neil Brown * Copyright (C) 2010-2018 Red Hat, Inc. All rights reserved. diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c index 06a38dc32025..65c8f434fb2a 100644 --- a/drivers/md/dm-raid1.c +++ b/drivers/md/dm-raid1.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2003 Sistina Software Limited. * Copyright (C) 2005-2008 Red Hat, Inc. All rights reserved. diff --git a/drivers/md/dm-region-hash.c b/drivers/md/dm-region-hash.c index 1f760451e6f4..317294ff5e9c 100644 --- a/drivers/md/dm-region-hash.c +++ b/drivers/md/dm-region-hash.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2003 Sistina Software Limited. * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved. diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c index a41209a43506..38be316a22a8 100644 --- a/drivers/md/dm-rq.c +++ b/drivers/md/dm-rq.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2016 Red Hat, Inc. All rights reserved. * diff --git a/drivers/md/dm-rq.h b/drivers/md/dm-rq.h index 1eea0da641db..7360b00630ee 100644 --- a/drivers/md/dm-rq.h +++ b/drivers/md/dm-rq.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Internal header file for device mapper * diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c index 680cc05ec654..4be2d1864f0c 100644 --- a/drivers/md/dm-snap-persistent.c +++ b/drivers/md/dm-snap-persistent.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2001-2002 Sistina Software (UK) Limited. * Copyright (C) 2006-2008 Red Hat GmbH diff --git a/drivers/md/dm-snap-transient.c b/drivers/md/dm-snap-transient.c index 0e0ae4c36b37..a57bbb005b4f 100644 --- a/drivers/md/dm-snap-transient.c +++ b/drivers/md/dm-snap-transient.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2001-2002 Sistina Software (UK) Limited. * Copyright (C) 2006-2008 Red Hat GmbH diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c index d1c2f84d27e3..f737513bd365 100644 --- a/drivers/md/dm-snap.c +++ b/drivers/md/dm-snap.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2001-2002 Sistina Software (UK) Limited. * diff --git a/drivers/md/dm-stats.c b/drivers/md/dm-stats.c index f105a71915ab..d7188d011985 100644 --- a/drivers/md/dm-stats.c +++ b/drivers/md/dm-stats.c @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 +// SPDX-License-Identifier: GPL-2.0-only #include #include #include diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c index baa085cc67bd..efd23832e731 100644 --- a/drivers/md/dm-stripe.c +++ b/drivers/md/dm-stripe.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2001-2003 Sistina Software (UK) Limited. * diff --git a/drivers/md/dm-switch.c b/drivers/md/dm-switch.c index 534dc2ca8bb0..f841923b3454 100644 --- a/drivers/md/dm-switch.c +++ b/drivers/md/dm-switch.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2010-2012 by Dell Inc. All rights reserved. * Copyright (C) 2011-2013 Red Hat, Inc. diff --git a/drivers/md/dm-sysfs.c b/drivers/md/dm-sysfs.c index e28c92478536..a32a5628f04d 100644 --- a/drivers/md/dm-sysfs.c +++ b/drivers/md/dm-sysfs.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2008 Red Hat, Inc. All rights reserved. * diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 24ad42b385c1..e6709cf760ed 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2001 Sistina Software (UK) Limited. * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved. diff --git a/drivers/md/dm-target.c b/drivers/md/dm-target.c index 8cd5184e62f0..abdbcad55a7f 100644 --- a/drivers/md/dm-target.c +++ b/drivers/md/dm-target.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2001 Sistina Software (UK) Limited * diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c index 6bcc4c4786d8..96068985072f 100644 --- a/drivers/md/dm-thin-metadata.c +++ b/drivers/md/dm-thin-metadata.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2011-2012 Red Hat, Inc. * diff --git a/drivers/md/dm-thin-metadata.h b/drivers/md/dm-thin-metadata.h index 4d7a2caf21d9..2f64f48b5f19 100644 --- a/drivers/md/dm-thin-metadata.h +++ b/drivers/md/dm-thin-metadata.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2010-2011 Red Hat, Inc. * diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index 64cfcf46881d..cc32f18a4796 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2011-2012 Red Hat UK. * diff --git a/drivers/md/dm-unstripe.c b/drivers/md/dm-unstripe.c index fdc8921e5c19..e7b7d5983a16 100644 --- a/drivers/md/dm-unstripe.c +++ b/drivers/md/dm-unstripe.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2017 Intel Corporation. * diff --git a/drivers/md/dm-verity-verify-sig.c b/drivers/md/dm-verity-verify-sig.c index db61a1f43ae9..4836508ea50c 100644 --- a/drivers/md/dm-verity-verify-sig.c +++ b/drivers/md/dm-verity-verify-sig.c @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2019 Microsoft Corporation. * diff --git a/drivers/md/dm-verity-verify-sig.h b/drivers/md/dm-verity-verify-sig.h index 3987c7141f79..f36ea92127bf 100644 --- a/drivers/md/dm-verity-verify-sig.h +++ b/drivers/md/dm-verity-verify-sig.h @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2019 Microsoft Corporation. * diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c index 96a003eb7323..b1a2cb1d57ea 100644 --- a/drivers/md/dm-writecache.c +++ b/drivers/md/dm-writecache.c @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2018 Red Hat. All rights reserved. * diff --git a/drivers/md/dm-zero.c b/drivers/md/dm-zero.c index faa1dbffc8b4..2601cd520384 100644 --- a/drivers/md/dm-zero.c +++ b/drivers/md/dm-zero.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2003 Jana Saout * diff --git a/drivers/md/dm-zone.c b/drivers/md/dm-zone.c index 3dafc0e8b7a9..4b82b7798ce4 100644 --- a/drivers/md/dm-zone.c +++ b/drivers/md/dm-zone.c @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2021 Western Digital Corporation or its affiliates. */ diff --git a/drivers/md/dm.c b/drivers/md/dm.c index c391a618fb71..1de9d212be00 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2001, 2002 Sistina Software (UK) Limited. * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved. diff --git a/drivers/md/persistent-data/dm-array.c b/drivers/md/persistent-data/dm-array.c index 3a963d783a86..0f77b557231f 100644 --- a/drivers/md/persistent-data/dm-array.c +++ b/drivers/md/persistent-data/dm-array.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2012 Red Hat, Inc. * diff --git a/drivers/md/persistent-data/dm-array.h b/drivers/md/persistent-data/dm-array.h index d7d2d579c662..331cc6db3850 100644 --- a/drivers/md/persistent-data/dm-array.h +++ b/drivers/md/persistent-data/dm-array.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2012 Red Hat, Inc. * diff --git a/drivers/md/persistent-data/dm-bitset.c b/drivers/md/persistent-data/dm-bitset.c index b7208d82e748..b56a9690a300 100644 --- a/drivers/md/persistent-data/dm-bitset.c +++ b/drivers/md/persistent-data/dm-bitset.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2012 Red Hat, Inc. * diff --git a/drivers/md/persistent-data/dm-bitset.h b/drivers/md/persistent-data/dm-bitset.h index df888da04ee1..a3392ece5fab 100644 --- a/drivers/md/persistent-data/dm-bitset.h +++ b/drivers/md/persistent-data/dm-bitset.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2012 Red Hat, Inc. * diff --git a/drivers/md/persistent-data/dm-block-manager.c b/drivers/md/persistent-data/dm-block-manager.c index 11935864f50f..81c8f72664b9 100644 --- a/drivers/md/persistent-data/dm-block-manager.c +++ b/drivers/md/persistent-data/dm-block-manager.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2011 Red Hat, Inc. * diff --git a/drivers/md/persistent-data/dm-block-manager.h b/drivers/md/persistent-data/dm-block-manager.h index e728937f376a..5cc605ba6f7c 100644 --- a/drivers/md/persistent-data/dm-block-manager.h +++ b/drivers/md/persistent-data/dm-block-manager.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2011 Red Hat, Inc. * diff --git a/drivers/md/persistent-data/dm-btree-internal.h b/drivers/md/persistent-data/dm-btree-internal.h index 893edb426dba..1e645633c62c 100644 --- a/drivers/md/persistent-data/dm-btree-internal.h +++ b/drivers/md/persistent-data/dm-btree-internal.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2011 Red Hat, Inc. * diff --git a/drivers/md/persistent-data/dm-btree-remove.c b/drivers/md/persistent-data/dm-btree-remove.c index 4ead31e0d8ce..d8645af16d43 100644 --- a/drivers/md/persistent-data/dm-btree-remove.c +++ b/drivers/md/persistent-data/dm-btree-remove.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2011 Red Hat, Inc. * diff --git a/drivers/md/persistent-data/dm-btree-spine.c b/drivers/md/persistent-data/dm-btree-spine.c index e653458888a7..9c3cdbaf47a2 100644 --- a/drivers/md/persistent-data/dm-btree-spine.c +++ b/drivers/md/persistent-data/dm-btree-spine.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2011 Red Hat, Inc. * diff --git a/drivers/md/persistent-data/dm-btree.c b/drivers/md/persistent-data/dm-btree.c index 5ce64e93aae7..a4b2a9ea7cc7 100644 --- a/drivers/md/persistent-data/dm-btree.c +++ b/drivers/md/persistent-data/dm-btree.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2011 Red Hat, Inc. * diff --git a/drivers/md/persistent-data/dm-btree.h b/drivers/md/persistent-data/dm-btree.h index d2ae5aa4d00b..62461e6db408 100644 --- a/drivers/md/persistent-data/dm-btree.h +++ b/drivers/md/persistent-data/dm-btree.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2011 Red Hat, Inc. * diff --git a/drivers/md/persistent-data/dm-persistent-data-internal.h b/drivers/md/persistent-data/dm-persistent-data-internal.h index c49e26fff36c..4cfc27a9f8af 100644 --- a/drivers/md/persistent-data/dm-persistent-data-internal.h +++ b/drivers/md/persistent-data/dm-persistent-data-internal.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2011 Red Hat, Inc. * diff --git a/drivers/md/persistent-data/dm-space-map-common.c b/drivers/md/persistent-data/dm-space-map-common.c index bfbfa750e016..51b57064d49d 100644 --- a/drivers/md/persistent-data/dm-space-map-common.c +++ b/drivers/md/persistent-data/dm-space-map-common.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2011 Red Hat, Inc. * diff --git a/drivers/md/persistent-data/dm-space-map-common.h b/drivers/md/persistent-data/dm-space-map-common.h index 706ceb85d680..a6ae642dbee5 100644 --- a/drivers/md/persistent-data/dm-space-map-common.h +++ b/drivers/md/persistent-data/dm-space-map-common.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2011 Red Hat, Inc. * diff --git a/drivers/md/persistent-data/dm-space-map-disk.c b/drivers/md/persistent-data/dm-space-map-disk.c index d0a8d5e73c28..233713a090ef 100644 --- a/drivers/md/persistent-data/dm-space-map-disk.c +++ b/drivers/md/persistent-data/dm-space-map-disk.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2011 Red Hat, Inc. * diff --git a/drivers/md/persistent-data/dm-space-map-disk.h b/drivers/md/persistent-data/dm-space-map-disk.h index 447a0a9a2d9f..6f8665db94db 100644 --- a/drivers/md/persistent-data/dm-space-map-disk.h +++ b/drivers/md/persistent-data/dm-space-map-disk.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2011 Red Hat, Inc. * diff --git a/drivers/md/persistent-data/dm-space-map-metadata.c b/drivers/md/persistent-data/dm-space-map-metadata.c index 392ae26134a4..69174957a05e 100644 --- a/drivers/md/persistent-data/dm-space-map-metadata.c +++ b/drivers/md/persistent-data/dm-space-map-metadata.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2011 Red Hat, Inc. * diff --git a/drivers/md/persistent-data/dm-space-map-metadata.h b/drivers/md/persistent-data/dm-space-map-metadata.h index 64df923974d8..ca5c3e532627 100644 --- a/drivers/md/persistent-data/dm-space-map-metadata.h +++ b/drivers/md/persistent-data/dm-space-map-metadata.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2011 Red Hat, Inc. * diff --git a/drivers/md/persistent-data/dm-space-map.h b/drivers/md/persistent-data/dm-space-map.h index a015cd11f6e9..dab490353781 100644 --- a/drivers/md/persistent-data/dm-space-map.h +++ b/drivers/md/persistent-data/dm-space-map.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2011 Red Hat, Inc. * diff --git a/drivers/md/persistent-data/dm-transaction-manager.c b/drivers/md/persistent-data/dm-transaction-manager.c index 16643fc974e8..315f487e457f 100644 --- a/drivers/md/persistent-data/dm-transaction-manager.c +++ b/drivers/md/persistent-data/dm-transaction-manager.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2011 Red Hat, Inc. * diff --git a/drivers/md/persistent-data/dm-transaction-manager.h b/drivers/md/persistent-data/dm-transaction-manager.h index 906c02ed0365..70c87ce96372 100644 --- a/drivers/md/persistent-data/dm-transaction-manager.h +++ b/drivers/md/persistent-data/dm-transaction-manager.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2011 Red Hat, Inc. * diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 04c6acf7faaa..425fa9be648c 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2001 Sistina Software (UK) Limited. * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved. diff --git a/include/linux/dm-bufio.h b/include/linux/dm-bufio.h index 15d9e15ca830..798379b8597a 100644 --- a/include/linux/dm-bufio.h +++ b/include/linux/dm-bufio.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2009-2011 Red Hat, Inc. * diff --git a/include/linux/dm-dirty-log.h b/include/linux/dm-dirty-log.h index 7084503c3405..c12d40e332c1 100644 --- a/include/linux/dm-dirty-log.h +++ b/include/linux/dm-dirty-log.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2003 Sistina Software * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved. diff --git a/include/linux/dm-io.h b/include/linux/dm-io.h index 8e1c4ab5df04..6846019da2a5 100644 --- a/include/linux/dm-io.h +++ b/include/linux/dm-io.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2003 Sistina Software * Copyright (C) 2004 - 2008 Red Hat, Inc. All rights reserved. diff --git a/include/linux/dm-kcopyd.h b/include/linux/dm-kcopyd.h index c1707ee5b540..6b4ece85a2a0 100644 --- a/include/linux/dm-kcopyd.h +++ b/include/linux/dm-kcopyd.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2001 - 2003 Sistina Software * Copyright (C) 2004 - 2008 Red Hat, Inc. All rights reserved. diff --git a/include/linux/dm-region-hash.h b/include/linux/dm-region-hash.h index 9e2a7a401df5..095541c59123 100644 --- a/include/linux/dm-region-hash.h +++ b/include/linux/dm-region-hash.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2003 Sistina Software Limited. * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved. -- cgit v1.2.3 From 86a3238c7b9b759cb864f4f768ab2e24687dc0e6 Mon Sep 17 00:00:00 2001 From: Heinz Mauelshagen Date: Wed, 25 Jan 2023 21:14:58 +0100 Subject: dm: change "unsigned" to "unsigned int" Signed-off-by: Heinz Mauelshagen Signed-off-by: Mike Snitzer --- drivers/md/dm-bio-prison-v1.c | 10 +- drivers/md/dm-bio-prison-v2.c | 12 +- drivers/md/dm-bio-prison-v2.h | 10 +- drivers/md/dm-bufio.c | 58 ++-- drivers/md/dm-cache-background-tracker.c | 8 +- drivers/md/dm-cache-background-tracker.h | 6 +- drivers/md/dm-cache-metadata.c | 40 +-- drivers/md/dm-cache-metadata.h | 4 +- drivers/md/dm-cache-policy-internal.h | 10 +- drivers/md/dm-cache-policy-smq.c | 163 +++++------ drivers/md/dm-cache-policy.c | 2 +- drivers/md/dm-cache-policy.h | 4 +- drivers/md/dm-cache-target.c | 50 ++-- drivers/md/dm-core.h | 6 +- drivers/md/dm-crypt.c | 48 +-- drivers/md/dm-delay.c | 6 +- drivers/md/dm-ebs-target.c | 2 +- drivers/md/dm-era-target.c | 32 +- drivers/md/dm-exception-store.c | 6 +- drivers/md/dm-exception-store.h | 18 +- drivers/md/dm-flakey.c | 22 +- drivers/md/dm-integrity.c | 321 +++++++++++---------- drivers/md/dm-io-rewind.c | 4 +- drivers/md/dm-io.c | 32 +- drivers/md/dm-ioctl.c | 18 +- drivers/md/dm-kcopyd.c | 30 +- drivers/md/dm-linear.c | 2 +- drivers/md/dm-log-userspace-base.c | 6 +- drivers/md/dm-log-userspace-transfer.c | 2 +- drivers/md/dm-log-writes.c | 10 +- drivers/md/dm-log.c | 10 +- drivers/md/dm-mpath.c | 46 +-- drivers/md/dm-mpath.h | 2 +- drivers/md/dm-path-selector.h | 2 +- drivers/md/dm-ps-io-affinity.c | 4 +- drivers/md/dm-ps-queue-length.c | 10 +- drivers/md/dm-ps-round-robin.c | 6 +- drivers/md/dm-ps-service-time.c | 14 +- drivers/md/dm-raid.c | 2 +- drivers/md/dm-raid1.c | 22 +- drivers/md/dm-region-hash.c | 22 +- drivers/md/dm-rq.c | 16 +- drivers/md/dm-rq.h | 2 +- drivers/md/dm-snap-persistent.c | 8 +- drivers/md/dm-snap-transient.c | 6 +- drivers/md/dm-snap.c | 34 +-- drivers/md/dm-stats.c | 74 ++--- drivers/md/dm-stats.h | 6 +- drivers/md/dm-stripe.c | 10 +- drivers/md/dm-switch.c | 46 +-- drivers/md/dm-table.c | 25 +- drivers/md/dm-thin-metadata.c | 24 +- drivers/md/dm-thin.c | 46 +-- drivers/md/dm-uevent.c | 4 +- drivers/md/dm-uevent.h | 4 +- drivers/md/dm-verity-fec.c | 30 +- drivers/md/dm-verity-fec.h | 18 +- drivers/md/dm-verity-target.c | 30 +- drivers/md/dm-verity.h | 8 +- drivers/md/dm-writecache.c | 80 ++--- drivers/md/dm.c | 50 ++-- drivers/md/dm.h | 4 +- drivers/md/persistent-data/dm-array.c | 69 ++--- drivers/md/persistent-data/dm-array.h | 2 +- drivers/md/persistent-data/dm-bitset.c | 12 +- drivers/md/persistent-data/dm-block-manager.c | 16 +- drivers/md/persistent-data/dm-block-manager.h | 6 +- drivers/md/persistent-data/dm-btree-remove.c | 46 +-- drivers/md/persistent-data/dm-btree-spine.c | 4 +- drivers/md/persistent-data/dm-btree.c | 98 +++---- drivers/md/persistent-data/dm-btree.h | 12 +- .../persistent-data/dm-persistent-data-internal.h | 6 +- drivers/md/persistent-data/dm-space-map-common.c | 28 +- drivers/md/persistent-data/dm-space-map-metadata.c | 20 +- .../md/persistent-data/dm-transaction-manager.c | 16 +- .../md/persistent-data/dm-transaction-manager.h | 2 +- include/linux/device-mapper.h | 38 +-- include/linux/dm-bufio.h | 12 +- include/linux/dm-dirty-log.h | 6 +- include/linux/dm-io.h | 8 +- include/linux/dm-kcopyd.h | 22 +- include/linux/dm-region-hash.h | 2 +- 82 files changed, 1016 insertions(+), 1016 deletions(-) (limited to 'include/linux') diff --git a/drivers/md/dm-bio-prison-v1.c b/drivers/md/dm-bio-prison-v1.c index 6b172fd6bd53..be0cd3eb1fa2 100644 --- a/drivers/md/dm-bio-prison-v1.c +++ b/drivers/md/dm-bio-prison-v1.c @@ -286,14 +286,14 @@ EXPORT_SYMBOL_GPL(dm_cell_promote_or_release); struct dm_deferred_entry { struct dm_deferred_set *ds; - unsigned count; + unsigned int count; struct list_head work_items; }; struct dm_deferred_set { spinlock_t lock; - unsigned current_entry; - unsigned sweeper; + unsigned int current_entry; + unsigned int sweeper; struct dm_deferred_entry entries[DEFERRED_SET_SIZE]; }; @@ -339,7 +339,7 @@ struct dm_deferred_entry *dm_deferred_entry_inc(struct dm_deferred_set *ds) } EXPORT_SYMBOL_GPL(dm_deferred_entry_inc); -static unsigned ds_next(unsigned index) +static unsigned int ds_next(unsigned int index) { return (index + 1) % DEFERRED_SET_SIZE; } @@ -374,7 +374,7 @@ EXPORT_SYMBOL_GPL(dm_deferred_entry_dec); int dm_deferred_set_add_work(struct dm_deferred_set *ds, struct list_head *work) { int r = 1; - unsigned next_entry; + unsigned int next_entry; spin_lock_irq(&ds->lock); if ((ds->sweeper == ds->current_entry) && diff --git a/drivers/md/dm-bio-prison-v2.c b/drivers/md/dm-bio-prison-v2.c index e25baed524ee..8c8da49e39cd 100644 --- a/drivers/md/dm-bio-prison-v2.c +++ b/drivers/md/dm-bio-prison-v2.c @@ -149,7 +149,7 @@ static bool __find_or_insert(struct dm_bio_prison_v2 *prison, static bool __get(struct dm_bio_prison_v2 *prison, struct dm_cell_key_v2 *key, - unsigned lock_level, + unsigned int lock_level, struct bio *inmate, struct dm_bio_prison_cell_v2 *cell_prealloc, struct dm_bio_prison_cell_v2 **cell) @@ -172,7 +172,7 @@ static bool __get(struct dm_bio_prison_v2 *prison, bool dm_cell_get_v2(struct dm_bio_prison_v2 *prison, struct dm_cell_key_v2 *key, - unsigned lock_level, + unsigned int lock_level, struct bio *inmate, struct dm_bio_prison_cell_v2 *cell_prealloc, struct dm_bio_prison_cell_v2 **cell_result) @@ -225,7 +225,7 @@ EXPORT_SYMBOL_GPL(dm_cell_put_v2); static int __lock(struct dm_bio_prison_v2 *prison, struct dm_cell_key_v2 *key, - unsigned lock_level, + unsigned int lock_level, struct dm_bio_prison_cell_v2 *cell_prealloc, struct dm_bio_prison_cell_v2 **cell_result) { @@ -256,7 +256,7 @@ static int __lock(struct dm_bio_prison_v2 *prison, int dm_cell_lock_v2(struct dm_bio_prison_v2 *prison, struct dm_cell_key_v2 *key, - unsigned lock_level, + unsigned int lock_level, struct dm_bio_prison_cell_v2 *cell_prealloc, struct dm_bio_prison_cell_v2 **cell_result) { @@ -292,7 +292,7 @@ EXPORT_SYMBOL_GPL(dm_cell_quiesce_v2); static int __promote(struct dm_bio_prison_v2 *prison, struct dm_bio_prison_cell_v2 *cell, - unsigned new_lock_level) + unsigned int new_lock_level) { if (!cell->exclusive_lock) return -EINVAL; @@ -303,7 +303,7 @@ static int __promote(struct dm_bio_prison_v2 *prison, int dm_cell_lock_promote_v2(struct dm_bio_prison_v2 *prison, struct dm_bio_prison_cell_v2 *cell, - unsigned new_lock_level) + unsigned int new_lock_level) { int r; diff --git a/drivers/md/dm-bio-prison-v2.h b/drivers/md/dm-bio-prison-v2.h index 8742f180f5e8..ce2cca5ef2f5 100644 --- a/drivers/md/dm-bio-prison-v2.h +++ b/drivers/md/dm-bio-prison-v2.h @@ -45,8 +45,8 @@ struct dm_cell_key_v2 { struct dm_bio_prison_cell_v2 { // FIXME: pack these bool exclusive_lock; - unsigned exclusive_level; - unsigned shared_count; + unsigned int exclusive_level; + unsigned int shared_count; struct work_struct *quiesce_continuation; struct rb_node node; @@ -87,7 +87,7 @@ void dm_bio_prison_free_cell_v2(struct dm_bio_prison_v2 *prison, */ bool dm_cell_get_v2(struct dm_bio_prison_v2 *prison, struct dm_cell_key_v2 *key, - unsigned lock_level, + unsigned int lock_level, struct bio *inmate, struct dm_bio_prison_cell_v2 *cell_prealloc, struct dm_bio_prison_cell_v2 **cell_result); @@ -115,7 +115,7 @@ bool dm_cell_put_v2(struct dm_bio_prison_v2 *prison, */ int dm_cell_lock_v2(struct dm_bio_prison_v2 *prison, struct dm_cell_key_v2 *key, - unsigned lock_level, + unsigned int lock_level, struct dm_bio_prison_cell_v2 *cell_prealloc, struct dm_bio_prison_cell_v2 **cell_result); @@ -133,7 +133,7 @@ void dm_cell_quiesce_v2(struct dm_bio_prison_v2 *prison, */ int dm_cell_lock_promote_v2(struct dm_bio_prison_v2 *prison, struct dm_bio_prison_cell_v2 *cell, - unsigned new_lock_level); + unsigned int new_lock_level); /* * Adds any held bios to the bio list. diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index 50e932951d09..811ce990e72f 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -90,7 +90,7 @@ struct dm_bufio_client { unsigned long n_buffers[LIST_SIZE]; struct block_device *bdev; - unsigned block_size; + unsigned int block_size; s8 sectors_per_block_bits; void (*alloc_callback)(struct dm_buffer *); void (*write_callback)(struct dm_buffer *); @@ -99,9 +99,9 @@ struct dm_bufio_client { struct dm_io_client *dm_io; struct list_head reserved_buffers; - unsigned need_reserved_buffers; + unsigned int need_reserved_buffers; - unsigned minimum_buffers; + unsigned int minimum_buffers; struct rb_root buffer_tree; wait_queue_head_t free_buffer_wait; @@ -146,14 +146,14 @@ struct dm_buffer { unsigned char list_mode; /* LIST_* */ blk_status_t read_error; blk_status_t write_error; - unsigned accessed; - unsigned hold_count; + unsigned int accessed; + unsigned int hold_count; unsigned long state; unsigned long last_accessed; - unsigned dirty_start; - unsigned dirty_end; - unsigned write_start; - unsigned write_end; + unsigned int dirty_start; + unsigned int dirty_end; + unsigned int write_start; + unsigned int write_end; struct dm_bufio_client *c; struct list_head write_list; void (*end_io)(struct dm_buffer *, blk_status_t); @@ -221,7 +221,7 @@ static unsigned long global_num = 0; /* * Buffers are freed after this timeout */ -static unsigned dm_bufio_max_age = DM_BUFIO_DEFAULT_AGE_SECS; +static unsigned int dm_bufio_max_age = DM_BUFIO_DEFAULT_AGE_SECS; static unsigned long dm_bufio_retain_bytes = DM_BUFIO_DEFAULT_RETAIN_BYTES; static unsigned long dm_bufio_peak_allocated; @@ -439,7 +439,7 @@ static void *alloc_buffer_data(struct dm_bufio_client *c, gfp_t gfp_mask, * as if GFP_NOIO was specified. */ if (gfp_mask & __GFP_NORETRY) { - unsigned noio_flag = memalloc_noio_save(); + unsigned int noio_flag = memalloc_noio_save(); void *ptr = __vmalloc(c->block_size, gfp_mask); memalloc_noio_restore(noio_flag); @@ -592,7 +592,7 @@ static void dmio_complete(unsigned long error, void *context) } static void use_dmio(struct dm_buffer *b, enum req_op op, sector_t sector, - unsigned n_sectors, unsigned offset) + unsigned int n_sectors, unsigned int offset) { int r; struct dm_io_request io_req = { @@ -630,11 +630,11 @@ static void bio_complete(struct bio *bio) } static void use_bio(struct dm_buffer *b, enum req_op op, sector_t sector, - unsigned n_sectors, unsigned offset) + unsigned int n_sectors, unsigned int offset) { struct bio *bio; char *ptr; - unsigned vec_size, len; + unsigned int vec_size, len; vec_size = b->c->block_size >> PAGE_SHIFT; if (unlikely(b->c->sectors_per_block_bits < PAGE_SHIFT - SECTOR_SHIFT)) @@ -655,7 +655,7 @@ dmio: len = n_sectors << SECTOR_SHIFT; do { - unsigned this_step = min((unsigned)(PAGE_SIZE - offset_in_page(ptr)), len); + unsigned int this_step = min((unsigned int)(PAGE_SIZE - offset_in_page(ptr)), len); if (!bio_add_page(bio, virt_to_page(ptr), this_step, offset_in_page(ptr))) { bio_put(bio); @@ -685,9 +685,9 @@ static inline sector_t block_to_sector(struct dm_bufio_client *c, sector_t block static void submit_io(struct dm_buffer *b, enum req_op op, void (*end_io)(struct dm_buffer *, blk_status_t)) { - unsigned n_sectors; + unsigned int n_sectors; sector_t sector; - unsigned offset, end; + unsigned int offset, end; b->end_io = end_io; @@ -1157,7 +1157,7 @@ void *dm_bufio_new(struct dm_bufio_client *c, sector_t block, EXPORT_SYMBOL_GPL(dm_bufio_new); void dm_bufio_prefetch(struct dm_bufio_client *c, - sector_t block, unsigned n_blocks) + sector_t block, unsigned int n_blocks) { struct blk_plug plug; @@ -1233,7 +1233,7 @@ void dm_bufio_release(struct dm_buffer *b) EXPORT_SYMBOL_GPL(dm_bufio_release); void dm_bufio_mark_partial_buffer_dirty(struct dm_buffer *b, - unsigned start, unsigned end) + unsigned int start, unsigned int end) { struct dm_bufio_client *c = b->c; @@ -1530,13 +1530,13 @@ void dm_bufio_forget_buffers(struct dm_bufio_client *c, sector_t block, sector_t } EXPORT_SYMBOL_GPL(dm_bufio_forget_buffers); -void dm_bufio_set_minimum_buffers(struct dm_bufio_client *c, unsigned n) +void dm_bufio_set_minimum_buffers(struct dm_bufio_client *c, unsigned int n) { c->minimum_buffers = n; } EXPORT_SYMBOL_GPL(dm_bufio_set_minimum_buffers); -unsigned dm_bufio_get_block_size(struct dm_bufio_client *c) +unsigned int dm_bufio_get_block_size(struct dm_bufio_client *c) { return c->block_size; } @@ -1735,15 +1735,15 @@ static unsigned long dm_bufio_shrink_count(struct shrinker *shrink, struct shrin /* * Create the buffering interface */ -struct dm_bufio_client *dm_bufio_client_create(struct block_device *bdev, unsigned block_size, - unsigned reserved_buffers, unsigned aux_size, +struct dm_bufio_client *dm_bufio_client_create(struct block_device *bdev, unsigned int block_size, + unsigned int reserved_buffers, unsigned int aux_size, void (*alloc_callback)(struct dm_buffer *), void (*write_callback)(struct dm_buffer *), unsigned int flags) { int r; struct dm_bufio_client *c; - unsigned i; + unsigned int i; char slab_name[27]; if (!block_size || block_size & ((1 << SECTOR_SHIFT) - 1)) { @@ -1797,7 +1797,7 @@ struct dm_bufio_client *dm_bufio_client_create(struct block_device *bdev, unsign if (block_size <= KMALLOC_MAX_SIZE && (block_size < PAGE_SIZE || !is_power_of_2(block_size))) { - unsigned align = min(1U << __ffs(block_size), (unsigned)PAGE_SIZE); + unsigned int align = min(1U << __ffs(block_size), (unsigned int)PAGE_SIZE); snprintf(slab_name, sizeof slab_name, "dm_bufio_cache-%u", block_size); c->slab_cache = kmem_cache_create(slab_name, block_size, align, SLAB_RECLAIM_ACCOUNT, NULL); @@ -1873,7 +1873,7 @@ EXPORT_SYMBOL_GPL(dm_bufio_client_create); */ void dm_bufio_client_destroy(struct dm_bufio_client *c) { - unsigned i; + unsigned int i; drop_buffers(c); @@ -1921,9 +1921,9 @@ void dm_bufio_set_sector_offset(struct dm_bufio_client *c, sector_t start) } EXPORT_SYMBOL_GPL(dm_bufio_set_sector_offset); -static unsigned get_max_age_hz(void) +static unsigned int get_max_age_hz(void) { - unsigned max_age = READ_ONCE(dm_bufio_max_age); + unsigned int max_age = READ_ONCE(dm_bufio_max_age); if (max_age > UINT_MAX / HZ) max_age = UINT_MAX / HZ; @@ -1974,7 +1974,7 @@ static void do_global_cleanup(struct work_struct *w) struct dm_bufio_client *locked_client = NULL; struct dm_bufio_client *current_client; struct dm_buffer *b; - unsigned spinlock_hold_count; + unsigned int spinlock_hold_count; unsigned long threshold = dm_bufio_cache_size - dm_bufio_cache_size / DM_BUFIO_LOW_WATERMARK_RATIO; unsigned long loops = global_num * 2; diff --git a/drivers/md/dm-cache-background-tracker.c b/drivers/md/dm-cache-background-tracker.c index 716c6ea4febb..9c5308298cf1 100644 --- a/drivers/md/dm-cache-background-tracker.c +++ b/drivers/md/dm-cache-background-tracker.c @@ -18,7 +18,7 @@ struct bt_work { }; struct background_tracker { - unsigned max_work; + unsigned int max_work; atomic_t pending_promotes; atomic_t pending_writebacks; atomic_t pending_demotes; @@ -30,7 +30,7 @@ struct background_tracker { struct kmem_cache *work_cache; }; -struct background_tracker *btracker_create(unsigned max_work) +struct background_tracker *btracker_create(unsigned int max_work) { struct background_tracker *b = kmalloc(sizeof(*b), GFP_KERNEL); @@ -156,13 +156,13 @@ static void update_stats(struct background_tracker *b, struct policy_work *w, in } } -unsigned btracker_nr_writebacks_queued(struct background_tracker *b) +unsigned int btracker_nr_writebacks_queued(struct background_tracker *b) { return atomic_read(&b->pending_writebacks); } EXPORT_SYMBOL_GPL(btracker_nr_writebacks_queued); -unsigned btracker_nr_demotions_queued(struct background_tracker *b) +unsigned int btracker_nr_demotions_queued(struct background_tracker *b) { return atomic_read(&b->pending_demotes); } diff --git a/drivers/md/dm-cache-background-tracker.h b/drivers/md/dm-cache-background-tracker.h index 001439a8514c..5b8f5c667b81 100644 --- a/drivers/md/dm-cache-background-tracker.h +++ b/drivers/md/dm-cache-background-tracker.h @@ -33,7 +33,7 @@ struct background_tracker; * Create a new tracker, it will not be able to queue more than * 'max_work' entries. */ -struct background_tracker *btracker_create(unsigned max_work); +struct background_tracker *btracker_create(unsigned int max_work); /* * Destroy the tracker. No issued, but not complete, work should @@ -42,8 +42,8 @@ struct background_tracker *btracker_create(unsigned max_work); */ void btracker_destroy(struct background_tracker *b); -unsigned btracker_nr_writebacks_queued(struct background_tracker *b); -unsigned btracker_nr_demotions_queued(struct background_tracker *b); +unsigned int btracker_nr_writebacks_queued(struct background_tracker *b); +unsigned int btracker_nr_demotions_queued(struct background_tracker *b); /* * Queue some work within the tracker. 'work' should point to the work diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c index dd51c298f8d6..c7c7b4d53fd1 100644 --- a/drivers/md/dm-cache-metadata.c +++ b/drivers/md/dm-cache-metadata.c @@ -105,7 +105,7 @@ struct dm_cache_metadata { refcount_t ref_count; struct list_head list; - unsigned version; + unsigned int version; struct block_device *bdev; struct dm_block_manager *bm; struct dm_space_map *metadata_sm; @@ -130,7 +130,7 @@ struct dm_cache_metadata { bool clean_when_opened:1; char policy_name[CACHE_POLICY_NAME_SIZE]; - unsigned policy_version[CACHE_POLICY_VERSION_SIZE]; + unsigned int policy_version[CACHE_POLICY_VERSION_SIZE]; size_t policy_hint_size; struct dm_cache_statistics stats; @@ -261,10 +261,10 @@ static int superblock_lock(struct dm_cache_metadata *cmd, static int __superblock_all_zeroes(struct dm_block_manager *bm, bool *result) { int r; - unsigned i; + unsigned int i; struct dm_block *b; __le64 *data_le, zero = cpu_to_le64(0); - unsigned sb_block_size = dm_bm_block_size(bm) / sizeof(__le64); + unsigned int sb_block_size = dm_bm_block_size(bm) / sizeof(__le64); /* * We can't use a validator here - it may be all zeroes. @@ -728,7 +728,7 @@ static int __commit_transaction(struct dm_cache_metadata *cmd, */ #define FLAGS_MASK ((1 << 16) - 1) -static __le64 pack_value(dm_oblock_t block, unsigned flags) +static __le64 pack_value(dm_oblock_t block, unsigned int flags) { uint64_t value = from_oblock(block); value <<= 16; @@ -736,7 +736,7 @@ static __le64 pack_value(dm_oblock_t block, unsigned flags) return cpu_to_le64(value); } -static void unpack_value(__le64 value_le, dm_oblock_t *block, unsigned *flags) +static void unpack_value(__le64 value_le, dm_oblock_t *block, unsigned int *flags) { uint64_t value = le64_to_cpu(value_le); uint64_t b = value >> 16; @@ -750,7 +750,7 @@ static struct dm_cache_metadata *metadata_open(struct block_device *bdev, sector_t data_block_size, bool may_format_device, size_t policy_hint_size, - unsigned metadata_version) + unsigned int metadata_version) { int r; struct dm_cache_metadata *cmd; @@ -811,7 +811,7 @@ static struct dm_cache_metadata *lookup_or_open(struct block_device *bdev, sector_t data_block_size, bool may_format_device, size_t policy_hint_size, - unsigned metadata_version) + unsigned int metadata_version) { struct dm_cache_metadata *cmd, *cmd2; @@ -856,7 +856,7 @@ struct dm_cache_metadata *dm_cache_metadata_open(struct block_device *bdev, sector_t data_block_size, bool may_format_device, size_t policy_hint_size, - unsigned metadata_version) + unsigned int metadata_version) { struct dm_cache_metadata *cmd = lookup_or_open(bdev, data_block_size, may_format_device, policy_hint_size, metadata_version); @@ -891,7 +891,7 @@ static int block_clean_combined_dirty(struct dm_cache_metadata *cmd, dm_cblock_t int r; __le64 value; dm_oblock_t ob; - unsigned flags; + unsigned int flags; r = dm_array_get_value(&cmd->info, cmd->root, from_cblock(b), &value); if (r) @@ -1289,7 +1289,7 @@ static bool policy_unchanged(struct dm_cache_metadata *cmd, struct dm_cache_policy *policy) { const char *policy_name = dm_cache_policy_get_name(policy); - const unsigned *policy_version = dm_cache_policy_get_version(policy); + const unsigned int *policy_version = dm_cache_policy_get_version(policy); size_t policy_hint_size = dm_cache_policy_get_hint_size(policy); /* @@ -1340,7 +1340,7 @@ static int __load_mapping_v1(struct dm_cache_metadata *cmd, __le32 *hint_value_le; dm_oblock_t oblock; - unsigned flags; + unsigned int flags; bool dirty = true; dm_array_cursor_get_value(mapping_cursor, (void **) &mapping_value_le); @@ -1382,7 +1382,7 @@ static int __load_mapping_v2(struct dm_cache_metadata *cmd, __le32 *hint_value_le; dm_oblock_t oblock; - unsigned flags; + unsigned int flags; bool dirty = true; dm_array_cursor_get_value(mapping_cursor, (void **) &mapping_value_le); @@ -1514,7 +1514,7 @@ static int __dump_mapping(void *context, uint64_t cblock, void *leaf) { __le64 value; dm_oblock_t oblock; - unsigned flags; + unsigned int flags; memcpy(&value, leaf, sizeof(value)); unpack_value(value, &oblock, &flags); @@ -1548,7 +1548,7 @@ int dm_cache_changed_this_transaction(struct dm_cache_metadata *cmd) static int __dirty(struct dm_cache_metadata *cmd, dm_cblock_t cblock, bool dirty) { int r; - unsigned flags; + unsigned int flags; dm_oblock_t oblock; __le64 value; @@ -1575,10 +1575,10 @@ static int __dirty(struct dm_cache_metadata *cmd, dm_cblock_t cblock, bool dirty } -static int __set_dirty_bits_v1(struct dm_cache_metadata *cmd, unsigned nr_bits, unsigned long *bits) +static int __set_dirty_bits_v1(struct dm_cache_metadata *cmd, unsigned int nr_bits, unsigned long *bits) { int r; - unsigned i; + unsigned int i; for (i = 0; i < nr_bits; i++) { r = __dirty(cmd, to_cblock(i), test_bit(i, bits)); if (r) @@ -1595,7 +1595,7 @@ static int is_dirty_callback(uint32_t index, bool *value, void *context) return 0; } -static int __set_dirty_bits_v2(struct dm_cache_metadata *cmd, unsigned nr_bits, unsigned long *bits) +static int __set_dirty_bits_v2(struct dm_cache_metadata *cmd, unsigned int nr_bits, unsigned long *bits) { int r = 0; @@ -1614,7 +1614,7 @@ static int __set_dirty_bits_v2(struct dm_cache_metadata *cmd, unsigned nr_bits, } int dm_cache_set_dirty_bits(struct dm_cache_metadata *cmd, - unsigned nr_bits, + unsigned int nr_bits, unsigned long *bits) { int r; @@ -1713,7 +1713,7 @@ static int write_hints(struct dm_cache_metadata *cmd, struct dm_cache_policy *po int r; size_t hint_size; const char *policy_name = dm_cache_policy_get_name(policy); - const unsigned *policy_version = dm_cache_policy_get_version(policy); + const unsigned int *policy_version = dm_cache_policy_get_version(policy); if (!policy_name[0] || (strlen(policy_name) > sizeof(cmd->policy_name) - 1)) diff --git a/drivers/md/dm-cache-metadata.h b/drivers/md/dm-cache-metadata.h index 2789f9e3ff26..57afc7047947 100644 --- a/drivers/md/dm-cache-metadata.h +++ b/drivers/md/dm-cache-metadata.h @@ -61,7 +61,7 @@ struct dm_cache_metadata *dm_cache_metadata_open(struct block_device *bdev, sector_t data_block_size, bool may_format_device, size_t policy_hint_size, - unsigned metadata_version); + unsigned int metadata_version); void dm_cache_metadata_close(struct dm_cache_metadata *cmd); @@ -97,7 +97,7 @@ int dm_cache_load_mappings(struct dm_cache_metadata *cmd, void *context); int dm_cache_set_dirty_bits(struct dm_cache_metadata *cmd, - unsigned nr_bits, unsigned long *bits); + unsigned int nr_bits, unsigned long *bits); struct dm_cache_statistics { uint32_t read_hits; diff --git a/drivers/md/dm-cache-policy-internal.h b/drivers/md/dm-cache-policy-internal.h index 44fc8b701441..aa73fd0976ec 100644 --- a/drivers/md/dm-cache-policy-internal.h +++ b/drivers/md/dm-cache-policy-internal.h @@ -86,7 +86,7 @@ static inline void policy_tick(struct dm_cache_policy *p, bool can_block) } static inline int policy_emit_config_values(struct dm_cache_policy *p, char *result, - unsigned maxlen, ssize_t *sz_ptr) + unsigned int maxlen, ssize_t *sz_ptr) { ssize_t sz = *sz_ptr; if (p->emit_config_values) @@ -113,18 +113,18 @@ static inline void policy_allow_migrations(struct dm_cache_policy *p, bool allow /* * Some utility functions commonly used by policies and the core target. */ -static inline size_t bitset_size_in_bytes(unsigned nr_entries) +static inline size_t bitset_size_in_bytes(unsigned int nr_entries) { return sizeof(unsigned long) * dm_div_up(nr_entries, BITS_PER_LONG); } -static inline unsigned long *alloc_bitset(unsigned nr_entries) +static inline unsigned long *alloc_bitset(unsigned int nr_entries) { size_t s = bitset_size_in_bytes(nr_entries); return vzalloc(s); } -static inline void clear_bitset(void *bitset, unsigned nr_entries) +static inline void clear_bitset(void *bitset, unsigned int nr_entries) { size_t s = bitset_size_in_bytes(nr_entries); memset(bitset, 0, s); @@ -155,7 +155,7 @@ void dm_cache_policy_destroy(struct dm_cache_policy *p); */ const char *dm_cache_policy_get_name(struct dm_cache_policy *p); -const unsigned *dm_cache_policy_get_version(struct dm_cache_policy *p); +const unsigned int *dm_cache_policy_get_version(struct dm_cache_policy *p); size_t dm_cache_policy_get_hint_size(struct dm_cache_policy *p); diff --git a/drivers/md/dm-cache-policy-smq.c b/drivers/md/dm-cache-policy-smq.c index e05977ae2923..cd3a37ffb33e 100644 --- a/drivers/md/dm-cache-policy-smq.c +++ b/drivers/md/dm-cache-policy-smq.c @@ -24,12 +24,12 @@ /* * Safe division functions that return zero on divide by zero. */ -static unsigned safe_div(unsigned n, unsigned d) +static unsigned int safe_div(unsigned int n, unsigned int d) { return d ? n / d : 0u; } -static unsigned safe_mod(unsigned n, unsigned d) +static unsigned int safe_mod(unsigned int n, unsigned int d) { return d ? n % d : 0u; } @@ -37,10 +37,10 @@ static unsigned safe_mod(unsigned n, unsigned d) /*----------------------------------------------------------------*/ struct entry { - unsigned hash_next:28; - unsigned prev:28; - unsigned next:28; - unsigned level:6; + unsigned int hash_next:28; + unsigned int prev:28; + unsigned int next:28; + unsigned int level:6; bool dirty:1; bool allocated:1; bool sentinel:1; @@ -63,7 +63,7 @@ struct entry_space { struct entry *end; }; -static int space_init(struct entry_space *es, unsigned nr_entries) +static int space_init(struct entry_space *es, unsigned int nr_entries) { if (!nr_entries) { es->begin = es->end = NULL; @@ -83,7 +83,7 @@ static void space_exit(struct entry_space *es) vfree(es->begin); } -static struct entry *__get_entry(struct entry_space *es, unsigned block) +static struct entry *__get_entry(struct entry_space *es, unsigned int block) { struct entry *e; @@ -93,13 +93,13 @@ static struct entry *__get_entry(struct entry_space *es, unsigned block) return e; } -static unsigned to_index(struct entry_space *es, struct entry *e) +static unsigned int to_index(struct entry_space *es, struct entry *e) { BUG_ON(e < es->begin || e >= es->end); return e - es->begin; } -static struct entry *to_entry(struct entry_space *es, unsigned block) +static struct entry *to_entry(struct entry_space *es, unsigned int block) { if (block == INDEXER_NULL) return NULL; @@ -110,8 +110,8 @@ static struct entry *to_entry(struct entry_space *es, unsigned block) /*----------------------------------------------------------------*/ struct ilist { - unsigned nr_elts; /* excluding sentinel entries */ - unsigned head, tail; + unsigned int nr_elts; /* excluding sentinel entries */ + unsigned int head, tail; }; static void l_init(struct ilist *l) @@ -253,23 +253,23 @@ static struct entry *l_pop_tail(struct entry_space *es, struct ilist *l) struct queue { struct entry_space *es; - unsigned nr_elts; - unsigned nr_levels; + unsigned int nr_elts; + unsigned int nr_levels; struct ilist qs[MAX_LEVELS]; /* * We maintain a count of the number of entries we would like in each * level. */ - unsigned last_target_nr_elts; - unsigned nr_top_levels; - unsigned nr_in_top_levels; - unsigned target_count[MAX_LEVELS]; + unsigned int last_target_nr_elts; + unsigned int nr_top_levels; + unsigned int nr_in_top_levels; + unsigned int target_count[MAX_LEVELS]; }; -static void q_init(struct queue *q, struct entry_space *es, unsigned nr_levels) +static void q_init(struct queue *q, struct entry_space *es, unsigned int nr_levels) { - unsigned i; + unsigned int i; q->es = es; q->nr_elts = 0; @@ -285,7 +285,7 @@ static void q_init(struct queue *q, struct entry_space *es, unsigned nr_levels) q->nr_in_top_levels = 0u; } -static unsigned q_size(struct queue *q) +static unsigned int q_size(struct queue *q) { return q->nr_elts; } @@ -333,9 +333,9 @@ static void q_del(struct queue *q, struct entry *e) /* * Return the oldest entry of the lowest populated level. */ -static struct entry *q_peek(struct queue *q, unsigned max_level, bool can_cross_sentinel) +static struct entry *q_peek(struct queue *q, unsigned int max_level, bool can_cross_sentinel) { - unsigned level; + unsigned int level; struct entry *e; max_level = min(max_level, q->nr_levels); @@ -370,7 +370,7 @@ static struct entry *q_pop(struct queue *q) * used by redistribute, so we know this is true. It also doesn't adjust * the q->nr_elts count. */ -static struct entry *__redist_pop_from(struct queue *q, unsigned level) +static struct entry *__redist_pop_from(struct queue *q, unsigned int level) { struct entry *e; @@ -384,9 +384,10 @@ static struct entry *__redist_pop_from(struct queue *q, unsigned level) return NULL; } -static void q_set_targets_subrange_(struct queue *q, unsigned nr_elts, unsigned lbegin, unsigned lend) +static void q_set_targets_subrange_(struct queue *q, unsigned int nr_elts, + unsigned int lbegin, unsigned int lend) { - unsigned level, nr_levels, entries_per_level, remainder; + unsigned int level, nr_levels, entries_per_level, remainder; BUG_ON(lbegin > lend); BUG_ON(lend > q->nr_levels); @@ -427,7 +428,7 @@ static void q_set_targets(struct queue *q) static void q_redistribute(struct queue *q) { - unsigned target, level; + unsigned int target, level; struct ilist *l, *l_above; struct entry *e; @@ -468,12 +469,12 @@ static void q_redistribute(struct queue *q) } } -static void q_requeue(struct queue *q, struct entry *e, unsigned extra_levels, +static void q_requeue(struct queue *q, struct entry *e, unsigned int extra_levels, struct entry *s1, struct entry *s2) { struct entry *de; - unsigned sentinels_passed = 0; - unsigned new_level = min(q->nr_levels - 1u, e->level + extra_levels); + unsigned int sentinels_passed = 0; + unsigned int new_level = min(q->nr_levels - 1u, e->level + extra_levels); /* try and find an entry to swap with */ if (extra_levels && (e->level < q->nr_levels - 1u)) { @@ -513,9 +514,9 @@ static void q_requeue(struct queue *q, struct entry *e, unsigned extra_levels, #define EIGHTH (1u << (FP_SHIFT - 3u)) struct stats { - unsigned hit_threshold; - unsigned hits; - unsigned misses; + unsigned int hit_threshold; + unsigned int hits; + unsigned int misses; }; enum performance { @@ -524,7 +525,7 @@ enum performance { Q_WELL }; -static void stats_init(struct stats *s, unsigned nr_levels) +static void stats_init(struct stats *s, unsigned int nr_levels) { s->hit_threshold = (nr_levels * 3u) / 4u; s->hits = 0u; @@ -536,7 +537,7 @@ static void stats_reset(struct stats *s) s->hits = s->misses = 0u; } -static void stats_level_accessed(struct stats *s, unsigned level) +static void stats_level_accessed(struct stats *s, unsigned int level) { if (level >= s->hit_threshold) s->hits++; @@ -557,7 +558,7 @@ static void stats_miss(struct stats *s) */ static enum performance stats_assess(struct stats *s) { - unsigned confidence = safe_div(s->hits << FP_SHIFT, s->hits + s->misses); + unsigned int confidence = safe_div(s->hits << FP_SHIFT, s->hits + s->misses); if (confidence < SIXTEENTH) return Q_POOR; @@ -574,16 +575,16 @@ static enum performance stats_assess(struct stats *s) struct smq_hash_table { struct entry_space *es; unsigned long long hash_bits; - unsigned *buckets; + unsigned int *buckets; }; /* * All cache entries are stored in a chained hash table. To save space we * use indexing again, and only store indexes to the next entry. */ -static int h_init(struct smq_hash_table *ht, struct entry_space *es, unsigned nr_entries) +static int h_init(struct smq_hash_table *ht, struct entry_space *es, unsigned int nr_entries) { - unsigned i, nr_buckets; + unsigned int i, nr_buckets; ht->es = es; nr_buckets = roundup_pow_of_two(max(nr_entries / 4u, 16u)); @@ -604,7 +605,7 @@ static void h_exit(struct smq_hash_table *ht) vfree(ht->buckets); } -static struct entry *h_head(struct smq_hash_table *ht, unsigned bucket) +static struct entry *h_head(struct smq_hash_table *ht, unsigned int bucket) { return to_entry(ht->es, ht->buckets[bucket]); } @@ -614,7 +615,7 @@ static struct entry *h_next(struct smq_hash_table *ht, struct entry *e) return to_entry(ht->es, e->hash_next); } -static void __h_insert(struct smq_hash_table *ht, unsigned bucket, struct entry *e) +static void __h_insert(struct smq_hash_table *ht, unsigned int bucket, struct entry *e) { e->hash_next = ht->buckets[bucket]; ht->buckets[bucket] = to_index(ht->es, e); @@ -622,11 +623,11 @@ static void __h_insert(struct smq_hash_table *ht, unsigned bucket, struct entry static void h_insert(struct smq_hash_table *ht, struct entry *e) { - unsigned h = hash_64(from_oblock(e->oblock), ht->hash_bits); + unsigned int h = hash_64(from_oblock(e->oblock), ht->hash_bits); __h_insert(ht, h, e); } -static struct entry *__h_lookup(struct smq_hash_table *ht, unsigned h, dm_oblock_t oblock, +static struct entry *__h_lookup(struct smq_hash_table *ht, unsigned int h, dm_oblock_t oblock, struct entry **prev) { struct entry *e; @@ -642,7 +643,7 @@ static struct entry *__h_lookup(struct smq_hash_table *ht, unsigned h, dm_oblock return NULL; } -static void __h_unlink(struct smq_hash_table *ht, unsigned h, +static void __h_unlink(struct smq_hash_table *ht, unsigned int h, struct entry *e, struct entry *prev) { if (prev) @@ -657,7 +658,7 @@ static void __h_unlink(struct smq_hash_table *ht, unsigned h, static struct entry *h_lookup(struct smq_hash_table *ht, dm_oblock_t oblock) { struct entry *e, *prev; - unsigned h = hash_64(from_oblock(oblock), ht->hash_bits); + unsigned int h = hash_64(from_oblock(oblock), ht->hash_bits); e = __h_lookup(ht, h, oblock, &prev); if (e && prev) { @@ -674,7 +675,7 @@ static struct entry *h_lookup(struct smq_hash_table *ht, dm_oblock_t oblock) static void h_remove(struct smq_hash_table *ht, struct entry *e) { - unsigned h = hash_64(from_oblock(e->oblock), ht->hash_bits); + unsigned int h = hash_64(from_oblock(e->oblock), ht->hash_bits); struct entry *prev; /* @@ -690,16 +691,16 @@ static void h_remove(struct smq_hash_table *ht, struct entry *e) struct entry_alloc { struct entry_space *es; - unsigned begin; + unsigned int begin; - unsigned nr_allocated; + unsigned int nr_allocated; struct ilist free; }; static void init_allocator(struct entry_alloc *ea, struct entry_space *es, - unsigned begin, unsigned end) + unsigned int begin, unsigned int end) { - unsigned i; + unsigned int i; ea->es = es; ea->nr_allocated = 0u; @@ -743,7 +744,7 @@ static struct entry *alloc_entry(struct entry_alloc *ea) /* * This assumes the cblock hasn't already been allocated. */ -static struct entry *alloc_particular_entry(struct entry_alloc *ea, unsigned i) +static struct entry *alloc_particular_entry(struct entry_alloc *ea, unsigned int i) { struct entry *e = __get_entry(ea->es, ea->begin + i); @@ -771,12 +772,12 @@ static bool allocator_empty(struct entry_alloc *ea) return l_empty(&ea->free); } -static unsigned get_index(struct entry_alloc *ea, struct entry *e) +static unsigned int get_index(struct entry_alloc *ea, struct entry *e) { return to_index(ea->es, e) - ea->begin; } -static struct entry *get_entry(struct entry_alloc *ea, unsigned index) +static struct entry *get_entry(struct entry_alloc *ea, unsigned int index) { return __get_entry(ea->es, ea->begin + index); } @@ -801,9 +802,9 @@ struct smq_policy { sector_t cache_block_size; sector_t hotspot_block_size; - unsigned nr_hotspot_blocks; - unsigned cache_blocks_per_hotspot_block; - unsigned hotspot_level_jump; + unsigned int nr_hotspot_blocks; + unsigned int cache_blocks_per_hotspot_block; + unsigned int hotspot_level_jump; struct entry_space es; struct entry_alloc writeback_sentinel_alloc; @@ -832,7 +833,7 @@ struct smq_policy { * Keeps track of time, incremented by the core. We use this to * avoid attributing multiple hits within the same tick. */ - unsigned tick; + unsigned int tick; /* * The hash tables allows us to quickly find an entry by origin @@ -847,8 +848,8 @@ struct smq_policy { bool current_demote_sentinels; unsigned long next_demote_period; - unsigned write_promote_level; - unsigned read_promote_level; + unsigned int write_promote_level; + unsigned int read_promote_level; unsigned long next_hotspot_period; unsigned long next_cache_period; @@ -860,24 +861,24 @@ struct smq_policy { /*----------------------------------------------------------------*/ -static struct entry *get_sentinel(struct entry_alloc *ea, unsigned level, bool which) +static struct entry *get_sentinel(struct entry_alloc *ea, unsigned int level, bool which) { return get_entry(ea, which ? level : NR_CACHE_LEVELS + level); } -static struct entry *writeback_sentinel(struct smq_policy *mq, unsigned level) +static struct entry *writeback_sentinel(struct smq_policy *mq, unsigned int level) { return get_sentinel(&mq->writeback_sentinel_alloc, level, mq->current_writeback_sentinels); } -static struct entry *demote_sentinel(struct smq_policy *mq, unsigned level) +static struct entry *demote_sentinel(struct smq_policy *mq, unsigned int level) { return get_sentinel(&mq->demote_sentinel_alloc, level, mq->current_demote_sentinels); } static void __update_writeback_sentinels(struct smq_policy *mq) { - unsigned level; + unsigned int level; struct queue *q = &mq->dirty; struct entry *sentinel; @@ -890,7 +891,7 @@ static void __update_writeback_sentinels(struct smq_policy *mq) static void __update_demote_sentinels(struct smq_policy *mq) { - unsigned level; + unsigned int level; struct queue *q = &mq->clean; struct entry *sentinel; @@ -918,7 +919,7 @@ static void update_sentinels(struct smq_policy *mq) static void __sentinels_init(struct smq_policy *mq) { - unsigned level; + unsigned int level; struct entry *sentinel; for (level = 0; level < NR_CACHE_LEVELS; level++) { @@ -1009,7 +1010,7 @@ static void requeue(struct smq_policy *mq, struct entry *e) } } -static unsigned default_promote_level(struct smq_policy *mq) +static unsigned int default_promote_level(struct smq_policy *mq) { /* * The promote level depends on the current performance of the @@ -1031,9 +1032,9 @@ static unsigned default_promote_level(struct smq_policy *mq) 1, 1, 1, 2, 4, 6, 7, 8, 7, 6, 4, 4, 3, 3, 2, 2, 1 }; - unsigned hits = mq->cache_stats.hits; - unsigned misses = mq->cache_stats.misses; - unsigned index = safe_div(hits << 4u, hits + misses); + unsigned int hits = mq->cache_stats.hits; + unsigned int misses = mq->cache_stats.misses; + unsigned int index = safe_div(hits << 4u, hits + misses); return table[index]; } @@ -1043,7 +1044,7 @@ static void update_promote_levels(struct smq_policy *mq) * If there are unused cache entries then we want to be really * eager to promote. */ - unsigned threshold_level = allocator_empty(&mq->cache_alloc) ? + unsigned int threshold_level = allocator_empty(&mq->cache_alloc) ? default_promote_level(mq) : (NR_HOTSPOT_LEVELS / 2u); threshold_level = max(threshold_level, NR_HOTSPOT_LEVELS); @@ -1125,7 +1126,7 @@ static void end_cache_period(struct smq_policy *mq) #define CLEAN_TARGET 25u #define FREE_TARGET 25u -static unsigned percent_to_target(struct smq_policy *mq, unsigned p) +static unsigned int percent_to_target(struct smq_policy *mq, unsigned int p) { return from_cblock(mq->cache_size) * p / 100u; } @@ -1151,7 +1152,7 @@ static bool clean_target_met(struct smq_policy *mq, bool idle) static bool free_target_met(struct smq_policy *mq) { - unsigned nr_free; + unsigned int nr_free; nr_free = from_cblock(mq->cache_size) - mq->cache_alloc.nr_allocated; return (nr_free + btracker_nr_demotions_queued(mq->bg_work)) >= @@ -1301,7 +1302,7 @@ static dm_oblock_t to_hblock(struct smq_policy *mq, dm_oblock_t b) static struct entry *update_hotspot_queue(struct smq_policy *mq, dm_oblock_t b) { - unsigned hi; + unsigned int hi; dm_oblock_t hb = to_hblock(mq, b); struct entry *e = h_lookup(&mq->hotspot_table, hb); @@ -1550,7 +1551,7 @@ static void smq_clear_dirty(struct dm_cache_policy *p, dm_cblock_t cblock) spin_unlock_irqrestore(&mq->lock, flags); } -static unsigned random_level(dm_cblock_t cblock) +static unsigned int random_level(dm_cblock_t cblock) { return hash_32(from_cblock(cblock), 9) & (NR_CACHE_LEVELS - 1); } @@ -1661,7 +1662,7 @@ static int mq_set_config_value(struct dm_cache_policy *p, } static int mq_emit_config_values(struct dm_cache_policy *p, char *result, - unsigned maxlen, ssize_t *sz_ptr) + unsigned int maxlen, ssize_t *sz_ptr) { ssize_t sz = *sz_ptr; @@ -1700,16 +1701,16 @@ static void init_policy_functions(struct smq_policy *mq, bool mimic_mq) static bool too_many_hotspot_blocks(sector_t origin_size, sector_t hotspot_block_size, - unsigned nr_hotspot_blocks) + unsigned int nr_hotspot_blocks) { return (hotspot_block_size * nr_hotspot_blocks) > origin_size; } static void calc_hotspot_params(sector_t origin_size, sector_t cache_block_size, - unsigned nr_cache_blocks, + unsigned int nr_cache_blocks, sector_t *hotspot_block_size, - unsigned *nr_hotspot_blocks) + unsigned int *nr_hotspot_blocks) { *hotspot_block_size = cache_block_size * 16u; *nr_hotspot_blocks = max(nr_cache_blocks / 4u, 1024u); @@ -1725,9 +1726,9 @@ static struct dm_cache_policy *__smq_create(dm_cblock_t cache_size, bool mimic_mq, bool migrations_allowed) { - unsigned i; - unsigned nr_sentinels_per_queue = 2u * NR_CACHE_LEVELS; - unsigned total_sentinels = 2u * nr_sentinels_per_queue; + unsigned int i; + unsigned int nr_sentinels_per_queue = 2u * NR_CACHE_LEVELS; + unsigned int total_sentinels = 2u * nr_sentinels_per_queue; struct smq_policy *mq = kzalloc(sizeof(*mq), GFP_KERNEL); if (!mq) diff --git a/drivers/md/dm-cache-policy.c b/drivers/md/dm-cache-policy.c index e1046ad50aca..9330d5748895 100644 --- a/drivers/md/dm-cache-policy.c +++ b/drivers/md/dm-cache-policy.c @@ -155,7 +155,7 @@ const char *dm_cache_policy_get_name(struct dm_cache_policy *p) } EXPORT_SYMBOL_GPL(dm_cache_policy_get_name); -const unsigned *dm_cache_policy_get_version(struct dm_cache_policy *p) +const unsigned int *dm_cache_policy_get_version(struct dm_cache_policy *p) { struct dm_cache_policy_type *t = p->private; diff --git a/drivers/md/dm-cache-policy.h b/drivers/md/dm-cache-policy.h index f8013a8a5a0f..148dc45248dd 100644 --- a/drivers/md/dm-cache-policy.h +++ b/drivers/md/dm-cache-policy.h @@ -129,7 +129,7 @@ struct dm_cache_policy { * Configuration. */ int (*emit_config_values)(struct dm_cache_policy *p, char *result, - unsigned maxlen, ssize_t *sz_ptr); + unsigned int maxlen, ssize_t *sz_ptr); int (*set_config_value)(struct dm_cache_policy *p, const char *key, const char *value); @@ -158,7 +158,7 @@ struct dm_cache_policy_type { * what gets passed on the target line to select your policy. */ char name[CACHE_POLICY_NAME_SIZE]; - unsigned version[CACHE_POLICY_VERSION_SIZE]; + unsigned int version[CACHE_POLICY_VERSION_SIZE]; /* * For use by an alias dm_cache_policy_type to point to the diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index f242a860efbd..4733105a130f 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -276,7 +276,7 @@ enum cache_io_mode { struct cache_features { enum cache_metadata_mode mode; enum cache_io_mode io_mode; - unsigned metadata_version; + unsigned int metadata_version; bool discard_passdown:1; }; @@ -363,7 +363,7 @@ struct cache { * Rather than reconstructing the table line for the status we just * save it and regurgitate. */ - unsigned nr_ctr_args; + unsigned int nr_ctr_args; const char **ctr_args; struct dm_kcopyd_client *copier; @@ -379,7 +379,7 @@ struct cache { unsigned long *dirty_bitset; atomic_t nr_dirty; - unsigned policy_nr_args; + unsigned int policy_nr_args; struct dm_cache_policy *policy; /* @@ -410,7 +410,7 @@ struct cache { struct per_bio_data { bool tick:1; - unsigned req_nr:2; + unsigned int req_nr:2; struct dm_bio_prison_cell_v2 *cell; struct dm_hook_info hook_info; sector_t len; @@ -518,7 +518,7 @@ static void build_key(dm_oblock_t begin, dm_oblock_t end, struct dm_cell_key_v2 #define WRITE_LOCK_LEVEL 0 #define READ_WRITE_LOCK_LEVEL 1 -static unsigned lock_level(struct bio *bio) +static unsigned int lock_level(struct bio *bio) { return bio_data_dir(bio) == WRITE ? WRITE_LOCK_LEVEL : @@ -1881,7 +1881,7 @@ static void check_migrations(struct work_struct *ws) */ static void destroy(struct cache *cache) { - unsigned i; + unsigned int i; mempool_exit(&cache->migration_pool); @@ -2121,7 +2121,7 @@ static int parse_features(struct cache_args *ca, struct dm_arg_set *as, }; int r, mode_ctr = 0; - unsigned argc; + unsigned int argc; const char *arg; struct cache_features *cf = &ca->features; @@ -2541,7 +2541,7 @@ bad: static int copy_ctr_args(struct cache *cache, int argc, const char **argv) { - unsigned i; + unsigned int i; const char **copy; copy = kcalloc(argc, sizeof(*copy), GFP_KERNEL); @@ -2563,7 +2563,7 @@ static int copy_ctr_args(struct cache *cache, int argc, const char **argv) return 0; } -static int cache_ctr(struct dm_target *ti, unsigned argc, char **argv) +static int cache_ctr(struct dm_target *ti, unsigned int argc, char **argv) { int r = -EINVAL; struct cache_args *ca; @@ -2666,7 +2666,7 @@ static int write_dirty_bitset(struct cache *cache) static int write_discard_bitset(struct cache *cache) { - unsigned i, r; + unsigned int i, r; if (get_cache_mode(cache) >= CM_READ_ONLY) return -EINVAL; @@ -2980,11 +2980,11 @@ static void cache_resume(struct dm_target *ti) } static void emit_flags(struct cache *cache, char *result, - unsigned maxlen, ssize_t *sz_ptr) + unsigned int maxlen, ssize_t *sz_ptr) { ssize_t sz = *sz_ptr; struct cache_features *cf = &cache->features; - unsigned count = (cf->metadata_version == 2) + !cf->discard_passdown + 1; + unsigned int count = (cf->metadata_version == 2) + !cf->discard_passdown + 1; DMEMIT("%u ", count); @@ -3024,10 +3024,10 @@ static void emit_flags(struct cache *cache, char *result, * <#policy args> * */ static void cache_status(struct dm_target *ti, status_type_t type, - unsigned status_flags, char *result, unsigned maxlen) + unsigned int status_flags, char *result, unsigned int maxlen) { int r = 0; - unsigned i; + unsigned int i; ssize_t sz = 0; dm_block_t nr_free_blocks_metadata = 0; dm_block_t nr_blocks_metadata = 0; @@ -3064,18 +3064,18 @@ static void cache_status(struct dm_target *ti, status_type_t type, residency = policy_residency(cache->policy); DMEMIT("%u %llu/%llu %llu %llu/%llu %u %u %u %u %u %u %lu ", - (unsigned)DM_CACHE_METADATA_BLOCK_SIZE, + (unsigned int)DM_CACHE_METADATA_BLOCK_SIZE, (unsigned long long)(nr_blocks_metadata - nr_free_blocks_metadata), (unsigned long long)nr_blocks_metadata, (unsigned long long)cache->sectors_per_block, (unsigned long long) from_cblock(residency), (unsigned long long) from_cblock(cache->cache_size), - (unsigned) atomic_read(&cache->stats.read_hit), - (unsigned) atomic_read(&cache->stats.read_miss), - (unsigned) atomic_read(&cache->stats.write_hit), - (unsigned) atomic_read(&cache->stats.write_miss), - (unsigned) atomic_read(&cache->stats.demotion), - (unsigned) atomic_read(&cache->stats.promotion), + (unsigned int) atomic_read(&cache->stats.read_hit), + (unsigned int) atomic_read(&cache->stats.read_miss), + (unsigned int) atomic_read(&cache->stats.write_hit), + (unsigned int) atomic_read(&cache->stats.write_miss), + (unsigned int) atomic_read(&cache->stats.demotion), + (unsigned int) atomic_read(&cache->stats.promotion), (unsigned long) atomic_read(&cache->nr_dirty)); emit_flags(cache, result, maxlen, &sz); @@ -3254,11 +3254,11 @@ static int request_invalidation(struct cache *cache, struct cblock_range *range) return r; } -static int process_invalidate_cblocks_message(struct cache *cache, unsigned count, +static int process_invalidate_cblocks_message(struct cache *cache, unsigned int count, const char **cblock_ranges) { int r = 0; - unsigned i; + unsigned int i; struct cblock_range range; if (!passthrough_mode(cache)) { @@ -3295,8 +3295,8 @@ static int process_invalidate_cblocks_message(struct cache *cache, unsigned coun * * The key migration_threshold is supported by the cache target core. */ -static int cache_message(struct dm_target *ti, unsigned argc, char **argv, - char *result, unsigned maxlen) +static int cache_message(struct dm_target *ti, unsigned int argc, char **argv, + char *result, unsigned int maxlen) { struct cache *cache = ti->private; diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h index 9d1c658da468..297ccc79008e 100644 --- a/drivers/md/dm-core.h +++ b/drivers/md/dm-core.h @@ -120,7 +120,7 @@ struct mapped_device { struct dm_stats stats; /* the number of internal suspends */ - unsigned internal_suspend_count; + unsigned int internal_suspend_count; int swap_bios; struct semaphore swap_bios_semaphore; @@ -327,9 +327,9 @@ static inline struct completion *dm_get_completion_from_kobject(struct kobject * return &container_of(kobj, struct dm_kobject_holder, kobj)->completion; } -unsigned __dm_get_module_param(unsigned *module_param, unsigned def, unsigned max); +unsigned int __dm_get_module_param(unsigned int *module_param, unsigned int def, unsigned int max); -static inline bool dm_message_test_buffer_overflow(char *result, unsigned maxlen) +static inline bool dm_message_test_buffer_overflow(char *result, unsigned int maxlen) { return !maxlen || strlen(result) + 1 >= maxlen; } diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index e892e52e961f..aeb8b19ddc34 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -172,14 +172,14 @@ struct crypt_config { } iv_gen_private; u64 iv_offset; unsigned int iv_size; - unsigned short int sector_size; + unsigned short sector_size; unsigned char sector_shift; union { struct crypto_skcipher **tfms; struct crypto_aead **tfms_aead; } cipher_tfm; - unsigned tfms_count; + unsigned int tfms_count; unsigned long cipher_flags; /* @@ -213,7 +213,7 @@ struct crypt_config { * pool for per bio private data, crypto requests, * encryption requeusts/buffer pages and integrity tags */ - unsigned tag_pool_max_sectors; + unsigned int tag_pool_max_sectors; mempool_t tag_pool; mempool_t req_pool; mempool_t page_pool; @@ -230,7 +230,7 @@ struct crypt_config { #define POOL_ENTRY_SIZE 512 static DEFINE_SPINLOCK(dm_crypt_clients_lock); -static unsigned dm_crypt_clients_n = 0; +static unsigned int dm_crypt_clients_n = 0; static volatile unsigned long dm_crypt_pages_per_client; #define DM_CRYPT_MEMORY_PERCENT 2 #define DM_CRYPT_MIN_PAGES_PER_CLIENT (BIO_MAX_VECS * 16) @@ -355,7 +355,7 @@ static int crypt_iv_essiv_gen(struct crypt_config *cc, u8 *iv, static int crypt_iv_benbi_ctr(struct crypt_config *cc, struct dm_target *ti, const char *opts) { - unsigned bs; + unsigned int bs; int log; if (crypt_integrity_aead(cc)) @@ -1465,7 +1465,7 @@ static void kcryptd_async_done(struct crypto_async_request *async_req, static int crypt_alloc_req_skcipher(struct crypt_config *cc, struct convert_context *ctx) { - unsigned key_index = ctx->cc_sector & (cc->tfms_count - 1); + unsigned int key_index = ctx->cc_sector & (cc->tfms_count - 1); if (!ctx->r.req) { ctx->r.req = mempool_alloc(&cc->req_pool, in_interrupt() ? GFP_ATOMIC : GFP_NOIO); @@ -1659,13 +1659,13 @@ static void crypt_free_buffer_pages(struct crypt_config *cc, struct bio *clone); * non-blocking allocations without a mutex first but on failure we fallback * to blocking allocations with a mutex. */ -static struct bio *crypt_alloc_buffer(struct dm_crypt_io *io, unsigned size) +static struct bio *crypt_alloc_buffer(struct dm_crypt_io *io, unsigned int size) { struct crypt_config *cc = io->cc; struct bio *clone; unsigned int nr_iovecs = (size + PAGE_SIZE - 1) >> PAGE_SHIFT; gfp_t gfp_mask = GFP_NOWAIT | __GFP_HIGHMEM; - unsigned i, len, remaining_size; + unsigned int i, len, remaining_size; struct page *page; retry: @@ -1805,7 +1805,7 @@ static void crypt_endio(struct bio *clone) { struct dm_crypt_io *io = clone->bi_private; struct crypt_config *cc = io->cc; - unsigned rw = bio_data_dir(clone); + unsigned int rw = bio_data_dir(clone); blk_status_t error; /* @@ -2258,7 +2258,7 @@ static void crypt_free_tfms_aead(struct crypt_config *cc) static void crypt_free_tfms_skcipher(struct crypt_config *cc) { - unsigned i; + unsigned int i; if (!cc->cipher_tfm.tfms) return; @@ -2283,7 +2283,7 @@ static void crypt_free_tfms(struct crypt_config *cc) static int crypt_alloc_tfms_skcipher(struct crypt_config *cc, char *ciphermode) { - unsigned i; + unsigned int i; int err; cc->cipher_tfm.tfms = kcalloc(cc->tfms_count, @@ -2341,12 +2341,12 @@ static int crypt_alloc_tfms(struct crypt_config *cc, char *ciphermode) return crypt_alloc_tfms_skcipher(cc, ciphermode); } -static unsigned crypt_subkey_size(struct crypt_config *cc) +static unsigned int crypt_subkey_size(struct crypt_config *cc) { return (cc->key_size - cc->key_extra_size) >> ilog2(cc->tfms_count); } -static unsigned crypt_authenckey_size(struct crypt_config *cc) +static unsigned int crypt_authenckey_size(struct crypt_config *cc) { return crypt_subkey_size(cc) + RTA_SPACE(sizeof(struct crypto_authenc_key_param)); } @@ -2357,7 +2357,7 @@ static unsigned crypt_authenckey_size(struct crypt_config *cc) * This funcion converts cc->key to this special format. */ static void crypt_copy_authenckey(char *p, const void *key, - unsigned enckeylen, unsigned authkeylen) + unsigned int enckeylen, unsigned int authkeylen) { struct crypto_authenc_key_param *param; struct rtattr *rta; @@ -2375,7 +2375,7 @@ static void crypt_copy_authenckey(char *p, const void *key, static int crypt_setkey(struct crypt_config *cc) { - unsigned subkey_size; + unsigned int subkey_size; int err = 0, i, r; /* Ignore extra keys (which are used for IV etc) */ @@ -3414,7 +3414,7 @@ static int crypt_map(struct dm_target *ti, struct bio *bio) crypt_io_init(io, cc, bio, dm_target_offset(ti, bio->bi_iter.bi_sector)); if (cc->on_disk_tag_size) { - unsigned tag_len = cc->on_disk_tag_size * (bio_sectors(bio) >> cc->sector_shift); + unsigned int tag_len = cc->on_disk_tag_size * (bio_sectors(bio) >> cc->sector_shift); if (unlikely(tag_len > KMALLOC_MAX_SIZE) || unlikely(!(io->integrity_metadata = kmalloc(tag_len, @@ -3442,14 +3442,14 @@ static int crypt_map(struct dm_target *ti, struct bio *bio) static char hex2asc(unsigned char c) { - return c + '0' + ((unsigned)(9 - c) >> 4 & 0x27); + return c + '0' + ((unsigned int)(9 - c) >> 4 & 0x27); } static void crypt_status(struct dm_target *ti, status_type_t type, - unsigned status_flags, char *result, unsigned maxlen) + unsigned int status_flags, char *result, unsigned int maxlen) { struct crypt_config *cc = ti->private; - unsigned i, sz = 0; + unsigned int i, sz = 0; int num_feature_args = 0; switch (type) { @@ -3565,8 +3565,8 @@ static void crypt_resume(struct dm_target *ti) * key set * key wipe */ -static int crypt_message(struct dm_target *ti, unsigned argc, char **argv, - char *result, unsigned maxlen) +static int crypt_message(struct dm_target *ti, unsigned int argc, char **argv, + char *result, unsigned int maxlen) { struct crypt_config *cc = ti->private; int key_size, ret = -EINVAL; @@ -3627,10 +3627,10 @@ static void crypt_io_hints(struct dm_target *ti, struct queue_limits *limits) limits->max_segment_size = PAGE_SIZE; limits->logical_block_size = - max_t(unsigned, limits->logical_block_size, cc->sector_size); + max_t(unsigned int, limits->logical_block_size, cc->sector_size); limits->physical_block_size = - max_t(unsigned, limits->physical_block_size, cc->sector_size); - limits->io_min = max_t(unsigned, limits->io_min, cc->sector_size); + max_t(unsigned int, limits->physical_block_size, cc->sector_size); + limits->io_min = max_t(unsigned int, limits->io_min, cc->sector_size); limits->dma_alignment = limits->logical_block_size - 1; } diff --git a/drivers/md/dm-delay.c b/drivers/md/dm-delay.c index 19ece841750a..a425046f88c7 100644 --- a/drivers/md/dm-delay.c +++ b/drivers/md/dm-delay.c @@ -21,8 +21,8 @@ struct delay_class { struct dm_dev *dev; sector_t start; - unsigned delay; - unsigned ops; + unsigned int delay; + unsigned int ops; }; struct delay_c { @@ -306,7 +306,7 @@ static int delay_map(struct dm_target *ti, struct bio *bio) DMEMIT("%s %llu %u", (c)->dev->name, (unsigned long long)(c)->start, (c)->delay) static void delay_status(struct dm_target *ti, status_type_t type, - unsigned status_flags, char *result, unsigned maxlen) + unsigned int status_flags, char *result, unsigned int maxlen) { struct delay_c *dc = ti->private; int sz = 0; diff --git a/drivers/md/dm-ebs-target.c b/drivers/md/dm-ebs-target.c index 23f9d868e20c..71b844bdcdb8 100644 --- a/drivers/md/dm-ebs-target.c +++ b/drivers/md/dm-ebs-target.c @@ -391,7 +391,7 @@ static int ebs_map(struct dm_target *ti, struct bio *bio) } static void ebs_status(struct dm_target *ti, status_type_t type, - unsigned status_flags, char *result, unsigned maxlen) + unsigned int status_flags, char *result, unsigned int maxlen) { struct ebs_c *ec = ti->private; diff --git a/drivers/md/dm-era-target.c b/drivers/md/dm-era-target.c index e92c1afc3677..a96290103cca 100644 --- a/drivers/md/dm-era-target.c +++ b/drivers/md/dm-era-target.c @@ -51,7 +51,7 @@ static void writeset_free(struct writeset *ws) } static int setup_on_disk_bitset(struct dm_disk_bitset *info, - unsigned nr_bits, dm_block_t *root) + unsigned int nr_bits, dm_block_t *root) { int r; @@ -62,7 +62,7 @@ static int setup_on_disk_bitset(struct dm_disk_bitset *info, return dm_bitset_resize(info, *root, 0, nr_bits, false, root); } -static size_t bitset_size(unsigned nr_bits) +static size_t bitset_size(unsigned int nr_bits) { return sizeof(unsigned long) * dm_div_up(nr_bits, BITS_PER_LONG); } @@ -323,10 +323,10 @@ static int superblock_lock(struct era_metadata *md, static int superblock_all_zeroes(struct dm_block_manager *bm, bool *result) { int r; - unsigned i; + unsigned int i; struct dm_block *b; __le64 *data_le, zero = cpu_to_le64(0); - unsigned sb_block_size = dm_bm_block_size(bm) / sizeof(__le64); + unsigned int sb_block_size = dm_bm_block_size(bm) / sizeof(__le64); /* * We can't use a validator here - it may be all zeroes. @@ -363,12 +363,12 @@ static void ws_unpack(const struct writeset_disk *disk, struct writeset_metadata core->root = le64_to_cpu(disk->root); } -static void ws_inc(void *context, const void *value, unsigned count) +static void ws_inc(void *context, const void *value, unsigned int count) { struct era_metadata *md = context; struct writeset_disk ws_d; dm_block_t b; - unsigned i; + unsigned int i; for (i = 0; i < count; i++) { memcpy(&ws_d, value + (i * sizeof(ws_d)), sizeof(ws_d)); @@ -377,12 +377,12 @@ static void ws_inc(void *context, const void *value, unsigned count) } } -static void ws_dec(void *context, const void *value, unsigned count) +static void ws_dec(void *context, const void *value, unsigned int count) { struct era_metadata *md = context; struct writeset_disk ws_d; dm_block_t b; - unsigned i; + unsigned int i; for (i = 0; i < count; i++) { memcpy(&ws_d, value + (i * sizeof(ws_d)), sizeof(ws_d)); @@ -667,7 +667,7 @@ static void swap_writeset(struct era_metadata *md, struct writeset *new_writeset *--------------------------------------------------------------*/ struct digest { uint32_t era; - unsigned nr_bits, current_bit; + unsigned int nr_bits, current_bit; struct writeset_metadata writeset; __le32 value; struct dm_disk_bitset info; @@ -702,7 +702,7 @@ static int metadata_digest_transcribe_writeset(struct era_metadata *md, { int r; bool marked; - unsigned b, e = min(d->current_bit + INSERTS_PER_STEP, d->nr_bits); + unsigned int b, e = min(d->current_bit + INSERTS_PER_STEP, d->nr_bits); for (b = d->current_bit; b < e; b++) { r = writeset_marked_on_disk(&d->info, &d->writeset, b, &marked); @@ -1439,7 +1439,7 @@ static bool valid_block_size(dm_block_t block_size) /* * */ -static int era_ctr(struct dm_target *ti, unsigned argc, char **argv) +static int era_ctr(struct dm_target *ti, unsigned int argc, char **argv) { int r; char dummy; @@ -1618,7 +1618,7 @@ static int era_preresume(struct dm_target *ti) * */ static void era_status(struct dm_target *ti, status_type_t type, - unsigned status_flags, char *result, unsigned maxlen) + unsigned int status_flags, char *result, unsigned int maxlen) { int r; struct era *era = ti->private; @@ -1633,10 +1633,10 @@ static void era_status(struct dm_target *ti, status_type_t type, goto err; DMEMIT("%u %llu/%llu %u", - (unsigned) (DM_ERA_METADATA_BLOCK_SIZE >> SECTOR_SHIFT), + (unsigned int) (DM_ERA_METADATA_BLOCK_SIZE >> SECTOR_SHIFT), (unsigned long long) stats.used, (unsigned long long) stats.total, - (unsigned) stats.era); + (unsigned int) stats.era); if (stats.snap != SUPERBLOCK_LOCATION) DMEMIT(" %llu", stats.snap); @@ -1662,8 +1662,8 @@ err: DMEMIT("Error"); } -static int era_message(struct dm_target *ti, unsigned argc, char **argv, - char *result, unsigned maxlen) +static int era_message(struct dm_target *ti, unsigned int argc, char **argv, + char *result, unsigned int maxlen) { struct era *era = ti->private; diff --git a/drivers/md/dm-exception-store.c b/drivers/md/dm-exception-store.c index b96e312d8d59..c3799757bf4a 100644 --- a/drivers/md/dm-exception-store.c +++ b/drivers/md/dm-exception-store.c @@ -143,7 +143,7 @@ EXPORT_SYMBOL(dm_exception_store_type_unregister); static int set_chunk_size(struct dm_exception_store *store, const char *chunk_size_arg, char **error) { - unsigned chunk_size; + unsigned int chunk_size; if (kstrtouint(chunk_size_arg, 10, &chunk_size)) { *error = "Invalid chunk size"; @@ -159,7 +159,7 @@ static int set_chunk_size(struct dm_exception_store *store, } int dm_exception_store_set_chunk_size(struct dm_exception_store *store, - unsigned chunk_size, + unsigned int chunk_size, char **error) { /* Check chunk_size is a power of 2 */ @@ -191,7 +191,7 @@ int dm_exception_store_set_chunk_size(struct dm_exception_store *store, int dm_exception_store_create(struct dm_target *ti, int argc, char **argv, struct dm_snapshot *snap, - unsigned *args_used, + unsigned int *args_used, struct dm_exception_store **store) { int r = 0; diff --git a/drivers/md/dm-exception-store.h b/drivers/md/dm-exception-store.h index 1773ecf942eb..62df388af33a 100644 --- a/drivers/md/dm-exception-store.h +++ b/drivers/md/dm-exception-store.h @@ -97,9 +97,9 @@ struct dm_exception_store_type { */ void (*drop_snapshot) (struct dm_exception_store *store); - unsigned (*status) (struct dm_exception_store *store, - status_type_t status, char *result, - unsigned maxlen); + unsigned int (*status) (struct dm_exception_store *store, + status_type_t status, char *result, + unsigned int maxlen); /* * Return how full the snapshot is. @@ -119,9 +119,9 @@ struct dm_exception_store { struct dm_snapshot *snap; /* Size of data blocks saved - must be a power of 2 */ - unsigned chunk_size; - unsigned chunk_mask; - unsigned chunk_shift; + unsigned int chunk_size; + unsigned int chunk_mask; + unsigned int chunk_shift; void *context; @@ -145,7 +145,7 @@ static inline chunk_t dm_chunk_number(chunk_t chunk) return chunk & (chunk_t)((1ULL << DM_CHUNK_NUMBER_BITS) - 1ULL); } -static inline unsigned dm_consecutive_chunk_count(struct dm_exception *e) +static inline unsigned int dm_consecutive_chunk_count(struct dm_exception *e) { return e->new_chunk >> DM_CHUNK_NUMBER_BITS; } @@ -182,12 +182,12 @@ int dm_exception_store_type_register(struct dm_exception_store_type *type); int dm_exception_store_type_unregister(struct dm_exception_store_type *type); int dm_exception_store_set_chunk_size(struct dm_exception_store *store, - unsigned chunk_size, + unsigned int chunk_size, char **error); int dm_exception_store_create(struct dm_target *ti, int argc, char **argv, struct dm_snapshot *snap, - unsigned *args_used, + unsigned int *args_used, struct dm_exception_store **store); void dm_exception_store_destroy(struct dm_exception_store *store); diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c index f3be0911a95b..1f469161998e 100644 --- a/drivers/md/dm-flakey.c +++ b/drivers/md/dm-flakey.c @@ -27,12 +27,12 @@ struct flakey_c { struct dm_dev *dev; unsigned long start_time; sector_t start; - unsigned up_interval; - unsigned down_interval; + unsigned int up_interval; + unsigned int down_interval; unsigned long flags; - unsigned corrupt_bio_byte; - unsigned corrupt_bio_rw; - unsigned corrupt_bio_value; + unsigned int corrupt_bio_byte; + unsigned int corrupt_bio_rw; + unsigned int corrupt_bio_value; blk_opf_t corrupt_bio_flags; }; @@ -49,7 +49,7 @@ static int parse_features(struct dm_arg_set *as, struct flakey_c *fc, struct dm_target *ti) { int r; - unsigned argc; + unsigned int argc; const char *arg_name; static const struct dm_arg _args[] = { @@ -149,7 +149,7 @@ static int parse_features(struct dm_arg_set *as, struct flakey_c *fc, BUILD_BUG_ON(sizeof(fc->corrupt_bio_flags) != sizeof(unsigned int)); r = dm_read_arg(_args + 3, as, - (__force unsigned *)&fc->corrupt_bio_flags, + (__force unsigned int *)&fc->corrupt_bio_flags, &ti->error); if (r) return r; @@ -325,7 +325,7 @@ static void corrupt_bio_data(struct bio *bio, struct flakey_c *fc) static int flakey_map(struct dm_target *ti, struct bio *bio) { struct flakey_c *fc = ti->private; - unsigned elapsed; + unsigned int elapsed; struct per_bio_data *pb = dm_per_bio_data(bio, sizeof(struct per_bio_data)); pb->bio_submitted = false; @@ -418,11 +418,11 @@ static int flakey_end_io(struct dm_target *ti, struct bio *bio, } static void flakey_status(struct dm_target *ti, status_type_t type, - unsigned status_flags, char *result, unsigned maxlen) + unsigned int status_flags, char *result, unsigned int maxlen) { - unsigned sz = 0; + unsigned int sz = 0; struct flakey_c *fc = ti->private; - unsigned drop_writes, error_writes; + unsigned int drop_writes, error_writes; switch (type) { case STATUSTYPE_INFO: diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index b4b62b79229f..efae9d7e3a56 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -158,13 +158,13 @@ struct alg_spec { char *alg_string; char *key_string; __u8 *key; - unsigned key_size; + unsigned int key_size; }; struct dm_integrity_c { struct dm_dev *dev; struct dm_dev *meta_dev; - unsigned tag_size; + unsigned int tag_size; __s8 log2_tag_size; sector_t start; mempool_t journal_io_mempool; @@ -172,8 +172,8 @@ struct dm_integrity_c { struct dm_bufio_client *bufio; struct workqueue_struct *metadata_wq; struct superblock *sb; - unsigned journal_pages; - unsigned n_bitmap_blocks; + unsigned int journal_pages; + unsigned int n_bitmap_blocks; struct page_list *journal; struct page_list *journal_io; @@ -181,7 +181,7 @@ struct dm_integrity_c { struct page_list *recalc_bitmap; struct page_list *may_write_bitmap; struct bitmap_block_status *bbs; - unsigned bitmap_flush_interval; + unsigned int bitmap_flush_interval; int synchronous_mode; struct bio_list synchronous_bios; struct delayed_work bitmap_flush_work; @@ -202,12 +202,12 @@ struct dm_integrity_c { unsigned char journal_entries_per_sector; unsigned char journal_section_entries; unsigned short journal_section_sectors; - unsigned journal_sections; - unsigned journal_entries; + unsigned int journal_sections; + unsigned int journal_entries; sector_t data_device_sectors; sector_t meta_device_sectors; - unsigned initial_sectors; - unsigned metadata_run; + unsigned int initial_sectors; + unsigned int metadata_run; __s8 log2_metadata_run; __u8 log2_buffer_sectors; __u8 sectors_per_block; @@ -231,17 +231,17 @@ struct dm_integrity_c { unsigned char commit_seq; commit_id_t commit_ids[N_COMMIT_IDS]; - unsigned committed_section; - unsigned n_committed_sections; + unsigned int committed_section; + unsigned int n_committed_sections; - unsigned uncommitted_section; - unsigned n_uncommitted_sections; + unsigned int uncommitted_section; + unsigned int n_uncommitted_sections; - unsigned free_section; + unsigned int free_section; unsigned char free_section_entry; - unsigned free_sectors; + unsigned int free_sectors; - unsigned free_sectors_threshold; + unsigned int free_sectors_threshold; struct workqueue_struct *commit_wq; struct work_struct commit_work; @@ -258,7 +258,7 @@ struct dm_integrity_c { unsigned long autocommit_jiffies; struct timer_list autocommit_timer; - unsigned autocommit_msec; + unsigned int autocommit_msec; wait_queue_head_t copy_to_journal_wait; @@ -306,7 +306,7 @@ struct dm_integrity_io { struct dm_integrity_range range; sector_t metadata_block; - unsigned metadata_offset; + unsigned int metadata_offset; atomic_t in_flight; blk_status_t bi_status; @@ -330,7 +330,7 @@ struct journal_io { struct bitmap_block_status { struct work_struct work; struct dm_integrity_c *ic; - unsigned idx; + unsigned int idx; unsigned long *bitmap; struct bio_list bio_queue; spinlock_t bio_queue_lock; @@ -411,8 +411,8 @@ static bool dm_integrity_disable_recalculate(struct dm_integrity_c *ic) return false; } -static commit_id_t dm_integrity_commit_id(struct dm_integrity_c *ic, unsigned i, - unsigned j, unsigned char seq) +static commit_id_t dm_integrity_commit_id(struct dm_integrity_c *ic, unsigned int i, + unsigned int j, unsigned char seq) { /* * Xor the number with section and sector, so that if a piece of @@ -427,7 +427,7 @@ static void get_area_and_offset(struct dm_integrity_c *ic, sector_t data_sector, if (!ic->meta_dev) { __u8 log2_interleave_sectors = ic->sb->log2_interleave_sectors; *area = data_sector >> log2_interleave_sectors; - *offset = (unsigned)data_sector & ((1U << log2_interleave_sectors) - 1); + *offset = (unsigned int)data_sector & ((1U << log2_interleave_sectors) - 1); } else { *area = 0; *offset = data_sector; @@ -436,15 +436,15 @@ static void get_area_and_offset(struct dm_integrity_c *ic, sector_t data_sector, #define sector_to_block(ic, n) \ do { \ - BUG_ON((n) & (unsigned)((ic)->sectors_per_block - 1)); \ + BUG_ON((n) & (unsigned int)((ic)->sectors_per_block - 1)); \ (n) >>= (ic)->sb->log2_sectors_per_block; \ } while (0) static __u64 get_metadata_sector_and_offset(struct dm_integrity_c *ic, sector_t area, - sector_t offset, unsigned *metadata_offset) + sector_t offset, unsigned int *metadata_offset) { __u64 ms; - unsigned mo; + unsigned int mo; ms = area << ic->sb->log2_interleave_sectors; if (likely(ic->log2_metadata_run >= 0)) @@ -485,7 +485,7 @@ static sector_t get_data_sector(struct dm_integrity_c *ic, sector_t area, sector return result; } -static void wraparound_section(struct dm_integrity_c *ic, unsigned *sec_ptr) +static void wraparound_section(struct dm_integrity_c *ic, unsigned int *sec_ptr) { if (unlikely(*sec_ptr >= ic->journal_sections)) *sec_ptr -= ic->journal_sections; @@ -509,7 +509,7 @@ static int sb_mac(struct dm_integrity_c *ic, bool wr) { SHASH_DESC_ON_STACK(desc, ic->journal_mac); int r; - unsigned size = crypto_shash_digestsize(ic->journal_mac); + unsigned int size = crypto_shash_digestsize(ic->journal_mac); if (sizeof(struct superblock) + size > 1 << SECTOR_SHIFT) { dm_integrity_io_error(ic, "digest is too long", -EINVAL); @@ -705,8 +705,8 @@ repeat: static void block_bitmap_copy(struct dm_integrity_c *ic, struct page_list *dst, struct page_list *src) { - unsigned n_bitmap_pages = DIV_ROUND_UP(ic->n_bitmap_blocks, PAGE_SIZE / BITMAP_BLOCK_SIZE); - unsigned i; + unsigned int n_bitmap_pages = DIV_ROUND_UP(ic->n_bitmap_blocks, PAGE_SIZE / BITMAP_BLOCK_SIZE); + unsigned int i; for (i = 0; i < n_bitmap_pages; i++) { unsigned long *dst_data = lowmem_page_address(dst[i].page); @@ -717,18 +717,18 @@ static void block_bitmap_copy(struct dm_integrity_c *ic, struct page_list *dst, static struct bitmap_block_status *sector_to_bitmap_block(struct dm_integrity_c *ic, sector_t sector) { - unsigned bit = sector >> (ic->sb->log2_sectors_per_block + ic->log2_blocks_per_bitmap_bit); - unsigned bitmap_block = bit / (BITMAP_BLOCK_SIZE * 8); + unsigned int bit = sector >> (ic->sb->log2_sectors_per_block + ic->log2_blocks_per_bitmap_bit); + unsigned int bitmap_block = bit / (BITMAP_BLOCK_SIZE * 8); BUG_ON(bitmap_block >= ic->n_bitmap_blocks); return &ic->bbs[bitmap_block]; } -static void access_journal_check(struct dm_integrity_c *ic, unsigned section, unsigned offset, +static void access_journal_check(struct dm_integrity_c *ic, unsigned int section, unsigned int offset, bool e, const char *function) { #if defined(CONFIG_DM_DEBUG) || defined(INTERNAL_VERIFY) - unsigned limit = e ? ic->journal_section_entries : ic->journal_section_sectors; + unsigned int limit = e ? ic->journal_section_entries : ic->journal_section_sectors; if (unlikely(section >= ic->journal_sections) || unlikely(offset >= limit)) { @@ -739,10 +739,10 @@ static void access_journal_check(struct dm_integrity_c *ic, unsigned section, un #endif } -static void page_list_location(struct dm_integrity_c *ic, unsigned section, unsigned offset, - unsigned *pl_index, unsigned *pl_offset) +static void page_list_location(struct dm_integrity_c *ic, unsigned int section, unsigned int offset, + unsigned int *pl_index, unsigned int *pl_offset) { - unsigned sector; + unsigned int sector; access_journal_check(ic, section, offset, false, "page_list_location"); @@ -753,9 +753,9 @@ static void page_list_location(struct dm_integrity_c *ic, unsigned section, unsi } static struct journal_sector *access_page_list(struct dm_integrity_c *ic, struct page_list *pl, - unsigned section, unsigned offset, unsigned *n_sectors) + unsigned int section, unsigned int offset, unsigned int *n_sectors) { - unsigned pl_index, pl_offset; + unsigned int pl_index, pl_offset; char *va; page_list_location(ic, section, offset, &pl_index, &pl_offset); @@ -768,14 +768,14 @@ static struct journal_sector *access_page_list(struct dm_integrity_c *ic, struct return (struct journal_sector *)(va + pl_offset); } -static struct journal_sector *access_journal(struct dm_integrity_c *ic, unsigned section, unsigned offset) +static struct journal_sector *access_journal(struct dm_integrity_c *ic, unsigned int section, unsigned int offset) { return access_page_list(ic, ic->journal, section, offset, NULL); } -static struct journal_entry *access_journal_entry(struct dm_integrity_c *ic, unsigned section, unsigned n) +static struct journal_entry *access_journal_entry(struct dm_integrity_c *ic, unsigned int section, unsigned int n) { - unsigned rel_sector, offset; + unsigned int rel_sector, offset; struct journal_sector *js; access_journal_check(ic, section, n, true, "access_journal_entry"); @@ -787,7 +787,7 @@ static struct journal_entry *access_journal_entry(struct dm_integrity_c *ic, uns return (struct journal_entry *)((char *)js + offset * ic->journal_entry_size); } -static struct journal_sector *access_journal_data(struct dm_integrity_c *ic, unsigned section, unsigned n) +static struct journal_sector *access_journal_data(struct dm_integrity_c *ic, unsigned int section, unsigned int n) { n <<= ic->sb->log2_sectors_per_block; @@ -798,11 +798,11 @@ static struct journal_sector *access_journal_data(struct dm_integrity_c *ic, uns return access_journal(ic, section, n); } -static void section_mac(struct dm_integrity_c *ic, unsigned section, __u8 result[JOURNAL_MAC_SIZE]) +static void section_mac(struct dm_integrity_c *ic, unsigned int section, __u8 result[JOURNAL_MAC_SIZE]) { SHASH_DESC_ON_STACK(desc, ic->journal_mac); int r; - unsigned j, size; + unsigned int j, size; desc->tfm = ic->journal_mac; @@ -867,10 +867,10 @@ err: memset(result, 0, JOURNAL_MAC_SIZE); } -static void rw_section_mac(struct dm_integrity_c *ic, unsigned section, bool wr) +static void rw_section_mac(struct dm_integrity_c *ic, unsigned int section, bool wr) { __u8 result[JOURNAL_MAC_SIZE]; - unsigned j; + unsigned int j; if (!ic->journal_mac) return; @@ -899,12 +899,12 @@ static void complete_journal_op(void *context) complete(&comp->comp); } -static void xor_journal(struct dm_integrity_c *ic, bool encrypt, unsigned section, - unsigned n_sections, struct journal_completion *comp) +static void xor_journal(struct dm_integrity_c *ic, bool encrypt, unsigned int section, + unsigned int n_sections, struct journal_completion *comp) { struct async_submit_ctl submit; size_t n_bytes = (size_t)(n_sections * ic->journal_section_sectors) << SECTOR_SHIFT; - unsigned pl_index, pl_offset, section_index; + unsigned int pl_index, pl_offset, section_index; struct page_list *source_pl, *target_pl; if (likely(encrypt)) { @@ -929,7 +929,7 @@ static void xor_journal(struct dm_integrity_c *ic, bool encrypt, unsigned sectio struct page *dst_page; while (unlikely(pl_index == section_index)) { - unsigned dummy; + unsigned int dummy; if (likely(encrypt)) rw_section_mac(ic, section, true); section++; @@ -991,8 +991,8 @@ static bool do_crypt(bool encrypt, struct skcipher_request *req, struct journal_ return false; } -static void crypt_journal(struct dm_integrity_c *ic, bool encrypt, unsigned section, - unsigned n_sections, struct journal_completion *comp) +static void crypt_journal(struct dm_integrity_c *ic, bool encrypt, unsigned int section, + unsigned int n_sections, struct journal_completion *comp) { struct scatterlist **source_sg; struct scatterlist **target_sg; @@ -1009,7 +1009,7 @@ static void crypt_journal(struct dm_integrity_c *ic, bool encrypt, unsigned sect do { struct skcipher_request *req; - unsigned ivsize; + unsigned int ivsize; char *iv; if (likely(encrypt)) @@ -1035,8 +1035,8 @@ static void crypt_journal(struct dm_integrity_c *ic, bool encrypt, unsigned sect complete_journal_op(comp); } -static void encrypt_journal(struct dm_integrity_c *ic, bool encrypt, unsigned section, - unsigned n_sections, struct journal_completion *comp) +static void encrypt_journal(struct dm_integrity_c *ic, bool encrypt, unsigned int section, + unsigned int n_sections, struct journal_completion *comp) { if (ic->journal_xor) return xor_journal(ic, encrypt, section, n_sections, comp); @@ -1053,12 +1053,12 @@ static void complete_journal_io(unsigned long error, void *context) } static void rw_journal_sectors(struct dm_integrity_c *ic, blk_opf_t opf, - unsigned sector, unsigned n_sectors, + unsigned int sector, unsigned int n_sectors, struct journal_completion *comp) { struct dm_io_request io_req; struct dm_io_region io_loc; - unsigned pl_index, pl_offset; + unsigned int pl_index, pl_offset; int r; if (unlikely(dm_integrity_failed(ic))) { @@ -1100,10 +1100,10 @@ static void rw_journal_sectors(struct dm_integrity_c *ic, blk_opf_t opf, } static void rw_journal(struct dm_integrity_c *ic, blk_opf_t opf, - unsigned section, unsigned n_sections, + unsigned int section, unsigned int n_sections, struct journal_completion *comp) { - unsigned sector, n_sectors; + unsigned int sector, n_sectors; sector = section * ic->journal_section_sectors; n_sectors = n_sections * ic->journal_section_sectors; @@ -1111,12 +1111,12 @@ static void rw_journal(struct dm_integrity_c *ic, blk_opf_t opf, rw_journal_sectors(ic, opf, sector, n_sectors, comp); } -static void write_journal(struct dm_integrity_c *ic, unsigned commit_start, unsigned commit_sections) +static void write_journal(struct dm_integrity_c *ic, unsigned int commit_start, unsigned int commit_sections) { struct journal_completion io_comp; struct journal_completion crypt_comp_1; struct journal_completion crypt_comp_2; - unsigned i; + unsigned int i; io_comp.ic = ic; init_completion(&io_comp.comp); @@ -1136,7 +1136,7 @@ static void write_journal(struct dm_integrity_c *ic, unsigned commit_start, unsi rw_journal(ic, REQ_OP_WRITE | REQ_FUA | REQ_SYNC, commit_start, commit_sections, &io_comp); } else { - unsigned to_end; + unsigned int to_end; io_comp.in_flight = (atomic_t)ATOMIC_INIT(2); to_end = ic->journal_sections - commit_start; if (ic->journal_io) { @@ -1173,15 +1173,15 @@ static void write_journal(struct dm_integrity_c *ic, unsigned commit_start, unsi wait_for_completion_io(&io_comp.comp); } -static void copy_from_journal(struct dm_integrity_c *ic, unsigned section, unsigned offset, - unsigned n_sectors, sector_t target, io_notify_fn fn, void *data) +static void copy_from_journal(struct dm_integrity_c *ic, unsigned int section, unsigned int offset, + unsigned int n_sectors, sector_t target, io_notify_fn fn, void *data) { struct dm_io_request io_req; struct dm_io_region io_loc; int r; - unsigned sector, pl_index, pl_offset; + unsigned int sector, pl_index, pl_offset; - BUG_ON((target | n_sectors | offset) & (unsigned)(ic->sectors_per_block - 1)); + BUG_ON((target | n_sectors | offset) & (unsigned int)(ic->sectors_per_block - 1)); if (unlikely(dm_integrity_failed(ic))) { fn(-1UL, data); @@ -1222,7 +1222,7 @@ static bool add_new_range(struct dm_integrity_c *ic, struct dm_integrity_range * struct rb_node **n = &ic->in_progress.rb_node; struct rb_node *parent; - BUG_ON((new_range->logical_sector | new_range->n_sectors) & (unsigned)(ic->sectors_per_block - 1)); + BUG_ON((new_range->logical_sector | new_range->n_sectors) & (unsigned int)(ic->sectors_per_block - 1)); if (likely(check_waiting)) { struct dm_integrity_range *range; @@ -1340,10 +1340,10 @@ static void remove_journal_node(struct dm_integrity_c *ic, struct journal_node * #define NOT_FOUND (-1U) -static unsigned find_journal_node(struct dm_integrity_c *ic, sector_t sector, sector_t *next_sector) +static unsigned int find_journal_node(struct dm_integrity_c *ic, sector_t sector, sector_t *next_sector) { struct rb_node *n = ic->journal_tree_root.rb_node; - unsigned found = NOT_FOUND; + unsigned int found = NOT_FOUND; *next_sector = (sector_t)-1; while (n) { struct journal_node *j = container_of(n, struct journal_node, node); @@ -1361,7 +1361,7 @@ static unsigned find_journal_node(struct dm_integrity_c *ic, sector_t sector, se return found; } -static bool test_journal_node(struct dm_integrity_c *ic, unsigned pos, sector_t sector) +static bool test_journal_node(struct dm_integrity_c *ic, unsigned int pos, sector_t sector) { struct journal_node *node, *next_node; struct rb_node *next; @@ -1386,7 +1386,7 @@ static bool find_newer_committed_node(struct dm_integrity_c *ic, struct journal_ { struct rb_node *next; struct journal_node *next_node; - unsigned next_section; + unsigned int next_section; BUG_ON(RB_EMPTY_NODE(&node->node)); @@ -1399,7 +1399,7 @@ static bool find_newer_committed_node(struct dm_integrity_c *ic, struct journal_ if (next_node->sector != node->sector) return false; - next_section = (unsigned)(next_node - ic->journal_tree) / ic->journal_section_entries; + next_section = (unsigned int)(next_node - ic->journal_tree) / ic->journal_section_entries; if (next_section >= ic->committed_section && next_section < ic->committed_section + ic->n_committed_sections) return true; @@ -1414,17 +1414,17 @@ static bool find_newer_committed_node(struct dm_integrity_c *ic, struct journal_ #define TAG_CMP 2 static int dm_integrity_rw_tag(struct dm_integrity_c *ic, unsigned char *tag, sector_t *metadata_block, - unsigned *metadata_offset, unsigned total_size, int op) + unsigned int *metadata_offset, unsigned int total_size, int op) { #define MAY_BE_FILLER 1 #define MAY_BE_HASH 2 - unsigned hash_offset = 0; - unsigned may_be = MAY_BE_HASH | (ic->discard ? MAY_BE_FILLER : 0); + unsigned int hash_offset = 0; + unsigned int may_be = MAY_BE_HASH | (ic->discard ? MAY_BE_FILLER : 0); do { unsigned char *data, *dp; struct dm_buffer *b; - unsigned to_copy; + unsigned int to_copy; int r; r = dm_integrity_failed(ic); @@ -1454,7 +1454,7 @@ static int dm_integrity_rw_tag(struct dm_integrity_c *ic, unsigned char *tag, se goto thorough_test; } } else { - unsigned i, ts; + unsigned int i, ts; thorough_test: ts = total_size; @@ -1653,7 +1653,7 @@ static void integrity_sector_checksum(struct dm_integrity_c *ic, sector_t sector __le64 sector_le = cpu_to_le64(sector); SHASH_DESC_ON_STACK(req, ic->internal_hash); int r; - unsigned digest_size; + unsigned int digest_size; req->tfm = ic->internal_hash; @@ -1710,13 +1710,13 @@ static void integrity_metadata(struct work_struct *w) if (ic->internal_hash) { struct bvec_iter iter; struct bio_vec bv; - unsigned digest_size = crypto_shash_digestsize(ic->internal_hash); + unsigned int digest_size = crypto_shash_digestsize(ic->internal_hash); struct bio *bio = dm_bio_from_per_bio_data(dio, sizeof(struct dm_integrity_io)); char *checksums; - unsigned extra_space = unlikely(digest_size > ic->tag_size) ? digest_size - ic->tag_size : 0; + unsigned int extra_space = unlikely(digest_size > ic->tag_size) ? digest_size - ic->tag_size : 0; char checksums_onstack[max((size_t)HASH_MAX_DIGESTSIZE, MAX_TAG_SIZE)]; sector_t sector; - unsigned sectors_to_process; + unsigned int sectors_to_process; if (unlikely(ic->mode == 'R')) goto skip_io; @@ -1736,13 +1736,13 @@ static void integrity_metadata(struct work_struct *w) } if (unlikely(dio->op == REQ_OP_DISCARD)) { - unsigned bi_size = dio->bio_details.bi_iter.bi_size; - unsigned max_size = likely(checksums != checksums_onstack) ? PAGE_SIZE : HASH_MAX_DIGESTSIZE; - unsigned max_blocks = max_size / ic->tag_size; + unsigned int bi_size = dio->bio_details.bi_iter.bi_size; + unsigned int max_size = likely(checksums != checksums_onstack) ? PAGE_SIZE : HASH_MAX_DIGESTSIZE; + unsigned int max_blocks = max_size / ic->tag_size; memset(checksums, DISCARD_FILLER, max_size); while (bi_size) { - unsigned this_step_blocks = bi_size >> (SECTOR_SHIFT + ic->sb->log2_sectors_per_block); + unsigned int this_step_blocks = bi_size >> (SECTOR_SHIFT + ic->sb->log2_sectors_per_block); this_step_blocks = min(this_step_blocks, max_blocks); r = dm_integrity_rw_tag(ic, checksums, &dio->metadata_block, &dio->metadata_offset, this_step_blocks * ic->tag_size, TAG_WRITE); @@ -1764,7 +1764,7 @@ static void integrity_metadata(struct work_struct *w) sectors_to_process = dio->range.n_sectors; __bio_for_each_segment(bv, bio, iter, dio->bio_details.bi_iter) { - unsigned pos; + unsigned int pos; char *mem, *checksums_ptr; again: @@ -1817,13 +1817,13 @@ again: if (bip) { struct bio_vec biv; struct bvec_iter iter; - unsigned data_to_process = dio->range.n_sectors; + unsigned int data_to_process = dio->range.n_sectors; sector_to_block(ic, data_to_process); data_to_process *= ic->tag_size; bip_for_each_vec(biv, bip, iter) { unsigned char *tag; - unsigned this_len; + unsigned int this_len; BUG_ON(PageHighMem(biv.bv_page)); tag = bvec_virt(&biv); @@ -1861,7 +1861,7 @@ static int dm_integrity_map(struct dm_target *ti, struct bio *bio) if (unlikely(dio->op == REQ_OP_DISCARD)) { if (ti->max_io_len) { sector_t sec = dm_target_offset(ti, bio->bi_iter.bi_sector); - unsigned log2_max_io_len = __fls(ti->max_io_len); + unsigned int log2_max_io_len = __fls(ti->max_io_len); sector_t start_boundary = sec >> log2_max_io_len; sector_t end_boundary = (sec + bio_sectors(bio) - 1) >> log2_max_io_len; if (start_boundary < end_boundary) { @@ -1891,7 +1891,7 @@ static int dm_integrity_map(struct dm_target *ti, struct bio *bio) ic->provided_data_sectors); return DM_MAPIO_KILL; } - if (unlikely((dio->range.logical_sector | bio_sectors(bio)) & (unsigned)(ic->sectors_per_block - 1))) { + if (unlikely((dio->range.logical_sector | bio_sectors(bio)) & (unsigned int)(ic->sectors_per_block - 1))) { DMERR("Bio not aligned on %u sectors: 0x%llx, 0x%x", ic->sectors_per_block, dio->range.logical_sector, bio_sectors(bio)); @@ -1913,7 +1913,7 @@ static int dm_integrity_map(struct dm_target *ti, struct bio *bio) bip = bio_integrity(bio); if (!ic->internal_hash) { if (bip) { - unsigned wanted_tag_size = bio_sectors(bio) >> ic->sb->log2_sectors_per_block; + unsigned int wanted_tag_size = bio_sectors(bio) >> ic->sb->log2_sectors_per_block; if (ic->log2_tag_size >= 0) wanted_tag_size <<= ic->log2_tag_size; else @@ -1943,11 +1943,11 @@ static int dm_integrity_map(struct dm_target *ti, struct bio *bio) } static bool __journal_read_write(struct dm_integrity_io *dio, struct bio *bio, - unsigned journal_section, unsigned journal_entry) + unsigned int journal_section, unsigned int journal_entry) { struct dm_integrity_c *ic = dio->ic; sector_t logical_sector; - unsigned n_sectors; + unsigned int n_sectors; logical_sector = dio->range.logical_sector; n_sectors = dio->range.n_sectors; @@ -1970,7 +1970,7 @@ retry_kmap: if (unlikely(dio->op == REQ_OP_READ)) { struct journal_sector *js; char *mem_ptr; - unsigned s; + unsigned int s; if (unlikely(journal_entry_is_inprogress(je))) { flush_dcache_page(bv.bv_page); @@ -2007,12 +2007,12 @@ retry_kmap: if (!ic->internal_hash) { struct bio_integrity_payload *bip = bio_integrity(bio); - unsigned tag_todo = ic->tag_size; + unsigned int tag_todo = ic->tag_size; char *tag_ptr = journal_entry_tag(ic, je); if (bip) do { struct bio_vec biv = bvec_iter_bvec(bip->bip_vec, bip->bip_iter); - unsigned tag_now = min(biv.bv_len, tag_todo); + unsigned int tag_now = min(biv.bv_len, tag_todo); char *tag_addr; BUG_ON(PageHighMem(biv.bv_page)); tag_addr = bvec_virt(&biv); @@ -2031,7 +2031,7 @@ retry_kmap: if (likely(dio->op == REQ_OP_WRITE)) { struct journal_sector *js; - unsigned s; + unsigned int s; js = access_journal_data(ic, journal_section, journal_entry); memcpy(js, mem + bv.bv_offset, ic->sectors_per_block << SECTOR_SHIFT); @@ -2042,7 +2042,7 @@ retry_kmap: } while (++s < ic->sectors_per_block); if (ic->internal_hash) { - unsigned digest_size = crypto_shash_digestsize(ic->internal_hash); + unsigned int digest_size = crypto_shash_digestsize(ic->internal_hash); if (unlikely(digest_size > ic->tag_size)) { char checksums_onstack[HASH_MAX_DIGESTSIZE]; integrity_sector_checksum(ic, logical_sector, (char *)js, checksums_onstack); @@ -2099,8 +2099,8 @@ static void dm_integrity_map_continue(struct dm_integrity_io *dio, bool from_map { struct dm_integrity_c *ic = dio->ic; struct bio *bio = dm_bio_from_per_bio_data(dio, sizeof(struct dm_integrity_io)); - unsigned journal_section, journal_entry; - unsigned journal_read_pos; + unsigned int journal_section, journal_entry; + unsigned int journal_read_pos; struct completion read_comp; bool discard_retried = false; bool need_sync_io = ic->internal_hash && dio->op == REQ_OP_READ; @@ -2125,8 +2125,8 @@ retry: journal_read_pos = NOT_FOUND; if (ic->mode == 'J' && likely(dio->op != REQ_OP_DISCARD)) { if (dio->op == REQ_OP_WRITE) { - unsigned next_entry, i, pos; - unsigned ws, we, range_sectors; + unsigned int next_entry, i, pos; + unsigned int ws, we, range_sectors; dio->range.n_sectors = min(dio->range.n_sectors, (sector_t)ic->free_sectors << ic->sb->log2_sectors_per_block); @@ -2179,8 +2179,8 @@ retry: if (unlikely(dio->range.n_sectors > next_sector - dio->range.logical_sector)) dio->range.n_sectors = next_sector - dio->range.logical_sector; } else { - unsigned i; - unsigned jp = journal_read_pos + 1; + unsigned int i; + unsigned int jp = journal_read_pos + 1; for (i = ic->sectors_per_block; i < dio->range.n_sectors; i += ic->sectors_per_block, jp++) { if (!test_journal_node(ic, jp, dio->range.logical_sector + i)) break; @@ -2212,7 +2212,7 @@ offload_to_thread: */ if (journal_read_pos != NOT_FOUND) { sector_t next_sector; - unsigned new_pos = find_journal_node(ic, dio->range.logical_sector, &next_sector); + unsigned int new_pos = find_journal_node(ic, dio->range.logical_sector, &next_sector); if (unlikely(new_pos != journal_read_pos)) { remove_range_unlocked(ic, &dio->range); goto retry; @@ -2221,7 +2221,7 @@ offload_to_thread: } if (ic->mode == 'J' && likely(dio->op == REQ_OP_DISCARD) && !discard_retried) { sector_t next_sector; - unsigned new_pos = find_journal_node(ic, dio->range.logical_sector, &next_sector); + unsigned int new_pos = find_journal_node(ic, dio->range.logical_sector, &next_sector); if (unlikely(new_pos != NOT_FOUND) || unlikely(next_sector < dio->range.logical_sector - dio->range.n_sectors)) { remove_range_unlocked(ic, &dio->range); @@ -2348,8 +2348,8 @@ static void pad_uncommitted(struct dm_integrity_c *ic) static void integrity_commit(struct work_struct *w) { struct dm_integrity_c *ic = container_of(w, struct dm_integrity_c, commit_work); - unsigned commit_start, commit_sections; - unsigned i, j, n; + unsigned int commit_start, commit_sections; + unsigned int i, j, n; struct bio *flushes; del_timer(&ic->autocommit_timer); @@ -2427,17 +2427,17 @@ static void complete_copy_from_journal(unsigned long error, void *context) static void restore_last_bytes(struct dm_integrity_c *ic, struct journal_sector *js, struct journal_entry *je) { - unsigned s = 0; + unsigned int s = 0; do { js->commit_id = je->last_bytes[s]; js++; } while (++s < ic->sectors_per_block); } -static void do_journal_write(struct dm_integrity_c *ic, unsigned write_start, - unsigned write_sections, bool from_replay) +static void do_journal_write(struct dm_integrity_c *ic, unsigned int write_start, + unsigned int write_sections, bool from_replay) { - unsigned i, j, n; + unsigned int i, j, n; struct journal_completion comp; struct blk_plug plug; @@ -2456,9 +2456,9 @@ static void do_journal_write(struct dm_integrity_c *ic, unsigned write_start, for (j = 0; j < ic->journal_section_entries; j++) { struct journal_entry *je = access_journal_entry(ic, i, j); sector_t sec, area, offset; - unsigned k, l, next_loop; + unsigned int k, l, next_loop; sector_t metadata_block; - unsigned metadata_offset; + unsigned int metadata_offset; struct journal_io *io; if (journal_entry_is_unused(je)) @@ -2466,7 +2466,7 @@ static void do_journal_write(struct dm_integrity_c *ic, unsigned write_start, BUG_ON(unlikely(journal_entry_is_inprogress(je)) && !from_replay); sec = journal_entry_get_sector(je); if (unlikely(from_replay)) { - if (unlikely(sec & (unsigned)(ic->sectors_per_block - 1))) { + if (unlikely(sec & (unsigned int)(ic->sectors_per_block - 1))) { dm_integrity_io_error(ic, "invalid sector in journal", -EIO); sec &= ~(sector_t)(ic->sectors_per_block - 1); } @@ -2584,9 +2584,9 @@ skip_io: static void integrity_writer(struct work_struct *w) { struct dm_integrity_c *ic = container_of(w, struct dm_integrity_c, writer_work); - unsigned write_start, write_sections; + unsigned int write_start, write_sections; - unsigned prev_free_sectors; + unsigned int prev_free_sectors; spin_lock_irq(&ic->endio_wait.lock); write_start = ic->committed_section; @@ -2633,12 +2633,12 @@ static void integrity_recalc(struct work_struct *w) struct dm_io_region io_loc; sector_t area, offset; sector_t metadata_block; - unsigned metadata_offset; + unsigned int metadata_offset; sector_t logical_sector, n_sectors; __u8 *t; - unsigned i; + unsigned int i; int r; - unsigned super_counter = 0; + unsigned int super_counter = 0; DEBUG_print("start recalculation... (position %llx)\n", le64_to_cpu(ic->sb->recalc_sector)); @@ -2662,7 +2662,7 @@ next_chunk: get_area_and_offset(ic, range.logical_sector, &area, &offset); range.n_sectors = min((sector_t)RECALC_SECTORS, ic->provided_data_sectors - range.logical_sector); if (!ic->meta_dev) - range.n_sectors = min(range.n_sectors, ((sector_t)1U << ic->sb->log2_interleave_sectors) - (unsigned)offset); + range.n_sectors = min(range.n_sectors, ((sector_t)1U << ic->sb->log2_interleave_sectors) - (unsigned int)offset); add_new_range_and_wait(ic, &range); spin_unlock_irq(&ic->endio_wait.lock); @@ -2853,10 +2853,10 @@ static void bitmap_flush_work(struct work_struct *work) } -static void init_journal(struct dm_integrity_c *ic, unsigned start_section, - unsigned n_sections, unsigned char commit_seq) +static void init_journal(struct dm_integrity_c *ic, unsigned int start_section, + unsigned int n_sections, unsigned char commit_seq) { - unsigned i, j, n; + unsigned int i, j, n; if (!n_sections) return; @@ -2879,7 +2879,7 @@ static void init_journal(struct dm_integrity_c *ic, unsigned start_section, write_journal(ic, start_section, n_sections); } -static int find_commit_seq(struct dm_integrity_c *ic, unsigned i, unsigned j, commit_id_t id) +static int find_commit_seq(struct dm_integrity_c *ic, unsigned int i, unsigned int j, commit_id_t id) { unsigned char k; for (k = 0; k < N_COMMIT_IDS; k++) { @@ -2892,11 +2892,11 @@ static int find_commit_seq(struct dm_integrity_c *ic, unsigned i, unsigned j, co static void replay_journal(struct dm_integrity_c *ic) { - unsigned i, j; + unsigned int i, j; bool used_commit_ids[N_COMMIT_IDS]; - unsigned max_commit_id_sections[N_COMMIT_IDS]; - unsigned write_start, write_sections; - unsigned continue_section; + unsigned int max_commit_id_sections[N_COMMIT_IDS]; + unsigned int write_start, write_sections; + unsigned int continue_section; bool journal_empty; unsigned char unused, last_used, want_commit_seq; @@ -3014,7 +3014,7 @@ brk: ic->commit_seq = want_commit_seq; DEBUG_print("continuing from section %u, commit seq %d\n", write_start, ic->commit_seq); } else { - unsigned s; + unsigned int s; unsigned char erase_seq; clear_journal: DEBUG_print("clearing journal\n"); @@ -3246,10 +3246,10 @@ static void dm_integrity_resume(struct dm_target *ti) } static void dm_integrity_status(struct dm_target *ti, status_type_t type, - unsigned status_flags, char *result, unsigned maxlen) + unsigned int status_flags, char *result, unsigned int maxlen) { struct dm_integrity_c *ic = (struct dm_integrity_c *)ti->private; - unsigned arg_count; + unsigned int arg_count; size_t sz = 0; switch (type) { @@ -3299,7 +3299,7 @@ static void dm_integrity_status(struct dm_target *ti, status_type_t type, DMEMIT(" interleave_sectors:%u", 1U << ic->sb->log2_interleave_sectors); DMEMIT(" buffer_sectors:%u", 1U << ic->log2_buffer_sectors); if (ic->mode == 'J') { - DMEMIT(" journal_watermark:%u", (unsigned)watermark_percentage); + DMEMIT(" journal_watermark:%u", (unsigned int)watermark_percentage); DMEMIT(" commit_time:%u", ic->autocommit_msec); } if (ic->mode == 'B') { @@ -3378,7 +3378,7 @@ static void dm_integrity_io_hints(struct dm_target *ti, struct queue_limits *lim static void calculate_journal_section_size(struct dm_integrity_c *ic) { - unsigned sector_space = JOURNAL_SECTOR_DATA; + unsigned int sector_space = JOURNAL_SECTOR_DATA; ic->journal_sections = le32_to_cpu(ic->sb->journal_sections); ic->journal_entry_size = roundup(offsetof(struct journal_entry, last_bytes[ic->sectors_per_block]) + ic->tag_size, @@ -3455,9 +3455,10 @@ static void get_provided_data_sectors(struct dm_integrity_c *ic) } } -static int initialize_superblock(struct dm_integrity_c *ic, unsigned journal_sectors, unsigned interleave_sectors) +static int initialize_superblock(struct dm_integrity_c *ic, + unsigned int journal_sectors, unsigned int interleave_sectors) { - unsigned journal_sections; + unsigned int journal_sections; int test_bit; memset(ic->sb, 0, SB_SECTORS << SECTOR_SHIFT); @@ -3542,7 +3543,7 @@ static void dm_integrity_set(struct dm_target *ti, struct dm_integrity_c *ic) static void dm_integrity_free_page_list(struct page_list *pl) { - unsigned i; + unsigned int i; if (!pl) return; @@ -3551,10 +3552,10 @@ static void dm_integrity_free_page_list(struct page_list *pl) kvfree(pl); } -static struct page_list *dm_integrity_alloc_page_list(unsigned n_pages) +static struct page_list *dm_integrity_alloc_page_list(unsigned int n_pages) { struct page_list *pl; - unsigned i; + unsigned int i; pl = kvmalloc_array(n_pages + 1, sizeof(struct page_list), GFP_KERNEL | __GFP_ZERO); if (!pl) @@ -3577,7 +3578,7 @@ static struct page_list *dm_integrity_alloc_page_list(unsigned n_pages) static void dm_integrity_free_journal_scatterlist(struct dm_integrity_c *ic, struct scatterlist **sl) { - unsigned i; + unsigned int i; for (i = 0; i < ic->journal_sections; i++) kvfree(sl[i]); kvfree(sl); @@ -3587,7 +3588,7 @@ static struct scatterlist **dm_integrity_alloc_journal_scatterlist(struct dm_int struct page_list *pl) { struct scatterlist **sl; - unsigned i; + unsigned int i; sl = kvmalloc_array(ic->journal_sections, sizeof(struct scatterlist *), @@ -3597,10 +3598,10 @@ static struct scatterlist **dm_integrity_alloc_journal_scatterlist(struct dm_int for (i = 0; i < ic->journal_sections; i++) { struct scatterlist *s; - unsigned start_index, start_offset; - unsigned end_index, end_offset; - unsigned n_pages; - unsigned idx; + unsigned int start_index, start_offset; + unsigned int end_index, end_offset; + unsigned int n_pages; + unsigned int idx; page_list_location(ic, i, 0, &start_index, &start_offset); page_list_location(ic, i, ic->journal_section_sectors - 1, @@ -3618,7 +3619,7 @@ static struct scatterlist **dm_integrity_alloc_journal_scatterlist(struct dm_int sg_init_table(s, n_pages); for (idx = start_index; idx <= end_index; idx++) { char *va = lowmem_page_address(pl[idx].page); - unsigned start = 0, end = PAGE_SIZE; + unsigned int start = 0, end = PAGE_SIZE; if (idx == start_index) start = start_offset; if (idx == end_index) @@ -3705,7 +3706,7 @@ static int get_mac(struct crypto_shash **hash, struct alg_spec *a, char **error, static int create_journal(struct dm_integrity_c *ic, char **error) { int r = 0; - unsigned i; + unsigned int i; __u64 journal_pages, journal_desc_size, journal_tree_size; unsigned char *crypt_data = NULL, *crypt_iv = NULL; struct skcipher_request *req = NULL; @@ -3732,7 +3733,7 @@ static int create_journal(struct dm_integrity_c *ic, char **error) goto bad; } if (ic->journal_crypt_alg.alg_string) { - unsigned ivsize, blocksize; + unsigned int ivsize, blocksize; struct journal_completion comp; comp.ic = ic; @@ -3821,7 +3822,7 @@ static int create_journal(struct dm_integrity_c *ic, char **error) crypto_free_skcipher(ic->journal_crypt); ic->journal_crypt = NULL; } else { - unsigned crypt_len = roundup(ivsize, blocksize); + unsigned int crypt_len = roundup(ivsize, blocksize); req = skcipher_request_alloc(ic->journal_crypt, GFP_KERNEL); if (!req) { @@ -3909,7 +3910,7 @@ static int create_journal(struct dm_integrity_c *ic, char **error) } for (i = 0; i < N_COMMIT_IDS; i++) { - unsigned j; + unsigned int j; retest_commit_id: for (j = 0; j < i; j++) { if (ic->commit_ids[j] == ic->commit_ids[i]) { @@ -3963,17 +3964,17 @@ bad: * journal_mac * recalculate */ -static int dm_integrity_ctr(struct dm_target *ti, unsigned argc, char **argv) +static int dm_integrity_ctr(struct dm_target *ti, unsigned int argc, char **argv) { struct dm_integrity_c *ic; char dummy; int r; - unsigned extra_args; + unsigned int extra_args; struct dm_arg_set as; static const struct dm_arg _args[] = { {0, 18, "Invalid number of feature args"}, }; - unsigned journal_sectors, interleave_sectors, buffer_sectors, journal_watermark, sync_msec; + unsigned int journal_sectors, interleave_sectors, buffer_sectors, journal_watermark, sync_msec; bool should_write_sb; __u64 threshold; unsigned long long start; @@ -4052,7 +4053,7 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned argc, char **argv) while (extra_args--) { const char *opt_string; - unsigned val; + unsigned int val; unsigned long long llval; opt_string = dm_shift_arg(&as); if (!opt_string) { @@ -4385,7 +4386,7 @@ try_smaller_buffer: DEBUG_print(" journal_entries_per_sector %u\n", ic->journal_entries_per_sector); DEBUG_print(" journal_section_entries %u\n", ic->journal_section_entries); DEBUG_print(" journal_section_sectors %u\n", ic->journal_section_sectors); - DEBUG_print(" journal_sections %u\n", (unsigned)le32_to_cpu(ic->sb->journal_sections)); + DEBUG_print(" journal_sections %u\n", (unsigned int)le32_to_cpu(ic->sb->journal_sections)); DEBUG_print(" journal_entries %u\n", ic->journal_entries); DEBUG_print(" log2_interleave_sectors %d\n", ic->sb->log2_interleave_sectors); DEBUG_print(" data_device_sectors 0x%llx\n", bdev_nr_sectors(ic->dev->bdev)); @@ -4459,8 +4460,8 @@ try_smaller_buffer: } if (ic->mode == 'B') { - unsigned i; - unsigned n_bitmap_pages = DIV_ROUND_UP(ic->n_bitmap_blocks, PAGE_SIZE / BITMAP_BLOCK_SIZE); + unsigned int i; + unsigned int n_bitmap_pages = DIV_ROUND_UP(ic->n_bitmap_blocks, PAGE_SIZE / BITMAP_BLOCK_SIZE); ic->recalc_bitmap = dm_integrity_alloc_page_list(n_bitmap_pages); if (!ic->recalc_bitmap) { @@ -4480,7 +4481,7 @@ try_smaller_buffer: INIT_DELAYED_WORK(&ic->bitmap_flush_work, bitmap_flush_work); for (i = 0; i < ic->n_bitmap_blocks; i++) { struct bitmap_block_status *bbs = &ic->bbs[i]; - unsigned sector, pl_index, pl_offset; + unsigned int sector, pl_index, pl_offset; INIT_WORK(&bbs->work, bitmap_block_work); bbs->ic = ic; @@ -4517,7 +4518,7 @@ try_smaller_buffer: goto bad; } if (ic->mode == 'B') { - unsigned max_io_len = ((sector_t)ic->sectors_per_block << ic->log2_blocks_per_bitmap_bit) * (BITMAP_BLOCK_SIZE * 8); + unsigned int max_io_len = ((sector_t)ic->sectors_per_block << ic->log2_blocks_per_bitmap_bit) * (BITMAP_BLOCK_SIZE * 8); if (!max_io_len) max_io_len = 1U << 31; DEBUG_print("max_io_len: old %u, new %u\n", ti->max_io_len, max_io_len); @@ -4588,7 +4589,7 @@ static void dm_integrity_dtr(struct dm_target *ti) if (ic->journal_io_scatterlist) dm_integrity_free_journal_scatterlist(ic, ic->journal_io_scatterlist); if (ic->sk_requests) { - unsigned i; + unsigned int i; for (i = 0; i < ic->journal_sections; i++) { struct skcipher_request *req = ic->sk_requests[i]; diff --git a/drivers/md/dm-io-rewind.c b/drivers/md/dm-io-rewind.c index 412e63ce3b60..e59b749eec82 100644 --- a/drivers/md/dm-io-rewind.c +++ b/drivers/md/dm-io-rewind.c @@ -57,7 +57,7 @@ static void dm_bio_integrity_rewind(struct bio *bio, unsigned int bytes_done) { struct bio_integrity_payload *bip = bio_integrity(bio); struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk); - unsigned bytes = bio_integrity_bytes(bi, bytes_done >> 9); + unsigned int bytes = bio_integrity_bytes(bi, bytes_done >> 9); bip->bip_iter.bi_sector -= bio_integrity_intervals(bi, bytes_done >> 9); dm_bvec_iter_rewind(bip->bip_vec, &bip->bip_iter, bytes); @@ -131,7 +131,7 @@ static inline void dm_bio_rewind_iter(const struct bio *bio, * rewinding from end of bio and restoring its original position. * Caller is also responsibile for restoring bio's size. */ -static void dm_bio_rewind(struct bio *bio, unsigned bytes) +static void dm_bio_rewind(struct bio *bio, unsigned int bytes) { if (bio_integrity(bio)) dm_bio_integrity_rewind(bio, bytes); diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c index 83903255ee57..eda61cfab312 100644 --- a/drivers/md/dm-io.c +++ b/drivers/md/dm-io.c @@ -49,7 +49,7 @@ static struct kmem_cache *_dm_io_cache; struct dm_io_client *dm_io_client_create(void) { struct dm_io_client *client; - unsigned min_ios = dm_get_reserved_bio_based_ios(); + unsigned int min_ios = dm_get_reserved_bio_based_ios(); int ret; client = kzalloc(sizeof(*client), GFP_KERNEL); @@ -89,7 +89,7 @@ EXPORT_SYMBOL(dm_io_client_destroy); * bi_private. *---------------------------------------------------------------*/ static void store_io_and_region_in_bio(struct bio *bio, struct io *io, - unsigned region) + unsigned int region) { if (unlikely(!IS_ALIGNED((unsigned long)io, DM_IO_MAX_REGIONS))) { DMCRIT("Unaligned struct io pointer %p", io); @@ -100,7 +100,7 @@ static void store_io_and_region_in_bio(struct bio *bio, struct io *io, } static void retrieve_io_and_region_from_bio(struct bio *bio, struct io **io, - unsigned *region) + unsigned int *region) { unsigned long val = (unsigned long)bio->bi_private; @@ -138,7 +138,7 @@ static void dec_count(struct io *io, unsigned int region, blk_status_t error) static void endio(struct bio *bio) { struct io *io; - unsigned region; + unsigned int region; blk_status_t error; if (bio->bi_status && bio_data_dir(bio) == READ) @@ -161,11 +161,11 @@ static void endio(struct bio *bio) *---------------------------------------------------------------*/ struct dpages { void (*get_page)(struct dpages *dp, - struct page **p, unsigned long *len, unsigned *offset); + struct page **p, unsigned long *len, unsigned int *offset); void (*next_page)(struct dpages *dp); union { - unsigned context_u; + unsigned int context_u; struct bvec_iter context_bi; }; void *context_ptr; @@ -178,9 +178,9 @@ struct dpages { * Functions for getting the pages from a list. */ static void list_get_page(struct dpages *dp, - struct page **p, unsigned long *len, unsigned *offset) + struct page **p, unsigned long *len, unsigned int *offset) { - unsigned o = dp->context_u; + unsigned int o = dp->context_u; struct page_list *pl = (struct page_list *) dp->context_ptr; *p = pl->page; @@ -195,7 +195,7 @@ static void list_next_page(struct dpages *dp) dp->context_u = 0; } -static void list_dp_init(struct dpages *dp, struct page_list *pl, unsigned offset) +static void list_dp_init(struct dpages *dp, struct page_list *pl, unsigned int offset) { dp->get_page = list_get_page; dp->next_page = list_next_page; @@ -207,7 +207,7 @@ static void list_dp_init(struct dpages *dp, struct page_list *pl, unsigned offse * Functions for getting the pages from a bvec. */ static void bio_get_page(struct dpages *dp, struct page **p, - unsigned long *len, unsigned *offset) + unsigned long *len, unsigned int *offset) { struct bio_vec bvec = bvec_iter_bvec((struct bio_vec *)dp->context_ptr, dp->context_bi); @@ -245,7 +245,7 @@ static void bio_dp_init(struct dpages *dp, struct bio *bio) * Functions for getting the pages from a VMA. */ static void vm_get_page(struct dpages *dp, - struct page **p, unsigned long *len, unsigned *offset) + struct page **p, unsigned long *len, unsigned int *offset) { *p = vmalloc_to_page(dp->context_ptr); *offset = dp->context_u; @@ -270,7 +270,7 @@ static void vm_dp_init(struct dpages *dp, void *data) * Functions for getting the pages from kernel memory. */ static void km_get_page(struct dpages *dp, struct page **p, unsigned long *len, - unsigned *offset) + unsigned int *offset) { *p = virt_to_page(dp->context_ptr); *offset = dp->context_u; @@ -294,15 +294,15 @@ static void km_dp_init(struct dpages *dp, void *data) /*----------------------------------------------------------------- * IO routines that accept a list of pages. *---------------------------------------------------------------*/ -static void do_region(const blk_opf_t opf, unsigned region, +static void do_region(const blk_opf_t opf, unsigned int region, struct dm_io_region *where, struct dpages *dp, struct io *io) { struct bio *bio; struct page *page; unsigned long len; - unsigned offset; - unsigned num_bvecs; + unsigned int offset; + unsigned int num_bvecs; sector_t remaining = where->count; struct request_queue *q = bdev_get_queue(where->bdev); sector_t num_sectors; @@ -509,7 +509,7 @@ static int dp_init(struct dm_io_request *io_req, struct dpages *dp, return 0; } -int dm_io(struct dm_io_request *io_req, unsigned num_regions, +int dm_io(struct dm_io_request *io_req, unsigned int num_regions, struct dm_io_region *where, unsigned long *sync_error_bits) { int r; diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c index 1c27b23c98f9..2dd2fa18afb6 100644 --- a/drivers/md/dm-ioctl.c +++ b/drivers/md/dm-ioctl.c @@ -32,7 +32,7 @@ struct dm_file { * poll will wait until the global event number is greater than * this value. */ - volatile unsigned global_event_nr; + volatile unsigned int global_event_nr; }; /*----------------------------------------------------------------- @@ -414,7 +414,7 @@ static struct mapped_device *dm_hash_rename(struct dm_ioctl *param, struct hash_cell *hc; struct dm_table *table; struct mapped_device *md; - unsigned change_uuid = (param->flags & DM_UUID_FLAG) ? 1 : 0; + unsigned int change_uuid = (param->flags & DM_UUID_FLAG) ? 1 : 0; int srcu_idx; /* @@ -1022,7 +1022,7 @@ static int dev_rename(struct file *filp, struct dm_ioctl *param, size_t param_si int r; char *new_data = (char *) param + param->data_start; struct mapped_device *md; - unsigned change_uuid = (param->flags & DM_UUID_FLAG) ? 1 : 0; + unsigned int change_uuid = (param->flags & DM_UUID_FLAG) ? 1 : 0; if (new_data < param->data || invalid_str(new_data, (void *) param + param_size) || !*new_data || @@ -1096,7 +1096,7 @@ out: static int do_suspend(struct dm_ioctl *param) { int r = 0; - unsigned suspend_flags = DM_SUSPEND_LOCKFS_FLAG; + unsigned int suspend_flags = DM_SUSPEND_LOCKFS_FLAG; struct mapped_device *md; md = find_device(param); @@ -1125,7 +1125,7 @@ out: static int do_resume(struct dm_ioctl *param) { int r = 0; - unsigned suspend_flags = DM_SUSPEND_LOCKFS_FLAG; + unsigned int suspend_flags = DM_SUSPEND_LOCKFS_FLAG; struct hash_cell *hc; struct mapped_device *md; struct dm_table *new_map, *old_map = NULL; @@ -1243,7 +1243,7 @@ static void retrieve_status(struct dm_table *table, char *outbuf, *outptr; status_type_t type; size_t remaining, len, used = 0; - unsigned status_flags = 0; + unsigned int status_flags = 0; outptr = outbuf = get_result_buffer(param, param_size, &len); @@ -1648,8 +1648,8 @@ static int table_status(struct file *filp, struct dm_ioctl *param, size_t param_ * Returns a number <= 1 if message was processed by device mapper. * Returns 2 if message should be delivered to the target. */ -static int message_for_md(struct mapped_device *md, unsigned argc, char **argv, - char *result, unsigned maxlen) +static int message_for_md(struct mapped_device *md, unsigned int argc, char **argv, + char *result, unsigned int maxlen) { int r; @@ -1859,7 +1859,7 @@ static int copy_params(struct dm_ioctl __user *user, struct dm_ioctl *param_kern struct dm_ioctl *dmi; int secure_data; const size_t minimum_data_size = offsetof(struct dm_ioctl, data); - unsigned noio_flag; + unsigned int noio_flag; if (copy_from_user(param_kernel, user, minimum_data_size)) return -EFAULT; diff --git a/drivers/md/dm-kcopyd.c b/drivers/md/dm-kcopyd.c index f0763efc2c83..25d2f1279466 100644 --- a/drivers/md/dm-kcopyd.c +++ b/drivers/md/dm-kcopyd.c @@ -35,14 +35,14 @@ #define DEFAULT_SUB_JOB_SIZE_KB 512 #define MAX_SUB_JOB_SIZE_KB 1024 -static unsigned kcopyd_subjob_size_kb = DEFAULT_SUB_JOB_SIZE_KB; +static unsigned int kcopyd_subjob_size_kb = DEFAULT_SUB_JOB_SIZE_KB; module_param(kcopyd_subjob_size_kb, uint, S_IRUGO | S_IWUSR); MODULE_PARM_DESC(kcopyd_subjob_size_kb, "Sub-job size for dm-kcopyd clients"); -static unsigned dm_get_kcopyd_subjob_size(void) +static unsigned int dm_get_kcopyd_subjob_size(void) { - unsigned sub_job_size_kb; + unsigned int sub_job_size_kb; sub_job_size_kb = __dm_get_module_param(&kcopyd_subjob_size_kb, DEFAULT_SUB_JOB_SIZE_KB, @@ -57,9 +57,9 @@ static unsigned dm_get_kcopyd_subjob_size(void) *---------------------------------------------------------------*/ struct dm_kcopyd_client { struct page_list *pages; - unsigned nr_reserved_pages; - unsigned nr_free_pages; - unsigned sub_job_size; + unsigned int nr_reserved_pages; + unsigned int nr_free_pages; + unsigned int sub_job_size; struct dm_io_client *io_client; @@ -120,7 +120,7 @@ static DEFINE_SPINLOCK(throttle_spinlock); static void io_job_start(struct dm_kcopyd_throttle *t) { - unsigned throttle, now, difference; + unsigned int throttle, now, difference; int slept = 0, skew; if (unlikely(!t)) @@ -183,7 +183,7 @@ static void io_job_finish(struct dm_kcopyd_throttle *t) goto skip_limit; if (!t->num_io_jobs) { - unsigned now, difference; + unsigned int now, difference; now = jiffies; difference = now - t->last_jiffies; @@ -304,9 +304,9 @@ static void drop_pages(struct page_list *pl) /* * Allocate and reserve nr_pages for the use of a specific client. */ -static int client_reserve_pages(struct dm_kcopyd_client *kc, unsigned nr_pages) +static int client_reserve_pages(struct dm_kcopyd_client *kc, unsigned int nr_pages) { - unsigned i; + unsigned int i; struct page_list *pl = NULL, *next; for (i = 0; i < nr_pages; i++) { @@ -342,7 +342,7 @@ static void client_free_pages(struct dm_kcopyd_client *kc) struct kcopyd_job { struct dm_kcopyd_client *kc; struct list_head list; - unsigned flags; + unsigned int flags; /* * Error state of the job. @@ -583,7 +583,7 @@ static int run_io_job(struct kcopyd_job *job) static int run_pages_job(struct kcopyd_job *job) { int r; - unsigned nr_pages = dm_div_up(job->dests[0].count, PAGE_SIZE >> 9); + unsigned int nr_pages = dm_div_up(job->dests[0].count, PAGE_SIZE >> 9); r = kcopyd_get_pages(job->kc, nr_pages, &job->pages); if (!r) { @@ -850,8 +850,8 @@ void dm_kcopyd_copy(struct dm_kcopyd_client *kc, struct dm_io_region *from, EXPORT_SYMBOL(dm_kcopyd_copy); void dm_kcopyd_zero(struct dm_kcopyd_client *kc, - unsigned num_dests, struct dm_io_region *dests, - unsigned flags, dm_kcopyd_notify_fn fn, void *context) + unsigned int num_dests, struct dm_io_region *dests, + unsigned int flags, dm_kcopyd_notify_fn fn, void *context) { dm_kcopyd_copy(kc, NULL, num_dests, dests, flags, fn, context); } @@ -907,7 +907,7 @@ int kcopyd_cancel(struct kcopyd_job *job, int block) struct dm_kcopyd_client *dm_kcopyd_client_create(struct dm_kcopyd_throttle *throttle) { int r; - unsigned reserve_pages; + unsigned int reserve_pages; struct dm_kcopyd_client *kc; kc = kzalloc(sizeof(*kc), GFP_KERNEL); diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c index b0a644bff294..e5bdfb3b4049 100644 --- a/drivers/md/dm-linear.c +++ b/drivers/md/dm-linear.c @@ -96,7 +96,7 @@ static int linear_map(struct dm_target *ti, struct bio *bio) } static void linear_status(struct dm_target *ti, status_type_t type, - unsigned status_flags, char *result, unsigned maxlen) + unsigned int status_flags, char *result, unsigned int maxlen) { struct linear_c *lc = (struct linear_c *) ti->private; size_t sz = 0; diff --git a/drivers/md/dm-log-userspace-base.c b/drivers/md/dm-log-userspace-base.c index 1aed04c855f9..bc418173c5f7 100644 --- a/drivers/md/dm-log-userspace-base.c +++ b/drivers/md/dm-log-userspace-base.c @@ -124,7 +124,7 @@ retry: } static int build_constructor_string(struct dm_target *ti, - unsigned argc, char **argv, + unsigned int argc, char **argv, char **ctr_str) { int i, str_size; @@ -189,7 +189,7 @@ static void do_flush(struct work_struct *work) * to the userspace ctr function. */ static int userspace_ctr(struct dm_dirty_log *log, struct dm_target *ti, - unsigned argc, char **argv) + unsigned int argc, char **argv) { int r = 0; int str_size; @@ -793,7 +793,7 @@ static region_t userspace_get_sync_count(struct dm_dirty_log *log) * Returns: amount of space consumed */ static int userspace_status(struct dm_dirty_log *log, status_type_t status_type, - char *result, unsigned maxlen) + char *result, unsigned int maxlen) { int r = 0; char *table_args; diff --git a/drivers/md/dm-log-userspace-transfer.c b/drivers/md/dm-log-userspace-transfer.c index 8037fb0dc03c..130d6725df0a 100644 --- a/drivers/md/dm-log-userspace-transfer.c +++ b/drivers/md/dm-log-userspace-transfer.c @@ -143,7 +143,7 @@ static void cn_ulog_callback(struct cn_msg *msg, struct netlink_skb_parms *nsp) fill_pkg(msg, NULL); else if (msg->len < sizeof(*tfr)) DMERR("Incomplete message received (expected %u, got %u): [%u]", - (unsigned)sizeof(*tfr), msg->len, msg->seq); + (unsigned int)sizeof(*tfr), msg->len, msg->seq); else fill_pkg(NULL, tfr); spin_unlock(&receiving_list_lock); diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c index b126263f814c..cbd0f81f4a35 100644 --- a/drivers/md/dm-log-writes.c +++ b/drivers/md/dm-log-writes.c @@ -793,10 +793,10 @@ static int normal_end_io(struct dm_target *ti, struct bio *bio, * INFO format: */ static void log_writes_status(struct dm_target *ti, status_type_t type, - unsigned status_flags, char *result, - unsigned maxlen) + unsigned int status_flags, char *result, + unsigned int maxlen) { - unsigned sz = 0; + unsigned int sz = 0; struct log_writes_c *lc = ti->private; switch (type) { @@ -845,8 +845,8 @@ static int log_writes_iterate_devices(struct dm_target *ti, * Messages supported: * mark - specify the marked data. */ -static int log_writes_message(struct dm_target *ti, unsigned argc, char **argv, - char *result, unsigned maxlen) +static int log_writes_message(struct dm_target *ti, unsigned int argc, char **argv, + char *result, unsigned int maxlen) { int r = -EINVAL; struct log_writes_c *lc = ti->private; diff --git a/drivers/md/dm-log.c b/drivers/md/dm-log.c index aefd977f8340..b57790e62484 100644 --- a/drivers/md/dm-log.c +++ b/drivers/md/dm-log.c @@ -224,7 +224,7 @@ struct log_c { unsigned int region_count; region_t sync_count; - unsigned bitset_uint32_count; + unsigned int bitset_uint32_count; uint32_t *clean_bits; uint32_t *sync_bits; uint32_t *recovering_bits; /* FIXME: this seems excessive */ @@ -256,20 +256,20 @@ struct log_c { * The touched member needs to be updated every time we access * one of the bitsets. */ -static inline int log_test_bit(uint32_t *bs, unsigned bit) +static inline int log_test_bit(uint32_t *bs, unsigned int bit) { return test_bit_le(bit, bs) ? 1 : 0; } static inline void log_set_bit(struct log_c *l, - uint32_t *bs, unsigned bit) + uint32_t *bs, unsigned int bit) { __set_bit_le(bit, bs); l->touched_cleaned = 1; } static inline void log_clear_bit(struct log_c *l, - uint32_t *bs, unsigned bit) + uint32_t *bs, unsigned int bit) { __clear_bit_le(bit, bs); l->touched_dirtied = 1; @@ -583,7 +583,7 @@ static void fail_log_device(struct log_c *lc) static int disk_resume(struct dm_dirty_log *log) { int r; - unsigned i; + unsigned int i; struct log_c *lc = (struct log_c *) log->context; size_t size = lc->bitset_uint32_count * sizeof(uint32_t); diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index a922794b2b40..27aa062590ea 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -30,7 +30,7 @@ #define DM_MSG_PREFIX "multipath" #define DM_PG_INIT_DELAY_MSECS 2000 -#define DM_PG_INIT_DELAY_DEFAULT ((unsigned) -1) +#define DM_PG_INIT_DELAY_DEFAULT ((unsigned int) -1) #define QUEUE_IF_NO_PATH_TIMEOUT_DEFAULT 0 static unsigned long queue_if_no_path_timeout_secs = QUEUE_IF_NO_PATH_TIMEOUT_DEFAULT; @@ -40,7 +40,7 @@ struct pgpath { struct list_head list; struct priority_group *pg; /* Owning PG */ - unsigned fail_count; /* Cumulative failure count */ + unsigned int fail_count; /* Cumulative failure count */ struct dm_path path; struct delayed_work activate_path; @@ -60,8 +60,8 @@ struct priority_group { struct multipath *m; /* Owning multipath instance */ struct path_selector ps; - unsigned pg_num; /* Reference number */ - unsigned nr_pgpaths; /* Number of paths in PG */ + unsigned int pg_num; /* Reference number */ + unsigned int nr_pgpaths; /* Number of paths in PG */ struct list_head pgpaths; bool bypassed:1; /* Temporarily bypass this PG? */ @@ -79,14 +79,14 @@ struct multipath { struct priority_group *next_pg; /* Switch to this PG if set */ atomic_t nr_valid_paths; /* Total number of usable paths */ - unsigned nr_priority_groups; + unsigned int nr_priority_groups; struct list_head priority_groups; const char *hw_handler_name; char *hw_handler_params; wait_queue_head_t pg_init_wait; /* Wait for pg_init completion */ - unsigned pg_init_retries; /* Number of times to retry pg_init */ - unsigned pg_init_delay_msecs; /* Number of msecs before pg_init retry */ + unsigned int pg_init_retries; /* Number of times to retry pg_init */ + unsigned int pg_init_delay_msecs; /* Number of msecs before pg_init retry */ atomic_t pg_init_in_progress; /* Only one pg_init allowed at once */ atomic_t pg_init_count; /* Number of times pg_init called */ @@ -398,7 +398,7 @@ static struct pgpath *choose_pgpath(struct multipath *m, size_t nr_bytes) unsigned long flags; struct priority_group *pg; struct pgpath *pgpath; - unsigned bypassed = 1; + unsigned int bypassed = 1; if (!atomic_read(&m->nr_valid_paths)) { spin_lock_irqsave(&m->lock, flags); @@ -841,7 +841,7 @@ static int parse_path_selector(struct dm_arg_set *as, struct priority_group *pg, { int r; struct path_selector_type *pst; - unsigned ps_argc; + unsigned int ps_argc; static const struct dm_arg _args[] = { {0, 1024, "invalid number of path selector args"}, @@ -984,7 +984,7 @@ static struct priority_group *parse_priority_group(struct dm_arg_set *as, }; int r; - unsigned i, nr_selector_args, nr_args; + unsigned int i, nr_selector_args, nr_args; struct priority_group *pg; struct dm_target *ti = m->ti; @@ -1050,7 +1050,7 @@ static struct priority_group *parse_priority_group(struct dm_arg_set *as, static int parse_hw_handler(struct dm_arg_set *as, struct multipath *m) { - unsigned hw_argc; + unsigned int hw_argc; int ret; struct dm_target *ti = m->ti; @@ -1102,7 +1102,7 @@ fail: static int parse_features(struct dm_arg_set *as, struct multipath *m) { int r; - unsigned argc; + unsigned int argc; struct dm_target *ti = m->ti; const char *arg_name; @@ -1171,7 +1171,7 @@ static int parse_features(struct dm_arg_set *as, struct multipath *m) return r; } -static int multipath_ctr(struct dm_target *ti, unsigned argc, char **argv) +static int multipath_ctr(struct dm_target *ti, unsigned int argc, char **argv) { /* target arguments */ static const struct dm_arg _args[] = { @@ -1182,8 +1182,8 @@ static int multipath_ctr(struct dm_target *ti, unsigned argc, char **argv) int r; struct multipath *m; struct dm_arg_set as; - unsigned pg_count = 0; - unsigned next_pg_num; + unsigned int pg_count = 0; + unsigned int next_pg_num; unsigned long flags; as.argc = argc; @@ -1225,7 +1225,7 @@ static int multipath_ctr(struct dm_target *ti, unsigned argc, char **argv) /* parse the priority groups */ while (as.argc) { struct priority_group *pg; - unsigned nr_valid_paths = atomic_read(&m->nr_valid_paths); + unsigned int nr_valid_paths = atomic_read(&m->nr_valid_paths); pg = parse_priority_group(&as, m); if (IS_ERR(pg)) { @@ -1366,7 +1366,7 @@ static int reinstate_path(struct pgpath *pgpath) int r = 0, run_queue = 0; unsigned long flags; struct multipath *m = pgpath->pg->m; - unsigned nr_valid_paths; + unsigned int nr_valid_paths; spin_lock_irqsave(&m->lock, flags); @@ -1455,7 +1455,7 @@ static void bypass_pg(struct multipath *m, struct priority_group *pg, static int switch_pg_num(struct multipath *m, const char *pgstr) { struct priority_group *pg; - unsigned pgnum; + unsigned int pgnum; unsigned long flags; char dummy; @@ -1488,7 +1488,7 @@ static int switch_pg_num(struct multipath *m, const char *pgstr) static int bypass_pg_num(struct multipath *m, const char *pgstr, bool bypassed) { struct priority_group *pg; - unsigned pgnum; + unsigned int pgnum; char dummy; if (!pgstr || (sscanf(pgstr, "%u%c", &pgnum, &dummy) != 1) || !pgnum || @@ -1790,14 +1790,14 @@ static void multipath_resume(struct dm_target *ti) * num_paths num_selector_args [path_dev [selector_args]* ]+ ]+ */ static void multipath_status(struct dm_target *ti, status_type_t type, - unsigned status_flags, char *result, unsigned maxlen) + unsigned int status_flags, char *result, unsigned int maxlen) { int sz = 0, pg_counter, pgpath_counter; unsigned long flags; struct multipath *m = ti->private; struct priority_group *pg; struct pgpath *p; - unsigned pg_num; + unsigned int pg_num; char state; spin_lock_irqsave(&m->lock, flags); @@ -1949,8 +1949,8 @@ static void multipath_status(struct dm_target *ti, status_type_t type, spin_unlock_irqrestore(&m->lock, flags); } -static int multipath_message(struct dm_target *ti, unsigned argc, char **argv, - char *result, unsigned maxlen) +static int multipath_message(struct dm_target *ti, unsigned int argc, char **argv, + char *result, unsigned int maxlen) { int r = -EINVAL; struct dm_dev *dev; diff --git a/drivers/md/dm-mpath.h b/drivers/md/dm-mpath.h index 61aa8e49cf59..0e168e0c82dd 100644 --- a/drivers/md/dm-mpath.h +++ b/drivers/md/dm-mpath.h @@ -18,6 +18,6 @@ struct dm_path { }; /* Callback for hwh_pg_init_fn to use when complete */ -void dm_pg_init_complete(struct dm_path *path, unsigned err_flags); +void dm_pg_init_complete(struct dm_path *path, unsigned int err_flags); #endif diff --git a/drivers/md/dm-path-selector.h b/drivers/md/dm-path-selector.h index 2e3ae9a1f687..8a32ef92907b 100644 --- a/drivers/md/dm-path-selector.h +++ b/drivers/md/dm-path-selector.h @@ -53,7 +53,7 @@ struct path_selector_type { /* * Constructs a path selector object, takes custom arguments */ - int (*create) (struct path_selector *ps, unsigned argc, char **argv); + int (*create) (struct path_selector *ps, unsigned int argc, char **argv); void (*destroy) (struct path_selector *ps); /* diff --git a/drivers/md/dm-ps-io-affinity.c b/drivers/md/dm-ps-io-affinity.c index f74501e65a8e..76ce4ce87222 100644 --- a/drivers/md/dm-ps-io-affinity.c +++ b/drivers/md/dm-ps-io-affinity.c @@ -108,7 +108,7 @@ free_pi: return ret; } -static int ioa_create(struct path_selector *ps, unsigned argc, char **argv) +static int ioa_create(struct path_selector *ps, unsigned int argc, char **argv) { struct selector *s; @@ -138,7 +138,7 @@ free_selector: static void ioa_destroy(struct path_selector *ps) { struct selector *s = ps->context; - unsigned cpu; + unsigned int cpu; for_each_cpu(cpu, s->path_mask) ioa_free_path(s, cpu); diff --git a/drivers/md/dm-ps-queue-length.c b/drivers/md/dm-ps-queue-length.c index 2a24eadfe772..387ec65ca0d7 100644 --- a/drivers/md/dm-ps-queue-length.c +++ b/drivers/md/dm-ps-queue-length.c @@ -36,7 +36,7 @@ struct selector { struct path_info { struct list_head list; struct dm_path *path; - unsigned repeat_count; + unsigned int repeat_count; atomic_t qlen; /* the number of in-flight I/Os */ }; @@ -53,7 +53,7 @@ static struct selector *alloc_selector(void) return s; } -static int ql_create(struct path_selector *ps, unsigned argc, char **argv) +static int ql_create(struct path_selector *ps, unsigned int argc, char **argv) { struct selector *s = alloc_selector(); @@ -85,9 +85,9 @@ static void ql_destroy(struct path_selector *ps) } static int ql_status(struct path_selector *ps, struct dm_path *path, - status_type_t type, char *result, unsigned maxlen) + status_type_t type, char *result, unsigned int maxlen) { - unsigned sz = 0; + unsigned int sz = 0; struct path_info *pi; /* When called with NULL path, return selector status/args. */ @@ -117,7 +117,7 @@ static int ql_add_path(struct path_selector *ps, struct dm_path *path, { struct selector *s = ps->context; struct path_info *pi; - unsigned repeat_count = QL_MIN_IO; + unsigned int repeat_count = QL_MIN_IO; char dummy; unsigned long flags; diff --git a/drivers/md/dm-ps-round-robin.c b/drivers/md/dm-ps-round-robin.c index e7b99a8c12a6..aaf805efaedd 100644 --- a/drivers/md/dm-ps-round-robin.c +++ b/drivers/md/dm-ps-round-robin.c @@ -27,7 +27,7 @@ struct path_info { struct list_head list; struct dm_path *path; - unsigned repeat_count; + unsigned int repeat_count; }; static void free_paths(struct list_head *paths) @@ -63,7 +63,7 @@ static struct selector *alloc_selector(void) return s; } -static int rr_create(struct path_selector *ps, unsigned argc, char **argv) +static int rr_create(struct path_selector *ps, unsigned int argc, char **argv) { struct selector *s; @@ -120,7 +120,7 @@ static int rr_add_path(struct path_selector *ps, struct dm_path *path, { struct selector *s = ps->context; struct path_info *pi; - unsigned repeat_count = RR_MIN_IO; + unsigned int repeat_count = RR_MIN_IO; char dummy; unsigned long flags; diff --git a/drivers/md/dm-ps-service-time.c b/drivers/md/dm-ps-service-time.c index debc88498784..b460054415f1 100644 --- a/drivers/md/dm-ps-service-time.c +++ b/drivers/md/dm-ps-service-time.c @@ -31,8 +31,8 @@ struct selector { struct path_info { struct list_head list; struct dm_path *path; - unsigned repeat_count; - unsigned relative_throughput; + unsigned int repeat_count; + unsigned int relative_throughput; atomic_t in_flight_size; /* Total size of in-flight I/Os */ }; @@ -49,7 +49,7 @@ static struct selector *alloc_selector(void) return s; } -static int st_create(struct path_selector *ps, unsigned argc, char **argv) +static int st_create(struct path_selector *ps, unsigned int argc, char **argv) { struct selector *s = alloc_selector(); @@ -81,9 +81,9 @@ static void st_destroy(struct path_selector *ps) } static int st_status(struct path_selector *ps, struct dm_path *path, - status_type_t type, char *result, unsigned maxlen) + status_type_t type, char *result, unsigned int maxlen) { - unsigned sz = 0; + unsigned int sz = 0; struct path_info *pi; if (!path) @@ -114,8 +114,8 @@ static int st_add_path(struct path_selector *ps, struct dm_path *path, { struct selector *s = ps->context; struct path_info *pi; - unsigned repeat_count = ST_MIN_IO; - unsigned relative_throughput = 1; + unsigned int repeat_count = ST_MIN_IO; + unsigned int relative_throughput = 1; char dummy; unsigned long flags; diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index cac781ecee5a..e4489f10aac2 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -3713,7 +3713,7 @@ static void raid_status(struct dm_target *ti, status_type_t type, } static int raid_message(struct dm_target *ti, unsigned int argc, char **argv, - char *result, unsigned maxlen) + char *result, unsigned int maxlen) { struct raid_set *rs = ti->private; struct mddev *mddev = &rs->md; diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c index 65c8f434fb2a..30d5aa5dec8f 100644 --- a/drivers/md/dm-raid1.c +++ b/drivers/md/dm-raid1.c @@ -83,7 +83,7 @@ struct mirror_set { struct work_struct trigger_event; - unsigned nr_mirrors; + unsigned int nr_mirrors; struct mirror mirror[]; }; @@ -328,7 +328,7 @@ static void recovery_complete(int read_err, unsigned long write_err, static void recover(struct mirror_set *ms, struct dm_region *reg) { - unsigned i; + unsigned int i; struct dm_io_region from, to[DM_KCOPYD_MAX_REGIONS], *dest; struct mirror *m; unsigned long flags = 0; @@ -594,7 +594,7 @@ static void do_reads(struct mirror_set *ms, struct bio_list *reads) static void write_callback(unsigned long error, void *context) { - unsigned i; + unsigned int i; struct bio *bio = (struct bio *) context; struct mirror_set *ms; int should_wake = 0; @@ -964,10 +964,10 @@ static int get_mirror(struct mirror_set *ms, struct dm_target *ti, * Create dirty log: log_type #log_params */ static struct dm_dirty_log *create_dirty_log(struct dm_target *ti, - unsigned argc, char **argv, - unsigned *args_used) + unsigned int argc, char **argv, + unsigned int *args_used) { - unsigned param_count; + unsigned int param_count; struct dm_dirty_log *dl; char dummy; @@ -998,10 +998,10 @@ static struct dm_dirty_log *create_dirty_log(struct dm_target *ti, return dl; } -static int parse_features(struct mirror_set *ms, unsigned argc, char **argv, - unsigned *args_used) +static int parse_features(struct mirror_set *ms, unsigned int argc, char **argv, + unsigned int *args_used) { - unsigned num_features; + unsigned int num_features; struct dm_target *ti = ms->ti; char dummy; int i; @@ -1390,7 +1390,7 @@ static char device_status_char(struct mirror *m) static void mirror_status(struct dm_target *ti, status_type_t type, - unsigned status_flags, char *result, unsigned maxlen) + unsigned int status_flags, char *result, unsigned int maxlen) { unsigned int m, sz = 0; int num_feature_args = 0; @@ -1459,7 +1459,7 @@ static int mirror_iterate_devices(struct dm_target *ti, { struct mirror_set *ms = ti->private; int ret = 0; - unsigned i; + unsigned int i; for (i = 0; !ret && i < ms->nr_mirrors; i++) ret = fn(ti, ms->mirror[i].dev, diff --git a/drivers/md/dm-region-hash.c b/drivers/md/dm-region-hash.c index 317294ff5e9c..462cb24ba92e 100644 --- a/drivers/md/dm-region-hash.c +++ b/drivers/md/dm-region-hash.c @@ -57,17 +57,17 @@ *---------------------------------------------------------------*/ struct dm_region_hash { uint32_t region_size; - unsigned region_shift; + unsigned int region_shift; /* holds persistent region state */ struct dm_dirty_log *log; /* hash table */ rwlock_t hash_lock; - unsigned mask; - unsigned nr_buckets; - unsigned prime; - unsigned shift; + unsigned int mask; + unsigned int nr_buckets; + unsigned int prime; + unsigned int shift; struct list_head *buckets; /* @@ -75,7 +75,7 @@ struct dm_region_hash { */ int flush_failure; - unsigned max_recovery; /* Max # of regions to recover in parallel */ + unsigned int max_recovery; /* Max # of regions to recover in parallel */ spinlock_t region_lock; atomic_t recovery_in_flight; @@ -164,12 +164,12 @@ struct dm_region_hash *dm_region_hash_create( struct bio_list *bios), void (*wakeup_workers)(void *context), void (*wakeup_all_recovery_waiters)(void *context), - sector_t target_begin, unsigned max_recovery, + sector_t target_begin, unsigned int max_recovery, struct dm_dirty_log *log, uint32_t region_size, region_t nr_regions) { struct dm_region_hash *rh; - unsigned nr_buckets, max_buckets; + unsigned int nr_buckets, max_buckets; size_t i; int ret; @@ -237,7 +237,7 @@ EXPORT_SYMBOL_GPL(dm_region_hash_create); void dm_region_hash_destroy(struct dm_region_hash *rh) { - unsigned h; + unsigned int h; struct dm_region *reg, *nreg; BUG_ON(!list_empty(&rh->quiesced_regions)); @@ -264,9 +264,9 @@ struct dm_dirty_log *dm_rh_dirty_log(struct dm_region_hash *rh) } EXPORT_SYMBOL_GPL(dm_rh_dirty_log); -static unsigned rh_hash(struct dm_region_hash *rh, region_t region) +static unsigned int rh_hash(struct dm_region_hash *rh, region_t region) { - return (unsigned) ((region * rh->prime) >> rh->shift) & rh->mask; + return (unsigned int) ((region * rh->prime) >> rh->shift) & rh->mask; } static struct dm_region *__rh_lookup(struct dm_region_hash *rh, region_t region) diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c index 38be316a22a8..7ba62219d9fb 100644 --- a/drivers/md/dm-rq.c +++ b/drivers/md/dm-rq.c @@ -24,33 +24,33 @@ struct dm_rq_target_io { union map_info info; struct dm_stats_aux stats_aux; unsigned long duration_jiffies; - unsigned n_sectors; - unsigned completed; + unsigned int n_sectors; + unsigned int completed; }; #define DM_MQ_NR_HW_QUEUES 1 #define DM_MQ_QUEUE_DEPTH 2048 -static unsigned dm_mq_nr_hw_queues = DM_MQ_NR_HW_QUEUES; -static unsigned dm_mq_queue_depth = DM_MQ_QUEUE_DEPTH; +static unsigned int dm_mq_nr_hw_queues = DM_MQ_NR_HW_QUEUES; +static unsigned int dm_mq_queue_depth = DM_MQ_QUEUE_DEPTH; /* * Request-based DM's mempools' reserved IOs set by the user. */ #define RESERVED_REQUEST_BASED_IOS 256 -static unsigned reserved_rq_based_ios = RESERVED_REQUEST_BASED_IOS; +static unsigned int reserved_rq_based_ios = RESERVED_REQUEST_BASED_IOS; -unsigned dm_get_reserved_rq_based_ios(void) +unsigned int dm_get_reserved_rq_based_ios(void) { return __dm_get_module_param(&reserved_rq_based_ios, RESERVED_REQUEST_BASED_IOS, DM_RESERVED_MAX_IOS); } -static unsigned dm_get_blk_mq_nr_hw_queues(void) +static unsigned int dm_get_blk_mq_nr_hw_queues(void) { return __dm_get_module_param(&dm_mq_nr_hw_queues, 1, 32); } -static unsigned dm_get_blk_mq_queue_depth(void) +static unsigned int dm_get_blk_mq_queue_depth(void) { return __dm_get_module_param(&dm_mq_queue_depth, DM_MQ_QUEUE_DEPTH, BLK_MQ_MAX_DEPTH); diff --git a/drivers/md/dm-rq.h b/drivers/md/dm-rq.h index 7360b00630ee..1f73e194e792 100644 --- a/drivers/md/dm-rq.h +++ b/drivers/md/dm-rq.h @@ -39,7 +39,7 @@ void dm_stop_queue(struct request_queue *q); void dm_mq_kick_requeue_list(struct mapped_device *md); -unsigned dm_get_reserved_rq_based_ios(void); +unsigned int dm_get_reserved_rq_based_ios(void); ssize_t dm_attr_rq_based_seq_io_merge_deadline_show(struct mapped_device *md, char *buf); ssize_t dm_attr_rq_based_seq_io_merge_deadline_store(struct mapped_device *md, diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c index 4be2d1864f0c..ce68143fe30b 100644 --- a/drivers/md/dm-snap-persistent.c +++ b/drivers/md/dm-snap-persistent.c @@ -304,7 +304,7 @@ static int read_header(struct pstore *ps, int *new_snapshot) { int r; struct disk_header *dh; - unsigned chunk_size; + unsigned int chunk_size; int chunk_size_supplied = 1; char *chunk_err; @@ -896,11 +896,11 @@ err_workqueue: return r; } -static unsigned persistent_status(struct dm_exception_store *store, +static unsigned int persistent_status(struct dm_exception_store *store, status_type_t status, char *result, - unsigned maxlen) + unsigned int maxlen) { - unsigned sz = 0; + unsigned int sz = 0; switch (status) { case STATUSTYPE_INFO: diff --git a/drivers/md/dm-snap-transient.c b/drivers/md/dm-snap-transient.c index a57bbb005b4f..122257405dcc 100644 --- a/drivers/md/dm-snap-transient.c +++ b/drivers/md/dm-snap-transient.c @@ -85,11 +85,11 @@ static int transient_ctr(struct dm_exception_store *store, char *options) return 0; } -static unsigned transient_status(struct dm_exception_store *store, +static unsigned int transient_status(struct dm_exception_store *store, status_type_t status, char *result, - unsigned maxlen) + unsigned int maxlen) { - unsigned sz = 0; + unsigned int sz = 0; switch (status) { case STATUSTYPE_INFO: diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c index dc69f6588ff6..f61622d46c72 100644 --- a/drivers/md/dm-snap.c +++ b/drivers/md/dm-snap.c @@ -42,7 +42,7 @@ static const char dm_snapshot_merge_target_name[] = "snapshot-merge"; struct dm_exception_table { uint32_t hash_mask; - unsigned hash_shift; + unsigned int hash_shift; struct hlist_bl_head *table; }; @@ -107,7 +107,7 @@ struct dm_snapshot { /* The on disk metadata handler */ struct dm_exception_store *store; - unsigned in_progress; + unsigned int in_progress; struct wait_queue_head in_progress_wait; struct dm_kcopyd_client *kcopyd_client; @@ -162,7 +162,7 @@ struct dm_snapshot { */ #define DEFAULT_COW_THRESHOLD 2048 -static unsigned cow_threshold = DEFAULT_COW_THRESHOLD; +static unsigned int cow_threshold = DEFAULT_COW_THRESHOLD; module_param_named(snapshot_cow_threshold, cow_threshold, uint, 0644); MODULE_PARM_DESC(snapshot_cow_threshold, "Maximum number of chunks being copied on write"); @@ -325,7 +325,7 @@ struct origin { struct dm_origin { struct dm_dev *dev; struct dm_target *ti; - unsigned split_boundary; + unsigned int split_boundary; struct list_head hash_list; }; @@ -378,7 +378,7 @@ static void exit_origin_hash(void) kfree(_dm_origins); } -static unsigned origin_hash(struct block_device *bdev) +static unsigned int origin_hash(struct block_device *bdev) { return bdev->bd_dev & ORIGIN_MASK; } @@ -653,7 +653,7 @@ static void dm_exception_table_unlock(struct dm_exception_table_lock *lock) } static int dm_exception_table_init(struct dm_exception_table *et, - uint32_t size, unsigned hash_shift) + uint32_t size, unsigned int hash_shift) { unsigned int i; @@ -851,7 +851,7 @@ static int dm_add_exception(void *context, chunk_t old, chunk_t new) static uint32_t __minimum_chunk_size(struct origin *o) { struct dm_snapshot *snap; - unsigned chunk_size = rounddown_pow_of_two(UINT_MAX); + unsigned int chunk_size = rounddown_pow_of_two(UINT_MAX); if (o) list_for_each_entry(snap, &o->snapshots, list) @@ -1011,7 +1011,7 @@ out: } static int origin_write_extent(struct dm_snapshot *merging_snap, - sector_t sector, unsigned chunk_size); + sector_t sector, unsigned int chunk_size); static void merge_callback(int read_err, unsigned long write_err, void *context); @@ -1184,7 +1184,7 @@ static int parse_snapshot_features(struct dm_arg_set *as, struct dm_snapshot *s, struct dm_target *ti) { int r; - unsigned argc; + unsigned int argc; const char *arg_name; static const struct dm_arg _args[] = { @@ -1242,7 +1242,7 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv) int r = -EINVAL; char *origin_path, *cow_path; dev_t origin_dev, cow_dev; - unsigned args_used, num_flush_bios = 1; + unsigned int args_used, num_flush_bios = 1; fmode_t origin_mode = FMODE_READ; if (argc < 4) { @@ -2316,11 +2316,11 @@ static void snapshot_merge_resume(struct dm_target *ti) } static void snapshot_status(struct dm_target *ti, status_type_t type, - unsigned status_flags, char *result, unsigned maxlen) + unsigned int status_flags, char *result, unsigned int maxlen) { - unsigned sz = 0; + unsigned int sz = 0; struct dm_snapshot *snap = ti->private; - unsigned num_features; + unsigned int num_features; switch (type) { case STATUSTYPE_INFO: @@ -2593,7 +2593,7 @@ again: * size must be a multiple of merging_snap's chunk_size. */ static int origin_write_extent(struct dm_snapshot *merging_snap, - sector_t sector, unsigned size) + sector_t sector, unsigned int size) { int must_wait = 0; sector_t n; @@ -2669,7 +2669,7 @@ static void origin_dtr(struct dm_target *ti) static int origin_map(struct dm_target *ti, struct bio *bio) { struct dm_origin *o = ti->private; - unsigned available_sectors; + unsigned int available_sectors; bio_set_dev(bio, o->dev->bdev); @@ -2680,7 +2680,7 @@ static int origin_map(struct dm_target *ti, struct bio *bio) return DM_MAPIO_REMAPPED; available_sectors = o->split_boundary - - ((unsigned)bio->bi_iter.bi_sector & (o->split_boundary - 1)); + ((unsigned int)bio->bi_iter.bi_sector & (o->split_boundary - 1)); if (bio_sectors(bio) > available_sectors) dm_accept_partial_bio(bio, available_sectors); @@ -2714,7 +2714,7 @@ static void origin_postsuspend(struct dm_target *ti) } static void origin_status(struct dm_target *ti, status_type_t type, - unsigned status_flags, char *result, unsigned maxlen) + unsigned int status_flags, char *result, unsigned int maxlen) { struct dm_origin *o = ti->private; diff --git a/drivers/md/dm-stats.c b/drivers/md/dm-stats.c index d7188d011985..1a94fb0e44f1 100644 --- a/drivers/md/dm-stats.c +++ b/drivers/md/dm-stats.c @@ -42,12 +42,12 @@ struct dm_stat_shared { struct dm_stat { struct list_head list_entry; int id; - unsigned stat_flags; + unsigned int stat_flags; size_t n_entries; sector_t start; sector_t end; sector_t step; - unsigned n_histogram_entries; + unsigned int n_histogram_entries; unsigned long long *histogram_boundaries; const char *program_id; const char *aux_data; @@ -63,7 +63,7 @@ struct dm_stat { struct dm_stats_last_position { sector_t last_sector; - unsigned last_rw; + unsigned int last_rw; }; /* @@ -250,8 +250,8 @@ static void dm_stats_recalc_precise_timestamps(struct dm_stats *stats) } static int dm_stats_create(struct dm_stats *stats, sector_t start, sector_t end, - sector_t step, unsigned stat_flags, - unsigned n_histogram_entries, + sector_t step, unsigned int stat_flags, + unsigned int n_histogram_entries, unsigned long long *histogram_boundaries, const char *program_id, const char *aux_data, void (*suspend_callback)(struct mapped_device *), @@ -470,11 +470,11 @@ do_sync_free: } static int dm_stats_list(struct dm_stats *stats, const char *program, - char *result, unsigned maxlen) + char *result, unsigned int maxlen) { struct dm_stat *s; sector_t len; - unsigned sz = 0; + unsigned int sz = 0; /* * Output format: @@ -494,7 +494,7 @@ static int dm_stats_list(struct dm_stats *stats, const char *program, if (s->stat_flags & STAT_PRECISE_TIMESTAMPS) DMEMIT(" precise_timestamps"); if (s->n_histogram_entries) { - unsigned i; + unsigned int i; DMEMIT(" histogram:"); for (i = 0; i < s->n_histogram_entries; i++) { if (i) @@ -518,7 +518,7 @@ static void dm_stat_round(struct dm_stat *s, struct dm_stat_shared *shared, * This is racy, but so is part_round_stats_single. */ unsigned long long now, difference; - unsigned in_flight_read, in_flight_write; + unsigned int in_flight_read, in_flight_write; if (likely(!(s->stat_flags & STAT_PRECISE_TIMESTAMPS))) now = jiffies; @@ -529,8 +529,8 @@ static void dm_stat_round(struct dm_stat *s, struct dm_stat_shared *shared, if (!difference) return; - in_flight_read = (unsigned)atomic_read(&shared->in_flight[READ]); - in_flight_write = (unsigned)atomic_read(&shared->in_flight[WRITE]); + in_flight_read = (unsigned int)atomic_read(&shared->in_flight[READ]); + in_flight_write = (unsigned int)atomic_read(&shared->in_flight[WRITE]); if (in_flight_read) p->io_ticks[READ] += difference; if (in_flight_write) @@ -591,9 +591,9 @@ static void dm_stat_for_entry(struct dm_stat *s, size_t entry, duration = stats_aux->duration_ns; } if (s->n_histogram_entries) { - unsigned lo = 0, hi = s->n_histogram_entries + 1; + unsigned int lo = 0, hi = s->n_histogram_entries + 1; while (lo + 1 < hi) { - unsigned mid = (lo + hi) / 2; + unsigned int mid = (lo + hi) / 2; if (s->histogram_boundaries[mid - 1] > duration) { hi = mid; } else { @@ -651,7 +651,7 @@ static void __dm_stat_bio(struct dm_stat *s, int bi_rw, } void dm_stats_account_io(struct dm_stats *stats, unsigned long bi_rw, - sector_t bi_sector, unsigned bi_sectors, bool end, + sector_t bi_sector, unsigned int bi_sectors, bool end, unsigned long start_time, struct dm_stats_aux *stats_aux) { @@ -740,7 +740,7 @@ static void __dm_stat_init_temporary_percpu_totals(struct dm_stat_shared *shared shared->tmp.io_ticks_total += READ_ONCE(p->io_ticks_total); shared->tmp.time_in_queue += READ_ONCE(p->time_in_queue); if (s->n_histogram_entries) { - unsigned i; + unsigned int i; for (i = 0; i < s->n_histogram_entries + 1; i++) shared->tmp.histogram[i] += READ_ONCE(p->histogram[i]); } @@ -774,7 +774,7 @@ static void __dm_stat_clear(struct dm_stat *s, size_t idx_start, size_t idx_end, p->time_in_queue -= shared->tmp.time_in_queue; local_irq_enable(); if (s->n_histogram_entries) { - unsigned i; + unsigned int i; for (i = 0; i < s->n_histogram_entries + 1; i++) { local_irq_disable(); p = &s->stat_percpu[smp_processor_id()][x]; @@ -811,7 +811,7 @@ static int dm_stats_clear(struct dm_stats *stats, int id) static unsigned long long dm_jiffies_to_msec64(struct dm_stat *s, unsigned long long j) { unsigned long long result; - unsigned mult; + unsigned int mult; if (s->stat_flags & STAT_PRECISE_TIMESTAMPS) return j; @@ -831,9 +831,9 @@ static unsigned long long dm_jiffies_to_msec64(struct dm_stat *s, unsigned long static int dm_stats_print(struct dm_stats *stats, int id, size_t idx_start, size_t idx_len, - bool clear, char *result, unsigned maxlen) + bool clear, char *result, unsigned int maxlen) { - unsigned sz = 0; + unsigned int sz = 0; struct dm_stat *s; size_t x; sector_t start, end, step; @@ -889,7 +889,7 @@ static int dm_stats_print(struct dm_stats *stats, int id, dm_jiffies_to_msec64(s, shared->tmp.io_ticks[READ]), dm_jiffies_to_msec64(s, shared->tmp.io_ticks[WRITE])); if (s->n_histogram_entries) { - unsigned i; + unsigned int i; for (i = 0; i < s->n_histogram_entries + 1; i++) { DMEMIT("%s%llu", !i ? " " : ":", shared->tmp.histogram[i]); } @@ -938,11 +938,11 @@ static int dm_stats_set_aux(struct dm_stats *stats, int id, const char *aux_data return 0; } -static int parse_histogram(const char *h, unsigned *n_histogram_entries, +static int parse_histogram(const char *h, unsigned int *n_histogram_entries, unsigned long long **histogram_boundaries) { const char *q; - unsigned n; + unsigned int n; unsigned long long last; *n_histogram_entries = 1; @@ -977,23 +977,23 @@ static int parse_histogram(const char *h, unsigned *n_histogram_entries, } static int message_stats_create(struct mapped_device *md, - unsigned argc, char **argv, - char *result, unsigned maxlen) + unsigned int argc, char **argv, + char *result, unsigned int maxlen) { int r; int id; char dummy; unsigned long long start, end, len, step; - unsigned divisor; + unsigned int divisor; const char *program_id, *aux_data; - unsigned stat_flags = 0; + unsigned int stat_flags = 0; - unsigned n_histogram_entries = 0; + unsigned int n_histogram_entries = 0; unsigned long long *histogram_boundaries = NULL; struct dm_arg_set as, as_backup; const char *a; - unsigned feature_args; + unsigned int feature_args; /* * Input format: @@ -1102,7 +1102,7 @@ ret: } static int message_stats_delete(struct mapped_device *md, - unsigned argc, char **argv) + unsigned int argc, char **argv) { int id; char dummy; @@ -1117,7 +1117,7 @@ static int message_stats_delete(struct mapped_device *md, } static int message_stats_clear(struct mapped_device *md, - unsigned argc, char **argv) + unsigned int argc, char **argv) { int id; char dummy; @@ -1132,8 +1132,8 @@ static int message_stats_clear(struct mapped_device *md, } static int message_stats_list(struct mapped_device *md, - unsigned argc, char **argv, - char *result, unsigned maxlen) + unsigned int argc, char **argv, + char *result, unsigned int maxlen) { int r; const char *program = NULL; @@ -1155,8 +1155,8 @@ static int message_stats_list(struct mapped_device *md, } static int message_stats_print(struct mapped_device *md, - unsigned argc, char **argv, bool clear, - char *result, unsigned maxlen) + unsigned int argc, char **argv, bool clear, + char *result, unsigned int maxlen) { int id; char dummy; @@ -1182,7 +1182,7 @@ static int message_stats_print(struct mapped_device *md, } static int message_stats_set_aux(struct mapped_device *md, - unsigned argc, char **argv) + unsigned int argc, char **argv) { int id; char dummy; @@ -1196,8 +1196,8 @@ static int message_stats_set_aux(struct mapped_device *md, return dm_stats_set_aux(dm_get_stats(md), id, argv[2]); } -int dm_stats_message(struct mapped_device *md, unsigned argc, char **argv, - char *result, unsigned maxlen) +int dm_stats_message(struct mapped_device *md, unsigned int argc, char **argv, + char *result, unsigned int maxlen) { int r; diff --git a/drivers/md/dm-stats.h b/drivers/md/dm-stats.h index 09c81a1ec057..0bc152c8e4f3 100644 --- a/drivers/md/dm-stats.h +++ b/drivers/md/dm-stats.h @@ -26,11 +26,11 @@ void dm_stats_cleanup(struct dm_stats *st); struct mapped_device; -int dm_stats_message(struct mapped_device *md, unsigned argc, char **argv, - char *result, unsigned maxlen); +int dm_stats_message(struct mapped_device *md, unsigned int argc, char **argv, + char *result, unsigned int maxlen); void dm_stats_account_io(struct dm_stats *stats, unsigned long bi_rw, - sector_t bi_sector, unsigned bi_sectors, bool end, + sector_t bi_sector, unsigned int bi_sectors, bool end, unsigned long start_time, struct dm_stats_aux *aux); diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c index efd23832e731..5ec4be4b978e 100644 --- a/drivers/md/dm-stripe.c +++ b/drivers/md/dm-stripe.c @@ -274,7 +274,7 @@ static int stripe_map(struct dm_target *ti, struct bio *bio) { struct stripe_c *sc = ti->private; uint32_t stripe; - unsigned target_bio_nr; + unsigned int target_bio_nr; if (bio->bi_opf & REQ_PREFLUSH) { target_bio_nr = dm_bio_get_target_bio_nr(bio); @@ -360,7 +360,7 @@ static size_t stripe_dax_recovery_write(struct dm_target *ti, pgoff_t pgoff, */ static void stripe_status(struct dm_target *ti, status_type_t type, - unsigned status_flags, char *result, unsigned maxlen) + unsigned int status_flags, char *result, unsigned int maxlen) { struct stripe_c *sc = (struct stripe_c *) ti->private; unsigned int sz = 0; @@ -407,7 +407,7 @@ static void stripe_status(struct dm_target *ti, status_type_t type, static int stripe_end_io(struct dm_target *ti, struct bio *bio, blk_status_t *error) { - unsigned i; + unsigned int i; char major_minor[16]; struct stripe_c *sc = ti->private; @@ -445,7 +445,7 @@ static int stripe_iterate_devices(struct dm_target *ti, { struct stripe_c *sc = ti->private; int ret = 0; - unsigned i = 0; + unsigned int i = 0; do { ret = fn(ti, sc->stripe[i].dev, @@ -460,7 +460,7 @@ static void stripe_io_hints(struct dm_target *ti, struct queue_limits *limits) { struct stripe_c *sc = ti->private; - unsigned chunk_size = sc->chunk_size << SECTOR_SHIFT; + unsigned int chunk_size = sc->chunk_size << SECTOR_SHIFT; blk_limits_io_min(limits, chunk_size); blk_limits_io_opt(limits, chunk_size * sc->stripes); diff --git a/drivers/md/dm-switch.c b/drivers/md/dm-switch.c index f841923b3454..ee2432927e90 100644 --- a/drivers/md/dm-switch.c +++ b/drivers/md/dm-switch.c @@ -39,9 +39,9 @@ struct switch_path { struct switch_ctx { struct dm_target *ti; - unsigned nr_paths; /* Number of paths in path_list. */ + unsigned int nr_paths; /* Number of paths in path_list. */ - unsigned region_size; /* Region size in 512-byte sectors */ + unsigned int region_size; /* Region size in 512-byte sectors */ unsigned long nr_regions; /* Number of regions making up the device */ signed char region_size_bits; /* log2 of region_size or -1 */ @@ -57,8 +57,8 @@ struct switch_ctx { struct switch_path path_list[]; }; -static struct switch_ctx *alloc_switch_ctx(struct dm_target *ti, unsigned nr_paths, - unsigned region_size) +static struct switch_ctx *alloc_switch_ctx(struct dm_target *ti, unsigned int nr_paths, + unsigned int region_size) { struct switch_ctx *sctx; @@ -74,7 +74,7 @@ static struct switch_ctx *alloc_switch_ctx(struct dm_target *ti, unsigned nr_pat return sctx; } -static int alloc_region_table(struct dm_target *ti, unsigned nr_paths) +static int alloc_region_table(struct dm_target *ti, unsigned int nr_paths) { struct switch_ctx *sctx = ti->private; sector_t nr_regions = ti->len; @@ -125,7 +125,7 @@ static int alloc_region_table(struct dm_target *ti, unsigned nr_paths) } static void switch_get_position(struct switch_ctx *sctx, unsigned long region_nr, - unsigned long *region_index, unsigned *bit) + unsigned long *region_index, unsigned int *bit) { if (sctx->region_entries_per_slot_bits >= 0) { *region_index = region_nr >> sctx->region_entries_per_slot_bits; @@ -138,10 +138,10 @@ static void switch_get_position(struct switch_ctx *sctx, unsigned long region_nr *bit *= sctx->region_table_entry_bits; } -static unsigned switch_region_table_read(struct switch_ctx *sctx, unsigned long region_nr) +static unsigned int switch_region_table_read(struct switch_ctx *sctx, unsigned long region_nr) { unsigned long region_index; - unsigned bit; + unsigned int bit; switch_get_position(sctx, region_nr, ®ion_index, &bit); @@ -152,9 +152,9 @@ static unsigned switch_region_table_read(struct switch_ctx *sctx, unsigned long /* * Find which path to use at given offset. */ -static unsigned switch_get_path_nr(struct switch_ctx *sctx, sector_t offset) +static unsigned int switch_get_path_nr(struct switch_ctx *sctx, sector_t offset) { - unsigned path_nr; + unsigned int path_nr; sector_t p; p = offset; @@ -173,10 +173,10 @@ static unsigned switch_get_path_nr(struct switch_ctx *sctx, sector_t offset) } static void switch_region_table_write(struct switch_ctx *sctx, unsigned long region_nr, - unsigned value) + unsigned int value) { unsigned long region_index; - unsigned bit; + unsigned int bit; region_table_slot_t pte; switch_get_position(sctx, region_nr, ®ion_index, &bit); @@ -192,7 +192,7 @@ static void switch_region_table_write(struct switch_ctx *sctx, unsigned long reg */ static void initialise_region_table(struct switch_ctx *sctx) { - unsigned path_nr = 0; + unsigned int path_nr = 0; unsigned long region_nr; for (region_nr = 0; region_nr < sctx->nr_regions; region_nr++) { @@ -250,7 +250,7 @@ static void switch_dtr(struct dm_target *ti) * Optional args are to allow for future extension: currently this * parameter must be 0. */ -static int switch_ctr(struct dm_target *ti, unsigned argc, char **argv) +static int switch_ctr(struct dm_target *ti, unsigned int argc, char **argv) { static const struct dm_arg _args[] = { {1, (KMALLOC_MAX_SIZE - sizeof(struct switch_ctx)) / sizeof(struct switch_path), "Invalid number of paths"}, @@ -260,7 +260,7 @@ static int switch_ctr(struct dm_target *ti, unsigned argc, char **argv) struct switch_ctx *sctx; struct dm_arg_set as; - unsigned nr_paths, region_size, nr_optional_args; + unsigned int nr_paths, region_size, nr_optional_args; int r; as.argc = argc; @@ -321,7 +321,7 @@ static int switch_map(struct dm_target *ti, struct bio *bio) { struct switch_ctx *sctx = ti->private; sector_t offset = dm_target_offset(ti, bio->bi_iter.bi_sector); - unsigned path_nr = switch_get_path_nr(sctx, offset); + unsigned int path_nr = switch_get_path_nr(sctx, offset); bio_set_dev(bio, sctx->path_list[path_nr].dmdev->bdev); bio->bi_iter.bi_sector = sctx->path_list[path_nr].start + offset; @@ -372,9 +372,9 @@ static __always_inline unsigned long parse_hex(const char **string) } static int process_set_region_mappings(struct switch_ctx *sctx, - unsigned argc, char **argv) + unsigned int argc, char **argv) { - unsigned i; + unsigned int i; unsigned long region_index = 0; for (i = 1; i < argc; i++) { @@ -467,8 +467,8 @@ static int process_set_region_mappings(struct switch_ctx *sctx, * * Only set_region_mappings is supported. */ -static int switch_message(struct dm_target *ti, unsigned argc, char **argv, - char *result, unsigned maxlen) +static int switch_message(struct dm_target *ti, unsigned int argc, char **argv, + char *result, unsigned int maxlen) { static DEFINE_MUTEX(message_mutex); @@ -488,10 +488,10 @@ static int switch_message(struct dm_target *ti, unsigned argc, char **argv, } static void switch_status(struct dm_target *ti, status_type_t type, - unsigned status_flags, char *result, unsigned maxlen) + unsigned int status_flags, char *result, unsigned int maxlen) { struct switch_ctx *sctx = ti->private; - unsigned sz = 0; + unsigned int sz = 0; int path_nr; switch (type) { @@ -520,7 +520,7 @@ static void switch_status(struct dm_target *ti, status_type_t type, static int switch_prepare_ioctl(struct dm_target *ti, struct block_device **bdev) { struct switch_ctx *sctx = ti->private; - unsigned path_nr; + unsigned int path_nr; path_nr = switch_get_path_nr(sctx, 0); diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index e6709cf760ed..455d7303e278 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -127,7 +127,7 @@ static int alloc_targets(struct dm_table *t, unsigned int num) } int dm_table_create(struct dm_table **result, fmode_t mode, - unsigned num_targets, struct mapped_device *md) + unsigned int num_targets, struct mapped_device *md) { struct dm_table *t = kzalloc(sizeof(*t), GFP_KERNEL); @@ -473,10 +473,10 @@ static int adjoin(struct dm_table *t, struct dm_target *ti) * On the other hand, dm-switch needs to process bulk data using messages and * excessive use of GFP_NOIO could cause trouble. */ -static char **realloc_argv(unsigned *size, char **old_argv) +static char **realloc_argv(unsigned int *size, char **old_argv) { char **argv; - unsigned new_size; + unsigned int new_size; gfp_t gfp; if (*size) { @@ -502,7 +502,7 @@ static char **realloc_argv(unsigned *size, char **old_argv) int dm_split_args(int *argc, char ***argvp, char *input) { char *start, *end = input, *out, **argv = NULL; - unsigned array_size = 0; + unsigned int array_size = 0; *argc = 0; @@ -735,9 +735,8 @@ int dm_table_add_target(struct dm_table *t, const char *type, /* * Target argument parsing helpers. */ -static int validate_next_arg(const struct dm_arg *arg, - struct dm_arg_set *arg_set, - unsigned *value, char **error, unsigned grouped) +static int validate_next_arg(const struct dm_arg *arg, struct dm_arg_set *arg_set, + unsigned int *value, char **error, unsigned int grouped) { const char *arg_str = dm_shift_arg(arg_set); char dummy; @@ -755,14 +754,14 @@ static int validate_next_arg(const struct dm_arg *arg, } int dm_read_arg(const struct dm_arg *arg, struct dm_arg_set *arg_set, - unsigned *value, char **error) + unsigned int *value, char **error) { return validate_next_arg(arg, arg_set, value, error, 0); } EXPORT_SYMBOL(dm_read_arg); int dm_read_arg_group(const struct dm_arg *arg, struct dm_arg_set *arg_set, - unsigned *value, char **error) + unsigned int *value, char **error) { return validate_next_arg(arg, arg_set, value, error, 1); } @@ -783,7 +782,7 @@ const char *dm_shift_arg(struct dm_arg_set *as) } EXPORT_SYMBOL(dm_shift_arg); -void dm_consume_args(struct dm_arg_set *as, unsigned num_args) +void dm_consume_args(struct dm_arg_set *as, unsigned int num_args) { BUG_ON(as->argc < num_args); as->argc -= num_args; @@ -859,7 +858,7 @@ static int device_is_rq_stackable(struct dm_target *ti, struct dm_dev *dev, static int dm_table_determine_type(struct dm_table *t) { - unsigned bio_based = 0, request_based = 0, hybrid = 0; + unsigned int bio_based = 0, request_based = 0, hybrid = 0; struct dm_target *ti; struct list_head *devices = dm_table_get_devices(t); enum dm_queue_mode live_md_type = dm_get_md_type(t->md); @@ -1538,7 +1537,7 @@ static bool dm_table_any_dev_attr(struct dm_table *t, static int count_device(struct dm_target *ti, struct dm_dev *dev, sector_t start, sector_t len, void *data) { - unsigned *num_devices = data; + unsigned int *num_devices = data; (*num_devices)++; @@ -1568,7 +1567,7 @@ bool dm_table_has_no_data_devices(struct dm_table *t) { for (unsigned int i = 0; i < t->num_targets; i++) { struct dm_target *ti = dm_table_get_target(t, i); - unsigned num_devices = 0; + unsigned int num_devices = 0; if (!ti->type->iterate_devices) return false; diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c index 96068985072f..f5f088aafa74 100644 --- a/drivers/md/dm-thin-metadata.c +++ b/drivers/md/dm-thin-metadata.c @@ -319,12 +319,12 @@ static void unpack_block_time(uint64_t v, dm_block_t *b, uint32_t *t) */ typedef int (*run_fn)(struct dm_space_map *, dm_block_t, dm_block_t); -static void with_runs(struct dm_space_map *sm, const __le64 *value_le, unsigned count, run_fn fn) +static void with_runs(struct dm_space_map *sm, const __le64 *value_le, unsigned int count, run_fn fn) { uint64_t b, begin, end; uint32_t t; bool in_run = false; - unsigned i; + unsigned int i; for (i = 0; i < count; i++, value_le++) { /* We know value_le is 8 byte aligned */ @@ -349,13 +349,13 @@ static void with_runs(struct dm_space_map *sm, const __le64 *value_le, unsigned fn(sm, begin, end); } -static void data_block_inc(void *context, const void *value_le, unsigned count) +static void data_block_inc(void *context, const void *value_le, unsigned int count) { with_runs((struct dm_space_map *) context, (const __le64 *) value_le, count, dm_sm_inc_blocks); } -static void data_block_dec(void *context, const void *value_le, unsigned count) +static void data_block_dec(void *context, const void *value_le, unsigned int count) { with_runs((struct dm_space_map *) context, (const __le64 *) value_le, count, dm_sm_dec_blocks); @@ -375,21 +375,21 @@ static int data_block_equal(void *context, const void *value1_le, const void *va return b1 == b2; } -static void subtree_inc(void *context, const void *value, unsigned count) +static void subtree_inc(void *context, const void *value, unsigned int count) { struct dm_btree_info *info = context; const __le64 *root_le = value; - unsigned i; + unsigned int i; for (i = 0; i < count; i++, root_le++) dm_tm_inc(info->tm, le64_to_cpu(*root_le)); } -static void subtree_dec(void *context, const void *value, unsigned count) +static void subtree_dec(void *context, const void *value, unsigned int count) { struct dm_btree_info *info = context; const __le64 *root_le = value; - unsigned i; + unsigned int i; for (i = 0; i < count; i++, root_le++) if (dm_btree_del(info, le64_to_cpu(*root_le))) @@ -449,10 +449,10 @@ static int superblock_lock(struct dm_pool_metadata *pmd, static int __superblock_all_zeroes(struct dm_block_manager *bm, int *result) { int r; - unsigned i; + unsigned int i; struct dm_block *b; __le64 *data_le, zero = cpu_to_le64(0); - unsigned block_size = dm_bm_block_size(bm) / sizeof(__le64); + unsigned int block_size = dm_bm_block_size(bm) / sizeof(__le64); /* * We can't use a validator here - it may be all zeroes. @@ -972,7 +972,7 @@ struct dm_pool_metadata *dm_pool_metadata_open(struct block_device *bdev, int dm_pool_metadata_close(struct dm_pool_metadata *pmd) { int r; - unsigned open_devices = 0; + unsigned int open_devices = 0; struct dm_thin_device *td, *tmp; down_read(&pmd->root_lock); @@ -1680,7 +1680,7 @@ int dm_thin_insert_block(struct dm_thin_device *td, dm_block_t block, static int __remove_range(struct dm_thin_device *td, dm_block_t begin, dm_block_t end) { int r; - unsigned count, total_count = 0; + unsigned int count, total_count = 0; struct dm_pool_metadata *pmd = td->pmd; dm_block_t keys[1] = { td->id }; __le64 value; diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index cc32f18a4796..c015b943f2e3 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -33,7 +33,7 @@ #define COMMIT_PERIOD HZ #define NO_SPACE_TIMEOUT_SECS 60 -static unsigned no_space_timeout_secs = NO_SPACE_TIMEOUT_SECS; +static unsigned int no_space_timeout_secs = NO_SPACE_TIMEOUT_SECS; DECLARE_DM_KCOPYD_THROTTLE_WITH_MODULE_PARM(snapshot_copy_throttle, "A percentage of time allocated for copy on write"); @@ -255,7 +255,7 @@ struct pool { struct delayed_work no_space_timeout; unsigned long last_commit_jiffies; - unsigned ref_count; + unsigned int ref_count; spinlock_t lock; struct bio_list deferred_flush_bios; @@ -2160,7 +2160,7 @@ static void process_thin_deferred_bios(struct thin_c *tc) struct bio *bio; struct bio_list bios; struct blk_plug plug; - unsigned count = 0; + unsigned int count = 0; if (tc->requeue_mode) { error_thin_bio_list(tc, &tc->deferred_bio_list, @@ -2229,9 +2229,9 @@ static int cmp_cells(const void *lhs, const void *rhs) return 0; } -static unsigned sort_cells(struct pool *pool, struct list_head *cells) +static unsigned int sort_cells(struct pool *pool, struct list_head *cells) { - unsigned count = 0; + unsigned int count = 0; struct dm_bio_prison_cell *cell, *tmp; list_for_each_entry_safe(cell, tmp, cells, user_list) { @@ -2252,7 +2252,7 @@ static void process_thin_deferred_cells(struct thin_c *tc) struct pool *pool = tc->pool; struct list_head cells; struct dm_bio_prison_cell *cell; - unsigned i, j, count; + unsigned int i, j, count; INIT_LIST_HEAD(&cells); @@ -3114,7 +3114,7 @@ static int parse_pool_features(struct dm_arg_set *as, struct pool_features *pf, struct dm_target *ti) { int r; - unsigned argc; + unsigned int argc; const char *arg_name; static const struct dm_arg _args[] = { @@ -3251,7 +3251,7 @@ static dm_block_t calc_metadata_threshold(struct pool_c *pt) * read_only: Don't allow any changes to be made to the pool metadata. * error_if_no_space: error IOs, instead of queueing, if no space. */ -static int pool_ctr(struct dm_target *ti, unsigned argc, char **argv) +static int pool_ctr(struct dm_target *ti, unsigned int argc, char **argv) { int r, pool_created = 0; struct pool_c *pt; @@ -3646,7 +3646,7 @@ static void pool_postsuspend(struct dm_target *ti) (void) commit(pool); } -static int check_arg_count(unsigned argc, unsigned args_required) +static int check_arg_count(unsigned int argc, unsigned int args_required) { if (argc != args_required) { DMWARN("Message received with %u arguments instead of %u.", @@ -3669,7 +3669,7 @@ static int read_dev_id(char *arg, dm_thin_id *dev_id, int warning) return -EINVAL; } -static int process_create_thin_mesg(unsigned argc, char **argv, struct pool *pool) +static int process_create_thin_mesg(unsigned int argc, char **argv, struct pool *pool) { dm_thin_id dev_id; int r; @@ -3692,7 +3692,7 @@ static int process_create_thin_mesg(unsigned argc, char **argv, struct pool *poo return 0; } -static int process_create_snap_mesg(unsigned argc, char **argv, struct pool *pool) +static int process_create_snap_mesg(unsigned int argc, char **argv, struct pool *pool) { dm_thin_id dev_id; dm_thin_id origin_dev_id; @@ -3720,7 +3720,7 @@ static int process_create_snap_mesg(unsigned argc, char **argv, struct pool *poo return 0; } -static int process_delete_mesg(unsigned argc, char **argv, struct pool *pool) +static int process_delete_mesg(unsigned int argc, char **argv, struct pool *pool) { dm_thin_id dev_id; int r; @@ -3740,7 +3740,7 @@ static int process_delete_mesg(unsigned argc, char **argv, struct pool *pool) return r; } -static int process_set_transaction_id_mesg(unsigned argc, char **argv, struct pool *pool) +static int process_set_transaction_id_mesg(unsigned int argc, char **argv, struct pool *pool) { dm_thin_id old_id, new_id; int r; @@ -3769,7 +3769,7 @@ static int process_set_transaction_id_mesg(unsigned argc, char **argv, struct po return 0; } -static int process_reserve_metadata_snap_mesg(unsigned argc, char **argv, struct pool *pool) +static int process_reserve_metadata_snap_mesg(unsigned int argc, char **argv, struct pool *pool) { int r; @@ -3786,7 +3786,7 @@ static int process_reserve_metadata_snap_mesg(unsigned argc, char **argv, struct return r; } -static int process_release_metadata_snap_mesg(unsigned argc, char **argv, struct pool *pool) +static int process_release_metadata_snap_mesg(unsigned int argc, char **argv, struct pool *pool) { int r; @@ -3810,8 +3810,8 @@ static int process_release_metadata_snap_mesg(unsigned argc, char **argv, struct * reserve_metadata_snap * release_metadata_snap */ -static int pool_message(struct dm_target *ti, unsigned argc, char **argv, - char *result, unsigned maxlen) +static int pool_message(struct dm_target *ti, unsigned int argc, char **argv, + char *result, unsigned int maxlen) { int r = -EINVAL; struct pool_c *pt = ti->private; @@ -3851,9 +3851,9 @@ static int pool_message(struct dm_target *ti, unsigned argc, char **argv, } static void emit_flags(struct pool_features *pf, char *result, - unsigned sz, unsigned maxlen) + unsigned int sz, unsigned int maxlen) { - unsigned count = !pf->zero_new_blocks + !pf->discard_enabled + + unsigned int count = !pf->zero_new_blocks + !pf->discard_enabled + !pf->discard_passdown + (pf->mode == PM_READ_ONLY) + pf->error_if_no_space; DMEMIT("%u ", count); @@ -3881,10 +3881,10 @@ static void emit_flags(struct pool_features *pf, char *result, * */ static void pool_status(struct dm_target *ti, status_type_t type, - unsigned status_flags, char *result, unsigned maxlen) + unsigned int status_flags, char *result, unsigned int maxlen) { int r; - unsigned sz = 0; + unsigned int sz = 0; uint64_t transaction_id; dm_block_t nr_free_blocks_data; dm_block_t nr_free_blocks_metadata; @@ -4146,7 +4146,7 @@ static void thin_dtr(struct dm_target *ti) * If the pool device has discards disabled, they get disabled for the thin * device as well. */ -static int thin_ctr(struct dm_target *ti, unsigned argc, char **argv) +static int thin_ctr(struct dm_target *ti, unsigned int argc, char **argv) { int r; struct thin_c *tc; @@ -4368,7 +4368,7 @@ static int thin_preresume(struct dm_target *ti) * */ static void thin_status(struct dm_target *ti, status_type_t type, - unsigned status_flags, char *result, unsigned maxlen) + unsigned int status_flags, char *result, unsigned int maxlen) { int r; ssize_t sz = 0; diff --git a/drivers/md/dm-uevent.c b/drivers/md/dm-uevent.c index 8671267200d8..a02b3f6ea47a 100644 --- a/drivers/md/dm-uevent.c +++ b/drivers/md/dm-uevent.c @@ -60,7 +60,7 @@ static struct dm_uevent *dm_build_path_uevent(struct mapped_device *md, enum kobject_action action, const char *dm_action, const char *path, - unsigned nr_valid_paths) + unsigned int nr_valid_paths) { struct dm_uevent *event; @@ -168,7 +168,7 @@ EXPORT_SYMBOL_GPL(dm_send_uevents); * */ void dm_path_uevent(enum dm_uevent_type event_type, struct dm_target *ti, - const char *path, unsigned nr_valid_paths) + const char *path, unsigned int nr_valid_paths) { struct mapped_device *md = dm_table_get_md(ti->table); struct dm_uevent *event; diff --git a/drivers/md/dm-uevent.h b/drivers/md/dm-uevent.h index d30d226f2a18..2c9ba561fd8e 100644 --- a/drivers/md/dm-uevent.h +++ b/drivers/md/dm-uevent.h @@ -20,7 +20,7 @@ extern void dm_uevent_exit(void); extern void dm_send_uevents(struct list_head *events, struct kobject *kobj); extern void dm_path_uevent(enum dm_uevent_type event_type, struct dm_target *ti, const char *path, - unsigned nr_valid_paths); + unsigned int nr_valid_paths); #else @@ -37,7 +37,7 @@ static inline void dm_send_uevents(struct list_head *events, } static inline void dm_path_uevent(enum dm_uevent_type event_type, struct dm_target *ti, const char *path, - unsigned nr_valid_paths) + unsigned int nr_valid_paths) { } diff --git a/drivers/md/dm-verity-fec.c b/drivers/md/dm-verity-fec.c index 23cffce56403..962fc32c947c 100644 --- a/drivers/md/dm-verity-fec.c +++ b/drivers/md/dm-verity-fec.c @@ -59,14 +59,14 @@ static int fec_decode_rs8(struct dm_verity *v, struct dm_verity_fec_io *fio, * to the data block. Caller is responsible for releasing buf. */ static u8 *fec_read_parity(struct dm_verity *v, u64 rsb, int index, - unsigned *offset, struct dm_buffer **buf) + unsigned int *offset, struct dm_buffer **buf) { u64 position, block, rem; u8 *res; position = (index + rsb) * v->fec->roots; block = div64_u64_rem(position, v->fec->io_size, &rem); - *offset = (unsigned)rem; + *offset = (unsigned int)rem; res = dm_bufio_read(v->fec->bufio, block, buf); if (IS_ERR(res)) { @@ -102,7 +102,7 @@ static u8 *fec_read_parity(struct dm_verity *v, u64 rsb, int index, */ static inline u8 *fec_buffer_rs_block(struct dm_verity *v, struct dm_verity_fec_io *fio, - unsigned i, unsigned j) + unsigned int i, unsigned int j) { return &fio->bufs[i][j * v->fec->rsn]; } @@ -111,7 +111,7 @@ static inline u8 *fec_buffer_rs_block(struct dm_verity *v, * Return an index to the current RS block when called inside * fec_for_each_buffer_rs_block. */ -static inline unsigned fec_buffer_rs_index(unsigned i, unsigned j) +static inline unsigned int fec_buffer_rs_index(unsigned int i, unsigned int j) { return (i << DM_VERITY_FEC_BUF_RS_BITS) + j; } @@ -121,12 +121,12 @@ static inline unsigned fec_buffer_rs_index(unsigned i, unsigned j) * starting from block_offset. */ static int fec_decode_bufs(struct dm_verity *v, struct dm_verity_fec_io *fio, - u64 rsb, int byte_index, unsigned block_offset, + u64 rsb, int byte_index, unsigned int block_offset, int neras) { int r, corrected = 0, res; struct dm_buffer *buf; - unsigned n, i, offset; + unsigned int n, i, offset; u8 *par, *block; par = fec_read_parity(v, rsb, block_offset, &offset, &buf); @@ -197,7 +197,7 @@ static int fec_is_erasure(struct dm_verity *v, struct dm_verity_io *io, * fits into buffers. Check for erasure locations if @neras is non-NULL. */ static int fec_read_bufs(struct dm_verity *v, struct dm_verity_io *io, - u64 rsb, u64 target, unsigned block_offset, + u64 rsb, u64 target, unsigned int block_offset, int *neras) { bool is_zero; @@ -208,7 +208,7 @@ static int fec_read_bufs(struct dm_verity *v, struct dm_verity_io *io, u64 block, ileaved; u8 *bbuf, *rs_block; u8 want_digest[HASH_MAX_DIGESTSIZE]; - unsigned n, k; + unsigned int n, k; if (neras) *neras = 0; @@ -304,7 +304,7 @@ done: */ static int fec_alloc_bufs(struct dm_verity *v, struct dm_verity_fec_io *fio) { - unsigned n; + unsigned int n; if (!fio->rs) fio->rs = mempool_alloc(&v->fec->rs_pool, GFP_NOIO); @@ -344,7 +344,7 @@ static int fec_alloc_bufs(struct dm_verity *v, struct dm_verity_fec_io *fio) */ static void fec_init_bufs(struct dm_verity *v, struct dm_verity_fec_io *fio) { - unsigned n; + unsigned int n; fec_for_each_buffer(fio, n) memset(fio->bufs[n], 0, v->fec->rsn << DM_VERITY_FEC_BUF_RS_BITS); @@ -362,7 +362,7 @@ static int fec_decode_rsb(struct dm_verity *v, struct dm_verity_io *io, bool use_erasures) { int r, neras = 0; - unsigned pos; + unsigned int pos; r = fec_alloc_bufs(v, fio); if (unlikely(r < 0)) @@ -484,7 +484,7 @@ done: */ void verity_fec_finish_io(struct dm_verity_io *io) { - unsigned n; + unsigned int n; struct dm_verity_fec *f = io->v->fec; struct dm_verity_fec_io *fio = fec_io(io); @@ -522,8 +522,8 @@ void verity_fec_init_io(struct dm_verity_io *io) /* * Append feature arguments and values to the status table. */ -unsigned verity_fec_status_table(struct dm_verity *v, unsigned sz, - char *result, unsigned maxlen) +unsigned int verity_fec_status_table(struct dm_verity *v, unsigned int sz, + char *result, unsigned int maxlen) { if (!verity_fec_is_enabled(v)) return sz; @@ -589,7 +589,7 @@ bool verity_is_fec_opt_arg(const char *arg_name) } int verity_fec_parse_opt_args(struct dm_arg_set *as, struct dm_verity *v, - unsigned *argc, const char *arg_name) + unsigned int *argc, const char *arg_name) { int r; struct dm_target *ti = v->ti; diff --git a/drivers/md/dm-verity-fec.h b/drivers/md/dm-verity-fec.h index 3c46c8d61883..8454070d2824 100644 --- a/drivers/md/dm-verity-fec.h +++ b/drivers/md/dm-verity-fec.h @@ -55,10 +55,10 @@ struct dm_verity_fec_io { struct rs_control *rs; /* Reed-Solomon state */ int erasures[DM_VERITY_FEC_MAX_RSN]; /* erasures for decode_rs8 */ u8 *bufs[DM_VERITY_FEC_BUF_MAX]; /* bufs for deinterleaving */ - unsigned nbufs; /* number of buffers allocated */ + unsigned int nbufs; /* number of buffers allocated */ u8 *output; /* buffer for corrected output */ size_t output_pos; - unsigned level; /* recursion level */ + unsigned int level; /* recursion level */ }; #ifdef CONFIG_DM_VERITY_FEC @@ -72,15 +72,15 @@ extern int verity_fec_decode(struct dm_verity *v, struct dm_verity_io *io, enum verity_block_type type, sector_t block, u8 *dest, struct bvec_iter *iter); -extern unsigned verity_fec_status_table(struct dm_verity *v, unsigned sz, - char *result, unsigned maxlen); +extern unsigned int verity_fec_status_table(struct dm_verity *v, unsigned int sz, + char *result, unsigned int maxlen); extern void verity_fec_finish_io(struct dm_verity_io *io); extern void verity_fec_init_io(struct dm_verity_io *io); extern bool verity_is_fec_opt_arg(const char *arg_name); extern int verity_fec_parse_opt_args(struct dm_arg_set *as, - struct dm_verity *v, unsigned *argc, + struct dm_verity *v, unsigned int *argc, const char *arg_name); extern void verity_fec_dtr(struct dm_verity *v); @@ -106,9 +106,9 @@ static inline int verity_fec_decode(struct dm_verity *v, return -EOPNOTSUPP; } -static inline unsigned verity_fec_status_table(struct dm_verity *v, - unsigned sz, char *result, - unsigned maxlen) +static inline unsigned int verity_fec_status_table(struct dm_verity *v, + unsigned int sz, char *result, + unsigned int maxlen) { return sz; } @@ -128,7 +128,7 @@ static inline bool verity_is_fec_opt_arg(const char *arg_name) static inline int verity_fec_parse_opt_args(struct dm_arg_set *as, struct dm_verity *v, - unsigned *argc, + unsigned int *argc, const char *arg_name) { return -EINVAL; diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c index 4c52b056ecf0..c9d937053910 100644 --- a/drivers/md/dm-verity-target.c +++ b/drivers/md/dm-verity-target.c @@ -41,7 +41,7 @@ #define DM_VERITY_OPTS_MAX (4 + DM_VERITY_OPTS_FEC + \ DM_VERITY_ROOT_HASH_VERIFICATION_OPTS) -static unsigned dm_verity_prefetch_cluster = DM_VERITY_DEFAULT_PREFETCH_SIZE; +static unsigned int dm_verity_prefetch_cluster = DM_VERITY_DEFAULT_PREFETCH_SIZE; module_param_named(prefetch_cluster, dm_verity_prefetch_cluster, uint, S_IRUGO | S_IWUSR); @@ -51,7 +51,7 @@ struct dm_verity_prefetch_work { struct work_struct work; struct dm_verity *v; sector_t block; - unsigned n_blocks; + unsigned int n_blocks; }; /* @@ -196,10 +196,10 @@ out: } static void verity_hash_at_level(struct dm_verity *v, sector_t block, int level, - sector_t *hash_block, unsigned *offset) + sector_t *hash_block, unsigned int *offset) { sector_t position = verity_position_at_level(v, block, level); - unsigned idx; + unsigned int idx; *hash_block = v->hash_level_block[level] + (position >> v->hash_per_block_bits); @@ -287,7 +287,7 @@ static int verity_verify_level(struct dm_verity *v, struct dm_verity_io *io, u8 *data; int r; sector_t hash_block; - unsigned offset; + unsigned int offset; verity_hash_at_level(v, block, level, &hash_block, &offset); @@ -445,13 +445,13 @@ int verity_for_bv_block(struct dm_verity *v, struct dm_verity_io *io, struct dm_verity_io *io, u8 *data, size_t len)) { - unsigned todo = 1 << v->data_dev_block_bits; + unsigned int todo = 1 << v->data_dev_block_bits; struct bio *bio = dm_bio_from_per_bio_data(io, v->ti->per_io_data_size); do { int r; u8 *page; - unsigned len; + unsigned int len; struct bio_vec bv = bio_iter_iovec(bio, *iter); page = bvec_kmap_local(&bv); @@ -688,7 +688,7 @@ static void verity_prefetch_io(struct work_struct *work) verity_hash_at_level(v, pw->block, i, &hash_block_start, NULL); verity_hash_at_level(v, pw->block + pw->n_blocks - 1, i, &hash_block_end, NULL); if (!i) { - unsigned cluster = READ_ONCE(dm_verity_prefetch_cluster); + unsigned int cluster = READ_ONCE(dm_verity_prefetch_cluster); cluster >>= v->data_dev_block_bits; if (unlikely(!cluster)) @@ -753,7 +753,7 @@ static int verity_map(struct dm_target *ti, struct bio *bio) bio_set_dev(bio, v->data_dev->bdev); bio->bi_iter.bi_sector = verity_map_sector(v, bio->bi_iter.bi_sector); - if (((unsigned)bio->bi_iter.bi_sector | bio_sectors(bio)) & + if (((unsigned int)bio->bi_iter.bi_sector | bio_sectors(bio)) & ((1 << (v->data_dev_block_bits - SECTOR_SHIFT)) - 1)) { DMERR_LIMIT("unaligned io"); return DM_MAPIO_KILL; @@ -789,12 +789,12 @@ static int verity_map(struct dm_target *ti, struct bio *bio) * Status: V (valid) or C (corruption found) */ static void verity_status(struct dm_target *ti, status_type_t type, - unsigned status_flags, char *result, unsigned maxlen) + unsigned int status_flags, char *result, unsigned int maxlen) { struct dm_verity *v = ti->private; - unsigned args = 0; - unsigned sz = 0; - unsigned x; + unsigned int args = 0; + unsigned int sz = 0; + unsigned int x; switch (type) { case STATUSTYPE_INFO: @@ -1054,7 +1054,7 @@ static int verity_parse_opt_args(struct dm_arg_set *as, struct dm_verity *v, bool only_modifier_opts) { int r = 0; - unsigned argc; + unsigned int argc; struct dm_target *ti = v->ti; const char *arg_name; @@ -1156,7 +1156,7 @@ static int verity_parse_opt_args(struct dm_arg_set *as, struct dm_verity *v, * * Hex string or "-" if no salt. */ -static int verity_ctr(struct dm_target *ti, unsigned argc, char **argv) +static int verity_ctr(struct dm_target *ti, unsigned int argc, char **argv) { struct dm_verity *v; struct dm_verity_sig_opts verify_args = {0}; diff --git a/drivers/md/dm-verity.h b/drivers/md/dm-verity.h index 98f306ec6a33..2f555b420367 100644 --- a/drivers/md/dm-verity.h +++ b/drivers/md/dm-verity.h @@ -42,7 +42,7 @@ struct dm_verity { u8 *root_digest; /* digest of the root block */ u8 *salt; /* salt: its size is salt_size */ u8 *zero_digest; /* digest for a zero block */ - unsigned salt_size; + unsigned int salt_size; sector_t data_start; /* data offset in 512-byte sectors */ sector_t hash_start; /* hash start in blocks */ sector_t data_blocks; /* the number of data blocks */ @@ -54,10 +54,10 @@ struct dm_verity { unsigned char version; bool hash_failed:1; /* set if hash of any block failed */ bool use_tasklet:1; /* try to verify in tasklet before work-queue */ - unsigned digest_size; /* digest size for the current hash algorithm */ + unsigned int digest_size; /* digest size for the current hash algorithm */ unsigned int ahash_reqsize;/* the size of temporary space for crypto */ enum verity_mode mode; /* mode for handling verification errors */ - unsigned corrupted_errs;/* Number of errors for corrupted blocks */ + unsigned int corrupted_errs;/* Number of errors for corrupted blocks */ struct workqueue_struct *verify_wq; @@ -77,7 +77,7 @@ struct dm_verity_io { bio_end_io_t *orig_bi_end_io; sector_t block; - unsigned n_blocks; + unsigned int n_blocks; bool in_tasklet; struct bvec_iter iter; diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c index b1a2cb1d57ea..17e064cde712 100644 --- a/drivers/md/dm-writecache.c +++ b/drivers/md/dm-writecache.c @@ -128,9 +128,9 @@ struct dm_writecache { unsigned long max_age; unsigned long pause; - unsigned uncommitted_blocks; - unsigned autocommit_blocks; - unsigned max_writeback_jobs; + unsigned int uncommitted_blocks; + unsigned int autocommit_blocks; + unsigned int max_writeback_jobs; int error; @@ -155,7 +155,7 @@ struct dm_writecache { sector_t data_device_sectors; void *block_start; struct wc_entry *entries; - unsigned block_size; + unsigned int block_size; unsigned char block_size_bits; bool pmem_mode:1; @@ -178,13 +178,13 @@ struct dm_writecache { bool metadata_only:1; bool pause_set:1; - unsigned high_wm_percent_value; - unsigned low_wm_percent_value; - unsigned autocommit_time_value; - unsigned max_age_value; - unsigned pause_value; + unsigned int high_wm_percent_value; + unsigned int low_wm_percent_value; + unsigned int autocommit_time_value; + unsigned int max_age_value; + unsigned int pause_value; - unsigned writeback_all; + unsigned int writeback_all; struct workqueue_struct *writeback_wq; struct work_struct writeback_work; struct work_struct flush_work; @@ -202,7 +202,7 @@ struct dm_writecache { struct dm_kcopyd_client *dm_kcopyd; unsigned long *dirty_bitmap; - unsigned dirty_bitmap_size; + unsigned int dirty_bitmap_size; struct bio_set bio_set; mempool_t copy_pool; @@ -227,7 +227,7 @@ struct writeback_struct { struct list_head endio_entry; struct dm_writecache *wc; struct wc_entry **wc_list; - unsigned wc_list_n; + unsigned int wc_list_n; struct wc_entry *wc_list_inline[WB_LIST_INLINE]; struct bio bio; }; @@ -236,7 +236,7 @@ struct copy_struct { struct list_head endio_entry; struct dm_writecache *wc; struct wc_entry *e; - unsigned n_entries; + unsigned int n_entries; int error; }; @@ -369,7 +369,7 @@ static struct page *persistent_memory_page(void *addr) return virt_to_page(addr); } -static unsigned persistent_memory_page_offset(void *addr) +static unsigned int persistent_memory_page_offset(void *addr) { return (unsigned long)addr & (PAGE_SIZE - 1); } @@ -502,11 +502,11 @@ static void ssd_commit_flushed(struct dm_writecache *wc, bool wait_for_ios) COMPLETION_INITIALIZER_ONSTACK(endio.c), ATOMIC_INIT(1), }; - unsigned bitmap_bits = wc->dirty_bitmap_size * 8; - unsigned i = 0; + unsigned int bitmap_bits = wc->dirty_bitmap_size * 8; + unsigned int i = 0; while (1) { - unsigned j; + unsigned int j; i = find_next_bit(wc->dirty_bitmap, bitmap_bits, i); if (unlikely(i == bitmap_bits)) break; @@ -1100,7 +1100,7 @@ erase_this: wc_unlock(wc); } -static int process_flush_mesg(unsigned argc, char **argv, struct dm_writecache *wc) +static int process_flush_mesg(unsigned int argc, char **argv, struct dm_writecache *wc) { if (argc != 1) return -EINVAL; @@ -1133,7 +1133,7 @@ static int process_flush_mesg(unsigned argc, char **argv, struct dm_writecache * return 0; } -static int process_flush_on_suspend_mesg(unsigned argc, char **argv, struct dm_writecache *wc) +static int process_flush_on_suspend_mesg(unsigned int argc, char **argv, struct dm_writecache *wc) { if (argc != 1) return -EINVAL; @@ -1153,7 +1153,7 @@ static void activate_cleaner(struct dm_writecache *wc) wc->freelist_low_watermark = wc->n_blocks; } -static int process_cleaner_mesg(unsigned argc, char **argv, struct dm_writecache *wc) +static int process_cleaner_mesg(unsigned int argc, char **argv, struct dm_writecache *wc) { if (argc != 1) return -EINVAL; @@ -1167,7 +1167,7 @@ static int process_cleaner_mesg(unsigned argc, char **argv, struct dm_writecache return 0; } -static int process_clear_stats_mesg(unsigned argc, char **argv, struct dm_writecache *wc) +static int process_clear_stats_mesg(unsigned int argc, char **argv, struct dm_writecache *wc) { if (argc != 1) return -EINVAL; @@ -1179,8 +1179,8 @@ static int process_clear_stats_mesg(unsigned argc, char **argv, struct dm_writec return 0; } -static int writecache_message(struct dm_target *ti, unsigned argc, char **argv, - char *result, unsigned maxlen) +static int writecache_message(struct dm_target *ti, unsigned int argc, char **argv, + char *result, unsigned int maxlen) { int r = -EINVAL; struct dm_writecache *wc = ti->private; @@ -1238,9 +1238,9 @@ static void memcpy_flushcache_optimized(void *dest, void *source, size_t size) static void bio_copy_block(struct dm_writecache *wc, struct bio *bio, void *data) { void *buf; - unsigned size; + unsigned int size; int rw = bio_data_dir(bio); - unsigned remaining_size = wc->block_size; + unsigned int remaining_size = wc->block_size; do { struct bio_vec bv = bio_iter_iovec(bio, bio->bi_iter); @@ -1371,7 +1371,7 @@ read_next_block: static void writecache_bio_copy_ssd(struct dm_writecache *wc, struct bio *bio, struct wc_entry *e, bool search_used) { - unsigned bio_size = wc->block_size; + unsigned int bio_size = wc->block_size; sector_t start_cache_sec = cache_sector(wc, e); sector_t current_cache_sec = start_cache_sec + (bio_size >> SECTOR_SHIFT); @@ -1540,7 +1540,7 @@ static int writecache_map(struct dm_target *ti, struct bio *bio) bio->bi_iter.bi_sector = dm_target_offset(ti, bio->bi_iter.bi_sector); - if (unlikely((((unsigned)bio->bi_iter.bi_sector | bio_sectors(bio)) & + if (unlikely((((unsigned int)bio->bi_iter.bi_sector | bio_sectors(bio)) & (wc->block_size / 512 - 1)) != 0)) { DMERR("I/O is not aligned, sector %llu, size %u, block size %u", (unsigned long long)bio->bi_iter.bi_sector, @@ -1666,7 +1666,7 @@ static void writecache_copy_endio(int read_err, unsigned long write_err, void *p static void __writecache_endio_pmem(struct dm_writecache *wc, struct list_head *list) { - unsigned i; + unsigned int i; struct writeback_struct *wb; struct wc_entry *e; unsigned long n_walked = 0; @@ -1782,7 +1782,7 @@ pop_from_list: static bool wc_add_block(struct writeback_struct *wb, struct wc_entry *e) { struct dm_writecache *wc = wb->wc; - unsigned block_size = wc->block_size; + unsigned int block_size = wc->block_size; void *address = memory_data(wc, e); persistent_memory_flush_cache(address, block_size); @@ -1817,7 +1817,7 @@ static void __writecache_writeback_pmem(struct dm_writecache *wc, struct writeba struct wc_entry *e, *f; struct bio *bio; struct writeback_struct *wb; - unsigned max_pages; + unsigned int max_pages; while (wbl->size) { wbl->size--; @@ -1880,7 +1880,7 @@ static void __writecache_writeback_ssd(struct dm_writecache *wc, struct writebac struct copy_struct *c; while (wbl->size) { - unsigned n_sectors; + unsigned int n_sectors; wbl->size--; e = container_of(wbl->list.prev, struct wc_entry, lru); @@ -2092,7 +2092,7 @@ restart: } } -static int calculate_memory_size(uint64_t device_size, unsigned block_size, +static int calculate_memory_size(uint64_t device_size, unsigned int block_size, size_t *n_blocks_p, size_t *n_metadata_blocks_p) { uint64_t n_blocks, offset; @@ -2207,12 +2207,12 @@ static void writecache_dtr(struct dm_target *ti) kfree(wc); } -static int writecache_ctr(struct dm_target *ti, unsigned argc, char **argv) +static int writecache_ctr(struct dm_target *ti, unsigned int argc, char **argv) { struct dm_writecache *wc; struct dm_arg_set as; const char *string; - unsigned opt_params; + unsigned int opt_params; size_t offset, data_size; int i, r; char dummy; @@ -2419,7 +2419,7 @@ static int writecache_ctr(struct dm_target *ti, unsigned argc, char **argv) goto invalid_optional; wc->autocommit_blocks_set = true; } else if (!strcasecmp(string, "autocommit_time") && opt_params >= 1) { - unsigned autocommit_msecs; + unsigned int autocommit_msecs; string = dm_shift_arg(&as), opt_params--; if (sscanf(string, "%u%c", &autocommit_msecs, &dummy) != 1) goto invalid_optional; @@ -2429,7 +2429,7 @@ static int writecache_ctr(struct dm_target *ti, unsigned argc, char **argv) wc->autocommit_time_value = autocommit_msecs; wc->autocommit_time_set = true; } else if (!strcasecmp(string, "max_age") && opt_params >= 1) { - unsigned max_age_msecs; + unsigned int max_age_msecs; string = dm_shift_arg(&as), opt_params--; if (sscanf(string, "%u%c", &max_age_msecs, &dummy) != 1) goto invalid_optional; @@ -2454,7 +2454,7 @@ static int writecache_ctr(struct dm_target *ti, unsigned argc, char **argv) } else if (!strcasecmp(string, "metadata_only")) { wc->metadata_only = true; } else if (!strcasecmp(string, "pause_writeback") && opt_params >= 1) { - unsigned pause_msecs; + unsigned int pause_msecs; if (WC_MODE_PMEM(wc)) goto invalid_optional; string = dm_shift_arg(&as), opt_params--; @@ -2653,11 +2653,11 @@ bad: } static void writecache_status(struct dm_target *ti, status_type_t type, - unsigned status_flags, char *result, unsigned maxlen) + unsigned int status_flags, char *result, unsigned int maxlen) { struct dm_writecache *wc = ti->private; - unsigned extra_args; - unsigned sz = 0; + unsigned int extra_args; + unsigned int sz = 0; switch (type) { case STATUSTYPE_INFO: diff --git a/drivers/md/dm.c b/drivers/md/dm.c index c97004b56ff0..b8db3214c810 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -84,7 +84,7 @@ struct clone_info { struct bio *bio; struct dm_io *io; sector_t sector; - unsigned sector_count; + unsigned int sector_count; bool is_abnormal_io:1; bool submit_as_polled:1; }; @@ -112,7 +112,7 @@ struct bio *dm_bio_from_per_bio_data(void *data, size_t data_size) } EXPORT_SYMBOL_GPL(dm_bio_from_per_bio_data); -unsigned dm_bio_get_target_bio_nr(const struct bio *bio) +unsigned int dm_bio_get_target_bio_nr(const struct bio *bio) { return container_of(bio, struct dm_target_io, clone)->target_bio_nr; } @@ -143,7 +143,7 @@ struct table_device { * Bio-based DM's mempools' reserved IOs set by the user. */ #define RESERVED_BIO_BASED_IOS 16 -static unsigned reserved_bio_based_ios = RESERVED_BIO_BASED_IOS; +static unsigned int reserved_bio_based_ios = RESERVED_BIO_BASED_IOS; static int __dm_get_module_param_int(int *module_param, int min, int max) { @@ -166,11 +166,10 @@ static int __dm_get_module_param_int(int *module_param, int min, int max) return param; } -unsigned __dm_get_module_param(unsigned *module_param, - unsigned def, unsigned max) +unsigned int __dm_get_module_param(unsigned int *module_param, unsigned int def, unsigned int max) { - unsigned param = READ_ONCE(*module_param); - unsigned modified_param = 0; + unsigned int param = READ_ONCE(*module_param); + unsigned int modified_param = 0; if (!param) modified_param = def; @@ -185,14 +184,14 @@ unsigned __dm_get_module_param(unsigned *module_param, return param; } -unsigned dm_get_reserved_bio_based_ios(void) +unsigned int dm_get_reserved_bio_based_ios(void) { return __dm_get_module_param(&reserved_bio_based_ios, RESERVED_BIO_BASED_IOS, DM_RESERVED_MAX_IOS); } EXPORT_SYMBOL_GPL(dm_get_reserved_bio_based_ios); -static unsigned dm_get_numa_node(void) +static unsigned int dm_get_numa_node(void) { return __dm_get_module_param_int(&dm_numa_node, DM_NUMA_NODE, num_online_nodes() - 1); @@ -605,7 +604,7 @@ static void free_io(struct dm_io *io) } static struct bio *alloc_tio(struct clone_info *ci, struct dm_target *ti, - unsigned target_bio_nr, unsigned *len, gfp_t gfp_mask) + unsigned int target_bio_nr, unsigned int *len, gfp_t gfp_mask) { struct mapped_device *md = ci->io->md; struct dm_target_io *tio; @@ -1315,11 +1314,11 @@ out: * the partially processed part (the sum of regions 1+2) must be the same for all * copies of the bio. */ -void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors) +void dm_accept_partial_bio(struct bio *bio, unsigned int n_sectors) { struct dm_target_io *tio = clone_to_tio(bio); struct dm_io *io = tio->io; - unsigned bio_sectors = bio_sectors(bio); + unsigned int bio_sectors = bio_sectors(bio); BUG_ON(dm_tio_flagged(tio, DM_TIO_IS_DUPLICATE_BIO)); BUG_ON(op_is_zone_mgmt(bio_op(bio))); @@ -1448,7 +1447,7 @@ static void __map_bio(struct bio *clone) } } -static void setup_split_accounting(struct clone_info *ci, unsigned len) +static void setup_split_accounting(struct clone_info *ci, unsigned int len) { struct dm_io *io = ci->io; @@ -1464,7 +1463,7 @@ static void setup_split_accounting(struct clone_info *ci, unsigned len) } static void alloc_multiple_bios(struct bio_list *blist, struct clone_info *ci, - struct dm_target *ti, unsigned num_bios) + struct dm_target *ti, unsigned int num_bios) { struct bio *bio; int try; @@ -1493,7 +1492,7 @@ static void alloc_multiple_bios(struct bio_list *blist, struct clone_info *ci, } static int __send_duplicate_bios(struct clone_info *ci, struct dm_target *ti, - unsigned int num_bios, unsigned *len) + unsigned int num_bios, unsigned int *len) { struct bio_list blist = BIO_EMPTY_LIST; struct bio *clone; @@ -1559,10 +1558,9 @@ static void __send_empty_flush(struct clone_info *ci) } static void __send_changing_extent_only(struct clone_info *ci, struct dm_target *ti, - unsigned num_bios) + unsigned int num_bios) { - unsigned len; - unsigned int bios; + unsigned int len, bios; len = min_t(sector_t, ci->sector_count, max_io_len_target_boundary(ti, dm_target_offset(ti, ci->sector))); @@ -1600,7 +1598,7 @@ static bool is_abnormal_io(struct bio *bio) static blk_status_t __process_abnormal_io(struct clone_info *ci, struct dm_target *ti) { - unsigned num_bios = 0; + unsigned int num_bios = 0; switch (bio_op(ci->bio)) { case REQ_OP_DISCARD: @@ -1678,7 +1676,7 @@ static blk_status_t __split_and_process_bio(struct clone_info *ci) { struct bio *clone; struct dm_target *ti; - unsigned len; + unsigned int len; ti = dm_table_find_target(ci->map, ci->sector); if (unlikely(!ti)) @@ -2373,7 +2371,7 @@ out_undo_holders: struct mapped_device *dm_get_md(dev_t dev) { struct mapped_device *md; - unsigned minor = MINOR(dev); + unsigned int minor = MINOR(dev); if (MAJOR(dev) != _major || minor >= (1 << MINORBITS)) return NULL; @@ -2655,7 +2653,7 @@ static void unlock_fs(struct mapped_device *md) * are being added to md->deferred list. */ static int __dm_suspend(struct mapped_device *md, struct dm_table *map, - unsigned suspend_flags, unsigned int task_state, + unsigned int suspend_flags, unsigned int task_state, int dmf_suspended_flag) { bool do_lockfs = suspend_flags & DM_SUSPEND_LOCKFS_FLAG; @@ -2762,7 +2760,7 @@ static int __dm_suspend(struct mapped_device *md, struct dm_table *map, * * To abort suspend, start the request_queue. */ -int dm_suspend(struct mapped_device *md, unsigned suspend_flags) +int dm_suspend(struct mapped_device *md, unsigned int suspend_flags) { struct dm_table *map = NULL; int r = 0; @@ -2864,7 +2862,7 @@ out: * It may be used only from the kernel. */ -static void __dm_internal_suspend(struct mapped_device *md, unsigned suspend_flags) +static void __dm_internal_suspend(struct mapped_device *md, unsigned int suspend_flags) { struct dm_table *map = NULL; @@ -2966,10 +2964,10 @@ EXPORT_SYMBOL_GPL(dm_internal_resume_fast); * Event notification. *---------------------------------------------------------------*/ int dm_kobject_uevent(struct mapped_device *md, enum kobject_action action, - unsigned cookie, bool need_resize_uevent) + unsigned int cookie, bool need_resize_uevent) { int r; - unsigned noio_flag; + unsigned int noio_flag; char udev_cookie[DM_COOKIE_LENGTH]; char *envp[3] = { NULL, NULL, NULL }; char **envpp = envp; diff --git a/drivers/md/dm.h b/drivers/md/dm.h index a9a3ffcad084..a7917df09caf 100644 --- a/drivers/md/dm.h +++ b/drivers/md/dm.h @@ -203,7 +203,7 @@ int dm_get_table_device(struct mapped_device *md, dev_t dev, fmode_t mode, void dm_put_table_device(struct mapped_device *md, struct dm_dev *d); int dm_kobject_uevent(struct mapped_device *md, enum kobject_action action, - unsigned cookie, bool need_resize_uevent); + unsigned int cookie, bool need_resize_uevent); void dm_internal_suspend(struct mapped_device *md); void dm_internal_resume(struct mapped_device *md); @@ -222,6 +222,6 @@ void dm_free_md_mempools(struct dm_md_mempools *pools); /* * Various helpers */ -unsigned dm_get_reserved_bio_based_ios(void); +unsigned int dm_get_reserved_bio_based_ios(void); #endif diff --git a/drivers/md/persistent-data/dm-array.c b/drivers/md/persistent-data/dm-array.c index 0f77b557231f..f968c17ddbcf 100644 --- a/drivers/md/persistent-data/dm-array.c +++ b/drivers/md/persistent-data/dm-array.c @@ -69,8 +69,8 @@ static int array_block_check(struct dm_block_validator *v, CSUM_XOR)); if (csum_disk != bh_le->csum) { DMERR_LIMIT("array_block_check failed: csum %u != wanted %u", - (unsigned) le32_to_cpu(csum_disk), - (unsigned) le32_to_cpu(bh_le->csum)); + (unsigned int) le32_to_cpu(csum_disk), + (unsigned int) le32_to_cpu(bh_le->csum)); return -EILSEQ; } @@ -95,7 +95,7 @@ static struct dm_block_validator array_validator = { * index - The index into _this_ specific block. */ static void *element_at(struct dm_array_info *info, struct array_block *ab, - unsigned index) + unsigned int index) { unsigned char *entry = (unsigned char *) (ab + 1); @@ -109,9 +109,9 @@ static void *element_at(struct dm_array_info *info, struct array_block *ab, * in an array block. */ static void on_entries(struct dm_array_info *info, struct array_block *ab, - void (*fn)(void *, const void *, unsigned)) + void (*fn)(void *, const void *, unsigned int)) { - unsigned nr_entries = le32_to_cpu(ab->nr_entries); + unsigned int nr_entries = le32_to_cpu(ab->nr_entries); fn(info->value_type.context, element_at(info, ab, 0), nr_entries); } @@ -172,7 +172,7 @@ static int alloc_ablock(struct dm_array_info *info, size_t size_of_block, * the current number of entries. */ static void fill_ablock(struct dm_array_info *info, struct array_block *ab, - const void *value, unsigned new_nr) + const void *value, unsigned int new_nr) { uint32_t nr_entries, delta, i; struct dm_btree_value_type *vt = &info->value_type; @@ -195,7 +195,7 @@ static void fill_ablock(struct dm_array_info *info, struct array_block *ab, * entries. */ static void trim_ablock(struct dm_array_info *info, struct array_block *ab, - unsigned new_nr) + unsigned int new_nr) { uint32_t nr_entries, delta; struct dm_btree_value_type *vt = &info->value_type; @@ -248,7 +248,7 @@ static void unlock_ablock(struct dm_array_info *info, struct dm_block *block) * / max_entries). */ static int lookup_ablock(struct dm_array_info *info, dm_block_t root, - unsigned index, struct dm_block **block, + unsigned int index, struct dm_block **block, struct array_block **ab) { int r; @@ -296,7 +296,7 @@ static int __shadow_ablock(struct dm_array_info *info, dm_block_t b, * The shadow op will often be a noop. Only insert if it really * copied data. */ -static int __reinsert_ablock(struct dm_array_info *info, unsigned index, +static int __reinsert_ablock(struct dm_array_info *info, unsigned int index, struct dm_block *block, dm_block_t b, dm_block_t *root) { @@ -322,7 +322,7 @@ static int __reinsert_ablock(struct dm_array_info *info, unsigned index, * for both the current root block, and the new one. */ static int shadow_ablock(struct dm_array_info *info, dm_block_t *root, - unsigned index, struct dm_block **block, + unsigned int index, struct dm_block **block, struct array_block **ab) { int r; @@ -347,7 +347,7 @@ static int shadow_ablock(struct dm_array_info *info, dm_block_t *root, */ static int insert_new_ablock(struct dm_array_info *info, size_t size_of_block, uint32_t max_entries, - unsigned block_index, uint32_t nr, + unsigned int block_index, uint32_t nr, const void *value, dm_block_t *root) { int r; @@ -366,8 +366,8 @@ static int insert_new_ablock(struct dm_array_info *info, size_t size_of_block, } static int insert_full_ablocks(struct dm_array_info *info, size_t size_of_block, - unsigned begin_block, unsigned end_block, - unsigned max_entries, const void *value, + unsigned int begin_block, unsigned int end_block, + unsigned int max_entries, const void *value, dm_block_t *root) { int r = 0; @@ -403,20 +403,20 @@ struct resize { /* * Maximum nr entries in an array block. */ - unsigned max_entries; + unsigned int max_entries; /* * nr of completely full blocks in the array. * * 'old' refers to before the resize, 'new' after. */ - unsigned old_nr_full_blocks, new_nr_full_blocks; + unsigned int old_nr_full_blocks, new_nr_full_blocks; /* * Number of entries in the final block. 0 iff only full blocks in * the array. */ - unsigned old_nr_entries_in_last_block, new_nr_entries_in_last_block; + unsigned int old_nr_entries_in_last_block, new_nr_entries_in_last_block; /* * The default value used when growing the array. @@ -431,8 +431,8 @@ struct resize { * begin_index - the index of the first array block to remove. * end_index - the one-past-the-end value. ie. this block is not removed. */ -static int drop_blocks(struct resize *resize, unsigned begin_index, - unsigned end_index) +static int drop_blocks(struct resize *resize, unsigned int begin_index, + unsigned int end_index) { int r; @@ -450,8 +450,8 @@ static int drop_blocks(struct resize *resize, unsigned begin_index, /* * Calculates how many blocks are needed for the array. */ -static unsigned total_nr_blocks_needed(unsigned nr_full_blocks, - unsigned nr_entries_in_last_block) +static unsigned int total_nr_blocks_needed(unsigned int nr_full_blocks, + unsigned int nr_entries_in_last_block) { return nr_full_blocks + (nr_entries_in_last_block ? 1 : 0); } @@ -462,7 +462,7 @@ static unsigned total_nr_blocks_needed(unsigned nr_full_blocks, static int shrink(struct resize *resize) { int r; - unsigned begin, end; + unsigned int begin, end; struct dm_block *block; struct array_block *ab; @@ -528,7 +528,7 @@ static int grow_add_tail_block(struct resize *resize) static int grow_needs_more_blocks(struct resize *resize) { int r; - unsigned old_nr_blocks = resize->old_nr_full_blocks; + unsigned int old_nr_blocks = resize->old_nr_full_blocks; if (resize->old_nr_entries_in_last_block > 0) { old_nr_blocks++; @@ -570,11 +570,11 @@ static int grow(struct resize *resize) * These are the value_type functions for the btree elements, which point * to array blocks. */ -static void block_inc(void *context, const void *value, unsigned count) +static void block_inc(void *context, const void *value, unsigned int count) { const __le64 *block_le = value; struct dm_array_info *info = context; - unsigned i; + unsigned int i; for (i = 0; i < count; i++, block_le++) dm_tm_inc(info->btree_info.tm, le64_to_cpu(*block_le)); @@ -619,9 +619,9 @@ static void __block_dec(void *context, const void *value) dm_tm_dec(info->btree_info.tm, b); } -static void block_dec(void *context, const void *value, unsigned count) +static void block_dec(void *context, const void *value, unsigned int count) { - unsigned i; + unsigned int i; for (i = 0; i < count; i++, value += sizeof(__le64)) __block_dec(context, value); } @@ -701,10 +701,11 @@ int dm_array_resize(struct dm_array_info *info, dm_block_t root, EXPORT_SYMBOL_GPL(dm_array_resize); static int populate_ablock_with_values(struct dm_array_info *info, struct array_block *ab, - value_fn fn, void *context, unsigned base, unsigned new_nr) + value_fn fn, void *context, + unsigned int base, unsigned int new_nr) { int r; - unsigned i; + unsigned int i; struct dm_btree_value_type *vt = &info->value_type; BUG_ON(le32_to_cpu(ab->nr_entries)); @@ -729,7 +730,7 @@ int dm_array_new(struct dm_array_info *info, dm_block_t *root, int r; struct dm_block *block; struct array_block *ab; - unsigned block_index, end_block, size_of_block, max_entries; + unsigned int block_index, end_block, size_of_block, max_entries; r = dm_array_empty(info, root); if (r) @@ -777,7 +778,7 @@ int dm_array_get_value(struct dm_array_info *info, dm_block_t root, struct dm_block *block; struct array_block *ab; size_t size_of_block; - unsigned entry, max_entries; + unsigned int entry, max_entries; size_of_block = dm_bm_block_size(dm_tm_get_bm(info->btree_info.tm)); max_entries = calc_max_entries(info->value_type.size, size_of_block); @@ -805,8 +806,8 @@ static int array_set_value(struct dm_array_info *info, dm_block_t root, struct dm_block *block; struct array_block *ab; size_t size_of_block; - unsigned max_entries; - unsigned entry; + unsigned int max_entries; + unsigned int entry; void *old_value; struct dm_btree_value_type *vt = &info->value_type; @@ -862,9 +863,9 @@ static int walk_ablock(void *context, uint64_t *keys, void *leaf) struct walk_info *wi = context; int r; - unsigned i; + unsigned int i; __le64 block_le; - unsigned nr_entries, max_entries; + unsigned int nr_entries, max_entries; struct dm_block *block; struct array_block *ab; diff --git a/drivers/md/persistent-data/dm-array.h b/drivers/md/persistent-data/dm-array.h index 331cc6db3850..91d6165427b3 100644 --- a/drivers/md/persistent-data/dm-array.h +++ b/drivers/md/persistent-data/dm-array.h @@ -199,7 +199,7 @@ struct dm_array_cursor { struct dm_block *block; struct array_block *ab; - unsigned index; + unsigned int index; }; int dm_array_cursor_begin(struct dm_array_info *info, diff --git a/drivers/md/persistent-data/dm-bitset.c b/drivers/md/persistent-data/dm-bitset.c index b56a9690a300..72734ff6fefb 100644 --- a/drivers/md/persistent-data/dm-bitset.c +++ b/drivers/md/persistent-data/dm-bitset.c @@ -42,7 +42,7 @@ EXPORT_SYMBOL_GPL(dm_bitset_empty); struct packer_context { bit_value_fn fn; - unsigned nr_bits; + unsigned int nr_bits; void *context; }; @@ -50,7 +50,7 @@ static int pack_bits(uint32_t index, void *value, void *context) { int r; struct packer_context *p = context; - unsigned bit, nr = min(64u, p->nr_bits - (index * 64)); + unsigned int bit, nr = min(64u, p->nr_bits - (index * 64)); uint64_t word = 0; bool bv; @@ -148,7 +148,7 @@ static int get_array_entry(struct dm_disk_bitset *info, dm_block_t root, uint32_t index, dm_block_t *new_root) { int r; - unsigned array_index = index / BITS_PER_ARRAY_ENTRY; + unsigned int array_index = index / BITS_PER_ARRAY_ENTRY; if (info->current_index_set) { if (info->current_index == array_index) @@ -166,7 +166,7 @@ int dm_bitset_set_bit(struct dm_disk_bitset *info, dm_block_t root, uint32_t index, dm_block_t *new_root) { int r; - unsigned b = index % BITS_PER_ARRAY_ENTRY; + unsigned int b = index % BITS_PER_ARRAY_ENTRY; r = get_array_entry(info, root, index, new_root); if (r) @@ -183,7 +183,7 @@ int dm_bitset_clear_bit(struct dm_disk_bitset *info, dm_block_t root, uint32_t index, dm_block_t *new_root) { int r; - unsigned b = index % BITS_PER_ARRAY_ENTRY; + unsigned int b = index % BITS_PER_ARRAY_ENTRY; r = get_array_entry(info, root, index, new_root); if (r) @@ -200,7 +200,7 @@ int dm_bitset_test_bit(struct dm_disk_bitset *info, dm_block_t root, uint32_t index, dm_block_t *new_root, bool *result) { int r; - unsigned b = index % BITS_PER_ARRAY_ENTRY; + unsigned int b = index % BITS_PER_ARRAY_ENTRY; r = get_array_entry(info, root, index, new_root); if (r) diff --git a/drivers/md/persistent-data/dm-block-manager.c b/drivers/md/persistent-data/dm-block-manager.c index 81c8f72664b9..af234c1176a7 100644 --- a/drivers/md/persistent-data/dm-block-manager.c +++ b/drivers/md/persistent-data/dm-block-manager.c @@ -58,10 +58,10 @@ struct waiter { int wants_write; }; -static unsigned __find_holder(struct block_lock *lock, +static unsigned int __find_holder(struct block_lock *lock, struct task_struct *task) { - unsigned i; + unsigned int i; for (i = 0; i < MAX_HOLDERS; i++) if (lock->holders[i] == task) @@ -74,7 +74,7 @@ static unsigned __find_holder(struct block_lock *lock, /* call this *after* you increment lock->count */ static void __add_holder(struct block_lock *lock, struct task_struct *task) { - unsigned h = __find_holder(lock, NULL); + unsigned int h = __find_holder(lock, NULL); #ifdef CONFIG_DM_DEBUG_BLOCK_STACK_TRACING struct stack_store *t; #endif @@ -91,14 +91,14 @@ static void __add_holder(struct block_lock *lock, struct task_struct *task) /* call this *before* you decrement lock->count */ static void __del_holder(struct block_lock *lock, struct task_struct *task) { - unsigned h = __find_holder(lock, task); + unsigned int h = __find_holder(lock, task); lock->holders[h] = NULL; put_task_struct(task); } static int __check_holder(struct block_lock *lock) { - unsigned i; + unsigned int i; for (i = 0; i < MAX_HOLDERS; i++) { if (lock->holders[i] == current) { @@ -377,8 +377,8 @@ struct dm_block_manager { }; struct dm_block_manager *dm_block_manager_create(struct block_device *bdev, - unsigned block_size, - unsigned max_held_per_thread) + unsigned int block_size, + unsigned int max_held_per_thread) { int r; struct dm_block_manager *bm; @@ -416,7 +416,7 @@ void dm_block_manager_destroy(struct dm_block_manager *bm) } EXPORT_SYMBOL_GPL(dm_block_manager_destroy); -unsigned dm_bm_block_size(struct dm_block_manager *bm) +unsigned int dm_bm_block_size(struct dm_block_manager *bm) { return dm_bufio_get_block_size(bm->bufio); } diff --git a/drivers/md/persistent-data/dm-block-manager.h b/drivers/md/persistent-data/dm-block-manager.h index 5cc605ba6f7c..5746b0f82a03 100644 --- a/drivers/md/persistent-data/dm-block-manager.h +++ b/drivers/md/persistent-data/dm-block-manager.h @@ -33,11 +33,11 @@ void *dm_block_data(struct dm_block *b); */ struct dm_block_manager; struct dm_block_manager *dm_block_manager_create( - struct block_device *bdev, unsigned block_size, - unsigned max_held_per_thread); + struct block_device *bdev, unsigned int block_size, + unsigned int max_held_per_thread); void dm_block_manager_destroy(struct dm_block_manager *bm); -unsigned dm_bm_block_size(struct dm_block_manager *bm); +unsigned int dm_bm_block_size(struct dm_block_manager *bm); dm_block_t dm_bm_nr_blocks(struct dm_block_manager *bm); /*----------------------------------------------------------------*/ diff --git a/drivers/md/persistent-data/dm-btree-remove.c b/drivers/md/persistent-data/dm-btree-remove.c index d8645af16d43..19647007c687 100644 --- a/drivers/md/persistent-data/dm-btree-remove.c +++ b/drivers/md/persistent-data/dm-btree-remove.c @@ -125,10 +125,10 @@ static int node_copy(struct btree_node *left, struct btree_node *right, int shif /* * Delete a specific entry from a leaf node. */ -static void delete_at(struct btree_node *n, unsigned index) +static void delete_at(struct btree_node *n, unsigned int index) { - unsigned nr_entries = le32_to_cpu(n->header.nr_entries); - unsigned nr_to_copy = nr_entries - (index + 1); + unsigned int nr_entries = le32_to_cpu(n->header.nr_entries); + unsigned int nr_to_copy = nr_entries - (index + 1); uint32_t value_size = le32_to_cpu(n->header.value_size); BUG_ON(index >= nr_entries); @@ -145,20 +145,20 @@ static void delete_at(struct btree_node *n, unsigned index) n->header.nr_entries = cpu_to_le32(nr_entries - 1); } -static unsigned merge_threshold(struct btree_node *n) +static unsigned int merge_threshold(struct btree_node *n) { return le32_to_cpu(n->header.max_entries) / 3; } struct child { - unsigned index; + unsigned int index; struct dm_block *block; struct btree_node *n; }; static int init_child(struct dm_btree_info *info, struct dm_btree_value_type *vt, struct btree_node *parent, - unsigned index, struct child *result) + unsigned int index, struct child *result) { int r, inc; dm_block_t root; @@ -264,7 +264,7 @@ static int __rebalance2(struct dm_btree_info *info, struct btree_node *parent, /* * Rebalance. */ - unsigned target_left = (nr_left + nr_right) / 2; + unsigned int target_left = (nr_left + nr_right) / 2; ret = shift(left, right, nr_left - target_left); if (ret) return ret; @@ -274,7 +274,7 @@ static int __rebalance2(struct dm_btree_info *info, struct btree_node *parent, } static int rebalance2(struct shadow_spine *s, struct dm_btree_info *info, - struct dm_btree_value_type *vt, unsigned left_index) + struct dm_btree_value_type *vt, unsigned int left_index) { int r; struct btree_node *parent; @@ -311,7 +311,7 @@ static int delete_center_node(struct dm_btree_info *info, struct btree_node *par uint32_t nr_left, uint32_t nr_center, uint32_t nr_right) { uint32_t max_entries = le32_to_cpu(left->header.max_entries); - unsigned shift = min(max_entries - nr_left, nr_center); + unsigned int shift = min(max_entries - nr_left, nr_center); if (nr_left + shift > max_entries) { DMERR("node shift out of bounds"); @@ -352,10 +352,10 @@ static int redistribute3(struct dm_btree_info *info, struct btree_node *parent, { int s, ret; uint32_t max_entries = le32_to_cpu(left->header.max_entries); - unsigned total = nr_left + nr_center + nr_right; - unsigned target_right = total / 3; - unsigned remainder = (target_right * 3) != total; - unsigned target_left = target_right + remainder; + unsigned int total = nr_left + nr_center + nr_right; + unsigned int target_right = total / 3; + unsigned int remainder = (target_right * 3) != total; + unsigned int target_left = target_right + remainder; BUG_ON(target_left > max_entries); BUG_ON(target_right > max_entries); @@ -423,7 +423,7 @@ static int __rebalance3(struct dm_btree_info *info, struct btree_node *parent, uint32_t nr_center = le32_to_cpu(center->header.nr_entries); uint32_t nr_right = le32_to_cpu(right->header.nr_entries); - unsigned threshold = merge_threshold(left) * 4 + 1; + unsigned int threshold = merge_threshold(left) * 4 + 1; if ((left->header.max_entries != center->header.max_entries) || (center->header.max_entries != right->header.max_entries)) { @@ -441,7 +441,7 @@ static int __rebalance3(struct dm_btree_info *info, struct btree_node *parent, } static int rebalance3(struct shadow_spine *s, struct dm_btree_info *info, - struct dm_btree_value_type *vt, unsigned left_index) + struct dm_btree_value_type *vt, unsigned int left_index) { int r; struct btree_node *parent = dm_block_data(shadow_current(s)); @@ -520,7 +520,7 @@ static int rebalance_children(struct shadow_spine *s, return r; } -static int do_leaf(struct btree_node *n, uint64_t key, unsigned *index) +static int do_leaf(struct btree_node *n, uint64_t key, unsigned int *index) { int i = lower_bound(n, key); @@ -540,7 +540,7 @@ static int do_leaf(struct btree_node *n, uint64_t key, unsigned *index) */ static int remove_raw(struct shadow_spine *s, struct dm_btree_info *info, struct dm_btree_value_type *vt, dm_block_t root, - uint64_t key, unsigned *index) + uint64_t key, unsigned int *index) { int i = *index, r; struct btree_node *n; @@ -590,7 +590,7 @@ static int remove_raw(struct shadow_spine *s, struct dm_btree_info *info, int dm_btree_remove(struct dm_btree_info *info, dm_block_t root, uint64_t *keys, dm_block_t *new_root) { - unsigned level, last_level = info->levels - 1; + unsigned int level, last_level = info->levels - 1; int index = 0, r = 0; struct shadow_spine spine; struct btree_node *n; @@ -602,7 +602,7 @@ int dm_btree_remove(struct dm_btree_info *info, dm_block_t root, r = remove_raw(&spine, info, (level == last_level ? &info->value_type : &le64_vt), - root, keys[level], (unsigned *)&index); + root, keys[level], (unsigned int *)&index); if (r < 0) break; @@ -686,9 +686,9 @@ static int remove_nearest(struct shadow_spine *s, struct dm_btree_info *info, static int remove_one(struct dm_btree_info *info, dm_block_t root, uint64_t *keys, uint64_t end_key, - dm_block_t *new_root, unsigned *nr_removed) + dm_block_t *new_root, unsigned int *nr_removed) { - unsigned level, last_level = info->levels - 1; + unsigned int level, last_level = info->levels - 1; int index = 0, r = 0; struct shadow_spine spine; struct btree_node *n; @@ -699,7 +699,7 @@ static int remove_one(struct dm_btree_info *info, dm_block_t root, init_shadow_spine(&spine, info); for (level = 0; level < last_level; level++) { r = remove_raw(&spine, info, &le64_vt, - root, keys[level], (unsigned *) &index); + root, keys[level], (unsigned int *) &index); if (r < 0) goto out; @@ -743,7 +743,7 @@ out: int dm_btree_remove_leaves(struct dm_btree_info *info, dm_block_t root, uint64_t *first_key, uint64_t end_key, - dm_block_t *new_root, unsigned *nr_removed) + dm_block_t *new_root, unsigned int *nr_removed) { int r; diff --git a/drivers/md/persistent-data/dm-btree-spine.c b/drivers/md/persistent-data/dm-btree-spine.c index 9c3cdbaf47a2..a04784bab21e 100644 --- a/drivers/md/persistent-data/dm-btree-spine.c +++ b/drivers/md/persistent-data/dm-btree-spine.c @@ -235,12 +235,12 @@ dm_block_t shadow_root(struct shadow_spine *s) return s->root; } -static void le64_inc(void *context, const void *value_le, unsigned count) +static void le64_inc(void *context, const void *value_le, unsigned int count) { dm_tm_with_runs(context, value_le, count, dm_tm_inc_range); } -static void le64_dec(void *context, const void *value_le, unsigned count) +static void le64_dec(void *context, const void *value_le, unsigned int count) { dm_tm_with_runs(context, value_le, count, dm_tm_dec_range); } diff --git a/drivers/md/persistent-data/dm-btree.c b/drivers/md/persistent-data/dm-btree.c index a4b2a9ea7cc7..f74822661022 100644 --- a/drivers/md/persistent-data/dm-btree.c +++ b/drivers/md/persistent-data/dm-btree.c @@ -24,8 +24,8 @@ static void memcpy_disk(void *dest, const void *src, size_t len) __dm_unbless_for_disk(src); } -static void array_insert(void *base, size_t elt_size, unsigned nr_elts, - unsigned index, void *elt) +static void array_insert(void *base, size_t elt_size, unsigned int nr_elts, + unsigned int index, void *elt) __dm_written_to_disk(elt) { if (index < nr_elts) @@ -81,7 +81,7 @@ void inc_children(struct dm_transaction_manager *tm, struct btree_node *n, vt->inc(vt->context, value_ptr(n, 0), nr_entries); } -static int insert_at(size_t value_size, struct btree_node *node, unsigned index, +static int insert_at(size_t value_size, struct btree_node *node, unsigned int index, uint64_t key, void *value) __dm_written_to_disk(value) { @@ -163,9 +163,9 @@ EXPORT_SYMBOL_GPL(dm_btree_empty); struct frame { struct dm_block *b; struct btree_node *n; - unsigned level; - unsigned nr_children; - unsigned current_child; + unsigned int level; + unsigned int nr_children; + unsigned int current_child; }; struct del_stack { @@ -194,7 +194,7 @@ static int unprocessed_frames(struct del_stack *s) static void prefetch_children(struct del_stack *s, struct frame *f) { - unsigned i; + unsigned int i; struct dm_block_manager *bm = dm_tm_get_bm(s->tm); for (i = 0; i < f->nr_children; i++) @@ -206,7 +206,7 @@ static bool is_internal_level(struct dm_btree_info *info, struct frame *f) return f->level < (info->levels - 1); } -static int push_frame(struct del_stack *s, dm_block_t b, unsigned level) +static int push_frame(struct del_stack *s, dm_block_t b, unsigned int level) { int r; uint32_t ref_count; @@ -372,7 +372,7 @@ static int btree_lookup_raw(struct ro_spine *s, dm_block_t block, uint64_t key, int dm_btree_lookup(struct dm_btree_info *info, dm_block_t root, uint64_t *keys, void *value_le) { - unsigned level, last_level = info->levels - 1; + unsigned int level, last_level = info->levels - 1; int r = -ENODATA; uint64_t rkey; __le64 internal_value_le; @@ -468,7 +468,7 @@ out: int dm_btree_lookup_next(struct dm_btree_info *info, dm_block_t root, uint64_t *keys, uint64_t *rkey, void *value_le) { - unsigned level; + unsigned int level; int r = -ENODATA; __le64 internal_value_le; struct ro_spine spine; @@ -503,9 +503,9 @@ EXPORT_SYMBOL_GPL(dm_btree_lookup_next); * Copies entries from one region of a btree node to another. The regions * must not overlap. */ -static void copy_entries(struct btree_node *dest, unsigned dest_offset, - struct btree_node *src, unsigned src_offset, - unsigned count) +static void copy_entries(struct btree_node *dest, unsigned int dest_offset, + struct btree_node *src, unsigned int src_offset, + unsigned int count) { size_t value_size = le32_to_cpu(dest->header.value_size); memcpy(dest->keys + dest_offset, src->keys + src_offset, count * sizeof(uint64_t)); @@ -516,9 +516,9 @@ static void copy_entries(struct btree_node *dest, unsigned dest_offset, * Moves entries from one region fo a btree node to another. The regions * may overlap. */ -static void move_entries(struct btree_node *dest, unsigned dest_offset, - struct btree_node *src, unsigned src_offset, - unsigned count) +static void move_entries(struct btree_node *dest, unsigned int dest_offset, + struct btree_node *src, unsigned int src_offset, + unsigned int count) { size_t value_size = le32_to_cpu(dest->header.value_size); memmove(dest->keys + dest_offset, src->keys + src_offset, count * sizeof(uint64_t)); @@ -529,7 +529,7 @@ static void move_entries(struct btree_node *dest, unsigned dest_offset, * Erases the first 'count' entries of a btree node, shifting following * entries down into their place. */ -static void shift_down(struct btree_node *n, unsigned count) +static void shift_down(struct btree_node *n, unsigned int count) { move_entries(n, 0, n, count, le32_to_cpu(n->header.nr_entries) - count); } @@ -538,7 +538,7 @@ static void shift_down(struct btree_node *n, unsigned count) * Moves entries in a btree node up 'count' places, making space for * new entries at the start of the node. */ -static void shift_up(struct btree_node *n, unsigned count) +static void shift_up(struct btree_node *n, unsigned int count) { move_entries(n, count, n, 0, le32_to_cpu(n->header.nr_entries)); } @@ -549,18 +549,18 @@ static void shift_up(struct btree_node *n, unsigned count) */ static void redistribute2(struct btree_node *left, struct btree_node *right) { - unsigned nr_left = le32_to_cpu(left->header.nr_entries); - unsigned nr_right = le32_to_cpu(right->header.nr_entries); - unsigned total = nr_left + nr_right; - unsigned target_left = total / 2; - unsigned target_right = total - target_left; + unsigned int nr_left = le32_to_cpu(left->header.nr_entries); + unsigned int nr_right = le32_to_cpu(right->header.nr_entries); + unsigned int total = nr_left + nr_right; + unsigned int target_left = total / 2; + unsigned int target_right = total - target_left; if (nr_left < target_left) { - unsigned delta = target_left - nr_left; + unsigned int delta = target_left - nr_left; copy_entries(left, nr_left, right, 0, delta); shift_down(right, delta); } else if (nr_left > target_left) { - unsigned delta = nr_left - target_left; + unsigned int delta = nr_left - target_left; if (nr_right) shift_up(right, delta); copy_entries(right, 0, left, target_left, delta); @@ -577,10 +577,10 @@ static void redistribute2(struct btree_node *left, struct btree_node *right) static void redistribute3(struct btree_node *left, struct btree_node *center, struct btree_node *right) { - unsigned nr_left = le32_to_cpu(left->header.nr_entries); - unsigned nr_center = le32_to_cpu(center->header.nr_entries); - unsigned nr_right = le32_to_cpu(right->header.nr_entries); - unsigned total, target_left, target_center, target_right; + unsigned int nr_left = le32_to_cpu(left->header.nr_entries); + unsigned int nr_center = le32_to_cpu(center->header.nr_entries); + unsigned int nr_right = le32_to_cpu(right->header.nr_entries); + unsigned int total, target_left, target_center, target_right; BUG_ON(nr_center); @@ -590,19 +590,19 @@ static void redistribute3(struct btree_node *left, struct btree_node *center, target_right = (total - target_left - target_center); if (nr_left < target_left) { - unsigned left_short = target_left - nr_left; + unsigned int left_short = target_left - nr_left; copy_entries(left, nr_left, right, 0, left_short); copy_entries(center, 0, right, left_short, target_center); shift_down(right, nr_right - target_right); } else if (nr_left < (target_left + target_center)) { - unsigned left_to_center = nr_left - target_left; + unsigned int left_to_center = nr_left - target_left; copy_entries(center, 0, left, target_left, left_to_center); copy_entries(center, left_to_center, right, 0, target_center - left_to_center); shift_down(right, nr_right - target_right); } else { - unsigned right_short = target_right - nr_right; + unsigned int right_short = target_right - nr_right; shift_up(right, right_short); copy_entries(right, 0, left, nr_left - right_short, right_short); copy_entries(center, 0, left, target_left, nr_left - target_left); @@ -643,7 +643,7 @@ static void redistribute3(struct btree_node *left, struct btree_node *center, * * Where A* is a shadow of A. */ -static int split_one_into_two(struct shadow_spine *s, unsigned parent_index, +static int split_one_into_two(struct shadow_spine *s, unsigned int parent_index, struct dm_btree_value_type *vt, uint64_t key) { int r; @@ -697,7 +697,7 @@ static int split_one_into_two(struct shadow_spine *s, unsigned parent_index, * to the new shadow. */ static int shadow_child(struct dm_btree_info *info, struct dm_btree_value_type *vt, - struct btree_node *parent, unsigned index, + struct btree_node *parent, unsigned int index, struct dm_block **result) { int r, inc; @@ -726,11 +726,11 @@ static int shadow_child(struct dm_btree_info *info, struct dm_btree_value_type * * Splits two nodes into three. This is more work, but results in fuller * nodes, so saves metadata space. */ -static int split_two_into_three(struct shadow_spine *s, unsigned parent_index, +static int split_two_into_three(struct shadow_spine *s, unsigned int parent_index, struct dm_btree_value_type *vt, uint64_t key) { int r; - unsigned middle_index; + unsigned int middle_index; struct dm_block *left, *middle, *right, *parent; struct btree_node *ln, *rn, *mn, *pn; __le64 location; @@ -831,7 +831,7 @@ static int btree_split_beneath(struct shadow_spine *s, uint64_t key) { int r; size_t size; - unsigned nr_left, nr_right; + unsigned int nr_left, nr_right; struct dm_block *left, *right, *new_parent; struct btree_node *pn, *ln, *rn; __le64 val; @@ -905,7 +905,7 @@ static int btree_split_beneath(struct shadow_spine *s, uint64_t key) * Redistributes a node's entries with its left sibling. */ static int rebalance_left(struct shadow_spine *s, struct dm_btree_value_type *vt, - unsigned parent_index, uint64_t key) + unsigned int parent_index, uint64_t key) { int r; struct dm_block *sib; @@ -934,7 +934,7 @@ static int rebalance_left(struct shadow_spine *s, struct dm_btree_value_type *vt * Redistributes a nodes entries with its right sibling. */ static int rebalance_right(struct shadow_spine *s, struct dm_btree_value_type *vt, - unsigned parent_index, uint64_t key) + unsigned int parent_index, uint64_t key) { int r; struct dm_block *sib; @@ -962,10 +962,10 @@ static int rebalance_right(struct shadow_spine *s, struct dm_btree_value_type *v /* * Returns the number of spare entries in a node. */ -static int get_node_free_space(struct dm_btree_info *info, dm_block_t b, unsigned *space) +static int get_node_free_space(struct dm_btree_info *info, dm_block_t b, unsigned int *space) { int r; - unsigned nr_entries; + unsigned int nr_entries; struct dm_block *block; struct btree_node *node; @@ -991,12 +991,12 @@ static int get_node_free_space(struct dm_btree_info *info, dm_block_t b, unsigne */ #define SPACE_THRESHOLD 8 static int rebalance_or_split(struct shadow_spine *s, struct dm_btree_value_type *vt, - unsigned parent_index, uint64_t key) + unsigned int parent_index, uint64_t key) { int r; struct btree_node *parent = dm_block_data(shadow_parent(s)); - unsigned nr_parent = le32_to_cpu(parent->header.nr_entries); - unsigned free_space; + unsigned int nr_parent = le32_to_cpu(parent->header.nr_entries); + unsigned int free_space; int left_shared = 0, right_shared = 0; /* Should we move entries to the left sibling? */ @@ -1081,7 +1081,7 @@ static bool has_space_for_insert(struct btree_node *node, uint64_t key) static int btree_insert_raw(struct shadow_spine *s, dm_block_t root, struct dm_btree_value_type *vt, - uint64_t key, unsigned *index) + uint64_t key, unsigned int *index) { int r, i = *index, top = 1; struct btree_node *node; @@ -1215,7 +1215,7 @@ int btree_get_overwrite_leaf(struct dm_btree_info *info, dm_block_t root, } static bool need_insert(struct btree_node *node, uint64_t *keys, - unsigned level, unsigned index) + unsigned int level, unsigned int index) { return ((index >= le32_to_cpu(node->header.nr_entries)) || (le64_to_cpu(node->keys[index]) != keys[level])); @@ -1227,7 +1227,7 @@ static int insert(struct dm_btree_info *info, dm_block_t root, __dm_written_to_disk(value) { int r; - unsigned level, index = -1, last_level = info->levels - 1; + unsigned int level, index = -1, last_level = info->levels - 1; dm_block_t block = root; struct shadow_spine spine; struct btree_node *n; @@ -1413,7 +1413,7 @@ static int walk_node(struct dm_btree_info *info, dm_block_t block, void *context) { int r; - unsigned i, nr; + unsigned int i, nr; struct dm_block *node; struct btree_node *n; uint64_t keys; @@ -1456,7 +1456,7 @@ EXPORT_SYMBOL_GPL(dm_btree_walk); static void prefetch_values(struct dm_btree_cursor *c) { - unsigned i, nr; + unsigned int i, nr; __le64 value_le; struct cursor_node *n = c->nodes + c->depth - 1; struct btree_node *bn = dm_block_data(n->b); diff --git a/drivers/md/persistent-data/dm-btree.h b/drivers/md/persistent-data/dm-btree.h index 62461e6db408..f3f2b21c82c8 100644 --- a/drivers/md/persistent-data/dm-btree.h +++ b/drivers/md/persistent-data/dm-btree.h @@ -59,14 +59,14 @@ struct dm_btree_value_type { * somewhere.) This method is _not_ called for insertion of a new * value: It is assumed the ref count is already 1. */ - void (*inc)(void *context, const void *value, unsigned count); + void (*inc)(void *context, const void *value, unsigned int count); /* * These values are being deleted. The btree takes care of freeing * the memory pointed to by @value. Often the del function just * needs to decrement a reference counts somewhere. */ - void (*dec)(void *context, const void *value, unsigned count); + void (*dec)(void *context, const void *value, unsigned int count); /* * A test for equality between two values. When a value is @@ -85,7 +85,7 @@ struct dm_btree_info { /* * Number of nested btrees. (Not the depth of a single tree.) */ - unsigned levels; + unsigned int levels; struct dm_btree_value_type value_type; }; @@ -150,7 +150,7 @@ int dm_btree_remove(struct dm_btree_info *info, dm_block_t root, */ int dm_btree_remove_leaves(struct dm_btree_info *info, dm_block_t root, uint64_t *keys, uint64_t end_key, - dm_block_t *new_root, unsigned *nr_removed); + dm_block_t *new_root, unsigned int *nr_removed); /* * Returns < 0 on failure. Otherwise the number of key entries that have @@ -189,7 +189,7 @@ int dm_btree_walk(struct dm_btree_info *info, dm_block_t root, struct cursor_node { struct dm_block *b; - unsigned index; + unsigned int index; }; struct dm_btree_cursor { @@ -197,7 +197,7 @@ struct dm_btree_cursor { dm_block_t root; bool prefetch_leaves; - unsigned depth; + unsigned int depth; struct cursor_node nodes[DM_BTREE_CURSOR_MAX_DEPTH]; }; diff --git a/drivers/md/persistent-data/dm-persistent-data-internal.h b/drivers/md/persistent-data/dm-persistent-data-internal.h index 4cfc27a9f8af..c482434e566b 100644 --- a/drivers/md/persistent-data/dm-persistent-data-internal.h +++ b/drivers/md/persistent-data/dm-persistent-data-internal.h @@ -10,11 +10,11 @@ #include "dm-block-manager.h" -static inline unsigned dm_hash_block(dm_block_t b, unsigned hash_mask) +static inline unsigned int dm_hash_block(dm_block_t b, unsigned int hash_mask) { - const unsigned BIG_PRIME = 4294967291UL; + const unsigned int BIG_PRIME = 4294967291UL; - return (((unsigned) b) * BIG_PRIME) & hash_mask; + return (((unsigned int) b) * BIG_PRIME) & hash_mask; } #endif /* _PERSISTENT_DATA_INTERNAL_H */ diff --git a/drivers/md/persistent-data/dm-space-map-common.c b/drivers/md/persistent-data/dm-space-map-common.c index 51b57064d49d..b18b6dc1b634 100644 --- a/drivers/md/persistent-data/dm-space-map-common.c +++ b/drivers/md/persistent-data/dm-space-map-common.c @@ -127,7 +127,7 @@ static void *dm_bitmap_data(struct dm_block *b) #define WORD_MASK_HIGH 0xAAAAAAAAAAAAAAAAULL -static unsigned dm_bitmap_word_used(void *addr, unsigned b) +static unsigned int dm_bitmap_word_used(void *addr, unsigned int b) { __le64 *words_le = addr; __le64 *w_le = words_le + (b >> ENTRIES_SHIFT); @@ -138,11 +138,11 @@ static unsigned dm_bitmap_word_used(void *addr, unsigned b) return !(~bits & mask); } -static unsigned sm_lookup_bitmap(void *addr, unsigned b) +static unsigned int sm_lookup_bitmap(void *addr, unsigned int b) { __le64 *words_le = addr; __le64 *w_le = words_le + (b >> ENTRIES_SHIFT); - unsigned hi, lo; + unsigned int hi, lo; b = (b & (ENTRIES_PER_WORD - 1)) << 1; hi = !!test_bit_le(b, (void *) w_le); @@ -150,7 +150,7 @@ static unsigned sm_lookup_bitmap(void *addr, unsigned b) return (hi << 1) | lo; } -static void sm_set_bitmap(void *addr, unsigned b, unsigned val) +static void sm_set_bitmap(void *addr, unsigned int b, unsigned int val) { __le64 *words_le = addr; __le64 *w_le = words_le + (b >> ENTRIES_SHIFT); @@ -168,8 +168,8 @@ static void sm_set_bitmap(void *addr, unsigned b, unsigned val) __clear_bit_le(b + 1, (void *) w_le); } -static int sm_find_free(void *addr, unsigned begin, unsigned end, - unsigned *result) +static int sm_find_free(void *addr, unsigned int begin, unsigned int end, + unsigned int *result) { while (begin < end) { if (!(begin & (ENTRIES_PER_WORD - 1)) && @@ -238,7 +238,7 @@ int sm_ll_extend(struct ll_disk *ll, dm_block_t extra_blocks) { int r; dm_block_t i, nr_blocks, nr_indexes; - unsigned old_blocks, blocks; + unsigned int old_blocks, blocks; nr_blocks = ll->nr_blocks + extra_blocks; old_blocks = dm_sector_div_up(ll->nr_blocks, ll->entries_per_block); @@ -352,7 +352,7 @@ int sm_ll_find_free_block(struct ll_disk *ll, dm_block_t begin, for (i = index_begin; i < index_end; i++, begin = 0) { struct dm_block *blk; - unsigned position; + unsigned int position; uint32_t bit_end; r = ll->load_ie(ll, i, &ie_disk); @@ -370,7 +370,7 @@ int sm_ll_find_free_block(struct ll_disk *ll, dm_block_t begin, bit_end = (i == index_end - 1) ? end : ll->entries_per_block; r = sm_find_free(dm_bitmap_data(blk), - max_t(unsigned, begin, le32_to_cpu(ie_disk.none_free_before)), + max_t(unsigned int, begin, le32_to_cpu(ie_disk.none_free_before)), bit_end, &position); if (r == -ENOSPC) { /* @@ -1098,7 +1098,7 @@ static inline int ie_cache_writeback(struct ll_disk *ll, struct ie_cache *iec) &iec->index, &iec->ie, &ll->bitmap_root); } -static inline unsigned hash_index(dm_block_t index) +static inline unsigned int hash_index(dm_block_t index) { return dm_hash_block(index, IE_CACHE_MASK); } @@ -1107,7 +1107,7 @@ static int disk_ll_load_ie(struct ll_disk *ll, dm_block_t index, struct disk_index_entry *ie) { int r; - unsigned h = hash_index(index); + unsigned int h = hash_index(index); struct ie_cache *iec = ll->ie_cache + h; if (iec->valid) { @@ -1138,7 +1138,7 @@ static int disk_ll_save_ie(struct ll_disk *ll, dm_block_t index, struct disk_index_entry *ie) { int r; - unsigned h = hash_index(index); + unsigned int h = hash_index(index); struct ie_cache *iec = ll->ie_cache + h; ll->bitmap_index_changed = true; @@ -1165,7 +1165,7 @@ static int disk_ll_save_ie(struct ll_disk *ll, dm_block_t index, static int disk_ll_init_index(struct ll_disk *ll) { - unsigned i; + unsigned int i; for (i = 0; i < IE_CACHE_SIZE; i++) { struct ie_cache *iec = ll->ie_cache + i; iec->valid = false; @@ -1187,7 +1187,7 @@ static dm_block_t disk_ll_max_entries(struct ll_disk *ll) static int disk_ll_commit(struct ll_disk *ll) { int r = 0; - unsigned i; + unsigned int i; for (i = 0; i < IE_CACHE_SIZE; i++) { struct ie_cache *iec = ll->ie_cache + i; diff --git a/drivers/md/persistent-data/dm-space-map-metadata.c b/drivers/md/persistent-data/dm-space-map-metadata.c index 69174957a05e..ec2487787617 100644 --- a/drivers/md/persistent-data/dm-space-map-metadata.c +++ b/drivers/md/persistent-data/dm-space-map-metadata.c @@ -95,8 +95,8 @@ struct block_op { }; struct bop_ring_buffer { - unsigned begin; - unsigned end; + unsigned int begin; + unsigned int end; struct block_op bops[MAX_RECURSIVE_ALLOCATIONS + 1]; }; @@ -111,9 +111,9 @@ static bool brb_empty(struct bop_ring_buffer *brb) return brb->begin == brb->end; } -static unsigned brb_next(struct bop_ring_buffer *brb, unsigned old) +static unsigned int brb_next(struct bop_ring_buffer *brb, unsigned int old) { - unsigned r = old + 1; + unsigned int r = old + 1; return r >= ARRAY_SIZE(brb->bops) ? 0 : r; } @@ -121,7 +121,7 @@ static int brb_push(struct bop_ring_buffer *brb, enum block_op_type type, dm_block_t b, dm_block_t e) { struct block_op *bop; - unsigned next = brb_next(brb, brb->end); + unsigned int next = brb_next(brb, brb->end); /* * We don't allow the last bop to be filled, this way we can @@ -172,8 +172,8 @@ struct sm_metadata { dm_block_t begin; - unsigned recursion_count; - unsigned allocated_this_transaction; + unsigned int recursion_count; + unsigned int allocated_this_transaction; struct bop_ring_buffer uncommitted; struct threshold threshold; @@ -301,9 +301,9 @@ static int sm_metadata_get_count(struct dm_space_map *sm, dm_block_t b, uint32_t *result) { int r; - unsigned i; + unsigned int i; struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm); - unsigned adjustment = 0; + unsigned int adjustment = 0; /* * We may have some uncommitted adjustments to add. This list @@ -341,7 +341,7 @@ static int sm_metadata_count_is_more_than_one(struct dm_space_map *sm, dm_block_t b, int *result) { int r, adjustment = 0; - unsigned i; + unsigned int i; struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm); uint32_t rc; diff --git a/drivers/md/persistent-data/dm-transaction-manager.c b/drivers/md/persistent-data/dm-transaction-manager.c index 315f487e457f..a725e49cc483 100644 --- a/drivers/md/persistent-data/dm-transaction-manager.c +++ b/drivers/md/persistent-data/dm-transaction-manager.c @@ -29,14 +29,14 @@ struct prefetch_set { dm_block_t blocks[PREFETCH_SIZE]; }; -static unsigned prefetch_hash(dm_block_t b) +static unsigned int prefetch_hash(dm_block_t b) { return hash_64(b, PREFETCH_BITS); } static void prefetch_wipe(struct prefetch_set *p) { - unsigned i; + unsigned int i; for (i = 0; i < PREFETCH_SIZE; i++) p->blocks[i] = PREFETCH_SENTINEL; } @@ -49,7 +49,7 @@ static void prefetch_init(struct prefetch_set *p) static void prefetch_add(struct prefetch_set *p, dm_block_t b) { - unsigned h = prefetch_hash(b); + unsigned int h = prefetch_hash(b); mutex_lock(&p->lock); if (p->blocks[h] == PREFETCH_SENTINEL) @@ -60,7 +60,7 @@ static void prefetch_add(struct prefetch_set *p, dm_block_t b) static void prefetch_issue(struct prefetch_set *p, struct dm_block_manager *bm) { - unsigned i; + unsigned int i; mutex_lock(&p->lock); @@ -104,7 +104,7 @@ struct dm_transaction_manager { static int is_shadow(struct dm_transaction_manager *tm, dm_block_t b) { int r = 0; - unsigned bucket = dm_hash_block(b, DM_HASH_MASK); + unsigned int bucket = dm_hash_block(b, DM_HASH_MASK); struct shadow_info *si; spin_lock(&tm->lock); @@ -124,7 +124,7 @@ static int is_shadow(struct dm_transaction_manager *tm, dm_block_t b) */ static void insert_shadow(struct dm_transaction_manager *tm, dm_block_t b) { - unsigned bucket; + unsigned int bucket; struct shadow_info *si; si = kmalloc(sizeof(*si), GFP_NOIO); @@ -394,11 +394,11 @@ void dm_tm_dec_range(struct dm_transaction_manager *tm, dm_block_t b, dm_block_t EXPORT_SYMBOL_GPL(dm_tm_dec_range); void dm_tm_with_runs(struct dm_transaction_manager *tm, - const __le64 *value_le, unsigned count, dm_tm_run_fn fn) + const __le64 *value_le, unsigned int count, dm_tm_run_fn fn) { uint64_t b, begin, end; bool in_run = false; - unsigned i; + unsigned int i; for (i = 0; i < count; i++, value_le++) { b = le64_to_cpu(*value_le); diff --git a/drivers/md/persistent-data/dm-transaction-manager.h b/drivers/md/persistent-data/dm-transaction-manager.h index 70c87ce96372..01f7e650118d 100644 --- a/drivers/md/persistent-data/dm-transaction-manager.h +++ b/drivers/md/persistent-data/dm-transaction-manager.h @@ -112,7 +112,7 @@ void dm_tm_dec_range(struct dm_transaction_manager *tm, dm_block_t b, dm_block_t */ typedef void (*dm_tm_run_fn)(struct dm_transaction_manager *, dm_block_t, dm_block_t); void dm_tm_with_runs(struct dm_transaction_manager *tm, - const __le64 *value_le, unsigned count, dm_tm_run_fn fn); + const __le64 *value_le, unsigned int count, dm_tm_run_fn fn); int dm_tm_ref(struct dm_transaction_manager *tm, dm_block_t b, uint32_t *result); diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 425fa9be648c..9881e772b68c 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -88,10 +88,10 @@ typedef int (*dm_preresume_fn) (struct dm_target *ti); typedef void (*dm_resume_fn) (struct dm_target *ti); typedef void (*dm_status_fn) (struct dm_target *ti, status_type_t status_type, - unsigned status_flags, char *result, unsigned maxlen); + unsigned int status_flags, char *result, unsigned int maxlen); -typedef int (*dm_message_fn) (struct dm_target *ti, unsigned argc, char **argv, - char *result, unsigned maxlen); +typedef int (*dm_message_fn) (struct dm_target *ti, unsigned int argc, char **argv, + char *result, unsigned int maxlen); typedef int (*dm_prepare_ioctl_fn) (struct dm_target *ti, struct block_device **bdev); @@ -188,7 +188,7 @@ struct target_type { uint64_t features; const char *name; struct module *module; - unsigned version[3]; + unsigned int version[3]; dm_ctr_fn ctr; dm_dtr_fn dtr; dm_map_fn map; @@ -314,31 +314,31 @@ struct dm_target { * It is a responsibility of the target driver to remap these bios * to the real underlying devices. */ - unsigned num_flush_bios; + unsigned int num_flush_bios; /* * The number of discard bios that will be submitted to the target. * The bio number can be accessed with dm_bio_get_target_bio_nr. */ - unsigned num_discard_bios; + unsigned int num_discard_bios; /* * The number of secure erase bios that will be submitted to the target. * The bio number can be accessed with dm_bio_get_target_bio_nr. */ - unsigned num_secure_erase_bios; + unsigned int num_secure_erase_bios; /* * The number of WRITE ZEROES bios that will be submitted to the target. * The bio number can be accessed with dm_bio_get_target_bio_nr. */ - unsigned num_write_zeroes_bios; + unsigned int num_write_zeroes_bios; /* * The minimum number of extra bytes allocated in each io for the * target to use. */ - unsigned per_io_data_size; + unsigned int per_io_data_size; /* target specific data */ void *private; @@ -384,7 +384,7 @@ struct dm_target { void *dm_per_bio_data(struct bio *bio, size_t data_size); struct bio *dm_bio_from_per_bio_data(void *data, size_t data_size); -unsigned dm_bio_get_target_bio_nr(const struct bio *bio); +unsigned int dm_bio_get_target_bio_nr(const struct bio *bio); u64 dm_start_time_ns_from_clone(struct bio *bio); @@ -395,7 +395,7 @@ void dm_unregister_target(struct target_type *t); * Target argument parsing. */ struct dm_arg_set { - unsigned argc; + unsigned int argc; char **argv; }; @@ -404,8 +404,8 @@ struct dm_arg_set { * the error message to use if the number is found to be outside that range. */ struct dm_arg { - unsigned min; - unsigned max; + unsigned int min; + unsigned int max; char *error; }; @@ -414,7 +414,7 @@ struct dm_arg { * returning -EINVAL and setting *error. */ int dm_read_arg(const struct dm_arg *arg, struct dm_arg_set *arg_set, - unsigned *value, char **error); + unsigned int *value, char **error); /* * Process the next argument as the start of a group containing between @@ -422,7 +422,7 @@ int dm_read_arg(const struct dm_arg *arg, struct dm_arg_set *arg_set, * *num_args or, if invalid, return -EINVAL and set *error. */ int dm_read_arg_group(const struct dm_arg *arg, struct dm_arg_set *arg_set, - unsigned *num_args, char **error); + unsigned int *num_args, char **error); /* * Return the current argument and shift to the next. @@ -432,7 +432,7 @@ const char *dm_shift_arg(struct dm_arg_set *as); /* * Move through num_args arguments. */ -void dm_consume_args(struct dm_arg_set *as, unsigned num_args); +void dm_consume_args(struct dm_arg_set *as, unsigned int num_args); /*----------------------------------------------------------------- * Functions for creating and manipulating mapped devices. @@ -462,7 +462,7 @@ void *dm_get_mdptr(struct mapped_device *md); /* * A device can still be used while suspended, but I/O is deferred. */ -int dm_suspend(struct mapped_device *md, unsigned suspend_flags); +int dm_suspend(struct mapped_device *md, unsigned int suspend_flags); int dm_resume(struct mapped_device *md); /* @@ -482,7 +482,7 @@ struct gendisk *dm_disk(struct mapped_device *md); int dm_suspended(struct dm_target *ti); int dm_post_suspending(struct dm_target *ti); int dm_noflush_suspending(struct dm_target *ti); -void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors); +void dm_accept_partial_bio(struct bio *bio, unsigned int n_sectors); void dm_submit_bio_remap(struct bio *clone, struct bio *tgt_clone); union map_info *dm_get_rq_mapinfo(struct request *rq); @@ -526,7 +526,7 @@ int dm_set_geometry(struct mapped_device *md, struct hd_geometry *geo); * First create an empty table. */ int dm_table_create(struct dm_table **result, fmode_t mode, - unsigned num_targets, struct mapped_device *md); + unsigned int num_targets, struct mapped_device *md); /* * Then call this once for each target. diff --git a/include/linux/dm-bufio.h b/include/linux/dm-bufio.h index 798379b8597a..2056743aaaaa 100644 --- a/include/linux/dm-bufio.h +++ b/include/linux/dm-bufio.h @@ -27,8 +27,8 @@ struct dm_buffer; * Create a buffered IO cache on a given device */ struct dm_bufio_client * -dm_bufio_client_create(struct block_device *bdev, unsigned block_size, - unsigned reserved_buffers, unsigned aux_size, +dm_bufio_client_create(struct block_device *bdev, unsigned int block_size, + unsigned int reserved_buffers, unsigned int aux_size, void (*alloc_callback)(struct dm_buffer *), void (*write_callback)(struct dm_buffer *), unsigned int flags); @@ -82,7 +82,7 @@ void *dm_bufio_new(struct dm_bufio_client *c, sector_t block, * I/O to finish. */ void dm_bufio_prefetch(struct dm_bufio_client *c, - sector_t block, unsigned n_blocks); + sector_t block, unsigned int n_blocks); /* * Release a reference obtained with dm_bufio_{read,get,new}. The data @@ -107,7 +107,7 @@ void dm_bufio_mark_buffer_dirty(struct dm_buffer *b); * write the specified part of the buffer or it may write a larger superset. */ void dm_bufio_mark_partial_buffer_dirty(struct dm_buffer *b, - unsigned start, unsigned end); + unsigned int start, unsigned int end); /* * Initiate writing of dirty buffers, without waiting for completion. @@ -153,9 +153,9 @@ void dm_bufio_forget_buffers(struct dm_bufio_client *c, sector_t block, sector_t /* * Set the minimum number of buffers before cleanup happens. */ -void dm_bufio_set_minimum_buffers(struct dm_bufio_client *c, unsigned n); +void dm_bufio_set_minimum_buffers(struct dm_bufio_client *c, unsigned int n); -unsigned dm_bufio_get_block_size(struct dm_bufio_client *c); +unsigned int dm_bufio_get_block_size(struct dm_bufio_client *c); sector_t dm_bufio_get_device_size(struct dm_bufio_client *c); struct dm_io_client *dm_bufio_get_dm_io_client(struct dm_bufio_client *c); sector_t dm_bufio_get_block_number(struct dm_buffer *b); diff --git a/include/linux/dm-dirty-log.h b/include/linux/dm-dirty-log.h index c12d40e332c1..a3eb7490d205 100644 --- a/include/linux/dm-dirty-log.h +++ b/include/linux/dm-dirty-log.h @@ -34,7 +34,7 @@ struct dm_dirty_log_type { struct list_head list; int (*ctr)(struct dm_dirty_log *log, struct dm_target *ti, - unsigned argc, char **argv); + unsigned int argc, char **argv); void (*dtr)(struct dm_dirty_log *log); /* @@ -117,7 +117,7 @@ struct dm_dirty_log_type { * Support function for mirror status requests. */ int (*status)(struct dm_dirty_log *log, status_type_t status_type, - char *result, unsigned maxlen); + char *result, unsigned int maxlen); /* * is_remote_recovering is necessary for cluster mirroring. It provides @@ -140,7 +140,7 @@ int dm_dirty_log_type_unregister(struct dm_dirty_log_type *type); struct dm_dirty_log *dm_dirty_log_create(const char *type_name, struct dm_target *ti, int (*flush_callback_fn)(struct dm_target *ti), - unsigned argc, char **argv); + unsigned int argc, char **argv); void dm_dirty_log_destroy(struct dm_dirty_log *log); #endif /* __KERNEL__ */ diff --git a/include/linux/dm-io.h b/include/linux/dm-io.h index 6846019da2a5..7595142f3fc5 100644 --- a/include/linux/dm-io.h +++ b/include/linux/dm-io.h @@ -27,7 +27,7 @@ struct page_list { struct page *page; }; -typedef void (*io_notify_fn)(unsigned long error, void *context); +typedef void (*io_notify_fn)(unsigned int long error, void *context); enum dm_io_mem_type { DM_IO_PAGE_LIST,/* Page list */ @@ -39,7 +39,7 @@ enum dm_io_mem_type { struct dm_io_memory { enum dm_io_mem_type type; - unsigned offset; + unsigned int offset; union { struct page_list *pl; @@ -79,8 +79,8 @@ void dm_io_client_destroy(struct dm_io_client *client); * Each bit in the optional 'sync_error_bits' bitset indicates whether an * error occurred doing io to the corresponding region. */ -int dm_io(struct dm_io_request *io_req, unsigned num_regions, - struct dm_io_region *region, unsigned long *sync_error_bits); +int dm_io(struct dm_io_request *io_req, unsigned int num_regions, + struct dm_io_region *region, unsigned int long *sync_error_bits); #endif /* __KERNEL__ */ #endif /* _LINUX_DM_IO_H */ diff --git a/include/linux/dm-kcopyd.h b/include/linux/dm-kcopyd.h index 6b4ece85a2a0..51fb1af0b63e 100644 --- a/include/linux/dm-kcopyd.h +++ b/include/linux/dm-kcopyd.h @@ -24,11 +24,11 @@ #define DM_KCOPYD_WRITE_SEQ 2 struct dm_kcopyd_throttle { - unsigned throttle; - unsigned num_io_jobs; - unsigned io_period; - unsigned total_period; - unsigned last_jiffies; + unsigned int throttle; + unsigned int num_io_jobs; + unsigned int io_period; + unsigned int total_period; + unsigned int last_jiffies; }; /* @@ -61,12 +61,12 @@ void dm_kcopyd_client_flush(struct dm_kcopyd_client *kc); * read_err is a boolean, * write_err is a bitset, with 1 bit for each destination region */ -typedef void (*dm_kcopyd_notify_fn)(int read_err, unsigned long write_err, +typedef void (*dm_kcopyd_notify_fn)(int read_err, unsigned int long write_err, void *context); void dm_kcopyd_copy(struct dm_kcopyd_client *kc, struct dm_io_region *from, - unsigned num_dests, struct dm_io_region *dests, - unsigned flags, dm_kcopyd_notify_fn fn, void *context); + unsigned int num_dests, struct dm_io_region *dests, + unsigned int flags, dm_kcopyd_notify_fn fn, void *context); /* * Prepare a callback and submit it via the kcopyd thread. @@ -81,11 +81,11 @@ void dm_kcopyd_copy(struct dm_kcopyd_client *kc, struct dm_io_region *from, */ void *dm_kcopyd_prepare_callback(struct dm_kcopyd_client *kc, dm_kcopyd_notify_fn fn, void *context); -void dm_kcopyd_do_callback(void *job, int read_err, unsigned long write_err); +void dm_kcopyd_do_callback(void *job, int read_err, unsigned int long write_err); void dm_kcopyd_zero(struct dm_kcopyd_client *kc, - unsigned num_dests, struct dm_io_region *dests, - unsigned flags, dm_kcopyd_notify_fn fn, void *context); + unsigned int num_dests, struct dm_io_region *dests, + unsigned int flags, dm_kcopyd_notify_fn fn, void *context); #endif /* __KERNEL__ */ #endif /* _LINUX_DM_KCOPYD_H */ diff --git a/include/linux/dm-region-hash.h b/include/linux/dm-region-hash.h index 095541c59123..4086098a0d8e 100644 --- a/include/linux/dm-region-hash.h +++ b/include/linux/dm-region-hash.h @@ -38,7 +38,7 @@ struct dm_region_hash *dm_region_hash_create( struct bio_list *bios), void (*wakeup_workers)(void *context), void (*wakeup_all_recovery_waiters)(void *context), - sector_t target_begin, unsigned max_recovery, + sector_t target_begin, unsigned int max_recovery, struct dm_dirty_log *log, uint32_t region_size, region_t nr_regions); void dm_region_hash_destroy(struct dm_region_hash *rh); -- cgit v1.2.3 From 44bc08ed63db7a852bd1ba16611b700ee666091c Mon Sep 17 00:00:00 2001 From: Heinz Mauelshagen Date: Wed, 1 Feb 2023 21:51:04 +0100 Subject: dm: enclose complex macros into parentheses where possible Signed-off-by: Heinz Mauelshagen Signed-off-by: Mike Snitzer --- drivers/md/dm-log.c | 6 ++++-- include/linux/device-mapper.h | 3 +-- 2 files changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/md/dm-log.c b/drivers/md/dm-log.c index b57790e62484..7c3f30c58785 100644 --- a/drivers/md/dm-log.c +++ b/drivers/md/dm-log.c @@ -773,8 +773,10 @@ static region_t core_get_sync_count(struct dm_dirty_log *log) } #define DMEMIT_SYNC \ - if (lc->sync != DEFAULTSYNC) \ - DMEMIT("%ssync ", lc->sync == NOSYNC ? "no" : "") + do { \ + if (lc->sync != DEFAULTSYNC) \ + DMEMIT("%ssync ", lc->sync == NOSYNC ? "no" : ""); \ + } while (0); static int core_status(struct dm_dirty_log *log, status_type_t status, char *result, unsigned int maxlen) diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 9881e772b68c..aa68267bc36f 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -613,8 +613,7 @@ void dm_destroy_crypto_profile(struct blk_crypto_profile *profile); #define DMDEBUG(fmt, ...) pr_debug(DM_FMT(fmt), ##__VA_ARGS__) #define DMDEBUG_LIMIT(fmt, ...) pr_debug_ratelimited(DM_FMT(fmt), ##__VA_ARGS__) -#define DMEMIT(x...) sz += ((sz >= maxlen) ? \ - 0 : scnprintf(result + sz, maxlen - sz, x)) +#define DMEMIT(x...) (sz += ((sz >= maxlen) ? 0 : scnprintf(result + sz, maxlen - sz, x))) #define DMEMIT_TARGET_NAME_VERSION(y) \ DMEMIT("target_name=%s,target_version=%u.%u.%u", \ -- cgit v1.2.3 From a4a82ce3d24d4409143a7b7b980072ada6e20b2a Mon Sep 17 00:00:00 2001 From: Heinz Mauelshagen Date: Thu, 26 Jan 2023 15:48:30 +0100 Subject: dm: correct block comments format. Signed-off-by: Heinz Mauelshagen Signed-off-by: Mike Snitzer --- drivers/md/dm-bufio.c | 30 +++++++++----- drivers/md/dm-cache-metadata.c | 7 ++-- drivers/md/dm-cache-target.c | 58 +++++++++++++++++---------- drivers/md/dm-crypt.c | 7 ++-- drivers/md/dm-era-target.c | 58 ++++++++++++++++++--------- drivers/md/dm-io.c | 24 +++++++---- drivers/md/dm-ioctl.c | 33 +++++++++------ drivers/md/dm-kcopyd.c | 18 ++++++--- drivers/md/dm-log.c | 24 +++++++---- drivers/md/dm-mpath.c | 33 +++++++++------ drivers/md/dm-ps-round-robin.c | 13 +++--- drivers/md/dm-raid.c | 12 +++--- drivers/md/dm-raid1.c | 44 ++++++++++++-------- drivers/md/dm-region-hash.c | 6 ++- drivers/md/dm-snap-persistent.c | 6 ++- drivers/md/dm-snap-transient.c | 6 ++- drivers/md/dm-snap.c | 7 ++-- drivers/md/dm-thin-metadata.c | 20 +++++---- drivers/md/dm-thin.c | 24 +++++++---- drivers/md/dm.c | 12 ++++-- drivers/md/dm.h | 12 ++++-- drivers/md/persistent-data/dm-block-manager.c | 6 ++- drivers/md/persistent-data/dm-btree.c | 6 ++- include/linux/device-mapper.h | 18 ++++++--- include/linux/dm-dirty-log.h | 2 +- include/linux/dm-region-hash.h | 6 ++- 26 files changed, 315 insertions(+), 177 deletions(-) (limited to 'include/linux') diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index 089a7892bd5d..8f600e9cb8d3 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -259,9 +259,11 @@ static void buffer_record_stack(struct dm_buffer *b) } #endif -/*---------------------------------------------------------------- +/* + *---------------------------------------------------------------- * A red/black tree acts as an index for all the buffers. - *--------------------------------------------------------------*/ + *---------------------------------------------------------------- + */ static struct dm_buffer *__find(struct dm_bufio_client *c, sector_t block) { struct rb_node *n = c->buffer_tree.rb_node; @@ -562,7 +564,8 @@ static void __relink_lru(struct dm_buffer *b, int dirty) b->last_accessed = jiffies; } -/*---------------------------------------------------------------- +/* + *-------------------------------------------------------------------------- * Submit I/O on the buffer. * * Bio interface is faster but it has some problems: @@ -578,7 +581,8 @@ static void __relink_lru(struct dm_buffer *b, int dirty) * rejects the bio because it is too large, use dm-io layer to do the I/O. * The dm-io layer splits the I/O into multiple requests, avoiding the above * shortcomings. - *--------------------------------------------------------------*/ + *-------------------------------------------------------------------------- + */ /* * dm-io completion routine. It just calls b->bio.bi_end_io, pretending @@ -717,9 +721,11 @@ static void submit_io(struct dm_buffer *b, enum req_op op, use_dmio(b, op, sector, n_sectors, offset); } -/*---------------------------------------------------------------- +/* + *-------------------------------------------------------------- * Writing dirty buffers - *--------------------------------------------------------------*/ + *-------------------------------------------------------------- + */ /* * The endio routine for write. @@ -999,9 +1005,11 @@ static void __check_watermark(struct dm_bufio_client *c, __write_dirty_buffers_async(c, 1, write_list); } -/*---------------------------------------------------------------- +/* + *-------------------------------------------------------------- * Getting a buffer - *--------------------------------------------------------------*/ + *-------------------------------------------------------------- + */ static struct dm_buffer *__bufio_new(struct dm_bufio_client *c, sector_t block, enum new_flag nf, int *need_submit, @@ -2060,9 +2068,11 @@ static void work_fn(struct work_struct *w) DM_BUFIO_WORK_TIMER_SECS * HZ); } -/*---------------------------------------------------------------- +/* + *-------------------------------------------------------------- * Module setup - *--------------------------------------------------------------*/ + *-------------------------------------------------------------- + */ /* * This is called only once for the whole dm_bufio module. diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c index f6817a371ddb..692d292f876f 100644 --- a/drivers/md/dm-cache-metadata.c +++ b/drivers/md/dm-cache-metadata.c @@ -163,10 +163,11 @@ struct dm_cache_metadata { struct dm_bitset_cursor dirty_cursor; }; -/*------------------------------------------------------------------- +/* + *----------------------------------------------------------------- * superblock validator - *-----------------------------------------------------------------*/ - + *----------------------------------------------------------------- + */ #define SUPERBLOCK_CSUM_XOR 9031977 static void sb_prepare_for_write(struct dm_block_validator *v, diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index 4733105a130f..bb511cb89f83 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -525,9 +525,11 @@ static unsigned int lock_level(struct bio *bio) READ_WRITE_LOCK_LEVEL; } -/*---------------------------------------------------------------- +/* + *-------------------------------------------------------------- * Per bio data - *--------------------------------------------------------------*/ + *-------------------------------------------------------------- + */ static struct per_bio_data *get_per_bio_data(struct bio *bio) { @@ -706,9 +708,11 @@ static bool is_discarded_oblock(struct cache *cache, dm_oblock_t b) return r; } -/*---------------------------------------------------------------- +/* + * ------------------------------------------------------------- * Remapping - *--------------------------------------------------------------*/ + *-------------------------------------------------------------- + */ static void remap_to_origin(struct cache *cache, struct bio *bio) { bio_set_dev(bio, cache->origin_dev->bdev); @@ -834,9 +838,11 @@ static void remap_to_origin_and_cache(struct cache *cache, struct bio *bio, remap_to_cache(cache, bio, cblock); } -/*---------------------------------------------------------------- +/* + *-------------------------------------------------------------- * Failure modes - *--------------------------------------------------------------*/ + *-------------------------------------------------------------- + */ static enum cache_metadata_mode get_cache_mode(struct cache *cache) { return cache->features.mode; @@ -973,13 +979,14 @@ static void update_stats(struct cache_stats *stats, enum policy_operation op) } } -/*---------------------------------------------------------------- +/* + *--------------------------------------------------------------------- * Migration processing * * Migration covers moving data from the origin device to the cache, or * vice versa. - *--------------------------------------------------------------*/ - + *--------------------------------------------------------------------- + */ static void inc_io_migrations(struct cache *cache) { atomic_inc(&cache->nr_io_migrations); @@ -1431,9 +1438,11 @@ static int mg_start(struct cache *cache, struct policy_work *op, struct bio *bio return mg_lock_writes(mg); } -/*---------------------------------------------------------------- +/* + *-------------------------------------------------------------- * invalidation processing - *--------------------------------------------------------------*/ + *-------------------------------------------------------------- + */ static void invalidate_complete(struct dm_cache_migration *mg, bool success) { @@ -1554,9 +1563,11 @@ static int invalidate_start(struct cache *cache, dm_cblock_t cblock, return invalidate_lock(mg); } -/*---------------------------------------------------------------- +/* + *-------------------------------------------------------------- * bio processing - *--------------------------------------------------------------*/ + *-------------------------------------------------------------- + */ enum busy { IDLE, @@ -1764,9 +1775,11 @@ static bool process_discard_bio(struct cache *cache, struct bio *bio) { dm_dblock_t b, e; - // FIXME: do we need to lock the region? Or can we just assume the - // user wont be so foolish as to issue discard concurrently with - // other IO? + /* + * FIXME: do we need to lock the region? Or can we just assume the + * user wont be so foolish as to issue discard concurrently with + * other IO? + */ calc_discard_block_range(cache, bio, &b, &e); while (b != e) { set_discard(cache, b); @@ -1812,10 +1825,11 @@ static void process_deferred_bios(struct work_struct *ws) schedule_commit(&cache->committer); } -/*---------------------------------------------------------------- +/* + *-------------------------------------------------------------- * Main worker loop - *--------------------------------------------------------------*/ - + *-------------------------------------------------------------- + */ static void requeue_deferred_bios(struct cache *cache) { struct bio *bio; @@ -1871,9 +1885,11 @@ static void check_migrations(struct work_struct *ws) } } -/*---------------------------------------------------------------- +/* + *-------------------------------------------------------------- * Target methods - *--------------------------------------------------------------*/ + *-------------------------------------------------------------- + */ /* * This function gets called on the error paths of the constructor, so we diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 47456fb71003..13ad9cf97170 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -364,9 +364,10 @@ static int crypt_iv_benbi_ctr(struct crypt_config *cc, struct dm_target *ti, bs = crypto_skcipher_blocksize(any_tfm(cc)); log = ilog2(bs); - /* we need to calculate how far we must shift the sector count - * to get the cipher block count, we use this shift in _gen */ - + /* + * We need to calculate how far we must shift the sector count + * to get the cipher block count, we use this shift in _gen. + */ if (1 << log != bs) { ti->error = "cypher blocksize is not a power of 2"; return -EINVAL; diff --git a/drivers/md/dm-era-target.c b/drivers/md/dm-era-target.c index a96290103cca..c4fd79135794 100644 --- a/drivers/md/dm-era-target.c +++ b/drivers/md/dm-era-target.c @@ -22,9 +22,11 @@ #define INVALID_WRITESET_ROOT SUPERBLOCK_LOCATION #define MIN_BLOCK_SIZE 8 -/*---------------------------------------------------------------- +/* + *-------------------------------------------------------------- * Writeset - *--------------------------------------------------------------*/ + *-------------------------------------------------------------- + */ struct writeset_metadata { uint32_t nr_bits; dm_block_t root; @@ -148,9 +150,11 @@ static int writeset_test_and_set(struct dm_disk_bitset *info, return 1; } -/*---------------------------------------------------------------- +/* + *-------------------------------------------------------------- * On disk metadata layout - *--------------------------------------------------------------*/ + *-------------------------------------------------------------- + */ #define SPACE_MAP_ROOT_SIZE 128 #define UUID_LEN 16 @@ -186,9 +190,11 @@ struct superblock_disk { __le64 metadata_snap; } __packed; -/*---------------------------------------------------------------- +/* + *-------------------------------------------------------------- * Superblock validation - *--------------------------------------------------------------*/ + *-------------------------------------------------------------- + */ static void sb_prepare_for_write(struct dm_block_validator *v, struct dm_block *b, size_t sb_block_size) @@ -252,9 +258,11 @@ static struct dm_block_validator sb_validator = { .check = sb_check }; -/*---------------------------------------------------------------- +/* + *-------------------------------------------------------------- * Low level metadata handling - *--------------------------------------------------------------*/ + *-------------------------------------------------------------- + */ #define DM_ERA_METADATA_BLOCK_SIZE 4096 #define ERA_MAX_CONCURRENT_LOCKS 5 @@ -658,13 +666,15 @@ static void swap_writeset(struct era_metadata *md, struct writeset *new_writeset synchronize_rcu(); } -/*---------------------------------------------------------------- +/* + *------------------------------------------------------------------------ * Writesets get 'digested' into the main era array. * * We're using a coroutine here so the worker thread can do the digestion, * thus avoiding synchronisation of the metadata. Digesting a whole * writeset in one go would cause too much latency. - *--------------------------------------------------------------*/ + *------------------------------------------------------------------------ + */ struct digest { uint32_t era; unsigned int nr_bits, current_bit; @@ -784,10 +794,12 @@ static int metadata_digest_start(struct era_metadata *md, struct digest *d) return 0; } -/*---------------------------------------------------------------- - * High level metadata interface. Target methods should use these, and not - * the lower level ones. - *--------------------------------------------------------------*/ +/* + *----------------------------------------------------------------- + * High level metadata interface. Target methods should use these, + * and not the lower level ones. + *----------------------------------------------------------------- + */ static struct era_metadata *metadata_open(struct block_device *bdev, sector_t block_size, bool may_format) @@ -1189,9 +1201,11 @@ struct rpc { struct completion complete; }; -/*---------------------------------------------------------------- +/* + *--------------------------------------------------------------- * Remapping. - *---------------------------------------------------------------*/ + *--------------------------------------------------------------- + */ static bool block_size_is_power_of_two(struct era *era) { return era->sectors_per_block_shift >= 0; @@ -1214,9 +1228,11 @@ static void remap_to_origin(struct era *era, struct bio *bio) bio_set_dev(bio, era->origin_dev->bdev); } -/*---------------------------------------------------------------- +/* + *-------------------------------------------------------------- * Worker thread - *--------------------------------------------------------------*/ + *-------------------------------------------------------------- + */ static void wake_worker(struct era *era) { if (!atomic_read(&era->suspended)) @@ -1403,9 +1419,11 @@ static void stop_worker(struct era *era) drain_workqueue(era->wq); } -/*---------------------------------------------------------------- +/* + *-------------------------------------------------------------- * Target methods - *--------------------------------------------------------------*/ + *-------------------------------------------------------------- + */ static void era_destroy(struct era *era) { if (era->md) diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c index eda61cfab312..628c5a13d010 100644 --- a/drivers/md/dm-io.c +++ b/drivers/md/dm-io.c @@ -81,13 +81,15 @@ void dm_io_client_destroy(struct dm_io_client *client) } EXPORT_SYMBOL(dm_io_client_destroy); -/*----------------------------------------------------------------- +/* + *------------------------------------------------------------------- * We need to keep track of which region a bio is doing io for. * To avoid a memory allocation to store just 5 or 6 bits, we * ensure the 'struct io' pointer is aligned so enough low bits are * always zero and then combine it with the region number directly in * bi_private. - *---------------------------------------------------------------*/ + *------------------------------------------------------------------- + */ static void store_io_and_region_in_bio(struct bio *bio, struct io *io, unsigned int region) { @@ -108,10 +110,12 @@ static void retrieve_io_and_region_from_bio(struct bio *bio, struct io **io, *region = val & (DM_IO_MAX_REGIONS - 1); } -/*----------------------------------------------------------------- +/* + *-------------------------------------------------------------- * We need an io object to keep track of the number of bios that * have been dispatched for a particular io. - *---------------------------------------------------------------*/ + *-------------------------------------------------------------- + */ static void complete_io(struct io *io) { unsigned long error_bits = io->error_bits; @@ -155,10 +159,12 @@ static void endio(struct bio *bio) dec_count(io, region, error); } -/*----------------------------------------------------------------- +/* + *-------------------------------------------------------------- * These little objects provide an abstraction for getting a new * destination page for io. - *---------------------------------------------------------------*/ + *-------------------------------------------------------------- + */ struct dpages { void (*get_page)(struct dpages *dp, struct page **p, unsigned long *len, unsigned int *offset); @@ -291,9 +297,11 @@ static void km_dp_init(struct dpages *dp, void *data) dp->context_ptr = data; } -/*----------------------------------------------------------------- +/* + *--------------------------------------------------------------- * IO routines that accept a list of pages. - *---------------------------------------------------------------*/ + *--------------------------------------------------------------- + */ static void do_region(const blk_opf_t opf, unsigned int region, struct dm_io_region *where, struct dpages *dp, struct io *io) diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c index 2dd2fa18afb6..f6e880a0e00c 100644 --- a/drivers/md/dm-ioctl.c +++ b/drivers/md/dm-ioctl.c @@ -35,10 +35,12 @@ struct dm_file { volatile unsigned int global_event_nr; }; -/*----------------------------------------------------------------- +/* + *--------------------------------------------------------------- * The ioctl interface needs to be able to look up devices by * name or uuid. - *---------------------------------------------------------------*/ + *--------------------------------------------------------------- + */ struct hash_cell { struct rb_node name_node; struct rb_node uuid_node; @@ -79,9 +81,11 @@ static void dm_hash_exit(void) dm_hash_remove_all(false, false, false); } -/*----------------------------------------------------------------- +/* + *--------------------------------------------------------------- * Code for looking up a device by name - *---------------------------------------------------------------*/ + *--------------------------------------------------------------- + */ static struct hash_cell *__get_name_cell(const char *str) { struct rb_node *n = name_rb_tree.rb_node; @@ -196,9 +200,11 @@ static struct hash_cell *__get_dev_cell(uint64_t dev) return hc; } -/*----------------------------------------------------------------- +/* + *--------------------------------------------------------------- * Inserting, removing and renaming a device. - *---------------------------------------------------------------*/ + *--------------------------------------------------------------- + */ static struct hash_cell *alloc_cell(const char *name, const char *uuid, struct mapped_device *md) { @@ -501,9 +507,11 @@ void dm_deferred_remove(void) dm_hash_remove_all(true, false, true); } -/*----------------------------------------------------------------- +/* + *--------------------------------------------------------------- * Implementation of the ioctl commands - *---------------------------------------------------------------*/ + *--------------------------------------------------------------- + */ /* * All the ioctl commands get dispatched to functions with this * prototype. @@ -1764,10 +1772,11 @@ static int target_message(struct file *filp, struct dm_ioctl *param, size_t para #define IOCTL_FLAGS_NO_PARAMS 1 #define IOCTL_FLAGS_ISSUE_GLOBAL_EVENT 2 -/*----------------------------------------------------------------- - * Implementation of open/close/ioctl on the special char - * device. - *---------------------------------------------------------------*/ +/* + *--------------------------------------------------------------- + * Implementation of open/close/ioctl on the special char device. + *--------------------------------------------------------------- + */ static ioctl_fn lookup_ioctl(unsigned int cmd, int *ioctl_flags) { static const struct { diff --git a/drivers/md/dm-kcopyd.c b/drivers/md/dm-kcopyd.c index 25d2f1279466..aecf9673b51a 100644 --- a/drivers/md/dm-kcopyd.c +++ b/drivers/md/dm-kcopyd.c @@ -51,10 +51,12 @@ static unsigned int dm_get_kcopyd_subjob_size(void) return sub_job_size_kb << 1; } -/*----------------------------------------------------------------- +/* + *---------------------------------------------------------------- * Each kcopyd client has its own little pool of preallocated * pages for kcopyd io. - *---------------------------------------------------------------*/ + *--------------------------------------------------------------- + */ struct dm_kcopyd_client { struct page_list *pages; unsigned int nr_reserved_pages; @@ -334,11 +336,13 @@ static void client_free_pages(struct dm_kcopyd_client *kc) kc->nr_free_pages = kc->nr_reserved_pages = 0; } -/*----------------------------------------------------------------- +/* + *--------------------------------------------------------------- * kcopyd_jobs need to be allocated by the *clients* of kcopyd, * for this reason we use a mempool to prevent the client from * ever having to do io (which could cause a deadlock). - *---------------------------------------------------------------*/ + *--------------------------------------------------------------- + */ struct kcopyd_job { struct dm_kcopyd_client *kc; struct list_head list; @@ -901,9 +905,11 @@ int kcopyd_cancel(struct kcopyd_job *job, int block) } #endif /* 0 */ -/*----------------------------------------------------------------- +/* + *--------------------------------------------------------------- * Client setup - *---------------------------------------------------------------*/ + *--------------------------------------------------------------- + */ struct dm_kcopyd_client *dm_kcopyd_client_create(struct dm_kcopyd_throttle *throttle) { int r; diff --git a/drivers/md/dm-log.c b/drivers/md/dm-log.c index fe7b24a45812..aea95bc18719 100644 --- a/drivers/md/dm-log.c +++ b/drivers/md/dm-log.c @@ -183,10 +183,12 @@ void dm_dirty_log_destroy(struct dm_dirty_log *log) } EXPORT_SYMBOL(dm_dirty_log_destroy); -/*----------------------------------------------------------------- +/* + *--------------------------------------------------------------- * Persistent and core logs share a lot of their implementation. * FIXME: need a reload method to be called from a resume - *---------------------------------------------------------------*/ + *--------------------------------------------------------------- + */ /* * Magic for persistent mirrors: "MiRr" */ @@ -275,9 +277,11 @@ static inline void log_clear_bit(struct log_c *l, l->touched_dirtied = 1; } -/*---------------------------------------------------------------- +/* + *--------------------------------------------------------------- * Header IO - *--------------------------------------------------------------*/ + *-------------------------------------------------------------- + */ static void header_to_disk(struct log_header_core *core, struct log_header_disk *disk) { disk->magic = cpu_to_le32(core->magic); @@ -353,11 +357,13 @@ static int _check_region_size(struct dm_target *ti, uint32_t region_size) return 1; } -/*---------------------------------------------------------------- +/* + *-------------------------------------------------------------- * core log constructor/destructor * * argv contains region_size followed optionally by [no]sync - *--------------------------------------------------------------*/ + *-------------------------------------------------------------- + */ #define BYTE_SHIFT 3 static int create_log_context(struct dm_dirty_log *log, struct dm_target *ti, unsigned int argc, char **argv, @@ -532,11 +538,13 @@ static void core_dtr(struct dm_dirty_log *log) destroy_log_context(lc); } -/*---------------------------------------------------------------- +/* + *--------------------------------------------------------------------- * disk log constructor/destructor * * argv contains log_device region_size followed optionally by [no]sync - *--------------------------------------------------------------*/ + *--------------------------------------------------------------------- + */ static int disk_ctr(struct dm_dirty_log *log, struct dm_target *ti, unsigned int argc, char **argv) { diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index 18df7ff98203..d6161a9e8c00 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -118,10 +118,11 @@ static void activate_path_work(struct work_struct *work); static void process_queued_bios(struct work_struct *work); static void queue_if_no_path_timeout_work(struct timer_list *t); -/*----------------------------------------------- +/* + *----------------------------------------------- * Multipath state flags. - *-----------------------------------------------*/ - + *----------------------------------------------- + */ #define MPATHF_QUEUE_IO 0 /* Must we queue all I/O? */ #define MPATHF_QUEUE_IF_NO_PATH 1 /* Queue I/O if last path fails? */ #define MPATHF_SAVED_QUEUE_IF_NO_PATH 2 /* Saved state during suspension */ @@ -144,10 +145,11 @@ static bool mpath_double_check_test_bit(int MPATHF_bit, struct multipath *m) return r; } -/*----------------------------------------------- +/* + *----------------------------------------------- * Allocation routines - *-----------------------------------------------*/ - + *----------------------------------------------- + */ static struct pgpath *alloc_pgpath(void) { struct pgpath *pgpath = kzalloc(sizeof(*pgpath), GFP_KERNEL); @@ -303,10 +305,11 @@ static void multipath_init_per_bio_data(struct bio *bio, struct dm_mpath_io **mp dm_bio_record(bio_details, bio); } -/*----------------------------------------------- +/* + *----------------------------------------------- * Path selection - *-----------------------------------------------*/ - + *----------------------------------------------- + */ static int __pg_init_all_paths(struct multipath *m) { struct pgpath *pgpath; @@ -826,7 +829,8 @@ static void trigger_event(struct work_struct *work) dm_table_event(m->ti->table); } -/*----------------------------------------------------------------- +/* + *--------------------------------------------------------------- * Constructor/argument parsing: * <#multipath feature args> []* * <#hw_handler args> [hw_handler []*] @@ -835,7 +839,8 @@ static void trigger_event(struct work_struct *work) * [ <#selector args> []* * <#paths> <#per-path selector args> * [ []* ]+ ]+ - *---------------------------------------------------------------*/ + *--------------------------------------------------------------- + */ static int parse_path_selector(struct dm_arg_set *as, struct priority_group *pg, struct dm_target *ti) { @@ -2169,9 +2174,11 @@ static int multipath_busy(struct dm_target *ti) return busy; } -/*----------------------------------------------------------------- +/* + *--------------------------------------------------------------- * Module setup - *---------------------------------------------------------------*/ + *--------------------------------------------------------------- + */ static struct target_type multipath_target = { .name = "multipath", .version = {1, 14, 0}, diff --git a/drivers/md/dm-ps-round-robin.c b/drivers/md/dm-ps-round-robin.c index 7c2dda9e871c..0f04b673597a 100644 --- a/drivers/md/dm-ps-round-robin.c +++ b/drivers/md/dm-ps-round-robin.c @@ -21,9 +21,11 @@ #define RR_MIN_IO 1 #define RR_VERSION "1.2.0" -/*----------------------------------------------------------------- +/* + *--------------------------------------------------------------- * Path-handling code, paths are held in lists - *---------------------------------------------------------------*/ + *--------------------------------------------------------------- + */ struct path_info { struct list_head list; struct dm_path *path; @@ -40,10 +42,11 @@ static void free_paths(struct list_head *paths) } } -/*----------------------------------------------------------------- +/* + *--------------------------------------------------------------- * Round-robin selector - *---------------------------------------------------------------*/ - + *--------------------------------------------------------------- + */ struct selector { struct list_head valid_paths; struct list_head invalid_paths; diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 6a2a985106d4..de646eca6de0 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -3184,12 +3184,12 @@ static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv) /* Out-of-place space has to be available to allow for a reshape unless raid1! */ if (reshape_sectors || rs_is_raid1(rs)) { /* - * We can only prepare for a reshape here, because the - * raid set needs to run to provide the repective reshape - * check functions via its MD personality instance. - * - * So do the reshape check after md_run() succeeded. - */ + * We can only prepare for a reshape here, because the + * raid set needs to run to provide the repective reshape + * check functions via its MD personality instance. + * + * So do the reshape check after md_run() succeeded. + */ r = rs_prepare_reshape(rs); if (r) goto bad; diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c index 86a0ff713b5b..640f199cf51c 100644 --- a/drivers/md/dm-raid1.c +++ b/drivers/md/dm-raid1.c @@ -33,9 +33,11 @@ static DECLARE_WAIT_QUEUE_HEAD(_kmirrord_recovery_stopped); -/*----------------------------------------------------------------- +/* + *--------------------------------------------------------------- * Mirror set structures. - *---------------------------------------------------------------*/ + *--------------------------------------------------------------- + */ enum dm_raid1_error { DM_RAID1_WRITE_ERROR, DM_RAID1_FLUSH_ERROR, @@ -286,13 +288,15 @@ static int mirror_flush(struct dm_target *ti) return 0; } -/*----------------------------------------------------------------- +/* + *--------------------------------------------------------------- * Recovery. * * When a mirror is first activated we may find that some regions * are in the no-sync state. We have to recover these by * recopying from the default mirror to all the others. - *---------------------------------------------------------------*/ + *--------------------------------------------------------------- + */ static void recovery_complete(int read_err, unsigned long write_err, void *context) { @@ -409,9 +413,11 @@ static void do_recovery(struct mirror_set *ms) } } -/*----------------------------------------------------------------- +/* + *--------------------------------------------------------------- * Reads - *---------------------------------------------------------------*/ + *--------------------------------------------------------------- + */ static struct mirror *choose_mirror(struct mirror_set *ms, sector_t sector) { struct mirror *m = get_default_mirror(ms); @@ -499,9 +505,11 @@ static void hold_bio(struct mirror_set *ms, struct bio *bio) spin_unlock_irq(&ms->lock); } -/*----------------------------------------------------------------- +/* + *--------------------------------------------------------------- * Reads - *---------------------------------------------------------------*/ + *--------------------------------------------------------------- + */ static void read_callback(unsigned long error, void *context) { struct bio *bio = context; @@ -580,7 +588,8 @@ static void do_reads(struct mirror_set *ms, struct bio_list *reads) } } -/*----------------------------------------------------------------- +/* + *--------------------------------------------------------------------- * Writes. * * We do different things with the write io depending on the @@ -589,9 +598,8 @@ static void do_reads(struct mirror_set *ms, struct bio_list *reads) * SYNC: increment pending, use kcopyd to write to *all* mirrors * RECOVERING: delay the io until recovery completes * NOSYNC: increment pending, just write to the default mirror - *---------------------------------------------------------------*/ - - + *--------------------------------------------------------------------- + */ static void write_callback(unsigned long error, void *context) { unsigned int i; @@ -843,9 +851,11 @@ static void trigger_event(struct work_struct *work) dm_table_event(ms->ti->table); } -/*----------------------------------------------------------------- +/* + *--------------------------------------------------------------- * kmirrord - *---------------------------------------------------------------*/ + *--------------------------------------------------------------- + */ static void do_mirror(struct work_struct *work) { struct mirror_set *ms = container_of(work, struct mirror_set, @@ -869,9 +879,11 @@ static void do_mirror(struct work_struct *work) do_failures(ms, &failures); } -/*----------------------------------------------------------------- +/* + *--------------------------------------------------------------- * Target functions - *---------------------------------------------------------------*/ + *--------------------------------------------------------------- + */ static struct mirror_set *alloc_context(unsigned int nr_mirrors, uint32_t region_size, struct dm_target *ti, diff --git a/drivers/md/dm-region-hash.c b/drivers/md/dm-region-hash.c index 462cb24ba92e..852cfa37d48a 100644 --- a/drivers/md/dm-region-hash.c +++ b/drivers/md/dm-region-hash.c @@ -19,7 +19,8 @@ #define DM_MSG_PREFIX "region hash" -/*----------------------------------------------------------------- +/* + *------------------------------------------------------------------ * Region hash * * The mirror splits itself up into discrete regions. Each @@ -54,7 +55,8 @@ * lists in the region_hash, with the 'state', 'list' and * 'delayed_bios' fields of the regions. This is used from irq * context, so all other uses will have to suspend local irqs. - *---------------------------------------------------------------*/ + *------------------------------------------------------------------ + */ struct dm_region_hash { uint32_t region_size; unsigned int region_shift; diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c index ce68143fe30b..fde50b014f3a 100644 --- a/drivers/md/dm-snap-persistent.c +++ b/drivers/md/dm-snap-persistent.c @@ -22,10 +22,12 @@ #define DM_PREFETCH_CHUNKS 12 -/*----------------------------------------------------------------- +/* + *--------------------------------------------------------------- * Persistent snapshots, by persistent we mean that the snapshot * will survive a reboot. - *---------------------------------------------------------------*/ + *--------------------------------------------------------------- + */ /* * We need to store a record of which parts of the origin have diff --git a/drivers/md/dm-snap-transient.c b/drivers/md/dm-snap-transient.c index 122257405dcc..346c2105fab7 100644 --- a/drivers/md/dm-snap-transient.c +++ b/drivers/md/dm-snap-transient.c @@ -17,9 +17,11 @@ #define DM_MSG_PREFIX "transient snapshot" -/*----------------------------------------------------------------- +/* + *--------------------------------------------------------------- * Implementation of the store for non-persistent snapshots. - *---------------------------------------------------------------*/ + *--------------------------------------------------------------- + */ struct transient_c { sector_t next_free; }; diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c index f61622d46c72..0887e0fe3268 100644 --- a/drivers/md/dm-snap.c +++ b/drivers/md/dm-snap.c @@ -2420,10 +2420,11 @@ static void snapshot_io_hints(struct dm_target *ti, struct queue_limits *limits) } } -/*----------------------------------------------------------------- +/* + *--------------------------------------------------------------- * Origin methods - *---------------------------------------------------------------*/ - + *--------------------------------------------------------------- + */ /* * If no exceptions need creating, DM_MAPIO_REMAPPED is returned and any * supplied bio was ignored. The caller may submit it immediately. diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c index f5f088aafa74..12289a95bc6d 100644 --- a/drivers/md/dm-thin-metadata.c +++ b/drivers/md/dm-thin-metadata.c @@ -15,7 +15,8 @@ #include #include -/*-------------------------------------------------------------------------- +/* + *-------------------------------------------------------------------------- * As far as the metadata goes, there is: * * - A superblock in block zero, taking up fewer than 512 bytes for @@ -71,7 +72,8 @@ * * All metadata io is in THIN_METADATA_BLOCK_SIZE sized/aligned chunks * from the block manager. - *--------------------------------------------------------------------------*/ + *-------------------------------------------------------------------------- + */ #define DM_MSG_PREFIX "thin metadata" @@ -240,10 +242,11 @@ struct dm_thin_device { uint32_t snapshotted_time; }; -/*---------------------------------------------------------------- +/* + *-------------------------------------------------------------- * superblock validator - *--------------------------------------------------------------*/ - + *-------------------------------------------------------------- + */ #define SUPERBLOCK_CSUM_XOR 160774 static void sb_prepare_for_write(struct dm_block_validator *v, @@ -297,10 +300,11 @@ static struct dm_block_validator sb_validator = { .check = sb_check }; -/*---------------------------------------------------------------- +/* + *-------------------------------------------------------------- * Methods for the btree value types - *--------------------------------------------------------------*/ - + *-------------------------------------------------------------- + */ static uint64_t pack_block_time(dm_block_t b, uint32_t t) { return (b << 24) | t; diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index c5a15e8d8cc3..1dc3476f6791 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -2800,9 +2800,11 @@ static void requeue_bios(struct pool *pool) rcu_read_unlock(); } -/*---------------------------------------------------------------- +/* + *-------------------------------------------------------------- * Binding of control targets to a pool object - *--------------------------------------------------------------*/ + *-------------------------------------------------------------- + */ static bool is_factor(sector_t block_size, uint32_t n) { return !sector_div(block_size, n); @@ -2866,9 +2868,11 @@ static void unbind_control_target(struct pool *pool, struct dm_target *ti) pool->ti = NULL; } -/*---------------------------------------------------------------- +/* + *-------------------------------------------------------------- * Pool creation - *--------------------------------------------------------------*/ + *-------------------------------------------------------------- + */ /* Initialize pool features. */ static void pool_features_init(struct pool_features *pf) { @@ -3092,9 +3096,11 @@ static struct pool *__pool_find(struct mapped_device *pool_md, return pool; } -/*---------------------------------------------------------------- +/* + *-------------------------------------------------------------- * Pool target methods - *--------------------------------------------------------------*/ + *-------------------------------------------------------------- + */ static void pool_dtr(struct dm_target *ti) { struct pool_c *pt = ti->private; @@ -4096,9 +4102,11 @@ static struct target_type pool_target = { .io_hints = pool_io_hints, }; -/*---------------------------------------------------------------- +/* + *-------------------------------------------------------------- * Thin target methods - *--------------------------------------------------------------*/ + *-------------------------------------------------------------- + */ static void thin_get(struct thin_c *tc) { refcount_inc(&tc->refcount); diff --git a/drivers/md/dm.c b/drivers/md/dm.c index b9273c99d748..eee4afb0ca98 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1873,9 +1873,11 @@ static int dm_poll_bio(struct bio *bio, struct io_comp_batch *iob, return 1; } -/*----------------------------------------------------------------- +/* + *--------------------------------------------------------------- * An IDR is used to keep track of allocated minor numbers. - *---------------------------------------------------------------*/ + *--------------------------------------------------------------- + */ static void free_minor(int minor) { spin_lock(&_minor_lock); @@ -2960,9 +2962,11 @@ done: } EXPORT_SYMBOL_GPL(dm_internal_resume_fast); -/*----------------------------------------------------------------- +/* + *--------------------------------------------------------------- * Event notification. - *---------------------------------------------------------------*/ + *--------------------------------------------------------------- + */ int dm_kobject_uevent(struct mapped_device *md, enum kobject_action action, unsigned int cookie, bool need_resize_uevent) { diff --git a/drivers/md/dm.h b/drivers/md/dm.h index a7917df09caf..22eaed188907 100644 --- a/drivers/md/dm.h +++ b/drivers/md/dm.h @@ -48,9 +48,11 @@ struct dm_md_mempools; struct dm_target_io; struct dm_io; -/*----------------------------------------------------------------- +/* + *--------------------------------------------------------------- * Internal table functions. - *---------------------------------------------------------------*/ + *--------------------------------------------------------------- + */ void dm_table_event_callback(struct dm_table *t, void (*fn)(void *), void *context); struct dm_target *dm_table_find_target(struct dm_table *t, sector_t sector); @@ -119,9 +121,11 @@ static inline int dm_zone_map_bio(struct dm_target_io *tio) } #endif -/*----------------------------------------------------------------- +/* + *--------------------------------------------------------------- * A registry of target types. - *---------------------------------------------------------------*/ + *--------------------------------------------------------------- + */ int dm_target_init(void); void dm_target_exit(void); struct target_type *dm_get_target_type(const char *name); diff --git a/drivers/md/persistent-data/dm-block-manager.c b/drivers/md/persistent-data/dm-block-manager.c index af234c1176a7..6200b0932135 100644 --- a/drivers/md/persistent-data/dm-block-manager.c +++ b/drivers/md/persistent-data/dm-block-manager.c @@ -368,9 +368,11 @@ static void dm_block_manager_write_callback(struct dm_buffer *buf) } } -/*---------------------------------------------------------------- +/* + * ------------------------------------------------------------- * Public interface - *--------------------------------------------------------------*/ + *-------------------------------------------------------------- + */ struct dm_block_manager { struct dm_bufio_client *bufio; bool read_only:1; diff --git a/drivers/md/persistent-data/dm-btree.c b/drivers/md/persistent-data/dm-btree.c index 67cf4c2ca258..0283d3c2b16f 100644 --- a/drivers/md/persistent-data/dm-btree.c +++ b/drivers/md/persistent-data/dm-btree.c @@ -14,9 +14,11 @@ #define DM_MSG_PREFIX "btree" -/*---------------------------------------------------------------- +/* + *-------------------------------------------------------------- * Array manipulation - *--------------------------------------------------------------*/ + *-------------------------------------------------------------- + */ static void memcpy_disk(void *dest, const void *src, size_t len) __dm_written_to_disk(src) { diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index aa68267bc36f..7975483816e4 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -434,10 +434,12 @@ const char *dm_shift_arg(struct dm_arg_set *as); */ void dm_consume_args(struct dm_arg_set *as, unsigned int num_args); -/*----------------------------------------------------------------- +/* + *---------------------------------------------------------------- * Functions for creating and manipulating mapped devices. * Drop the reference with dm_put when you finish with the object. - *---------------------------------------------------------------*/ + *---------------------------------------------------------------- + */ /* * DM_ANY_MINOR chooses the next available minor number. @@ -518,9 +520,11 @@ struct queue_limits *dm_get_queue_limits(struct mapped_device *md); int dm_get_geometry(struct mapped_device *md, struct hd_geometry *geo); int dm_set_geometry(struct mapped_device *md, struct hd_geometry *geo); -/*----------------------------------------------------------------- +/* + *--------------------------------------------------------------- * Functions for manipulating device-mapper tables. - *---------------------------------------------------------------*/ + *--------------------------------------------------------------- + */ /* * First create an empty table. @@ -594,9 +598,11 @@ struct dm_table *dm_swap_table(struct mapped_device *md, */ void dm_destroy_crypto_profile(struct blk_crypto_profile *profile); -/*----------------------------------------------------------------- +/* + *--------------------------------------------------------------- * Macros. - *---------------------------------------------------------------*/ + *--------------------------------------------------------------- + */ #define DM_NAME "device-mapper" #define DM_FMT(fmt) DM_NAME ": " DM_MSG_PREFIX ": " fmt "\n" diff --git a/include/linux/dm-dirty-log.h b/include/linux/dm-dirty-log.h index a3eb7490d205..0b10faedb26a 100644 --- a/include/linux/dm-dirty-log.h +++ b/include/linux/dm-dirty-log.h @@ -97,7 +97,7 @@ struct dm_dirty_log_type { * Do not confuse this function with 'in_sync()', one * tells you if an area is synchronised, the other * assigns recovery work. - */ + */ int (*get_resync_work)(struct dm_dirty_log *log, region_t *region); /* diff --git a/include/linux/dm-region-hash.h b/include/linux/dm-region-hash.h index 4086098a0d8e..3079ed93dd2d 100644 --- a/include/linux/dm-region-hash.h +++ b/include/linux/dm-region-hash.h @@ -13,9 +13,11 @@ #include -/*----------------------------------------------------------------- +/* + *---------------------------------------------------------------- * Region hash - *----------------------------------------------------------------*/ + *---------------------------------------------------------------- + */ struct dm_region_hash; struct dm_region; -- cgit v1.2.3 From ade1229caed9433921b69e20bd6fadf1bba9558e Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 14 Feb 2023 15:01:21 +0100 Subject: dma-mapping: no need to pass a bus_type into get_arch_dma_ops() The get_arch_dma_ops() arch-specific function never does anything with the struct bus_type that is passed into it, so remove it entirely as it is not needed. Cc: Richard Henderson Cc: Ivan Kokshaysky Cc: Matt Turner Cc: Thomas Bogendoerfer Cc: "James E.J. Bottomley" Cc: Helge Deller Cc: "David S. Miller" Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: Dave Hansen Cc: x86@kernel.org Cc: "H. Peter Anvin" Cc: Marek Szyprowski Cc: Robin Murphy Cc: Konrad Rzeszutek Wilk Cc: linux-alpha@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: linux-ia64@vger.kernel.org Cc: linux-mips@vger.kernel.org Cc: linux-parisc@vger.kernel.org Cc: sparclinux@vger.kernel.org Cc: iommu@lists.linux.dev Cc: linux-arch@vger.kernel.org Acked-by: Christoph Hellwig Reviewed-by: Arnd Bergmann Link: https://lore.kernel.org/r/20230214140121.131859-1-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- arch/alpha/include/asm/dma-mapping.h | 2 +- arch/ia64/include/asm/dma-mapping.h | 2 +- arch/mips/include/asm/dma-mapping.h | 2 +- arch/parisc/include/asm/dma-mapping.h | 2 +- arch/sparc/include/asm/dma-mapping.h | 2 +- arch/x86/include/asm/dma-mapping.h | 2 +- include/asm-generic/dma-mapping.h | 2 +- include/linux/dma-map-ops.h | 2 +- 8 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/arch/alpha/include/asm/dma-mapping.h b/arch/alpha/include/asm/dma-mapping.h index 0ee6a5c99b16..6ce7e2041685 100644 --- a/arch/alpha/include/asm/dma-mapping.h +++ b/arch/alpha/include/asm/dma-mapping.h @@ -4,7 +4,7 @@ extern const struct dma_map_ops alpha_pci_ops; -static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus) +static inline const struct dma_map_ops *get_arch_dma_ops(void) { #ifdef CONFIG_ALPHA_JENSEN return NULL; diff --git a/arch/ia64/include/asm/dma-mapping.h b/arch/ia64/include/asm/dma-mapping.h index a5d9d788eede..af6fa8e1597c 100644 --- a/arch/ia64/include/asm/dma-mapping.h +++ b/arch/ia64/include/asm/dma-mapping.h @@ -8,7 +8,7 @@ */ extern const struct dma_map_ops *dma_ops; -static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus) +static inline const struct dma_map_ops *get_arch_dma_ops(void) { return dma_ops; } diff --git a/arch/mips/include/asm/dma-mapping.h b/arch/mips/include/asm/dma-mapping.h index 34de7b17b41b..0fee561ac796 100644 --- a/arch/mips/include/asm/dma-mapping.h +++ b/arch/mips/include/asm/dma-mapping.h @@ -6,7 +6,7 @@ extern const struct dma_map_ops jazz_dma_ops; -static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus) +static inline const struct dma_map_ops *get_arch_dma_ops(void) { #if defined(CONFIG_MACH_JAZZ) return &jazz_dma_ops; diff --git a/arch/parisc/include/asm/dma-mapping.h b/arch/parisc/include/asm/dma-mapping.h index d5bd94247371..635665004fe6 100644 --- a/arch/parisc/include/asm/dma-mapping.h +++ b/arch/parisc/include/asm/dma-mapping.h @@ -21,7 +21,7 @@ extern const struct dma_map_ops *hppa_dma_ops; -static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus) +static inline const struct dma_map_ops *get_arch_dma_ops(void) { return hppa_dma_ops; } diff --git a/arch/sparc/include/asm/dma-mapping.h b/arch/sparc/include/asm/dma-mapping.h index 2f051343612e..55c12fc2ba63 100644 --- a/arch/sparc/include/asm/dma-mapping.h +++ b/arch/sparc/include/asm/dma-mapping.h @@ -4,7 +4,7 @@ extern const struct dma_map_ops *dma_ops; -static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus) +static inline const struct dma_map_ops *get_arch_dma_ops(void) { /* sparc32 uses per-device dma_ops */ return IS_ENABLED(CONFIG_SPARC64) ? dma_ops : NULL; diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h index 1c66708e3062..d1dac96ee30b 100644 --- a/arch/x86/include/asm/dma-mapping.h +++ b/arch/x86/include/asm/dma-mapping.h @@ -4,7 +4,7 @@ extern const struct dma_map_ops *dma_ops; -static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus) +static inline const struct dma_map_ops *get_arch_dma_ops(void) { return dma_ops; } diff --git a/include/asm-generic/dma-mapping.h b/include/asm-generic/dma-mapping.h index c13f46109e88..46a0016efd81 100644 --- a/include/asm-generic/dma-mapping.h +++ b/include/asm-generic/dma-mapping.h @@ -2,7 +2,7 @@ #ifndef _ASM_GENERIC_DMA_MAPPING_H #define _ASM_GENERIC_DMA_MAPPING_H -static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus) +static inline const struct dma_map_ops *get_arch_dma_ops(void) { return NULL; } diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h index d678afeb8a13..41bf4bdb117a 100644 --- a/include/linux/dma-map-ops.h +++ b/include/linux/dma-map-ops.h @@ -90,7 +90,7 @@ static inline const struct dma_map_ops *get_dma_ops(struct device *dev) { if (dev->dma_ops) return dev->dma_ops; - return get_arch_dma_ops(dev->bus); + return get_arch_dma_ops(); } static inline void set_dma_ops(struct device *dev, -- cgit v1.2.3 From d16c0cd27331179daa86a3a489f50ce409121c80 Mon Sep 17 00:00:00 2001 From: Ricardo Cañuelo Date: Mon, 10 Oct 2022 08:43:59 +0200 Subject: docs: driver-api: virtio: virtio on Linux Basic doc about Virtio on Linux and a short tutorial on Virtio drivers. includes the following fixup: virtio: fix virtio_config_ops kerneldocs Fixes two warning messages when building htmldocs: warning: duplicate section name 'Note' warning: expecting prototype for virtio_config_ops(). Prototype was for vq_callback_t() instead Message-Id: <20221010064359.1324353-2-ricardo.canuelo@collabora.com> Signed-off-by: Ricardo Cañuelo Reviewed-by: Cornelia Huck Message-Id: <20221220100035.2712449-1-ricardo.canuelo@collabora.com> Reported-by: Stephen Rothwell Reviewed-by: Bagas Sanjaya Signed-off-by: Michael S. Tsirkin --- Documentation/driver-api/index.rst | 1 + Documentation/driver-api/virtio/index.rst | 11 ++ Documentation/driver-api/virtio/virtio.rst | 144 +++++++++++++++ .../driver-api/virtio/writing_virtio_drivers.rst | 197 +++++++++++++++++++++ MAINTAINERS | 1 + include/linux/virtio_config.h | 8 +- 6 files changed, 359 insertions(+), 3 deletions(-) create mode 100644 Documentation/driver-api/virtio/index.rst create mode 100644 Documentation/driver-api/virtio/virtio.rst create mode 100644 Documentation/driver-api/virtio/writing_virtio_drivers.rst (limited to 'include/linux') diff --git a/Documentation/driver-api/index.rst b/Documentation/driver-api/index.rst index d3a58f77328e..30a3de452b1d 100644 --- a/Documentation/driver-api/index.rst +++ b/Documentation/driver-api/index.rst @@ -106,6 +106,7 @@ available subsections can be seen below. vfio-mediated-device vfio vfio-pci-device-specific-driver-acceptance + virtio/index xilinx/index xillybus zorro diff --git a/Documentation/driver-api/virtio/index.rst b/Documentation/driver-api/virtio/index.rst new file mode 100644 index 000000000000..528b14b291e3 --- /dev/null +++ b/Documentation/driver-api/virtio/index.rst @@ -0,0 +1,11 @@ +.. SPDX-License-Identifier: GPL-2.0 + +====== +Virtio +====== + +.. toctree:: + :maxdepth: 1 + + virtio + writing_virtio_drivers diff --git a/Documentation/driver-api/virtio/virtio.rst b/Documentation/driver-api/virtio/virtio.rst new file mode 100644 index 000000000000..70b3aa6bcf55 --- /dev/null +++ b/Documentation/driver-api/virtio/virtio.rst @@ -0,0 +1,144 @@ +.. SPDX-License-Identifier: GPL-2.0 + +.. _virtio: + +=============== +Virtio on Linux +=============== + +Introduction +============ + +Virtio is an open standard that defines a protocol for communication +between drivers and devices of different types, see Chapter 5 ("Device +Types") of the virtio spec `[1]`_. Originally developed as a standard +for paravirtualized devices implemented by a hypervisor, it can be used +to interface any compliant device (real or emulated) with a driver. + +For illustrative purposes, this document will focus on the common case +of a Linux kernel running in a virtual machine and using paravirtualized +devices provided by the hypervisor, which exposes them as virtio devices +via standard mechanisms such as PCI. + + +Device - Driver communication: virtqueues +========================================= + +Although the virtio devices are really an abstraction layer in the +hypervisor, they're exposed to the guest as if they are physical devices +using a specific transport method -- PCI, MMIO or CCW -- that is +orthogonal to the device itself. The virtio spec defines these transport +methods in detail, including device discovery, capabilities and +interrupt handling. + +The communication between the driver in the guest OS and the device in +the hypervisor is done through shared memory (that's what makes virtio +devices so efficient) using specialized data structures called +virtqueues, which are actually ring buffers [#f1]_ of buffer descriptors +similar to the ones used in a network device: + +.. kernel-doc:: include/uapi/linux/virtio_ring.h + :identifiers: struct vring_desc + +All the buffers the descriptors point to are allocated by the guest and +used by the host either for reading or for writing but not for both. + +Refer to Chapter 2.5 ("Virtqueues") of the virtio spec `[1]`_ for the +reference definitions of virtqueues and to `[2]`_ for an illustrated +overview of how the host device and the guest driver communicate. + +The :c:type:`vring_virtqueue` struct models a virtqueue, including the +ring buffers and management data. Embedded in this struct is the +:c:type:`virtqueue` struct, which is the data structure that's +ultimately used by virtio drivers: + +.. kernel-doc:: include/linux/virtio.h + :identifiers: struct virtqueue + +The callback function pointed by this struct is triggered when the +device has consumed the buffers provided by the driver. More +specifically, the trigger will be an interrupt issued by the hypervisor +(see vring_interrupt()). Interrupt request handlers are registered for +a virtqueue during the virtqueue setup process (transport-specific). + +.. kernel-doc:: drivers/virtio/virtio_ring.c + :identifiers: vring_interrupt + + +Device discovery and probing +============================ + +In the kernel, the virtio core contains the virtio bus driver and +transport-specific drivers like `virtio-pci` and `virtio-mmio`. Then +there are individual virtio drivers for specific device types that are +registered to the virtio bus driver. + +How a virtio device is found and configured by the kernel depends on how +the hypervisor defines it. Taking the `QEMU virtio-console +`__ +device as an example. When using PCI as a transport method, the device +will present itself on the PCI bus with vendor 0x1af4 (Red Hat, Inc.) +and device id 0x1003 (virtio console), as defined in the spec, so the +kernel will detect it as it would do with any other PCI device. + +During the PCI enumeration process, if a device is found to match the +virtio-pci driver (according to the virtio-pci device table, any PCI +device with vendor id = 0x1af4):: + + /* Qumranet donated their vendor ID for devices 0x1000 thru 0x10FF. */ + static const struct pci_device_id virtio_pci_id_table[] = { + { PCI_DEVICE(PCI_VENDOR_ID_REDHAT_QUMRANET, PCI_ANY_ID) }, + { 0 } + }; + +then the virtio-pci driver is probed and, if the probing goes well, the +device is registered to the virtio bus:: + + static int virtio_pci_probe(struct pci_dev *pci_dev, + const struct pci_device_id *id) + { + ... + + if (force_legacy) { + rc = virtio_pci_legacy_probe(vp_dev); + /* Also try modern mode if we can't map BAR0 (no IO space). */ + if (rc == -ENODEV || rc == -ENOMEM) + rc = virtio_pci_modern_probe(vp_dev); + if (rc) + goto err_probe; + } else { + rc = virtio_pci_modern_probe(vp_dev); + if (rc == -ENODEV) + rc = virtio_pci_legacy_probe(vp_dev); + if (rc) + goto err_probe; + } + + ... + + rc = register_virtio_device(&vp_dev->vdev); + +When the device is registered to the virtio bus the kernel will look +for a driver in the bus that can handle the device and call that +driver's ``probe`` method. + +It's at this stage that the virtqueues will be allocated and configured +by calling the appropriate ``virtio_find`` helper function, such as +virtio_find_single_vq() or virtio_find_vqs(), which will end up +calling a transport-specific ``find_vqs`` method. + + +References +========== + +_`[1]` Virtio Spec v1.2: +https://docs.oasis-open.org/virtio/virtio/v1.2/virtio-v1.2.html + +Check for later versions of the spec as well. + +_`[2]` Virtqueues and virtio ring: How the data travels +https://www.redhat.com/en/blog/virtqueues-and-virtio-ring-how-data-travels + +.. rubric:: Footnotes + +.. [#f1] that's why they may be also referred to as virtrings. diff --git a/Documentation/driver-api/virtio/writing_virtio_drivers.rst b/Documentation/driver-api/virtio/writing_virtio_drivers.rst new file mode 100644 index 000000000000..e14c58796d25 --- /dev/null +++ b/Documentation/driver-api/virtio/writing_virtio_drivers.rst @@ -0,0 +1,197 @@ +.. SPDX-License-Identifier: GPL-2.0 + +.. _writing_virtio_drivers: + +====================== +Writing Virtio Drivers +====================== + +Introduction +============ + +This document serves as a basic guideline for driver programmers that +need to hack a new virtio driver or understand the essentials of the +existing ones. See :ref:`Virtio on Linux ` for a general +overview of virtio. + + +Driver boilerplate +================== + +As a bare minimum, a virtio driver needs to register in the virtio bus +and configure the virtqueues for the device according to its spec, the +configuration of the virtqueues in the driver side must match the +virtqueue definitions in the device. A basic driver skeleton could look +like this:: + + #include + #include + #include + #include + + /* device private data (one per device) */ + struct virtio_dummy_dev { + struct virtqueue *vq; + }; + + static void virtio_dummy_recv_cb(struct virtqueue *vq) + { + struct virtio_dummy_dev *dev = vq->vdev->priv; + char *buf; + unsigned int len; + + while ((buf = virtqueue_get_buf(dev->vq, &len)) != NULL) { + /* process the received data */ + } + } + + static int virtio_dummy_probe(struct virtio_device *vdev) + { + struct virtio_dummy_dev *dev = NULL; + + /* initialize device data */ + dev = kzalloc(sizeof(struct virtio_dummy_dev), GFP_KERNEL); + if (!dev) + return -ENOMEM; + + /* the device has a single virtqueue */ + dev->vq = virtio_find_single_vq(vdev, virtio_dummy_recv_cb, "input"); + if (IS_ERR(dev->vq)) { + kfree(dev); + return PTR_ERR(dev->vq); + + } + vdev->priv = dev; + + /* from this point on, the device can notify and get callbacks */ + virtio_device_ready(vdev); + + return 0; + } + + static void virtio_dummy_remove(struct virtio_device *vdev) + { + struct virtio_dummy_dev *dev = vdev->priv; + + /* + * disable vq interrupts: equivalent to + * vdev->config->reset(vdev) + */ + virtio_reset_device(vdev); + + /* detach unused buffers */ + while ((buf = virtqueue_detach_unused_buf(dev->vq)) != NULL) { + kfree(buf); + } + + /* remove virtqueues */ + vdev->config->del_vqs(vdev); + + kfree(dev); + } + + static const struct virtio_device_id id_table[] = { + { VIRTIO_ID_DUMMY, VIRTIO_DEV_ANY_ID }, + { 0 }, + }; + + static struct virtio_driver virtio_dummy_driver = { + .driver.name = KBUILD_MODNAME, + .driver.owner = THIS_MODULE, + .id_table = id_table, + .probe = virtio_dummy_probe, + .remove = virtio_dummy_remove, + }; + + module_virtio_driver(virtio_dummy_driver); + MODULE_DEVICE_TABLE(virtio, id_table); + MODULE_DESCRIPTION("Dummy virtio driver"); + MODULE_LICENSE("GPL"); + +The device id ``VIRTIO_ID_DUMMY`` here is a placeholder, virtio drivers +should be added only for devices that are defined in the spec, see +include/uapi/linux/virtio_ids.h. Device ids need to be at least reserved +in the virtio spec before being added to that file. + +If your driver doesn't have to do anything special in its ``init`` and +``exit`` methods, you can use the module_virtio_driver() helper to +reduce the amount of boilerplate code. + +The ``probe`` method does the minimum driver setup in this case +(memory allocation for the device data) and initializes the +virtqueue. virtio_device_ready() is used to enable the virtqueue and to +notify the device that the driver is ready to manage the device +("DRIVER_OK"). The virtqueues are anyway enabled automatically by the +core after ``probe`` returns. + +.. kernel-doc:: include/linux/virtio_config.h + :identifiers: virtio_device_ready + +In any case, the virtqueues need to be enabled before adding buffers to +them. + +Sending and receiving data +========================== + +The virtio_dummy_recv_cb() callback in the code above will be triggered +when the device notifies the driver after it finishes processing a +descriptor or descriptor chain, either for reading or writing. However, +that's only the second half of the virtio device-driver communication +process, as the communication is always started by the driver regardless +of the direction of the data transfer. + +To configure a buffer transfer from the driver to the device, first you +have to add the buffers -- packed as `scatterlists` -- to the +appropriate virtqueue using any of the virtqueue_add_inbuf(), +virtqueue_add_outbuf() or virtqueue_add_sgs(), depending on whether you +need to add one input `scatterlist` (for the device to fill in), one +output `scatterlist` (for the device to consume) or multiple +`scatterlists`, respectively. Then, once the virtqueue is set up, a call +to virtqueue_kick() sends a notification that will be serviced by the +hypervisor that implements the device:: + + struct scatterlist sg[1]; + sg_init_one(sg, buffer, BUFLEN); + virtqueue_add_inbuf(dev->vq, sg, 1, buffer, GFP_ATOMIC); + virtqueue_kick(dev->vq); + +.. kernel-doc:: drivers/virtio/virtio_ring.c + :identifiers: virtqueue_add_inbuf + +.. kernel-doc:: drivers/virtio/virtio_ring.c + :identifiers: virtqueue_add_outbuf + +.. kernel-doc:: drivers/virtio/virtio_ring.c + :identifiers: virtqueue_add_sgs + +Then, after the device has read or written the buffers prepared by the +driver and notifies it back, the driver can call virtqueue_get_buf() to +read the data produced by the device (if the virtqueue was set up with +input buffers) or simply to reclaim the buffers if they were already +consumed by the device: + +.. kernel-doc:: drivers/virtio/virtio_ring.c + :identifiers: virtqueue_get_buf_ctx + +The virtqueue callbacks can be disabled and re-enabled using the +virtqueue_disable_cb() and the family of virtqueue_enable_cb() functions +respectively. See drivers/virtio/virtio_ring.c for more details: + +.. kernel-doc:: drivers/virtio/virtio_ring.c + :identifiers: virtqueue_disable_cb + +.. kernel-doc:: drivers/virtio/virtio_ring.c + :identifiers: virtqueue_enable_cb + +But note that some spurious callbacks can still be triggered under +certain scenarios. The way to disable callbacks reliably is to reset the +device or the virtqueue (virtio_reset_device()). + + +References +========== + +_`[1]` Virtio Spec v1.2: +https://docs.oasis-open.org/virtio/virtio/v1.2/virtio-v1.2.html + +Check for later versions of the spec as well. diff --git a/MAINTAINERS b/MAINTAINERS index 39ff1a717625..478bc3536741 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -22040,6 +22040,7 @@ S: Maintained F: Documentation/ABI/testing/sysfs-bus-vdpa F: Documentation/ABI/testing/sysfs-class-vduse F: Documentation/devicetree/bindings/virtio/ +F: Documentation/driver-api/virtio/ F: drivers/block/virtio_blk.c F: drivers/crypto/virtio/ F: drivers/net/virtio_net.c diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index 4b517649cfe8..2b3438de2c4d 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -16,8 +16,10 @@ struct virtio_shm_region { u64 len; }; +typedef void vq_callback_t(struct virtqueue *); + /** - * virtio_config_ops - operations for configuring a virtio device + * struct virtio_config_ops - operations for configuring a virtio device * Note: Do not assume that a transport implements all of the operations * getting/setting a value as a simple read/write! Generally speaking, * any of @get/@set, @get_status/@set_status, or @get_features/ @@ -69,7 +71,8 @@ struct virtio_shm_region { * vdev: the virtio_device * This sends the driver feature bits to the device: it can change * the dev->feature bits if it wants. - * Note: despite the name this can be called any number of times. + * Note that despite the name this can be called any number of + * times. * Returns 0 on success or error status * @bus_name: return the bus name associated with the device (optional) * vdev: the virtio_device @@ -91,7 +94,6 @@ struct virtio_shm_region { * If disable_vq_and_reset is set, then enable_vq_after_reset must also be * set. */ -typedef void vq_callback_t(struct virtqueue *); struct virtio_config_ops { void (*get)(struct virtio_device *vdev, unsigned offset, void *buf, unsigned len); -- cgit v1.2.3 From 88f94c782b0ee2297685764f942e7c176d6b89aa Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Tue, 14 Feb 2023 22:41:19 +0100 Subject: mmc: core: support setting card detect interrupt from drivers On certain platforms like Amlogic Meson gpiod_to_irq() isn't supported due to the design of gpio / interrupt controller. Therefore provide an option for drivers to pass the card detect interrupt number (retrieved e.g. from device tree) to mmc core. Suggested-by refers to the mechanism to pass and store the interrupt. Suggested-by: Ulf Hansson Signed-off-by: Heiner Kallweit Link: https://lore.kernel.org/r/5777f38b-465f-ce48-a87f-5eb8b3c57b0a@gmail.com Signed-off-by: Ulf Hansson --- drivers/mmc/core/slot-gpio.c | 17 ++++++++++++++++- include/linux/mmc/slot-gpio.h | 1 + 2 files changed, 17 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/mmc/core/slot-gpio.c b/drivers/mmc/core/slot-gpio.c index dd2a4b6ab6ad..2a2d949a9344 100644 --- a/drivers/mmc/core/slot-gpio.c +++ b/drivers/mmc/core/slot-gpio.c @@ -23,6 +23,7 @@ struct mmc_gpio { char *ro_label; char *cd_label; u32 cd_debounce_delay_ms; + int cd_irq; }; static irqreturn_t mmc_gpio_cd_irqt(int irq, void *dev_id) @@ -53,12 +54,24 @@ int mmc_gpio_alloc(struct mmc_host *host) ctx->ro_label = devm_kasprintf(host->parent, GFP_KERNEL, "%s ro", devname); if (!ctx->ro_label) return -ENOMEM; + ctx->cd_irq = -EINVAL; host->slot.handler_priv = ctx; host->slot.cd_irq = -EINVAL; return 0; } +void mmc_gpio_set_cd_irq(struct mmc_host *host, int irq) +{ + struct mmc_gpio *ctx = host->slot.handler_priv; + + if (!ctx || irq < 0) + return; + + ctx->cd_irq = irq; +} +EXPORT_SYMBOL(mmc_gpio_set_cd_irq); + int mmc_gpio_get_ro(struct mmc_host *host) { struct mmc_gpio *ctx = host->slot.handler_priv; @@ -98,7 +111,9 @@ void mmc_gpiod_request_cd_irq(struct mmc_host *host) * Do not use IRQ if the platform prefers to poll, e.g., because that * IRQ number is already used by another unit and cannot be shared. */ - if (!(host->caps & MMC_CAP_NEEDS_POLL)) + if (ctx->cd_irq >= 0) + irq = ctx->cd_irq; + else if (!(host->caps & MMC_CAP_NEEDS_POLL)) irq = gpiod_to_irq(ctx->cd_gpio); if (irq >= 0) { diff --git a/include/linux/mmc/slot-gpio.h b/include/linux/mmc/slot-gpio.h index 4ae2f2908f99..5d3d15e97868 100644 --- a/include/linux/mmc/slot-gpio.h +++ b/include/linux/mmc/slot-gpio.h @@ -15,6 +15,7 @@ struct mmc_host; int mmc_gpio_get_ro(struct mmc_host *host); int mmc_gpio_get_cd(struct mmc_host *host); +void mmc_gpio_set_cd_irq(struct mmc_host *host, int irq); int mmc_gpiod_request_cd(struct mmc_host *host, const char *con_id, unsigned int idx, bool override_active_level, unsigned int debounce); -- cgit v1.2.3 From 007ed7900aae514986770f6e14069ebd99c4a4c6 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 12 Feb 2023 23:03:24 -0800 Subject: i3c: fix device.h kernel-doc warnings Fix all kernel-doc warnings in : include/linux/i3c/device.h:27: warning: contents before sections include/linux/i3c/device.h:196: warning: Excess function parameter 'dev' description in 'dev_to_i3cdev' Fixes: fa838c8ce537 ("i3c: move dev_to_i3cdev() to use container_of_const()") Fixes: 3a379bbcea0a ("i3c: Add core I3C infrastructure") Signed-off-by: Randy Dunlap Cc: Boris Brezillon Cc: Greg Kroah-Hartman Cc: Alexandre Belloni Cc: linux-i3c@lists.infradead.org Link: https://lore.kernel.org/r/20230213070324.1564-1-rdunlap@infradead.org Signed-off-by: Greg Kroah-Hartman --- include/linux/i3c/device.h | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i3c/device.h b/include/linux/i3c/device.h index ce115ef08fec..90fa83464f00 100644 --- a/include/linux/i3c/device.h +++ b/include/linux/i3c/device.h @@ -18,17 +18,18 @@ /** * enum i3c_error_code - I3C error codes * + * @I3C_ERROR_UNKNOWN: unknown error, usually means the error is not I3C + * related + * @I3C_ERROR_M0: M0 error + * @I3C_ERROR_M1: M1 error + * @I3C_ERROR_M2: M2 error + * * These are the standard error codes as defined by the I3C specification. * When -EIO is returned by the i3c_device_do_priv_xfers() or * i3c_device_send_hdr_cmds() one can check the error code in * &struct_i3c_priv_xfer.err or &struct i3c_hdr_cmd.err to get a better idea of * what went wrong. * - * @I3C_ERROR_UNKNOWN: unknown error, usually means the error is not I3C - * related - * @I3C_ERROR_M0: M0 error - * @I3C_ERROR_M1: M1 error - * @I3C_ERROR_M2: M2 error */ enum i3c_error_code { I3C_ERROR_UNKNOWN = 0, @@ -189,7 +190,7 @@ struct device *i3cdev_to_dev(struct i3c_device *i3cdev); /** * dev_to_i3cdev() - Returns the I3C device containing @dev - * @dev: device object + * @__dev: device object * * Return: a pointer to an I3C device object. */ -- cgit v1.2.3 From 5e7b9a6ae8c352819a2d998a065910b536de0e8c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 16 Feb 2023 07:24:19 +0100 Subject: swiotlb: remove swiotlb_max_segment swiotlb_max_segment has always been a bogus API, so remove it now that the remaining callers are gone. Signed-off-by: Christoph Hellwig Reviewed-by: Robin Murphy --- include/linux/swiotlb.h | 5 ----- kernel/dma/swiotlb.c | 8 -------- 2 files changed, 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 35bc4e281c21..bcef10e20ea4 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -121,7 +121,6 @@ static inline bool is_swiotlb_force_bounce(struct device *dev) void swiotlb_init(bool addressing_limited, unsigned int flags); void __init swiotlb_exit(void); -unsigned int swiotlb_max_segment(void); size_t swiotlb_max_mapping_size(struct device *dev); bool is_swiotlb_active(struct device *dev); void __init swiotlb_adjust_size(unsigned long size); @@ -140,10 +139,6 @@ static inline bool is_swiotlb_force_bounce(struct device *dev) static inline void swiotlb_exit(void) { } -static inline unsigned int swiotlb_max_segment(void) -{ - return 0; -} static inline size_t swiotlb_max_mapping_size(struct device *dev) { return SIZE_MAX; diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index a34c38bbe28f..f35d934f6e58 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -156,14 +156,6 @@ setup_io_tlb_npages(char *str) } early_param("swiotlb", setup_io_tlb_npages); -unsigned int swiotlb_max_segment(void) -{ - if (!io_tlb_default_mem.nslabs) - return 0; - return rounddown(io_tlb_default_mem.nslabs << IO_TLB_SHIFT, PAGE_SIZE); -} -EXPORT_SYMBOL_GPL(swiotlb_max_segment); - unsigned long swiotlb_size_or_default(void) { return default_nslabs << IO_TLB_SHIFT; -- cgit v1.2.3 From 5720a18baa4686d56d0a235e6ecbcc55f8d716d7 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Thu, 16 Feb 2023 11:34:19 -0800 Subject: hwmon: Deprecate [devm_]hwmon_device_register_with_groups Even though the hardware monitoring documentation already stated that new drivers should use [devm_]devm_hwmon_device_register_with_info() to register with the hardware monitoring subsystem, we still get submissions for new drivers using the older APIs. There is no benefit to use those APIs. On the contrary, using the older APIs results in substantially larger code size. Explicitly deprecate [devm_]hwmon_device_register_with_groups() to ensure that all new drivers use the latest API. Signed-off-by: Guenter Roeck --- Documentation/hwmon/submitting-patches.rst | 2 +- include/linux/hwmon.h | 4 ++++ 2 files changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/Documentation/hwmon/submitting-patches.rst b/Documentation/hwmon/submitting-patches.rst index d953ee763c96..6482c4f137dc 100644 --- a/Documentation/hwmon/submitting-patches.rst +++ b/Documentation/hwmon/submitting-patches.rst @@ -126,7 +126,7 @@ increase the chances of your change being accepted. * Use devm_hwmon_device_register_with_info() or, if your driver needs a remove function, hwmon_device_register_with_info() to register your driver with the hwmon subsystem. Try using devm_add_action() instead of a remove function if - possible. Do not use hwmon_device_register(). + possible. Do not use any of the deprecated registration functions. * Your driver should be buildable as module. If not, please be prepared to explain why it has to be built into the kernel. diff --git a/include/linux/hwmon.h b/include/linux/hwmon.h index 14325f93c6b2..c1b62384b6ee 100644 --- a/include/linux/hwmon.h +++ b/include/linux/hwmon.h @@ -436,6 +436,10 @@ struct hwmon_chip_info { /* hwmon_device_register() is deprecated */ struct device *hwmon_device_register(struct device *dev); +/* + * hwmon_device_register_with_groups() and + * devm_hwmon_device_register_with_groups() are deprecated. + */ struct device * hwmon_device_register_with_groups(struct device *dev, const char *name, void *drvdata, -- cgit v1.2.3 From 15ef6a982f40a2b53b057dad24f00c3fb43e7e70 Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Fri, 10 Feb 2023 22:15:49 +0100 Subject: lib/stackdepot: put functions in logical order Patch series "lib/stackdepot: fixes and clean-ups", v2. A set of fixes, comments, and clean-ups I came up with while reading the stack depot code. This patch (of 18): Put stack depot functions' declarations and definitions in a more logical order: 1. Functions that save stack traces into stack depot. 2. Functions that fetch and print stack traces. 3. stack_depot_get_extra_bits that operates on stack depot handles and does not interact with the stack depot storage. No functional changes. Link: https://lkml.kernel.org/r/cover.1676063693.git.andreyknvl@google.com Link: https://lkml.kernel.org/r/daca1319b665d826b94c596b992a8d8117846147.1676063693.git.andreyknvl@google.com Signed-off-by: Andrey Konovalov Reviewed-by: Alexander Potapenko Cc: Evgenii Stepanov Cc: Marco Elver Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- include/linux/stackdepot.h | 15 ++- lib/stackdepot.c | 314 ++++++++++++++++++++++----------------------- 2 files changed, 165 insertions(+), 164 deletions(-) (limited to 'include/linux') diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h index 9ca7798d7a31..1296a6eeaec0 100644 --- a/include/linux/stackdepot.h +++ b/include/linux/stackdepot.h @@ -14,17 +14,13 @@ #include typedef u32 depot_stack_handle_t; + /* * Number of bits in the handle that stack depot doesn't use. Users may store * information in them. */ #define STACK_DEPOT_EXTRA_BITS 5 -depot_stack_handle_t __stack_depot_save(unsigned long *entries, - unsigned int nr_entries, - unsigned int extra_bits, - gfp_t gfp_flags, bool can_alloc); - /* * Every user of stack depot has to call stack_depot_init() during its own init * when it's decided that it will be calling stack_depot_save() later. This is @@ -59,17 +55,22 @@ static inline void stack_depot_want_early_init(void) { } static inline int stack_depot_early_init(void) { return 0; } #endif +depot_stack_handle_t __stack_depot_save(unsigned long *entries, + unsigned int nr_entries, + unsigned int extra_bits, + gfp_t gfp_flags, bool can_alloc); + depot_stack_handle_t stack_depot_save(unsigned long *entries, unsigned int nr_entries, gfp_t gfp_flags); unsigned int stack_depot_fetch(depot_stack_handle_t handle, unsigned long **entries); -unsigned int stack_depot_get_extra_bits(depot_stack_handle_t handle); +void stack_depot_print(depot_stack_handle_t stack); int stack_depot_snprint(depot_stack_handle_t handle, char *buf, size_t size, int spaces); -void stack_depot_print(depot_stack_handle_t stack); +unsigned int stack_depot_get_extra_bits(depot_stack_handle_t handle); #endif diff --git a/lib/stackdepot.c b/lib/stackdepot.c index 79e894cf8406..4bfaf3bce619 100644 --- a/lib/stackdepot.c +++ b/lib/stackdepot.c @@ -79,84 +79,6 @@ static int next_slab_inited; static size_t depot_offset; static DEFINE_RAW_SPINLOCK(depot_lock); -unsigned int stack_depot_get_extra_bits(depot_stack_handle_t handle) -{ - union handle_parts parts = { .handle = handle }; - - return parts.extra; -} -EXPORT_SYMBOL(stack_depot_get_extra_bits); - -static bool init_stack_slab(void **prealloc) -{ - if (!*prealloc) - return false; - /* - * This smp_load_acquire() pairs with smp_store_release() to - * |next_slab_inited| below and in depot_alloc_stack(). - */ - if (smp_load_acquire(&next_slab_inited)) - return true; - if (stack_slabs[depot_index] == NULL) { - stack_slabs[depot_index] = *prealloc; - *prealloc = NULL; - } else { - /* If this is the last depot slab, do not touch the next one. */ - if (depot_index + 1 < STACK_ALLOC_MAX_SLABS) { - stack_slabs[depot_index + 1] = *prealloc; - *prealloc = NULL; - } - /* - * This smp_store_release pairs with smp_load_acquire() from - * |next_slab_inited| above and in stack_depot_save(). - */ - smp_store_release(&next_slab_inited, 1); - } - return true; -} - -/* Allocation of a new stack in raw storage */ -static struct stack_record * -depot_alloc_stack(unsigned long *entries, int size, u32 hash, void **prealloc) -{ - struct stack_record *stack; - size_t required_size = struct_size(stack, entries, size); - - required_size = ALIGN(required_size, 1 << STACK_ALLOC_ALIGN); - - if (unlikely(depot_offset + required_size > STACK_ALLOC_SIZE)) { - if (unlikely(depot_index + 1 >= STACK_ALLOC_MAX_SLABS)) { - WARN_ONCE(1, "Stack depot reached limit capacity"); - return NULL; - } - depot_index++; - depot_offset = 0; - /* - * smp_store_release() here pairs with smp_load_acquire() from - * |next_slab_inited| in stack_depot_save() and - * init_stack_slab(). - */ - if (depot_index + 1 < STACK_ALLOC_MAX_SLABS) - smp_store_release(&next_slab_inited, 0); - } - init_stack_slab(prealloc); - if (stack_slabs[depot_index] == NULL) - return NULL; - - stack = stack_slabs[depot_index] + depot_offset; - - stack->hash = hash; - stack->size = size; - stack->handle.slabindex = depot_index; - stack->handle.offset = depot_offset >> STACK_ALLOC_ALIGN; - stack->handle.valid = 1; - stack->handle.extra = 0; - memcpy(stack->entries, entries, flex_array_size(stack, entries, size)); - depot_offset += required_size; - - return stack; -} - /* one hash table bucket entry per 16kB of memory */ #define STACK_HASH_SCALE 14 /* limited between 4k and 1M buckets */ @@ -270,6 +192,76 @@ int stack_depot_init(void) } EXPORT_SYMBOL_GPL(stack_depot_init); +static bool init_stack_slab(void **prealloc) +{ + if (!*prealloc) + return false; + /* + * This smp_load_acquire() pairs with smp_store_release() to + * |next_slab_inited| below and in depot_alloc_stack(). + */ + if (smp_load_acquire(&next_slab_inited)) + return true; + if (stack_slabs[depot_index] == NULL) { + stack_slabs[depot_index] = *prealloc; + *prealloc = NULL; + } else { + /* If this is the last depot slab, do not touch the next one. */ + if (depot_index + 1 < STACK_ALLOC_MAX_SLABS) { + stack_slabs[depot_index + 1] = *prealloc; + *prealloc = NULL; + } + /* + * This smp_store_release pairs with smp_load_acquire() from + * |next_slab_inited| above and in stack_depot_save(). + */ + smp_store_release(&next_slab_inited, 1); + } + return true; +} + +/* Allocation of a new stack in raw storage */ +static struct stack_record * +depot_alloc_stack(unsigned long *entries, int size, u32 hash, void **prealloc) +{ + struct stack_record *stack; + size_t required_size = struct_size(stack, entries, size); + + required_size = ALIGN(required_size, 1 << STACK_ALLOC_ALIGN); + + if (unlikely(depot_offset + required_size > STACK_ALLOC_SIZE)) { + if (unlikely(depot_index + 1 >= STACK_ALLOC_MAX_SLABS)) { + WARN_ONCE(1, "Stack depot reached limit capacity"); + return NULL; + } + depot_index++; + depot_offset = 0; + /* + * smp_store_release() here pairs with smp_load_acquire() from + * |next_slab_inited| in stack_depot_save() and + * init_stack_slab(). + */ + if (depot_index + 1 < STACK_ALLOC_MAX_SLABS) + smp_store_release(&next_slab_inited, 0); + } + init_stack_slab(prealloc); + if (stack_slabs[depot_index] == NULL) + return NULL; + + stack = stack_slabs[depot_index] + depot_offset; + + stack->hash = hash; + stack->size = size; + stack->handle.slabindex = depot_index; + stack->handle.offset = depot_offset >> STACK_ALLOC_ALIGN; + stack->handle.valid = 1; + stack->handle.extra = 0; + memcpy(stack->entries, entries, flex_array_size(stack, entries, size)); + depot_offset += required_size; + + return stack; +} + /* Calculate hash for a stack */ static inline u32 hash_stack(unsigned long *entries, unsigned int size) { @@ -309,85 +301,6 @@ static inline struct stack_record *find_stack(struct stack_record *bucket, return NULL; } -/** - * stack_depot_snprint - print stack entries from a depot into a buffer - * - * @handle: Stack depot handle which was returned from - * stack_depot_save(). - * @buf: Pointer to the print buffer - * - * @size: Size of the print buffer - * - * @spaces: Number of leading spaces to print - * - * Return: Number of bytes printed. - */ -int stack_depot_snprint(depot_stack_handle_t handle, char *buf, size_t size, - int spaces) -{ - unsigned long *entries; - unsigned int nr_entries; - - nr_entries = stack_depot_fetch(handle, &entries); - return nr_entries ? stack_trace_snprint(buf, size, entries, nr_entries, - spaces) : 0; -} -EXPORT_SYMBOL_GPL(stack_depot_snprint); - -/** - * stack_depot_print - print stack entries from a depot - * - * @stack: Stack depot handle which was returned from - * stack_depot_save(). - * - */ -void stack_depot_print(depot_stack_handle_t stack) -{ - unsigned long *entries; - unsigned int nr_entries; - - nr_entries = stack_depot_fetch(stack, &entries); - if (nr_entries > 0) - stack_trace_print(entries, nr_entries, 0); -} -EXPORT_SYMBOL_GPL(stack_depot_print); - -/** - * stack_depot_fetch - Fetch stack entries from a depot - * - * @handle: Stack depot handle which was returned from - * stack_depot_save(). - * @entries: Pointer to store the entries address - * - * Return: The number of trace entries for this depot. - */ -unsigned int stack_depot_fetch(depot_stack_handle_t handle, - unsigned long **entries) -{ - union handle_parts parts = { .handle = handle }; - void *slab; - size_t offset = parts.offset << STACK_ALLOC_ALIGN; - struct stack_record *stack; - - *entries = NULL; - if (!handle) - return 0; - - if (parts.slabindex > depot_index) { - WARN(1, "slab index %d out of bounds (%d) for stack id %08x\n", - parts.slabindex, depot_index, handle); - return 0; - } - slab = stack_slabs[parts.slabindex]; - if (!slab) - return 0; - stack = slab + offset; - - *entries = stack->entries; - return stack->size; -} -EXPORT_SYMBOL_GPL(stack_depot_fetch); - /** * __stack_depot_save - Save a stack trace from an array * @@ -533,3 +446,90 @@ depot_stack_handle_t stack_depot_save(unsigned long *entries, return __stack_depot_save(entries, nr_entries, 0, alloc_flags, true); } EXPORT_SYMBOL_GPL(stack_depot_save); + +/** + * stack_depot_fetch - Fetch stack entries from a depot + * + * @handle: Stack depot handle which was returned from + * stack_depot_save(). + * @entries: Pointer to store the entries address + * + * Return: The number of trace entries for this depot. + */ +unsigned int stack_depot_fetch(depot_stack_handle_t handle, + unsigned long **entries) +{ + union handle_parts parts = { .handle = handle }; + void *slab; + size_t offset = parts.offset << STACK_ALLOC_ALIGN; + struct stack_record *stack; + + *entries = NULL; + if (!handle) + return 0; + + if (parts.slabindex > depot_index) { + WARN(1, "slab index %d out of bounds (%d) for stack id %08x\n", + parts.slabindex, depot_index, handle); + return 0; + } + slab = stack_slabs[parts.slabindex]; + if (!slab) + return 0; + stack = slab + offset; + + *entries = stack->entries; + return stack->size; +} +EXPORT_SYMBOL_GPL(stack_depot_fetch); + +/** + * stack_depot_print - print stack entries from a depot + * + * @stack: Stack depot handle which was returned from + * stack_depot_save(). + * + */ +void stack_depot_print(depot_stack_handle_t stack) +{ + unsigned long *entries; + unsigned int nr_entries; + + nr_entries = stack_depot_fetch(stack, &entries); + if (nr_entries > 0) + stack_trace_print(entries, nr_entries, 0); +} +EXPORT_SYMBOL_GPL(stack_depot_print); + +/** + * stack_depot_snprint - print stack entries from a depot into a buffer + * + * @handle: Stack depot handle which was returned from + * stack_depot_save(). + * @buf: Pointer to the print buffer + * + * @size: Size of the print buffer + * + * @spaces: Number of leading spaces to print + * + * Return: Number of bytes printed. + */ +int stack_depot_snprint(depot_stack_handle_t handle, char *buf, size_t size, + int spaces) +{ + unsigned long *entries; + unsigned int nr_entries; + + nr_entries = stack_depot_fetch(handle, &entries); + return nr_entries ? stack_trace_snprint(buf, size, entries, nr_entries, + spaces) : 0; +} +EXPORT_SYMBOL_GPL(stack_depot_snprint); + +unsigned int stack_depot_get_extra_bits(depot_stack_handle_t handle) +{ + union handle_parts parts = { .handle = handle }; + + return parts.extra; +} +EXPORT_SYMBOL(stack_depot_get_extra_bits); -- cgit v1.2.3 From 1c0310add78e7e47e3357c24369b61453a5a72eb Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Fri, 10 Feb 2023 22:15:51 +0100 Subject: lib/stackdepot, mm: rename stack_depot_want_early_init Rename stack_depot_want_early_init to stack_depot_request_early_init. The old name is confusing, as it hints at returning some kind of intention of stack depot. The new name reflects that this function requests an action from stack depot instead. No functional changes. [akpm@linux-foundation.org: update mm/kmemleak.c] Link: https://lkml.kernel.org/r/359f31bf67429a06e630b4395816a967214ef753.1676063693.git.andreyknvl@google.com Signed-off-by: Andrey Konovalov Reviewed-by: Alexander Potapenko Acked-by: Vlastimil Babka Signed-off-by: Andrew Morton --- include/linux/stackdepot.h | 14 +++++++------- lib/stackdepot.c | 10 +++++----- mm/kmemleak.c | 2 +- mm/page_owner.c | 2 +- mm/slub.c | 4 ++-- 5 files changed, 16 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h index 1296a6eeaec0..c4e3abc16b16 100644 --- a/include/linux/stackdepot.h +++ b/include/linux/stackdepot.h @@ -31,26 +31,26 @@ typedef u32 depot_stack_handle_t; * enabled as part of mm_init(), for subsystems where it's known at compile time * that stack depot will be used. * - * Another alternative is to call stack_depot_want_early_init(), when the + * Another alternative is to call stack_depot_request_early_init(), when the * decision to use stack depot is taken e.g. when evaluating kernel boot * parameters, which precedes the enablement point in mm_init(). * - * stack_depot_init() and stack_depot_want_early_init() can be called regardless - * of CONFIG_STACKDEPOT and are no-op when disabled. The actual save/fetch/print - * functions should only be called from code that makes sure CONFIG_STACKDEPOT - * is enabled. + * stack_depot_init() and stack_depot_request_early_init() can be called + * regardless of CONFIG_STACKDEPOT and are no-op when disabled. The actual + * save/fetch/print functions should only be called from code that makes sure + * CONFIG_STACKDEPOT is enabled. */ #ifdef CONFIG_STACKDEPOT int stack_depot_init(void); -void __init stack_depot_want_early_init(void); +void __init stack_depot_request_early_init(void); /* This is supposed to be called only from mm_init() */ int __init stack_depot_early_init(void); #else static inline int stack_depot_init(void) { return 0; } -static inline void stack_depot_want_early_init(void) { } +static inline void stack_depot_request_early_init(void) { } static inline int stack_depot_early_init(void) { return 0; } #endif diff --git a/lib/stackdepot.c b/lib/stackdepot.c index 83787e46a3ab..136706efe339 100644 --- a/lib/stackdepot.c +++ b/lib/stackdepot.c @@ -71,7 +71,7 @@ struct stack_record { unsigned long entries[]; /* Variable-sized array of entries. */ }; -static bool __stack_depot_want_early_init __initdata = IS_ENABLED(CONFIG_STACKDEPOT_ALWAYS_INIT); +static bool __stack_depot_early_init_requested __initdata = IS_ENABLED(CONFIG_STACKDEPOT_ALWAYS_INIT); static bool __stack_depot_early_init_passed __initdata; static void *stack_slabs[STACK_ALLOC_MAX_SLABS]; @@ -107,12 +107,12 @@ static int __init is_stack_depot_disabled(char *str) } early_param("stack_depot_disable", is_stack_depot_disabled); -void __init stack_depot_want_early_init(void) +void __init stack_depot_request_early_init(void) { - /* Too late to request early init now */ + /* Too late to request early init now. */ WARN_ON(__stack_depot_early_init_passed); - __stack_depot_want_early_init = true; + __stack_depot_early_init_requested = true; } int __init stack_depot_early_init(void) @@ -128,7 +128,7 @@ int __init stack_depot_early_init(void) if (kasan_enabled() && !stack_hash_order) stack_hash_order = STACK_HASH_ORDER_MAX; - if (!__stack_depot_want_early_init || stack_depot_disable) + if (!__stack_depot_early_init_requested || stack_depot_disable) return 0; if (stack_hash_order) diff --git a/mm/kmemleak.c b/mm/kmemleak.c index d9b242cfdb1c..a2d34226e3c8 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -2071,7 +2071,7 @@ static int __init kmemleak_boot_config(char *str) kmemleak_disable(); else if (strcmp(str, "on") == 0) { kmemleak_skip_disable = 1; - stack_depot_want_early_init(); + stack_depot_request_early_init(); } else return -EINVAL; diff --git a/mm/page_owner.c b/mm/page_owner.c index 80dc8f4050fa..220cdeddc295 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -48,7 +48,7 @@ static int __init early_page_owner_param(char *buf) int ret = kstrtobool(buf, &page_owner_enabled); if (page_owner_enabled) - stack_depot_want_early_init(); + stack_depot_request_early_init(); return ret; } diff --git a/mm/slub.c b/mm/slub.c index 67020074ecb4..f8dba33e4d15 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1592,7 +1592,7 @@ static int __init setup_slub_debug(char *str) } else { slab_list_specified = true; if (flags & SLAB_STORE_USER) - stack_depot_want_early_init(); + stack_depot_request_early_init(); } } @@ -1611,7 +1611,7 @@ static int __init setup_slub_debug(char *str) out: slub_debug = global_flags; if (slub_debug & SLAB_STORE_USER) - stack_depot_want_early_init(); + stack_depot_request_early_init(); if (slub_debug != 0 || slub_debug_string) static_branch_enable(&slub_debug_enabled); else -- cgit v1.2.3 From 36aa1e6779c3c6f8e0d4552544214f5cffe3c287 Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Fri, 10 Feb 2023 22:16:03 +0100 Subject: lib/stacktrace, kasan, kmsan: rework extra_bits interface The current implementation of the extra_bits interface is confusing: passing extra_bits to __stack_depot_save makes it seem that the extra bits are somehow stored in stack depot. In reality, they are only embedded into a stack depot handle and are not used within stack depot. Drop the extra_bits argument from __stack_depot_save and instead provide a new stack_depot_set_extra_bits function (similar to the exsiting stack_depot_get_extra_bits) that saves extra bits into a stack depot handle. Update the callers of __stack_depot_save to use the new interace. This change also fixes a minor issue in the old code: __stack_depot_save does not return NULL if saving stack trace fails and extra_bits is used. Link: https://lkml.kernel.org/r/317123b5c05e2f82854fc55d8b285e0869d3cb77.1676063693.git.andreyknvl@google.com Signed-off-by: Andrey Konovalov Reviewed-by: Alexander Potapenko Signed-off-by: Andrew Morton --- include/linux/stackdepot.h | 4 +++- lib/stackdepot.c | 42 +++++++++++++++++++++++++++++++++--------- mm/kasan/common.c | 2 +- mm/kmsan/core.c | 10 +++++++--- 4 files changed, 44 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h index c4e3abc16b16..267f4b2634ee 100644 --- a/include/linux/stackdepot.h +++ b/include/linux/stackdepot.h @@ -57,7 +57,6 @@ static inline int stack_depot_early_init(void) { return 0; } depot_stack_handle_t __stack_depot_save(unsigned long *entries, unsigned int nr_entries, - unsigned int extra_bits, gfp_t gfp_flags, bool can_alloc); depot_stack_handle_t stack_depot_save(unsigned long *entries, @@ -71,6 +70,9 @@ void stack_depot_print(depot_stack_handle_t stack); int stack_depot_snprint(depot_stack_handle_t handle, char *buf, size_t size, int spaces); +depot_stack_handle_t __must_check stack_depot_set_extra_bits( + depot_stack_handle_t handle, unsigned int extra_bits); + unsigned int stack_depot_get_extra_bits(depot_stack_handle_t handle); #endif diff --git a/lib/stackdepot.c b/lib/stackdepot.c index 4df162a84bfe..8c6e4e9cb535 100644 --- a/lib/stackdepot.c +++ b/lib/stackdepot.c @@ -357,7 +357,6 @@ static inline struct stack_record *find_stack(struct stack_record *bucket, * * @entries: Pointer to storage array * @nr_entries: Size of the storage array - * @extra_bits: Flags to store in unused bits of depot_stack_handle_t * @alloc_flags: Allocation gfp flags * @can_alloc: Allocate stack pools (increased chance of failure if false) * @@ -369,10 +368,6 @@ static inline struct stack_record *find_stack(struct stack_record *bucket, * If the stack trace in @entries is from an interrupt, only the portion up to * interrupt entry is saved. * - * Additional opaque flags can be passed in @extra_bits, stored in the unused - * bits of the stack handle, and retrieved using stack_depot_get_extra_bits() - * without calling stack_depot_fetch(). - * * Context: Any context, but setting @can_alloc to %false is required if * alloc_pages() cannot be used from the current context. Currently * this is the case from contexts where neither %GFP_ATOMIC nor @@ -382,7 +377,6 @@ static inline struct stack_record *find_stack(struct stack_record *bucket, */ depot_stack_handle_t __stack_depot_save(unsigned long *entries, unsigned int nr_entries, - unsigned int extra_bits, gfp_t alloc_flags, bool can_alloc) { struct stack_record *found = NULL, **bucket; @@ -471,8 +465,6 @@ exit: if (found) retval.handle = found->handle.handle; fast_exit: - retval.extra = extra_bits; - return retval.handle; } EXPORT_SYMBOL_GPL(__stack_depot_save); @@ -493,7 +485,7 @@ depot_stack_handle_t stack_depot_save(unsigned long *entries, unsigned int nr_entries, gfp_t alloc_flags) { - return __stack_depot_save(entries, nr_entries, 0, alloc_flags, true); + return __stack_depot_save(entries, nr_entries, alloc_flags, true); } EXPORT_SYMBOL_GPL(stack_depot_save); @@ -576,6 +568,38 @@ int stack_depot_snprint(depot_stack_handle_t handle, char *buf, size_t size, } EXPORT_SYMBOL_GPL(stack_depot_snprint); +/** + * stack_depot_set_extra_bits - Set extra bits in a stack depot handle + * + * @handle: Stack depot handle returned from stack_depot_save() + * @extra_bits: Value to set the extra bits + * + * Return: Stack depot handle with extra bits set + * + * Stack depot handles have a few unused bits, which can be used for storing + * user-specific information. These bits are transparent to the stack depot. + */ +depot_stack_handle_t __must_check stack_depot_set_extra_bits( + depot_stack_handle_t handle, unsigned int extra_bits) +{ + union handle_parts parts = { .handle = handle }; + + /* Don't set extra bits on empty handles. */ + if (!handle) + return 0; + + parts.extra = extra_bits; + return parts.handle; +} +EXPORT_SYMBOL(stack_depot_set_extra_bits); + +/** + * stack_depot_get_extra_bits - Retrieve extra bits from a stack depot handle + * + * @handle: Stack depot handle with extra bits saved + * + * Return: Extra bits retrieved from the stack depot handle + */ unsigned int stack_depot_get_extra_bits(depot_stack_handle_t handle) { union handle_parts parts = { .handle = handle }; diff --git a/mm/kasan/common.c b/mm/kasan/common.c index 1e7336ae3786..b376a5d055e5 100644 --- a/mm/kasan/common.c +++ b/mm/kasan/common.c @@ -43,7 +43,7 @@ depot_stack_handle_t kasan_save_stack(gfp_t flags, bool can_alloc) unsigned int nr_entries; nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 0); - return __stack_depot_save(entries, nr_entries, 0, flags, can_alloc); + return __stack_depot_save(entries, nr_entries, flags, can_alloc); } void kasan_set_track(struct kasan_track *track, gfp_t flags) diff --git a/mm/kmsan/core.c b/mm/kmsan/core.c index 112dce135c7f..f710257d6867 100644 --- a/mm/kmsan/core.c +++ b/mm/kmsan/core.c @@ -69,13 +69,15 @@ depot_stack_handle_t kmsan_save_stack_with_flags(gfp_t flags, { unsigned long entries[KMSAN_STACK_DEPTH]; unsigned int nr_entries; + depot_stack_handle_t handle; nr_entries = stack_trace_save(entries, KMSAN_STACK_DEPTH, 0); /* Don't sleep (see might_sleep_if() in __alloc_pages_nodemask()). */ flags &= ~__GFP_DIRECT_RECLAIM; - return __stack_depot_save(entries, nr_entries, extra, flags, true); + handle = __stack_depot_save(entries, nr_entries, flags, true); + return stack_depot_set_extra_bits(handle, extra); } /* Copy the metadata following the memmove() behavior. */ @@ -215,6 +217,7 @@ depot_stack_handle_t kmsan_internal_chain_origin(depot_stack_handle_t id) u32 extra_bits; int depth; bool uaf; + depot_stack_handle_t handle; if (!id) return id; @@ -250,8 +253,9 @@ depot_stack_handle_t kmsan_internal_chain_origin(depot_stack_handle_t id) * positives when __stack_depot_save() passes it to instrumented code. */ kmsan_internal_unpoison_memory(entries, sizeof(entries), false); - return __stack_depot_save(entries, ARRAY_SIZE(entries), extra_bits, - GFP_ATOMIC, true); + handle = __stack_depot_save(entries, ARRAY_SIZE(entries), GFP_ATOMIC, + true); + return stack_depot_set_extra_bits(handle, extra_bits); } void kmsan_internal_set_shadow_origin(void *addr, size_t size, int b, -- cgit v1.2.3 From b232b9995a6dbaafe19d07d81acc039bc84bd569 Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Fri, 10 Feb 2023 22:16:05 +0100 Subject: lib/stackdepot: various comments clean-ups Clean up comments in include/linux/stackdepot.h and lib/stackdepot.c: 1. Rework the initialization comment in stackdepot.h. 2. Rework the header comment in stackdepot.c. 3. Various clean-ups for other comments. Also adjust whitespaces for find_stack and depot_alloc_stack call sites. No functional changes. Link: https://lkml.kernel.org/r/5836231b7954355e2311fc9b5870f697ea8e1f7d.1676063693.git.andreyknvl@google.com Signed-off-by: Andrey Konovalov Reviewed-by: Alexander Potapenko Signed-off-by: Andrew Morton --- include/linux/stackdepot.h | 36 +++++++------- lib/stackdepot.c | 120 ++++++++++++++++++++++----------------------- 2 files changed, 78 insertions(+), 78 deletions(-) (limited to 'include/linux') diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h index 267f4b2634ee..afdf8ee7b597 100644 --- a/include/linux/stackdepot.h +++ b/include/linux/stackdepot.h @@ -1,11 +1,11 @@ /* SPDX-License-Identifier: GPL-2.0-or-later */ /* - * A generic stack depot implementation + * Stack depot - a stack trace storage that avoids duplication. * * Author: Alexander Potapenko * Copyright (C) 2016 Google, Inc. * - * Based on code by Dmitry Chernenkov. + * Based on the code by Dmitry Chernenkov. */ #ifndef _LINUX_STACKDEPOT_H @@ -17,35 +17,37 @@ typedef u32 depot_stack_handle_t; /* * Number of bits in the handle that stack depot doesn't use. Users may store - * information in them. + * information in them via stack_depot_set/get_extra_bits. */ #define STACK_DEPOT_EXTRA_BITS 5 /* - * Every user of stack depot has to call stack_depot_init() during its own init - * when it's decided that it will be calling stack_depot_save() later. This is - * recommended for e.g. modules initialized later in the boot process, when - * slab_is_available() is true. + * Using stack depot requires its initialization, which can be done in 3 ways: * - * The alternative is to select STACKDEPOT_ALWAYS_INIT to have stack depot - * enabled as part of mm_init(), for subsystems where it's known at compile time - * that stack depot will be used. + * 1. Selecting CONFIG_STACKDEPOT_ALWAYS_INIT. This option is suitable in + * scenarios where it's known at compile time that stack depot will be used. + * Enabling this config makes the kernel initialize stack depot in mm_init(). * - * Another alternative is to call stack_depot_request_early_init(), when the - * decision to use stack depot is taken e.g. when evaluating kernel boot - * parameters, which precedes the enablement point in mm_init(). + * 2. Calling stack_depot_request_early_init() during early boot, before + * stack_depot_early_init() in mm_init() completes. For example, this can + * be done when evaluating kernel boot parameters. + * + * 3. Calling stack_depot_init(). Possible after boot is complete. This option + * is recommended for modules initialized later in the boot process, after + * mm_init() completes. * * stack_depot_init() and stack_depot_request_early_init() can be called - * regardless of CONFIG_STACKDEPOT and are no-op when disabled. The actual - * save/fetch/print functions should only be called from code that makes sure - * CONFIG_STACKDEPOT is enabled. + * regardless of whether CONFIG_STACKDEPOT is enabled and are no-op when this + * config is disabled. The save/fetch/print stack depot functions can only be + * called from the code that makes sure CONFIG_STACKDEPOT is enabled _and_ + * initializes stack depot via one of the ways listed above. */ #ifdef CONFIG_STACKDEPOT int stack_depot_init(void); void __init stack_depot_request_early_init(void); -/* This is supposed to be called only from mm_init() */ +/* Must be only called from mm_init(). */ int __init stack_depot_early_init(void); #else static inline int stack_depot_init(void) { return 0; } diff --git a/lib/stackdepot.c b/lib/stackdepot.c index b625090890e1..aaa5d2f1abc2 100644 --- a/lib/stackdepot.c +++ b/lib/stackdepot.c @@ -1,22 +1,26 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Generic stack depot for storing stack traces. + * Stack depot - a stack trace storage that avoids duplication. * - * Some debugging tools need to save stack traces of certain events which can - * be later presented to the user. For example, KASAN needs to safe alloc and - * free stacks for each object, but storing two stack traces per object - * requires too much memory (e.g. SLUB_DEBUG needs 256 bytes per object for - * that). + * Stack depot is intended to be used by subsystems that need to store and + * later retrieve many potentially duplicated stack traces without wasting + * memory. * - * Instead, stack depot maintains a hashtable of unique stacktraces. Since alloc - * and free stacks repeat a lot, we save about 100x space. - * Stacks are never removed from depot, so we store them contiguously one after - * another in a contiguous memory allocation. + * For example, KASAN needs to save allocation and free stack traces for each + * object. Storing two stack traces per object requires a lot of memory (e.g. + * SLUB_DEBUG needs 256 bytes per object for that). Since allocation and free + * stack traces often repeat, using stack depot allows to save about 100x space. + * + * Internally, stack depot maintains a hash table of unique stacktraces. The + * stack traces themselves are stored contiguously one after another in a set + * of separate page allocations. + * + * Stack traces are never removed from stack depot. * * Author: Alexander Potapenko * Copyright (C) 2016 Google, Inc. * - * Based on code by Dmitry Chernenkov. + * Based on the code by Dmitry Chernenkov. */ #define pr_fmt(fmt) "stackdepot: " fmt @@ -50,7 +54,7 @@ (((1LL << (DEPOT_POOL_INDEX_BITS)) < DEPOT_POOLS_CAP) ? \ (1LL << (DEPOT_POOL_INDEX_BITS)) : DEPOT_POOLS_CAP) -/* The compact structure to store the reference to stacks. */ +/* Compact structure that stores a reference to a stack. */ union handle_parts { depot_stack_handle_t handle; struct { @@ -62,11 +66,11 @@ union handle_parts { }; struct stack_record { - struct stack_record *next; /* Link in the hashtable */ - u32 hash; /* Hash in the hastable */ - u32 size; /* Number of frames in the stack */ + struct stack_record *next; /* Link in the hash table */ + u32 hash; /* Hash in the hash table */ + u32 size; /* Number of stored frames */ union handle_parts handle; - unsigned long entries[]; /* Variable-sized array of entries. */ + unsigned long entries[]; /* Variable-sized array of frames */ }; static bool stack_depot_disabled; @@ -317,7 +321,7 @@ depot_alloc_stack(unsigned long *entries, int size, u32 hash, void **prealloc) return stack; } -/* Calculate hash for a stack */ +/* Calculates the hash for a stack. */ static inline u32 hash_stack(unsigned long *entries, unsigned int size) { return jhash2((u32 *)entries, @@ -325,9 +329,9 @@ static inline u32 hash_stack(unsigned long *entries, unsigned int size) STACK_HASH_SEED); } -/* Use our own, non-instrumented version of memcmp(). - * - * We actually don't care about the order, just the equality. +/* + * Non-instrumented version of memcmp(). + * Does not check the lexicographical order, only the equality. */ static inline int stackdepot_memcmp(const unsigned long *u1, const unsigned long *u2, @@ -340,7 +344,7 @@ int stackdepot_memcmp(const unsigned long *u1, const unsigned long *u2, return 0; } -/* Find a stack that is equal to the one stored in entries in the hash */ +/* Finds a stack in a bucket of the hash table. */ static inline struct stack_record *find_stack(struct stack_record *bucket, unsigned long *entries, int size, u32 hash) @@ -357,27 +361,27 @@ static inline struct stack_record *find_stack(struct stack_record *bucket, } /** - * __stack_depot_save - Save a stack trace from an array + * __stack_depot_save - Save a stack trace to stack depot * - * @entries: Pointer to storage array - * @nr_entries: Size of the storage array - * @alloc_flags: Allocation gfp flags + * @entries: Pointer to the stack trace + * @nr_entries: Number of frames in the stack + * @alloc_flags: Allocation GFP flags * @can_alloc: Allocate stack pools (increased chance of failure if false) * * Saves a stack trace from @entries array of size @nr_entries. If @can_alloc is - * %true, is allowed to replenish the stack pool in case no space is left + * %true, stack depot can replenish the stack pools in case no space is left * (allocates using GFP flags of @alloc_flags). If @can_alloc is %false, avoids - * any allocations and will fail if no space is left to store the stack trace. + * any allocations and fails if no space is left to store the stack trace. * - * If the stack trace in @entries is from an interrupt, only the portion up to - * interrupt entry is saved. + * If the provided stack trace comes from the interrupt context, only the part + * up to the interrupt entry is saved. * * Context: Any context, but setting @can_alloc to %false is required if * alloc_pages() cannot be used from the current context. Currently - * this is the case from contexts where neither %GFP_ATOMIC nor + * this is the case for contexts where neither %GFP_ATOMIC nor * %GFP_NOWAIT can be used (NMI, raw_spin_lock). * - * Return: The handle of the stack struct stored in depot, 0 on failure. + * Return: Handle of the stack struct stored in depot, 0 on failure */ depot_stack_handle_t __stack_depot_save(unsigned long *entries, unsigned int nr_entries, @@ -392,11 +396,11 @@ depot_stack_handle_t __stack_depot_save(unsigned long *entries, /* * If this stack trace is from an interrupt, including anything before - * interrupt entry usually leads to unbounded stackdepot growth. + * interrupt entry usually leads to unbounded stack depot growth. * - * Because use of filter_irq_stacks() is a requirement to ensure - * stackdepot can efficiently deduplicate interrupt stacks, always - * filter_irq_stacks() to simplify all callers' use of stackdepot. + * Since use of filter_irq_stacks() is a requirement to ensure stack + * depot can efficiently deduplicate interrupt stacks, always + * filter_irq_stacks() to simplify all callers' use of stack depot. */ nr_entries = filter_irq_stacks(entries, nr_entries); @@ -411,8 +415,7 @@ depot_stack_handle_t __stack_depot_save(unsigned long *entries, * The smp_load_acquire() here pairs with smp_store_release() to * |bucket| below. */ - found = find_stack(smp_load_acquire(bucket), entries, - nr_entries, hash); + found = find_stack(smp_load_acquire(bucket), entries, nr_entries, hash); if (found) goto exit; @@ -441,7 +444,8 @@ depot_stack_handle_t __stack_depot_save(unsigned long *entries, found = find_stack(*bucket, entries, nr_entries, hash); if (!found) { - struct stack_record *new = depot_alloc_stack(entries, nr_entries, hash, &prealloc); + struct stack_record *new = + depot_alloc_stack(entries, nr_entries, hash, &prealloc); if (new) { new->next = *bucket; @@ -454,8 +458,8 @@ depot_stack_handle_t __stack_depot_save(unsigned long *entries, } } else if (prealloc) { /* - * We didn't need to store this stack trace, but let's keep - * the preallocated memory for the future. + * Stack depot already contains this stack trace, but let's + * keep the preallocated memory for the future. */ depot_init_pool(&prealloc); } @@ -463,7 +467,7 @@ depot_stack_handle_t __stack_depot_save(unsigned long *entries, raw_spin_unlock_irqrestore(&pool_lock, flags); exit: if (prealloc) { - /* Nobody used this memory, ok to free it. */ + /* Stack depot didn't use this memory, free it. */ free_pages((unsigned long)prealloc, DEPOT_POOL_ORDER); } if (found) @@ -474,16 +478,16 @@ fast_exit: EXPORT_SYMBOL_GPL(__stack_depot_save); /** - * stack_depot_save - Save a stack trace from an array + * stack_depot_save - Save a stack trace to stack depot * - * @entries: Pointer to storage array - * @nr_entries: Size of the storage array - * @alloc_flags: Allocation gfp flags + * @entries: Pointer to the stack trace + * @nr_entries: Number of frames in the stack + * @alloc_flags: Allocation GFP flags * * Context: Contexts where allocations via alloc_pages() are allowed. * See __stack_depot_save() for more details. * - * Return: The handle of the stack struct stored in depot, 0 on failure. + * Return: Handle of the stack trace stored in depot, 0 on failure */ depot_stack_handle_t stack_depot_save(unsigned long *entries, unsigned int nr_entries, @@ -494,13 +498,12 @@ depot_stack_handle_t stack_depot_save(unsigned long *entries, EXPORT_SYMBOL_GPL(stack_depot_save); /** - * stack_depot_fetch - Fetch stack entries from a depot + * stack_depot_fetch - Fetch a stack trace from stack depot * - * @handle: Stack depot handle which was returned from - * stack_depot_save(). - * @entries: Pointer to store the entries address + * @handle: Stack depot handle returned from stack_depot_save() + * @entries: Pointer to store the address of the stack trace * - * Return: The number of trace entries for this depot. + * Return: Number of frames for the fetched stack */ unsigned int stack_depot_fetch(depot_stack_handle_t handle, unsigned long **entries) @@ -535,11 +538,9 @@ unsigned int stack_depot_fetch(depot_stack_handle_t handle, EXPORT_SYMBOL_GPL(stack_depot_fetch); /** - * stack_depot_print - print stack entries from a depot - * - * @stack: Stack depot handle which was returned from - * stack_depot_save(). + * stack_depot_print - Print a stack trace from stack depot * + * @stack: Stack depot handle returned from stack_depot_save() */ void stack_depot_print(depot_stack_handle_t stack) { @@ -553,17 +554,14 @@ void stack_depot_print(depot_stack_handle_t stack) EXPORT_SYMBOL_GPL(stack_depot_print); /** - * stack_depot_snprint - print stack entries from a depot into a buffer + * stack_depot_snprint - Print a stack trace from stack depot into a buffer * - * @handle: Stack depot handle which was returned from - * stack_depot_save(). + * @handle: Stack depot handle returned from stack_depot_save() * @buf: Pointer to the print buffer - * * @size: Size of the print buffer - * * @spaces: Number of leading spaces to print * - * Return: Number of bytes printed. + * Return: Number of bytes printed */ int stack_depot_snprint(depot_stack_handle_t handle, char *buf, size_t size, int spaces) -- cgit v1.2.3 From 0621d160f1003a8aedd3628133568ecffdd724f7 Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Fri, 10 Feb 2023 22:16:06 +0100 Subject: lib/stackdepot: move documentation comments to stackdepot.h Move all interface- and usage-related documentation comments to include/linux/stackdepot.h. It makes sense to have them in the header where they are available to the interface users. [akpm@linux-foundation.org: grammar fix, per Alexander] Link: https://lkml.kernel.org/r/fbfee41495b306dd8881f9b1c1b80999c885e82f.1676063693.git.andreyknvl@google.com Signed-off-by: Andrey Konovalov Reviewed-by: Alexander Potapenko Signed-off-by: Andrew Morton --- include/linux/stackdepot.h | 87 ++++++++++++++++++++++++++++++++++++++++++++++ lib/stackdepot.c | 87 ---------------------------------------------- 2 files changed, 87 insertions(+), 87 deletions(-) (limited to 'include/linux') diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h index afdf8ee7b597..e58306783d8e 100644 --- a/include/linux/stackdepot.h +++ b/include/linux/stackdepot.h @@ -2,6 +2,17 @@ /* * Stack depot - a stack trace storage that avoids duplication. * + * Stack depot is intended to be used by subsystems that need to store and + * later retrieve many potentially duplicated stack traces without wasting + * memory. + * + * For example, KASAN needs to save allocation and free stack traces for each + * object. Storing two stack traces per object requires a lot of memory (e.g. + * SLUB_DEBUG needs 256 bytes per object for that). Since allocation and free + * stack traces often repeat, using stack depot allows to save about 100x space. + * + * Stack traces are never removed from the stack depot. + * * Author: Alexander Potapenko * Copyright (C) 2016 Google, Inc. * @@ -57,24 +68,100 @@ static inline void stack_depot_request_early_init(void) { } static inline int stack_depot_early_init(void) { return 0; } #endif +/** + * __stack_depot_save - Save a stack trace to stack depot + * + * @entries: Pointer to the stack trace + * @nr_entries: Number of frames in the stack + * @alloc_flags: Allocation GFP flags + * @can_alloc: Allocate stack pools (increased chance of failure if false) + * + * Saves a stack trace from @entries array of size @nr_entries. If @can_alloc is + * %true, stack depot can replenish the stack pools in case no space is left + * (allocates using GFP flags of @alloc_flags). If @can_alloc is %false, avoids + * any allocations and fails if no space is left to store the stack trace. + * + * If the provided stack trace comes from the interrupt context, only the part + * up to the interrupt entry is saved. + * + * Context: Any context, but setting @can_alloc to %false is required if + * alloc_pages() cannot be used from the current context. Currently + * this is the case for contexts where neither %GFP_ATOMIC nor + * %GFP_NOWAIT can be used (NMI, raw_spin_lock). + * + * Return: Handle of the stack struct stored in depot, 0 on failure + */ depot_stack_handle_t __stack_depot_save(unsigned long *entries, unsigned int nr_entries, gfp_t gfp_flags, bool can_alloc); +/** + * stack_depot_save - Save a stack trace to stack depot + * + * @entries: Pointer to the stack trace + * @nr_entries: Number of frames in the stack + * @alloc_flags: Allocation GFP flags + * + * Context: Contexts where allocations via alloc_pages() are allowed. + * See __stack_depot_save() for more details. + * + * Return: Handle of the stack trace stored in depot, 0 on failure + */ depot_stack_handle_t stack_depot_save(unsigned long *entries, unsigned int nr_entries, gfp_t gfp_flags); +/** + * stack_depot_fetch - Fetch a stack trace from stack depot + * + * @handle: Stack depot handle returned from stack_depot_save() + * @entries: Pointer to store the address of the stack trace + * + * Return: Number of frames for the fetched stack + */ unsigned int stack_depot_fetch(depot_stack_handle_t handle, unsigned long **entries); +/** + * stack_depot_print - Print a stack trace from stack depot + * + * @stack: Stack depot handle returned from stack_depot_save() + */ void stack_depot_print(depot_stack_handle_t stack); +/** + * stack_depot_snprint - Print a stack trace from stack depot into a buffer + * + * @handle: Stack depot handle returned from stack_depot_save() + * @buf: Pointer to the print buffer + * @size: Size of the print buffer + * @spaces: Number of leading spaces to print + * + * Return: Number of bytes printed + */ int stack_depot_snprint(depot_stack_handle_t handle, char *buf, size_t size, int spaces); +/** + * stack_depot_set_extra_bits - Set extra bits in a stack depot handle + * + * @handle: Stack depot handle returned from stack_depot_save() + * @extra_bits: Value to set the extra bits + * + * Return: Stack depot handle with extra bits set + * + * Stack depot handles have a few unused bits, which can be used for storing + * user-specific information. These bits are transparent to the stack depot. + */ depot_stack_handle_t __must_check stack_depot_set_extra_bits( depot_stack_handle_t handle, unsigned int extra_bits); +/** + * stack_depot_get_extra_bits - Retrieve extra bits from a stack depot handle + * + * @handle: Stack depot handle with extra bits saved + * + * Return: Extra bits retrieved from the stack depot handle + */ unsigned int stack_depot_get_extra_bits(depot_stack_handle_t handle); #endif diff --git a/lib/stackdepot.c b/lib/stackdepot.c index aaa5d2f1abc2..036da8e295d1 100644 --- a/lib/stackdepot.c +++ b/lib/stackdepot.c @@ -2,21 +2,10 @@ /* * Stack depot - a stack trace storage that avoids duplication. * - * Stack depot is intended to be used by subsystems that need to store and - * later retrieve many potentially duplicated stack traces without wasting - * memory. - * - * For example, KASAN needs to save allocation and free stack traces for each - * object. Storing two stack traces per object requires a lot of memory (e.g. - * SLUB_DEBUG needs 256 bytes per object for that). Since allocation and free - * stack traces often repeat, using stack depot allows to save about 100x space. - * * Internally, stack depot maintains a hash table of unique stacktraces. The * stack traces themselves are stored contiguously one after another in a set * of separate page allocations. * - * Stack traces are never removed from stack depot. - * * Author: Alexander Potapenko * Copyright (C) 2016 Google, Inc. * @@ -360,29 +349,6 @@ static inline struct stack_record *find_stack(struct stack_record *bucket, return NULL; } -/** - * __stack_depot_save - Save a stack trace to stack depot - * - * @entries: Pointer to the stack trace - * @nr_entries: Number of frames in the stack - * @alloc_flags: Allocation GFP flags - * @can_alloc: Allocate stack pools (increased chance of failure if false) - * - * Saves a stack trace from @entries array of size @nr_entries. If @can_alloc is - * %true, stack depot can replenish the stack pools in case no space is left - * (allocates using GFP flags of @alloc_flags). If @can_alloc is %false, avoids - * any allocations and fails if no space is left to store the stack trace. - * - * If the provided stack trace comes from the interrupt context, only the part - * up to the interrupt entry is saved. - * - * Context: Any context, but setting @can_alloc to %false is required if - * alloc_pages() cannot be used from the current context. Currently - * this is the case for contexts where neither %GFP_ATOMIC nor - * %GFP_NOWAIT can be used (NMI, raw_spin_lock). - * - * Return: Handle of the stack struct stored in depot, 0 on failure - */ depot_stack_handle_t __stack_depot_save(unsigned long *entries, unsigned int nr_entries, gfp_t alloc_flags, bool can_alloc) @@ -477,18 +443,6 @@ fast_exit: } EXPORT_SYMBOL_GPL(__stack_depot_save); -/** - * stack_depot_save - Save a stack trace to stack depot - * - * @entries: Pointer to the stack trace - * @nr_entries: Number of frames in the stack - * @alloc_flags: Allocation GFP flags - * - * Context: Contexts where allocations via alloc_pages() are allowed. - * See __stack_depot_save() for more details. - * - * Return: Handle of the stack trace stored in depot, 0 on failure - */ depot_stack_handle_t stack_depot_save(unsigned long *entries, unsigned int nr_entries, gfp_t alloc_flags) @@ -497,14 +451,6 @@ depot_stack_handle_t stack_depot_save(unsigned long *entries, } EXPORT_SYMBOL_GPL(stack_depot_save); -/** - * stack_depot_fetch - Fetch a stack trace from stack depot - * - * @handle: Stack depot handle returned from stack_depot_save() - * @entries: Pointer to store the address of the stack trace - * - * Return: Number of frames for the fetched stack - */ unsigned int stack_depot_fetch(depot_stack_handle_t handle, unsigned long **entries) { @@ -537,11 +483,6 @@ unsigned int stack_depot_fetch(depot_stack_handle_t handle, } EXPORT_SYMBOL_GPL(stack_depot_fetch); -/** - * stack_depot_print - Print a stack trace from stack depot - * - * @stack: Stack depot handle returned from stack_depot_save() - */ void stack_depot_print(depot_stack_handle_t stack) { unsigned long *entries; @@ -553,16 +494,6 @@ void stack_depot_print(depot_stack_handle_t stack) } EXPORT_SYMBOL_GPL(stack_depot_print); -/** - * stack_depot_snprint - Print a stack trace from stack depot into a buffer - * - * @handle: Stack depot handle returned from stack_depot_save() - * @buf: Pointer to the print buffer - * @size: Size of the print buffer - * @spaces: Number of leading spaces to print - * - * Return: Number of bytes printed - */ int stack_depot_snprint(depot_stack_handle_t handle, char *buf, size_t size, int spaces) { @@ -575,17 +506,6 @@ int stack_depot_snprint(depot_stack_handle_t handle, char *buf, size_t size, } EXPORT_SYMBOL_GPL(stack_depot_snprint); -/** - * stack_depot_set_extra_bits - Set extra bits in a stack depot handle - * - * @handle: Stack depot handle returned from stack_depot_save() - * @extra_bits: Value to set the extra bits - * - * Return: Stack depot handle with extra bits set - * - * Stack depot handles have a few unused bits, which can be used for storing - * user-specific information. These bits are transparent to the stack depot. - */ depot_stack_handle_t __must_check stack_depot_set_extra_bits( depot_stack_handle_t handle, unsigned int extra_bits) { @@ -600,13 +520,6 @@ depot_stack_handle_t __must_check stack_depot_set_extra_bits( } EXPORT_SYMBOL(stack_depot_set_extra_bits); -/** - * stack_depot_get_extra_bits - Retrieve extra bits from a stack depot handle - * - * @handle: Stack depot handle with extra bits saved - * - * Return: Extra bits retrieved from the stack depot handle - */ unsigned int stack_depot_get_extra_bits(depot_stack_handle_t handle) { union handle_parts parts = { .handle = handle }; -- cgit v1.2.3 From 64c8902ed4418317cd416c566f896bd4a92b2efc Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Mon, 13 Feb 2023 20:34:39 +0800 Subject: migrate_pages: split unmap_and_move() to _unmap() and _move() This is a preparation patch to batch the folio unmapping and moving. In this patch, unmap_and_move() is split to migrate_folio_unmap() and migrate_folio_move(). So, we can batch _unmap() and _move() in different loops later. To pass some information between unmap and move, the original unused dst->mapping and dst->private are used. Link: https://lkml.kernel.org/r/20230213123444.155149-5-ying.huang@intel.com Signed-off-by: "Huang, Ying" Reviewed-by: Baolin Wang Reviewed-by: Xin Hao Cc: Zi Yan Cc: Yang Shi Cc: Oscar Salvador Cc: Matthew Wilcox Cc: Bharata B Rao Cc: Alistair Popple Cc: Minchan Kim Cc: Mike Kravetz Cc: Hyeonggon Yoo <42.hyeyoo@gmail.com> Signed-off-by: Andrew Morton --- include/linux/migrate.h | 1 + mm/migrate.c | 169 ++++++++++++++++++++++++++++++++++++------------ 2 files changed, 129 insertions(+), 41 deletions(-) (limited to 'include/linux') diff --git a/include/linux/migrate.h b/include/linux/migrate.h index bdff950a8bb4..c88b96b48be7 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -18,6 +18,7 @@ struct migration_target_control; * - zero on page migration success; */ #define MIGRATEPAGE_SUCCESS 0 +#define MIGRATEPAGE_UNMAP 1 /** * struct movable_operations - Driver page migration diff --git a/mm/migrate.c b/mm/migrate.c index d436f35fa145..5fd18a7cce62 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1027,11 +1027,53 @@ out: return rc; } -static int __unmap_and_move(struct folio *src, struct folio *dst, +/* + * To record some information during migration, we use some unused + * fields (mapping and private) of struct folio of the newly allocated + * destination folio. This is safe because nobody is using them + * except us. + */ +static void __migrate_folio_record(struct folio *dst, + unsigned long page_was_mapped, + struct anon_vma *anon_vma) +{ + dst->mapping = (void *)anon_vma; + dst->private = (void *)page_was_mapped; +} + +static void __migrate_folio_extract(struct folio *dst, + int *page_was_mappedp, + struct anon_vma **anon_vmap) +{ + *anon_vmap = (void *)dst->mapping; + *page_was_mappedp = (unsigned long)dst->private; + dst->mapping = NULL; + dst->private = NULL; +} + +/* Cleanup src folio upon migration success */ +static void migrate_folio_done(struct folio *src, + enum migrate_reason reason) +{ + /* + * Compaction can migrate also non-LRU pages which are + * not accounted to NR_ISOLATED_*. They can be recognized + * as __PageMovable + */ + if (likely(!__folio_test_movable(src))) + mod_node_page_state(folio_pgdat(src), NR_ISOLATED_ANON + + folio_is_file_lru(src), -folio_nr_pages(src)); + + if (reason != MR_MEMORY_FAILURE) + /* We release the page in page_handle_poison. */ + folio_put(src); +} + +static int __migrate_folio_unmap(struct folio *src, struct folio *dst, int force, enum migrate_mode mode) { int rc = -EAGAIN; - bool page_was_mapped = false; + int page_was_mapped = 0; struct anon_vma *anon_vma = NULL; bool is_lru = !__PageMovable(&src->page); @@ -1107,8 +1149,8 @@ static int __unmap_and_move(struct folio *src, struct folio *dst, goto out_unlock; if (unlikely(!is_lru)) { - rc = move_to_new_folio(dst, src, mode); - goto out_unlock_both; + __migrate_folio_record(dst, page_was_mapped, anon_vma); + return MIGRATEPAGE_UNMAP; } /* @@ -1133,11 +1175,42 @@ static int __unmap_and_move(struct folio *src, struct folio *dst, VM_BUG_ON_FOLIO(folio_test_anon(src) && !folio_test_ksm(src) && !anon_vma, src); try_to_migrate(src, 0); - page_was_mapped = true; + page_was_mapped = 1; } - if (!folio_mapped(src)) - rc = move_to_new_folio(dst, src, mode); + if (!folio_mapped(src)) { + __migrate_folio_record(dst, page_was_mapped, anon_vma); + return MIGRATEPAGE_UNMAP; + } + + if (page_was_mapped) + remove_migration_ptes(src, src, false); + +out_unlock_both: + folio_unlock(dst); +out_unlock: + /* Drop an anon_vma reference if we took one */ + if (anon_vma) + put_anon_vma(anon_vma); + folio_unlock(src); +out: + + return rc; +} + +static int __migrate_folio_move(struct folio *src, struct folio *dst, + enum migrate_mode mode) +{ + int rc; + int page_was_mapped = 0; + struct anon_vma *anon_vma = NULL; + bool is_lru = !__PageMovable(&src->page); + + __migrate_folio_extract(dst, &page_was_mapped, &anon_vma); + + rc = move_to_new_folio(dst, src, mode); + if (unlikely(!is_lru)) + goto out_unlock_both; /* * When successful, push dst to LRU immediately: so that if it @@ -1160,12 +1233,10 @@ static int __unmap_and_move(struct folio *src, struct folio *dst, out_unlock_both: folio_unlock(dst); -out_unlock: /* Drop an anon_vma reference if we took one */ if (anon_vma) put_anon_vma(anon_vma); folio_unlock(src); -out: /* * If migration is successful, decrease refcount of dst, * which will not free the page because new page owner increased @@ -1177,19 +1248,15 @@ out: return rc; } -/* - * Obtain the lock on folio, remove all ptes and migrate the folio - * to the newly allocated folio in dst. - */ -static int unmap_and_move(new_page_t get_new_page, - free_page_t put_new_page, - unsigned long private, struct folio *src, - int force, enum migrate_mode mode, - enum migrate_reason reason, - struct list_head *ret) +/* Obtain the lock on page, remove all ptes. */ +static int migrate_folio_unmap(new_page_t get_new_page, free_page_t put_new_page, + unsigned long private, struct folio *src, + struct folio **dstp, int force, + enum migrate_mode mode, enum migrate_reason reason, + struct list_head *ret) { struct folio *dst; - int rc = MIGRATEPAGE_SUCCESS; + int rc = MIGRATEPAGE_UNMAP; struct page *newpage = NULL; if (!thp_migration_supported() && folio_test_transhuge(src)) @@ -1200,20 +1267,49 @@ static int unmap_and_move(new_page_t get_new_page, folio_clear_active(src); folio_clear_unevictable(src); /* free_pages_prepare() will clear PG_isolated. */ - goto out; + list_del(&src->lru); + migrate_folio_done(src, reason); + return MIGRATEPAGE_SUCCESS; } newpage = get_new_page(&src->page, private); if (!newpage) return -ENOMEM; dst = page_folio(newpage); + *dstp = dst; dst->private = NULL; - rc = __unmap_and_move(src, dst, force, mode); + rc = __migrate_folio_unmap(src, dst, force, mode); + if (rc == MIGRATEPAGE_UNMAP) + return rc; + + /* + * A folio that has not been unmapped will be restored to + * right list unless we want to retry. + */ + if (rc != -EAGAIN) + list_move_tail(&src->lru, ret); + + if (put_new_page) + put_new_page(&dst->page, private); + else + folio_put(dst); + + return rc; +} + +/* Migrate the folio to the newly allocated folio in dst. */ +static int migrate_folio_move(free_page_t put_new_page, unsigned long private, + struct folio *src, struct folio *dst, + enum migrate_mode mode, enum migrate_reason reason, + struct list_head *ret) +{ + int rc; + + rc = __migrate_folio_move(src, dst, mode); if (rc == MIGRATEPAGE_SUCCESS) set_page_owner_migrate_reason(&dst->page, reason); -out: if (rc != -EAGAIN) { /* * A folio that has been migrated has all references @@ -1229,20 +1325,7 @@ out: * we want to retry. */ if (rc == MIGRATEPAGE_SUCCESS) { - /* - * Compaction can migrate also non-LRU folios which are - * not accounted to NR_ISOLATED_*. They can be recognized - * as __folio_test_movable - */ - if (likely(!__folio_test_movable(src))) - mod_node_page_state(folio_pgdat(src), NR_ISOLATED_ANON + - folio_is_file_lru(src), -folio_nr_pages(src)); - - if (reason != MR_MEMORY_FAILURE) - /* - * We release the folio in page_handle_poison. - */ - folio_put(src); + migrate_folio_done(src, reason); } else { if (rc != -EAGAIN) list_add_tail(&src->lru, ret); @@ -1534,7 +1617,7 @@ static int migrate_pages_batch(struct list_head *from, new_page_t get_new_page, int pass = 0; bool is_large = false; bool is_thp = false; - struct folio *folio, *folio2; + struct folio *folio, *folio2, *dst = NULL; int rc, nr_pages; LIST_HEAD(split_folios); bool nosplit = (reason == MR_NUMA_MISPLACED); @@ -1561,9 +1644,13 @@ split_folio_migration: cond_resched(); - rc = unmap_and_move(get_new_page, put_new_page, - private, folio, pass > 2, mode, - reason, ret_folios); + rc = migrate_folio_unmap(get_new_page, put_new_page, private, + folio, &dst, pass > 2, mode, + reason, ret_folios); + if (rc == MIGRATEPAGE_UNMAP) + rc = migrate_folio_move(put_new_page, private, + folio, dst, mode, + reason, ret_folios); /* * The rules are: * Success: folio will be freed -- cgit v1.2.3 From f7a449f779608efe1941a0e0c4bd7b5f57000be7 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Mon, 13 Feb 2023 11:29:22 -0800 Subject: mm: memcontrol: rename memcg_kmem_enabled() Currently there are two kmem-related helper functions with a confusing semantics: memcg_kmem_enabled() and mem_cgroup_kmem_disabled(). The problem is that an obvious expectation memcg_kmem_enabled() == !mem_cgroup_kmem_disabled(), can be false. mem_cgroup_kmem_disabled() is similar to mem_cgroup_disabled(): it returns true only if CONFIG_MEMCG_KMEM is not set or the kmem accounting is disabled using a boot time kernel option "cgroup.memory=nokmem". It never changes the value dynamically. memcg_kmem_enabled() is different: it always returns false until the first non-root memory cgroup will get online (assuming the kernel memory accounting is enabled). It's goal is to improve the performance on systems without the cgroupfs mounted/memory controller enabled or on the systems with only the root memory cgroup. To make things more obvious and avoid potential bugs, let's rename memcg_kmem_enabled() to memcg_kmem_online(). Link: https://lkml.kernel.org/r/20230213192922.1146370-1-roman.gushchin@linux.dev Signed-off-by: Roman Gushchin Acked-by: Muchun Song Acked-by: Michal Hocko Cc: Johannes Weiner Cc: Shakeel Butt Cc: Dennis Zhou Signed-off-by: Andrew Morton --- include/linux/memcontrol.h | 14 +++++++------- mm/memcontrol.c | 8 ++++---- mm/page_alloc.c | 8 ++++---- mm/percpu.c | 2 +- mm/slab.h | 10 +++++----- mm/vmscan.c | 2 +- 6 files changed, 22 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 35478695cabf..5567319027d1 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1776,24 +1776,24 @@ struct obj_cgroup *get_obj_cgroup_from_page(struct page *page); int obj_cgroup_charge(struct obj_cgroup *objcg, gfp_t gfp, size_t size); void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size); -extern struct static_key_false memcg_kmem_enabled_key; +extern struct static_key_false memcg_kmem_online_key; -static inline bool memcg_kmem_enabled(void) +static inline bool memcg_kmem_online(void) { - return static_branch_likely(&memcg_kmem_enabled_key); + return static_branch_likely(&memcg_kmem_online_key); } static inline int memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order) { - if (memcg_kmem_enabled()) + if (memcg_kmem_online()) return __memcg_kmem_charge_page(page, gfp, order); return 0; } static inline void memcg_kmem_uncharge_page(struct page *page, int order) { - if (memcg_kmem_enabled()) + if (memcg_kmem_online()) __memcg_kmem_uncharge_page(page, order); } @@ -1814,7 +1814,7 @@ static inline void count_objcg_event(struct obj_cgroup *objcg, { struct mem_cgroup *memcg; - if (!memcg_kmem_enabled()) + if (!memcg_kmem_online()) return; rcu_read_lock(); @@ -1854,7 +1854,7 @@ static inline struct obj_cgroup *get_obj_cgroup_from_page(struct page *page) return NULL; } -static inline bool memcg_kmem_enabled(void) +static inline bool memcg_kmem_online(void) { return false; } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 17335459d8dc..3e3cdb9bed95 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -345,8 +345,8 @@ static void memcg_reparent_objcgs(struct mem_cgroup *memcg, * conditional to this static branch, we'll have to allow modules that does * kmem_cache_alloc and the such to see this symbol as well */ -DEFINE_STATIC_KEY_FALSE(memcg_kmem_enabled_key); -EXPORT_SYMBOL(memcg_kmem_enabled_key); +DEFINE_STATIC_KEY_FALSE(memcg_kmem_online_key); +EXPORT_SYMBOL(memcg_kmem_online_key); #endif /** @@ -3034,7 +3034,7 @@ struct obj_cgroup *get_obj_cgroup_from_page(struct page *page) { struct obj_cgroup *objcg; - if (!memcg_kmem_enabled()) + if (!memcg_kmem_online()) return NULL; if (PageMemcgKmem(page)) { @@ -3746,7 +3746,7 @@ static int memcg_online_kmem(struct mem_cgroup *memcg) objcg->memcg = memcg; rcu_assign_pointer(memcg->objcg, objcg); - static_branch_enable(&memcg_kmem_enabled_key); + static_branch_enable(&memcg_kmem_online_key); memcg->kmemcg_id = memcg->id.id; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 4b6bcec41c8f..4c9ab8b93b1a 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1410,7 +1410,7 @@ static __always_inline bool free_pages_prepare(struct page *page, * Do not let hwpoison pages hit pcplists/buddy * Untie memcg state and reset page's owner */ - if (memcg_kmem_enabled() && PageMemcgKmem(page)) + if (memcg_kmem_online() && PageMemcgKmem(page)) __memcg_kmem_uncharge_page(page, order); reset_page_owner(page, order); page_table_check_free(page, order); @@ -1441,7 +1441,7 @@ static __always_inline bool free_pages_prepare(struct page *page, } if (PageMappingFlags(page)) page->mapping = NULL; - if (memcg_kmem_enabled() && PageMemcgKmem(page)) + if (memcg_kmem_online() && PageMemcgKmem(page)) __memcg_kmem_uncharge_page(page, order); if (check_free && free_page_is_bad(page)) bad++; @@ -5432,7 +5432,7 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, goto out; /* Bulk allocator does not support memcg accounting. */ - if (memcg_kmem_enabled() && (gfp & __GFP_ACCOUNT)) + if (memcg_kmem_online() && (gfp & __GFP_ACCOUNT)) goto failed; /* Use the single page allocator for one page. */ @@ -5604,7 +5604,7 @@ struct page *__alloc_pages(gfp_t gfp, unsigned int order, int preferred_nid, page = __alloc_pages_slowpath(alloc_gfp, order, &ac); out: - if (memcg_kmem_enabled() && (gfp & __GFP_ACCOUNT) && page && + if (memcg_kmem_online() && (gfp & __GFP_ACCOUNT) && page && unlikely(__memcg_kmem_charge_page(page, gfp, order) != 0)) { __free_pages(page, order); page = NULL; diff --git a/mm/percpu.c b/mm/percpu.c index acd78da0493b..28e07ede46f6 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -1625,7 +1625,7 @@ static bool pcpu_memcg_pre_alloc_hook(size_t size, gfp_t gfp, { struct obj_cgroup *objcg; - if (!memcg_kmem_enabled() || !(gfp & __GFP_ACCOUNT)) + if (!memcg_kmem_online() || !(gfp & __GFP_ACCOUNT)) return true; objcg = get_obj_cgroup_from_current(); diff --git a/mm/slab.h b/mm/slab.h index 63fb4c00d529..43966aa5fadf 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -494,7 +494,7 @@ static inline bool memcg_slab_pre_alloc_hook(struct kmem_cache *s, { struct obj_cgroup *objcg; - if (!memcg_kmem_enabled()) + if (!memcg_kmem_online()) return true; if (!(flags & __GFP_ACCOUNT) && !(s->flags & SLAB_ACCOUNT)) @@ -535,7 +535,7 @@ static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s, unsigned long off; size_t i; - if (!memcg_kmem_enabled() || !objcg) + if (!memcg_kmem_online() || !objcg) return; for (i = 0; i < size; i++) { @@ -567,7 +567,7 @@ static inline void memcg_slab_free_hook(struct kmem_cache *s, struct slab *slab, struct obj_cgroup **objcgs; int i; - if (!memcg_kmem_enabled()) + if (!memcg_kmem_online()) return; objcgs = slab_objcgs(slab); @@ -649,7 +649,7 @@ static inline struct kmem_cache *virt_to_cache(const void *obj) static __always_inline void account_slab(struct slab *slab, int order, struct kmem_cache *s, gfp_t gfp) { - if (memcg_kmem_enabled() && (s->flags & SLAB_ACCOUNT)) + if (memcg_kmem_online() && (s->flags & SLAB_ACCOUNT)) memcg_alloc_slab_cgroups(slab, s, gfp, true); mod_node_page_state(slab_pgdat(slab), cache_vmstat_idx(s), @@ -659,7 +659,7 @@ static __always_inline void account_slab(struct slab *slab, int order, static __always_inline void unaccount_slab(struct slab *slab, int order, struct kmem_cache *s) { - if (memcg_kmem_enabled()) + if (memcg_kmem_online()) memcg_free_slab_cgroups(slab); mod_node_page_state(slab_pgdat(slab), cache_vmstat_idx(s), diff --git a/mm/vmscan.c b/mm/vmscan.c index 34535bbd4fe9..098c79129c42 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -915,7 +915,7 @@ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, } /* Call non-slab shrinkers even though kmem is disabled */ - if (!memcg_kmem_enabled() && + if (!memcg_kmem_online() && !(shrinker->flags & SHRINKER_NONSLAB)) continue; -- cgit v1.2.3 From 4b7296aa6c6618d6a6840fbe857e4990f626bd90 Mon Sep 17 00:00:00 2001 From: Or Har-Toov Date: Tue, 17 Jan 2023 15:14:49 +0200 Subject: net/mlx5: Expose bits for querying special mkeys Add needed HW bits to query the values of all special mkeys. Link: https://lore.kernel.org/r/080ebb563a9717c15b1ea75d669aede676df386b.1673960981.git.leon@kernel.org Signed-off-by: Or Har-Toov Reviewed-by: Michael Guralnik Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/linux/mlx5/mlx5_ifc.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index c3d3a2eef7d4..67cfac8fbe46 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1485,7 +1485,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 relaxed_ordering_write[0x1]; u8 relaxed_ordering_read[0x1]; u8 log_max_mkey[0x6]; - u8 reserved_at_f0[0x8]; + u8 reserved_at_f0[0x6]; + u8 terminate_scatter_list_mkey[0x1]; + u8 repeated_mkey[0x1]; u8 dump_fill_mkey[0x1]; u8 reserved_at_f9[0x2]; u8 fast_teardown[0x1]; @@ -5210,7 +5212,11 @@ struct mlx5_ifc_query_special_contexts_out_bits { u8 null_mkey[0x20]; - u8 reserved_at_a0[0x60]; + u8 terminate_scatter_list_mkey[0x20]; + + u8 repeated_mkey[0x20]; + + u8 reserved_at_a0[0x20]; }; struct mlx5_ifc_query_special_contexts_in_bits { -- cgit v1.2.3 From a419bfb7632095410adc3aecb1e863568f049add Mon Sep 17 00:00:00 2001 From: Or Har-Toov Date: Tue, 17 Jan 2023 15:14:50 +0200 Subject: net/mlx5: Change define name for 0x100 lkey value Change define of 0x100 lkey value from MLX5_INVALID_LKEY to be MLX5_TERMINATE_SCATTER_LIST_LKEY as 0x100 is the value of terminate_scatter_list_mkey. Link: https://lore.kernel.org/r/3a116dc3fbae4cb6b76a63d27d418830b06ade0c.1673960981.git.leon@kernel.org Signed-off-by: Or Har-Toov Reviewed-by: Michael Guralnik Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/mlx5/odp.c | 10 +++++----- drivers/infiniband/hw/mlx5/srq.c | 2 +- drivers/infiniband/hw/mlx5/wr.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 3 ++- include/linux/mlx5/qp.h | 2 +- 5 files changed, 10 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c index e6e021af6aa9..b4ebeadce67c 100644 --- a/drivers/infiniband/hw/mlx5/odp.c +++ b/drivers/infiniband/hw/mlx5/odp.c @@ -986,7 +986,7 @@ static int pagefault_data_segments(struct mlx5_ib_dev *dev, { int ret = 0, npages = 0; u64 io_virt; - u32 key; + __be32 key; u32 byte_count; size_t bcnt; int inline_segment; @@ -1000,7 +1000,7 @@ static int pagefault_data_segments(struct mlx5_ib_dev *dev, struct mlx5_wqe_data_seg *dseg = wqe; io_virt = be64_to_cpu(dseg->addr); - key = be32_to_cpu(dseg->lkey); + key = dseg->lkey; byte_count = be32_to_cpu(dseg->byte_count); inline_segment = !!(byte_count & MLX5_INLINE_SEG); bcnt = byte_count & ~MLX5_INLINE_SEG; @@ -1014,8 +1014,8 @@ static int pagefault_data_segments(struct mlx5_ib_dev *dev, } /* receive WQE end of sg list. */ - if (receive_queue && bcnt == 0 && key == MLX5_INVALID_LKEY && - io_virt == 0) + if (receive_queue && bcnt == 0 && + key == MLX5_TERMINATE_SCATTER_LIST_LKEY && io_virt == 0) break; if (!inline_segment && total_wqe_bytes) { @@ -1034,7 +1034,7 @@ static int pagefault_data_segments(struct mlx5_ib_dev *dev, continue; } - ret = pagefault_single_data_segment(dev, NULL, key, + ret = pagefault_single_data_segment(dev, NULL, be32_to_cpu(key), io_virt, bcnt, &pfault->bytes_committed, bytes_mapped); diff --git a/drivers/infiniband/hw/mlx5/srq.c b/drivers/infiniband/hw/mlx5/srq.c index 09b365a98bbf..0ac8d2c57365 100644 --- a/drivers/infiniband/hw/mlx5/srq.c +++ b/drivers/infiniband/hw/mlx5/srq.c @@ -447,7 +447,7 @@ int mlx5_ib_post_srq_recv(struct ib_srq *ibsrq, const struct ib_recv_wr *wr, if (i < srq->msrq.max_avail_gather) { scat[i].byte_count = 0; - scat[i].lkey = cpu_to_be32(MLX5_INVALID_LKEY); + scat[i].lkey = MLX5_TERMINATE_SCATTER_LIST_LKEY; scat[i].addr = 0; } } diff --git a/drivers/infiniband/hw/mlx5/wr.c b/drivers/infiniband/hw/mlx5/wr.c index 855f3f4fefad..bc44551493e2 100644 --- a/drivers/infiniband/hw/mlx5/wr.c +++ b/drivers/infiniband/hw/mlx5/wr.c @@ -1252,7 +1252,7 @@ int mlx5_ib_post_recv(struct ib_qp *ibqp, const struct ib_recv_wr *wr, if (i < qp->rq.max_gs) { scat[i].byte_count = 0; - scat[i].lkey = cpu_to_be32(MLX5_INVALID_LKEY); + scat[i].lkey = MLX5_TERMINATE_SCATTER_LIST_LKEY; scat[i].addr = 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 85b51039d2a6..a941a4880cc5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -829,7 +829,8 @@ static int mlx5e_alloc_rq(struct mlx5e_params *params, /* check if num_frags is not a pow of two */ if (rq->wqe.info.num_frags < (1 << rq->wqe.info.log_num_frags)) { wqe->data[f].byte_count = 0; - wqe->data[f].lkey = cpu_to_be32(MLX5_INVALID_LKEY); + wqe->data[f].lkey = + MLX5_TERMINATE_SCATTER_LIST_LKEY; wqe->data[f].addr = 0; } } diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index 4657d5c54abe..df55fbb65717 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -36,7 +36,7 @@ #include #include -#define MLX5_INVALID_LKEY 0x100 +#define MLX5_TERMINATE_SCATTER_LIST_LKEY cpu_to_be32(0x100) /* UMR (3 WQE_BB's) + SIG (3 WQE_BB's) + PSV (mem) + PSV (wire) */ #define MLX5_SIG_WQE_SIZE (MLX5_SEND_WQE_BB * 8) #define MLX5_DIF_SIZE 8 -- cgit v1.2.3 From d88cbbb39b4db057feb1552de31f22c02a21b36f Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Fri, 17 Feb 2023 10:29:10 +0100 Subject: blk-mq: Reorder fields in 'struct blk_mq_tag_set' Group some variables based on their sizes to reduce hole and avoid padding. On x86_64, this shrinks the size of 'struct blk_mq_tag_set' from 304 to 296 bytes. Signed-off-by: Christophe JAILLET Link: https://lore.kernel.org/r/6f249f9b02a3490283ef0278096556de41aa0cf0.1676626130.git.christophe.jaillet@wanadoo.fr Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 779fba613bd0..dd5ce1137f04 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -473,6 +473,7 @@ enum hctx_type { /** * struct blk_mq_tag_set - tag set that can be shared between request queues + * @ops: Pointers to functions that implement block driver behavior. * @map: One or more ctx -> hctx mappings. One map exists for each * hardware queue type (enum hctx_type) that the driver wishes * to support. There are no restrictions on maps being of the @@ -480,7 +481,6 @@ enum hctx_type { * types. * @nr_maps: Number of elements in the @map array. A number in the range * [1, HCTX_MAX_TYPES]. - * @ops: Pointers to functions that implement block driver behavior. * @nr_hw_queues: Number of hardware queues supported by the block driver that * owns this data structure. * @queue_depth: Number of tags per hardware queue, reserved tags included. @@ -505,9 +505,9 @@ enum hctx_type { * (BLK_MQ_F_BLOCKING). */ struct blk_mq_tag_set { + const struct blk_mq_ops *ops; struct blk_mq_queue_map map[HCTX_MAX_TYPES]; unsigned int nr_maps; - const struct blk_mq_ops *ops; unsigned int nr_hw_queues; unsigned int queue_depth; unsigned int reserved_tags; -- cgit v1.2.3 From 9cbad37ce8122de32a1529e394b468bc101c9e7f Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Thu, 9 Feb 2023 15:35:01 -0600 Subject: of: Add of_property_present() helper Add an of_property_present() function similar to fwnode_property_present(). of_property_read_bool() could be used directly, but it is cleaner to not use it on non-boolean properties. Reviewed-by: Frank Rowand Tested-by: Frank Rowand Link: https://lore.kernel.org/all/20230215215547.691573-1-robh@kernel.org/ Signed-off-by: Rob Herring --- include/linux/of.h | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index 8bb348666709..37afd04f36eb 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -1155,7 +1155,8 @@ static inline int of_property_read_string_index(const struct device_node *np, * @np: device node from which the property value is to be read. * @propname: name of the property to be searched. * - * Search for a property in a device node. + * Search for a boolean property in a device node. Usage on non-boolean + * property types is deprecated. * * Return: true if the property exists false otherwise. */ @@ -1167,6 +1168,20 @@ static inline bool of_property_read_bool(const struct device_node *np, return prop ? true : false; } +/** + * of_property_present - Test if a property is present in a node + * @np: device node to search for the property. + * @propname: name of the property to be searched. + * + * Test for a property present in a device node. + * + * Return: true if the property exists false otherwise. + */ +static inline bool of_property_present(const struct device_node *np, const char *propname) +{ + return of_property_read_bool(np, propname); +} + /** * of_property_read_u8_array - Find and read an array of u8 from a property. * -- cgit v1.2.3 From 2455f0e124d317dd08d337a7550a78a224d4ba41 Mon Sep 17 00:00:00 2001 From: Ross Zwisler Date: Wed, 15 Feb 2023 15:33:45 -0700 Subject: tracing: Always use canonical ftrace path The canonical location for the tracefs filesystem is at /sys/kernel/tracing. But, from Documentation/trace/ftrace.rst: Before 4.1, all ftrace tracing control files were within the debugfs file system, which is typically located at /sys/kernel/debug/tracing. For backward compatibility, when mounting the debugfs file system, the tracefs file system will be automatically mounted at: /sys/kernel/debug/tracing Many comments and Kconfig help messages in the tracing code still refer to this older debugfs path, so let's update them to avoid confusion. Link: https://lore.kernel.org/linux-trace-kernel/20230215223350.2658616-2-zwisler@google.com Acked-by: Masami Hiramatsu (Google) Reviewed-by: Mukesh Ojha Signed-off-by: Ross Zwisler Signed-off-by: Steven Rostedt (Google) --- include/linux/kernel.h | 2 +- include/linux/tracepoint.h | 4 ++-- kernel/trace/Kconfig | 20 ++++++++++---------- kernel/trace/kprobe_event_gen_test.c | 2 +- kernel/trace/ring_buffer.c | 2 +- kernel/trace/synth_event_gen_test.c | 2 +- kernel/trace/trace.c | 2 +- samples/user_events/example.c | 4 ++-- scripts/tracing/draw_functrace.py | 6 +++--- tools/lib/api/fs/tracing_path.c | 4 ++-- tools/tracing/latency/latency-collector.c | 2 +- 11 files changed, 25 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index fe6efb24d151..40bce7495af8 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -297,7 +297,7 @@ bool mac_pton(const char *s, u8 *mac); * * Use tracing_on/tracing_off when you want to quickly turn on or off * tracing. It simply enables or disables the recording of the trace events. - * This also corresponds to the user space /sys/kernel/debug/tracing/tracing_on + * This also corresponds to the user space /sys/kernel/tracing/tracing_on * file, which gives a means for the kernel and userspace to interact. * Place a tracing_off() in the kernel where you want tracing to end. * From user space, examine the trace, and then echo 1 > tracing_on diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 4b33b95eb8be..fa1004fcf810 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -471,7 +471,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) * * This is how the trace record is structured and will * * be saved into the ring buffer. These are the fields * * that will be exposed to user-space in - * * /sys/kernel/debug/tracing/events/<*>/format. + * * /sys/kernel/tracing/events/<*>/format. * * * * The declared 'local variable' is called '__entry' * * @@ -531,7 +531,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) * tracepoint callback (this is used by programmatic plugins and * can also by used by generic instrumentation like SystemTap), and * it is also used to expose a structured trace record in - * /sys/kernel/debug/tracing/events/. + * /sys/kernel/tracing/events/. * * A set of (un)registration functions can be passed to the variant * TRACE_EVENT_FN to perform any (un)registration work. diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index d7043043f59c..5f5e64f9e715 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -239,7 +239,7 @@ config DYNAMIC_FTRACE enabled, and the functions not enabled will not affect performance of the system. - See the files in /sys/kernel/debug/tracing: + See the files in /sys/kernel/tracing: available_filter_functions set_ftrace_filter set_ftrace_notrace @@ -299,7 +299,7 @@ config STACK_TRACER select KALLSYMS help This special tracer records the maximum stack footprint of the - kernel and displays it in /sys/kernel/debug/tracing/stack_trace. + kernel and displays it in /sys/kernel/tracing/stack_trace. This tracer works by hooking into every function call that the kernel executes, and keeping a maximum stack depth value and @@ -339,7 +339,7 @@ config IRQSOFF_TRACER disabled by default and can be runtime (re-)started via: - echo 0 > /sys/kernel/debug/tracing/tracing_max_latency + echo 0 > /sys/kernel/tracing/tracing_max_latency (Note that kernel size and overhead increase with this option enabled. This option and the preempt-off timing option can be @@ -363,7 +363,7 @@ config PREEMPT_TRACER disabled by default and can be runtime (re-)started via: - echo 0 > /sys/kernel/debug/tracing/tracing_max_latency + echo 0 > /sys/kernel/tracing/tracing_max_latency (Note that kernel size and overhead increase with this option enabled. This option and the irqs-off timing option can be @@ -515,7 +515,7 @@ config TRACER_SNAPSHOT Allow tracing users to take snapshot of the current buffer using the ftrace interface, e.g.: - echo 1 > /sys/kernel/debug/tracing/snapshot + echo 1 > /sys/kernel/tracing/snapshot cat snapshot config TRACER_SNAPSHOT_PER_CPU_SWAP @@ -527,7 +527,7 @@ config TRACER_SNAPSHOT_PER_CPU_SWAP full swap (all buffers). If this is set, then the following is allowed: - echo 1 > /sys/kernel/debug/tracing/per_cpu/cpu2/snapshot + echo 1 > /sys/kernel/tracing/per_cpu/cpu2/snapshot After which, only the tracing buffer for CPU 2 was swapped with the main tracing buffer, and the other CPU buffers remain the same. @@ -574,7 +574,7 @@ config PROFILE_ANNOTATED_BRANCHES This tracer profiles all likely and unlikely macros in the kernel. It will display the results in: - /sys/kernel/debug/tracing/trace_stat/branch_annotated + /sys/kernel/tracing/trace_stat/branch_annotated Note: this will add a significant overhead; only turn this on if you need to profile the system's use of these macros. @@ -587,7 +587,7 @@ config PROFILE_ALL_BRANCHES taken in the kernel is recorded whether it hit or miss. The results will be displayed in: - /sys/kernel/debug/tracing/trace_stat/branch_all + /sys/kernel/tracing/trace_stat/branch_all This option also enables the likely/unlikely profiler. @@ -638,8 +638,8 @@ config BLK_DEV_IO_TRACE Tracing also is possible using the ftrace interface, e.g.: echo 1 > /sys/block/sda/sda1/trace/enable - echo blk > /sys/kernel/debug/tracing/current_tracer - cat /sys/kernel/debug/tracing/trace_pipe + echo blk > /sys/kernel/tracing/current_tracer + cat /sys/kernel/tracing/trace_pipe If unsure, say N. diff --git a/kernel/trace/kprobe_event_gen_test.c b/kernel/trace/kprobe_event_gen_test.c index c736487fc0e4..4850fdfe27f1 100644 --- a/kernel/trace/kprobe_event_gen_test.c +++ b/kernel/trace/kprobe_event_gen_test.c @@ -21,7 +21,7 @@ * Then: * * # insmod kernel/trace/kprobe_event_gen_test.ko - * # cat /sys/kernel/debug/tracing/trace + * # cat /sys/kernel/tracing/trace * * You should see many instances of the "gen_kprobe_test" and * "gen_kretprobe_test" events in the trace buffer. diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 45d4a23d6044..071184324d18 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -2886,7 +2886,7 @@ rb_check_timestamp(struct ring_buffer_per_cpu *cpu_buffer, sched_clock_stable() ? "" : "If you just came from a suspend/resume,\n" "please switch to the trace global clock:\n" - " echo global > /sys/kernel/debug/tracing/trace_clock\n" + " echo global > /sys/kernel/tracing/trace_clock\n" "or add trace_clock=global to the kernel command line\n"); } diff --git a/kernel/trace/synth_event_gen_test.c b/kernel/trace/synth_event_gen_test.c index 8d77526892f4..8dfe85499d4a 100644 --- a/kernel/trace/synth_event_gen_test.c +++ b/kernel/trace/synth_event_gen_test.c @@ -22,7 +22,7 @@ * Then: * * # insmod kernel/trace/synth_event_gen_test.ko - * # cat /sys/kernel/debug/tracing/trace + * # cat /sys/kernel/tracing/trace * * You should see several events in the trace buffer - * "create_synth_test", "empty_synth_test", and several instances of diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 97c88711f270..fbb602a8b64b 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1187,7 +1187,7 @@ void tracing_snapshot_instance(struct trace_array *tr) * * Note, make sure to allocate the snapshot with either * a tracing_snapshot_alloc(), or by doing it manually - * with: echo 1 > /sys/kernel/debug/tracing/snapshot + * with: echo 1 > /sys/kernel/tracing/snapshot * * If the snapshot buffer is not allocated, it will stop tracing. * Basically making a permanent snapshot. diff --git a/samples/user_events/example.c b/samples/user_events/example.c index d06dc24156ec..18e34c9d708e 100644 --- a/samples/user_events/example.c +++ b/samples/user_events/example.c @@ -23,8 +23,8 @@ #endif /* Assumes debugfs is mounted */ -const char *data_file = "/sys/kernel/debug/tracing/user_events_data"; -const char *status_file = "/sys/kernel/debug/tracing/user_events_status"; +const char *data_file = "/sys/kernel/tracing/user_events_data"; +const char *status_file = "/sys/kernel/tracing/user_events_status"; static int event_status(long **status) { diff --git a/scripts/tracing/draw_functrace.py b/scripts/tracing/draw_functrace.py index 438516bdfb3c..42fa87300941 100755 --- a/scripts/tracing/draw_functrace.py +++ b/scripts/tracing/draw_functrace.py @@ -12,9 +12,9 @@ calls. Only the functions's names and the call time are provided. Usage: Be sure that you have CONFIG_FUNCTION_TRACER - # mount -t debugfs nodev /sys/kernel/debug - # echo function > /sys/kernel/debug/tracing/current_tracer - $ cat /sys/kernel/debug/tracing/trace_pipe > ~/raw_trace_func + # mount -t tracefs nodev /sys/kernel/tracing + # echo function > /sys/kernel/tracing/current_tracer + $ cat /sys/kernel/tracing/trace_pipe > ~/raw_trace_func Wait some times but not too much, the script is a bit slow. Break the pipe (Ctrl + Z) $ scripts/tracing/draw_functrace.py < ~/raw_trace_func > draw_functrace diff --git a/tools/lib/api/fs/tracing_path.c b/tools/lib/api/fs/tracing_path.c index b8e457c841ab..7ba3e81274e8 100644 --- a/tools/lib/api/fs/tracing_path.c +++ b/tools/lib/api/fs/tracing_path.c @@ -14,8 +14,8 @@ #include "tracing_path.h" static char tracing_mnt[PATH_MAX] = "/sys/kernel/debug"; -static char tracing_path[PATH_MAX] = "/sys/kernel/debug/tracing"; -static char tracing_events_path[PATH_MAX] = "/sys/kernel/debug/tracing/events"; +static char tracing_path[PATH_MAX] = "/sys/kernel/tracing"; +static char tracing_events_path[PATH_MAX] = "/sys/kernel/tracing/events"; static void __tracing_path_set(const char *tracing, const char *mountpoint) { diff --git a/tools/tracing/latency/latency-collector.c b/tools/tracing/latency/latency-collector.c index 59a7f2346eab..0fd9c747d396 100644 --- a/tools/tracing/latency/latency-collector.c +++ b/tools/tracing/latency/latency-collector.c @@ -1584,7 +1584,7 @@ static void *do_printloop(void *arg) /* * Toss a coin to decide if we want to sleep before printing * out the backtrace. The reason for this is that opening - * /sys/kernel/debug/tracing/trace will cause a blackout of + * /sys/kernel/tracing/trace will cause a blackout of * hundreds of ms, where no latencies will be noted by the * latency tracer. Thus by randomly sleeping we try to avoid * missing traces systematically due to this. With this option -- cgit v1.2.3 From 66fb1d5df6ace316a4a6e2c31e13fc123ea2b644 Mon Sep 17 00:00:00 2001 From: Edward Srouji Date: Thu, 16 Feb 2023 11:13:45 +0200 Subject: IB/mlx5: Extend debug control for CC parameters This patch adds rtt_resp_dscp to the current debug controllability of congestion control (CC) parameters. rtt_resp_dscp can be read or written through debugfs. If set, its value overwrites the DSCP of the generated RTT response. Signed-off-by: Edward Srouji Reviewed-by: Maor Gottlieb Link: https://lore.kernel.org/r/1dcc3440ee53c688f19f579a051ded81a2aaa70a.1676538714.git.leon@kernel.org Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/mlx5/cong.c | 28 +++++++++++++++++++++++++--- drivers/infiniband/hw/mlx5/mlx5_ib.h | 2 ++ include/linux/mlx5/mlx5_ifc.h | 12 ++++++++++++ 3 files changed, 39 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/infiniband/hw/mlx5/cong.c b/drivers/infiniband/hw/mlx5/cong.c index 290ea8ac3838..f87531318feb 100644 --- a/drivers/infiniband/hw/mlx5/cong.c +++ b/drivers/infiniband/hw/mlx5/cong.c @@ -38,6 +38,7 @@ enum mlx5_ib_cong_node_type { MLX5_IB_RROCE_ECN_RP = 1, MLX5_IB_RROCE_ECN_NP = 2, + MLX5_IB_RROCE_GENERAL = 3, }; static const char * const mlx5_ib_dbg_cc_name[] = { @@ -61,6 +62,8 @@ static const char * const mlx5_ib_dbg_cc_name[] = { "np_cnp_dscp", "np_cnp_prio_mode", "np_cnp_prio", + "rtt_resp_dscp_valid", + "rtt_resp_dscp", }; #define MLX5_IB_RP_CLAMP_TGT_RATE_ATTR BIT(1) @@ -84,14 +87,18 @@ static const char * const mlx5_ib_dbg_cc_name[] = { #define MLX5_IB_NP_CNP_DSCP_ATTR BIT(3) #define MLX5_IB_NP_CNP_PRIO_MODE_ATTR BIT(4) +#define MLX5_IB_GENERAL_RTT_RESP_DSCP_ATTR BIT(0) + static enum mlx5_ib_cong_node_type mlx5_ib_param_to_node(enum mlx5_ib_dbg_cc_types param_offset) { - if (param_offset >= MLX5_IB_DBG_CC_RP_CLAMP_TGT_RATE && - param_offset <= MLX5_IB_DBG_CC_RP_GD) + if (param_offset <= MLX5_IB_DBG_CC_RP_GD) return MLX5_IB_RROCE_ECN_RP; - else + + if (param_offset <= MLX5_IB_DBG_CC_NP_CNP_PRIO) return MLX5_IB_RROCE_ECN_NP; + + return MLX5_IB_RROCE_GENERAL; } static u32 mlx5_get_cc_param_val(void *field, int offset) @@ -157,6 +164,12 @@ static u32 mlx5_get_cc_param_val(void *field, int offset) case MLX5_IB_DBG_CC_NP_CNP_PRIO: return MLX5_GET(cong_control_r_roce_ecn_np, field, cnp_802p_prio); + case MLX5_IB_DBG_CC_GENERAL_RTT_RESP_DSCP_VALID: + return MLX5_GET(cong_control_r_roce_general, field, + rtt_resp_dscp_valid); + case MLX5_IB_DBG_CC_GENERAL_RTT_RESP_DSCP: + return MLX5_GET(cong_control_r_roce_general, field, + rtt_resp_dscp); default: return 0; } @@ -264,6 +277,15 @@ static void mlx5_ib_set_cc_param_mask_val(void *field, int offset, MLX5_SET(cong_control_r_roce_ecn_np, field, cnp_prio_mode, 0); MLX5_SET(cong_control_r_roce_ecn_np, field, cnp_802p_prio, var); break; + case MLX5_IB_DBG_CC_GENERAL_RTT_RESP_DSCP_VALID: + *attr_mask |= MLX5_IB_GENERAL_RTT_RESP_DSCP_ATTR; + MLX5_SET(cong_control_r_roce_general, field, rtt_resp_dscp_valid, var); + break; + case MLX5_IB_DBG_CC_GENERAL_RTT_RESP_DSCP: + *attr_mask |= MLX5_IB_GENERAL_RTT_RESP_DSCP_ATTR; + MLX5_SET(cong_control_r_roce_general, field, rtt_resp_dscp_valid, 1); + MLX5_SET(cong_control_r_roce_general, field, rtt_resp_dscp, var); + break; } } diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h index f6c799f75b8e..efa4dc6e7dee 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -888,6 +888,8 @@ enum mlx5_ib_dbg_cc_types { MLX5_IB_DBG_CC_NP_CNP_DSCP, MLX5_IB_DBG_CC_NP_CNP_PRIO_MODE, MLX5_IB_DBG_CC_NP_CNP_PRIO, + MLX5_IB_DBG_CC_GENERAL_RTT_RESP_DSCP_VALID, + MLX5_IB_DBG_CC_GENERAL_RTT_RESP_DSCP, MLX5_IB_DBG_CC_MAX, }; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 67cfac8fbe46..c63b92aa4c96 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -2159,6 +2159,17 @@ struct mlx5_ifc_cong_control_r_roce_ecn_rp_bits { u8 reserved_at_360[0x4a0]; }; +struct mlx5_ifc_cong_control_r_roce_general_bits { + u8 reserved_at_0[0x80]; + + u8 reserved_at_80[0x10]; + u8 rtt_resp_dscp_valid[0x1]; + u8 reserved_at_91[0x9]; + u8 rtt_resp_dscp[0x6]; + + u8 reserved_at_a0[0x760]; +}; + struct mlx5_ifc_cong_control_802_1qau_rp_bits { u8 reserved_at_0[0x80]; @@ -4304,6 +4315,7 @@ union mlx5_ifc_cong_control_roce_ecn_auto_bits { struct mlx5_ifc_cong_control_802_1qau_rp_bits cong_control_802_1qau_rp; struct mlx5_ifc_cong_control_r_roce_ecn_rp_bits cong_control_r_roce_ecn_rp; struct mlx5_ifc_cong_control_r_roce_ecn_np_bits cong_control_r_roce_ecn_np; + struct mlx5_ifc_cong_control_r_roce_general_bits cong_control_r_roce_general; u8 reserved_at_0[0x800]; }; -- cgit v1.2.3 From e1f19857f94be09f9526f180e64f20138bd4e394 Mon Sep 17 00:00:00 2001 From: Richard Weinberger Date: Wed, 7 Dec 2022 09:43:08 +0100 Subject: fs: namei: Allow follow_down() to uncover auto mounts This function is only used by NFSD to cross mount points. If a mount point is of type auto mount, follow_down() will not uncover it. Add LOOKUP_AUTOMOUNT to the lookup flags to have ->d_automount() called when NFSD walks down the mount tree. Signed-off-by: Richard Weinberger Reviewed-by: Ian Kent Reviewed-by: Jeff Layton Acked-by: Al Viro Signed-off-by: Chuck Lever --- fs/namei.c | 6 +++--- fs/nfsd/vfs.c | 6 +++++- include/linux/namei.h | 2 +- 3 files changed, 9 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/fs/namei.c b/fs/namei.c index 309ae6fc8c99..c06f47066063 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1458,11 +1458,11 @@ EXPORT_SYMBOL(follow_down_one); * point, the filesystem owning that dentry may be queried as to whether the * caller is permitted to proceed or not. */ -int follow_down(struct path *path) +int follow_down(struct path *path, unsigned int flags) { struct vfsmount *mnt = path->mnt; bool jumped; - int ret = traverse_mounts(path, &jumped, NULL, 0); + int ret = traverse_mounts(path, &jumped, NULL, flags); if (path->mnt != mnt) mntput(mnt); @@ -2864,7 +2864,7 @@ int path_pts(struct path *path) path->dentry = child; dput(parent); - follow_down(path); + follow_down(path, 0); return 0; } #endif diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 780856561bbb..21d5209f6e04 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -126,9 +126,13 @@ nfsd_cross_mnt(struct svc_rqst *rqstp, struct dentry **dpp, struct dentry *dentry = *dpp; struct path path = {.mnt = mntget(exp->ex_path.mnt), .dentry = dget(dentry)}; + unsigned int follow_flags = 0; int err = 0; - err = follow_down(&path); + if (exp->ex_flags & NFSEXP_CROSSMOUNT) + follow_flags = LOOKUP_AUTOMOUNT; + + err = follow_down(&path, follow_flags); if (err < 0) goto out; if (path.mnt == exp->ex_path.mnt && path.dentry == dentry && diff --git a/include/linux/namei.h b/include/linux/namei.h index 00fee52df842..c82e2ac65846 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -77,7 +77,7 @@ struct dentry *lookup_one_positive_unlocked(struct user_namespace *mnt_userns, struct dentry *base, int len); extern int follow_down_one(struct path *); -extern int follow_down(struct path *); +extern int follow_down(struct path *path, unsigned int flags); extern int follow_up(struct path *); extern struct dentry *lock_rename(struct dentry *, struct dentry *); -- cgit v1.2.3 From 846b5756d7632523b5bfce78c163aa883aa9d587 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 2 Jan 2023 12:05:43 -0500 Subject: SUNRPC: Add an XDR decoding helper for struct opaque_auth RFC 5531 defines the body of an RPC Call message like this: struct call_body { unsigned int rpcvers; unsigned int prog; unsigned int vers; unsigned int proc; opaque_auth cred; opaque_auth verf; /* procedure-specific parameters start here */ }; In the current server code, decoding a struct opaque_auth type is open-coded in several places, and is thus difficult to harden everywhere. Introduce a helper for decoding an opaque_auth within the context of a xdr_stream. This helper can be shared with all authentication flavor implemenations, even on the client-side. Done as part of hardening the server-side RPC header decoding paths. Reviewed-by: Jeff Layton Signed-off-by: Chuck Lever --- include/linux/sunrpc/xdr.h | 3 +++ net/sunrpc/xdr.c | 28 ++++++++++++++++++++++++++++ 2 files changed, 31 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index f84e2a1358e1..8b5c9d0cdcb5 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -346,6 +346,9 @@ ssize_t xdr_stream_decode_string(struct xdr_stream *xdr, char *str, size_t size); ssize_t xdr_stream_decode_string_dup(struct xdr_stream *xdr, char **str, size_t maxlen, gfp_t gfp_flags); +ssize_t xdr_stream_decode_opaque_auth(struct xdr_stream *xdr, u32 *flavor, + void **body, unsigned int *body_len); + /** * xdr_align_size - Calculate padded size of an object * @n: Size of an object being XDR encoded (in bytes) diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index f7767bf22406..4845ba2113fd 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -2274,3 +2274,31 @@ ssize_t xdr_stream_decode_string_dup(struct xdr_stream *xdr, char **str, return ret; } EXPORT_SYMBOL_GPL(xdr_stream_decode_string_dup); + +/** + * xdr_stream_decode_opaque_auth - Decode struct opaque_auth (RFC5531 S8.2) + * @xdr: pointer to xdr_stream + * @flavor: location to store decoded flavor + * @body: location to store decode body + * @body_len: location to store length of decoded body + * + * Return values: + * On success, returns the number of buffer bytes consumed + * %-EBADMSG on XDR buffer overflow + * %-EMSGSIZE if the decoded size of the body field exceeds 400 octets + */ +ssize_t xdr_stream_decode_opaque_auth(struct xdr_stream *xdr, u32 *flavor, + void **body, unsigned int *body_len) +{ + ssize_t ret, len; + + len = xdr_stream_decode_u32(xdr, flavor); + if (unlikely(len < 0)) + return len; + ret = xdr_stream_decode_opaque_inline(xdr, body, RPC_MAX_AUTH_SIZE); + if (unlikely(ret < 0)) + return ret; + *body_len = ret; + return len + ret; +} +EXPORT_SYMBOL_GPL(xdr_stream_decode_opaque_auth); -- cgit v1.2.3 From 6181b0c6432bf0807512e85e0c5863f7aca8e515 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 2 Jan 2023 12:05:56 -0500 Subject: SUNRPC: Convert svcauth_unix_accept() to use xdr_stream Done as part of hardening the server-side RPC header decoding path. Since the server-side of the Linux kernel SunRPC implementation ignores the contents of the Call's machinename field, there's no need for its RPC_AUTH_UNIX authenticator to reject names that are larger than UNX_MAXNODENAME. Reviewed-by: Jeff Layton Signed-off-by: Chuck Lever --- include/linux/sunrpc/msg_prot.h | 5 +++ net/sunrpc/svcauth_unix.c | 71 +++++++++++++++++++++++++++++------------ 2 files changed, 56 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/msg_prot.h b/include/linux/sunrpc/msg_prot.h index 02117ed0fa2e..c4b0eb2b2f04 100644 --- a/include/linux/sunrpc/msg_prot.h +++ b/include/linux/sunrpc/msg_prot.h @@ -34,6 +34,11 @@ enum rpc_auth_flavors { RPC_AUTH_GSS_SPKMP = 390011, }; +/* Maximum size (in octets) of the machinename in an AUTH_UNIX + * credential (per RFC 5531 Appendix A) + */ +#define RPC_MAX_MACHINENAME (255) + /* Maximum size (in bytes) of an rpc credential or verifier */ #define RPC_MAX_AUTH_SIZE (400) diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c index 95354f03bb05..b6aef9c5113b 100644 --- a/net/sunrpc/svcauth_unix.c +++ b/net/sunrpc/svcauth_unix.c @@ -867,26 +867,45 @@ struct auth_ops svcauth_tls = { }; +/** + * svcauth_unix_accept - Decode and validate incoming RPC_AUTH_SYS credential + * @rqstp: RPC transaction + * + * Return values: + * %SVC_OK: Both credential and verifier are valid + * %SVC_DENIED: Credential or verifier is not valid + * %SVC_GARBAGE: Failed to decode credential or verifier + * %SVC_CLOSE: Temporary failure + * + * rqstp->rq_auth_stat is set as mandated by RFC 5531. + */ static int svcauth_unix_accept(struct svc_rqst *rqstp) { - struct kvec *argv = &rqstp->rq_arg.head[0]; struct kvec *resv = &rqstp->rq_res.head[0]; + struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct svc_cred *cred = &rqstp->rq_cred; struct user_namespace *userns; - u32 slen, i; - int len = argv->iov_len; + u32 flavor, len, i; + void *body; + __be32 *p; + + svcxdr_init_decode(rqstp); - if ((len -= 3*4) < 0) + /* + * This implementation ignores the length of the Call's + * credential body field and the timestamp and machinename + * fields. + */ + p = xdr_inline_decode(xdr, XDR_UNIT * 3); + if (!p) + return SVC_GARBAGE; + len = be32_to_cpup(p + 2); + if (len > RPC_MAX_MACHINENAME) + return SVC_GARBAGE; + if (!xdr_inline_decode(xdr, len)) return SVC_GARBAGE; - svc_getu32(argv); /* length */ - svc_getu32(argv); /* time stamp */ - slen = XDR_QUADLEN(svc_getnl(argv)); /* machname length */ - if (slen > 64 || (len -= (slen + 3)*4) < 0) - goto badcred; - argv->iov_base = (void*)((__be32*)argv->iov_base + slen); /* skip machname */ - argv->iov_len -= slen*4; /* * Note: we skip uid_valid()/gid_valid() checks here for * backwards compatibility with clients that use -1 id's. @@ -896,20 +915,33 @@ svcauth_unix_accept(struct svc_rqst *rqstp) */ userns = (rqstp->rq_xprt && rqstp->rq_xprt->xpt_cred) ? rqstp->rq_xprt->xpt_cred->user_ns : &init_user_ns; - cred->cr_uid = make_kuid(userns, svc_getnl(argv)); /* uid */ - cred->cr_gid = make_kgid(userns, svc_getnl(argv)); /* gid */ - slen = svc_getnl(argv); /* gids length */ - if (slen > UNX_NGROUPS || (len -= (slen + 2)*4) < 0) + if (xdr_stream_decode_u32(xdr, &i) < 0) + return SVC_GARBAGE; + cred->cr_uid = make_kuid(userns, i); + if (xdr_stream_decode_u32(xdr, &i) < 0) + return SVC_GARBAGE; + cred->cr_gid = make_kgid(userns, i); + + if (xdr_stream_decode_u32(xdr, &len) < 0) + return SVC_GARBAGE; + if (len > UNX_NGROUPS) goto badcred; - cred->cr_group_info = groups_alloc(slen); + p = xdr_inline_decode(xdr, XDR_UNIT * len); + if (!p) + return SVC_GARBAGE; + cred->cr_group_info = groups_alloc(len); if (cred->cr_group_info == NULL) return SVC_CLOSE; - for (i = 0; i < slen; i++) { - kgid_t kgid = make_kgid(userns, svc_getnl(argv)); + for (i = 0; i < len; i++) { + kgid_t kgid = make_kgid(userns, be32_to_cpup(p++)); cred->cr_group_info->gid[i] = kgid; } groups_sort(cred->cr_group_info); - if (svc_getu32(argv) != htonl(RPC_AUTH_NULL) || svc_getu32(argv) != 0) { + + /* Call's verf field: */ + if (xdr_stream_decode_opaque_auth(xdr, &flavor, &body, &len) < 0) + return SVC_GARBAGE; + if (flavor != RPC_AUTH_NULL || len != 0) { rqstp->rq_auth_stat = rpc_autherr_badverf; return SVC_DENIED; } @@ -919,7 +951,6 @@ svcauth_unix_accept(struct svc_rqst *rqstp) svc_putnl(resv, 0); rqstp->rq_cred.cr_flavor = RPC_AUTH_UNIX; - svcxdr_init_decode(rqstp); return SVC_OK; badcred: -- cgit v1.2.3 From b68e4c5c32275e23d35badb7287faaa310c15ba0 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 2 Jan 2023 12:06:54 -0500 Subject: SUNRPC: Convert unwrap_integ_data() to use xdr_stream Done as part of hardening the server-side RPC header decoding path. Reviewed-by: Jeff Layton Signed-off-by: Chuck Lever --- include/linux/sunrpc/xdr.h | 1 + net/sunrpc/auth_gss/svcauth_gss.c | 47 ++++++++++++++++++++++++++------------- net/sunrpc/xdr.c | 15 +++++++++++++ 3 files changed, 47 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 8b5c9d0cdcb5..accfe8d6e283 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -247,6 +247,7 @@ extern int xdr_reserve_space_vec(struct xdr_stream *xdr, struct kvec *vec, size_t nbytes); extern void __xdr_commit_encode(struct xdr_stream *xdr); extern void xdr_truncate_encode(struct xdr_stream *xdr, size_t len); +extern void xdr_truncate_decode(struct xdr_stream *xdr, size_t len); extern int xdr_restrict_buflen(struct xdr_stream *xdr, int newbuflen); extern void xdr_write_pages(struct xdr_stream *xdr, struct page **pages, unsigned int base, unsigned int len); diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index 79222a42845a..e19974b57683 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -904,13 +904,14 @@ EXPORT_SYMBOL_GPL(svcauth_gss_register_pseudoflavor); * proc_req_arg_t arg; * }; */ -static int -svcauth_gss_unwrap_integ(struct svc_rqst *rqstp, struct xdr_buf *buf, u32 seq, - struct gss_ctx *ctx) +static noinline_for_stack int +svcauth_gss_unwrap_integ(struct svc_rqst *rqstp, u32 seq, struct gss_ctx *ctx) { struct gss_svc_data *gsd = rqstp->rq_auth_data; + struct xdr_stream *xdr = &rqstp->rq_arg_stream; + u32 len, offset, seq_num, maj_stat; + struct xdr_buf *buf = xdr->buf; struct xdr_buf databody_integ; - u32 len, seq_num, maj_stat; struct xdr_netobj checksum; /* NFS READ normally uses splice to send data in-place. However @@ -925,29 +926,43 @@ svcauth_gss_unwrap_integ(struct svc_rqst *rqstp, struct xdr_buf *buf, u32 seq, if (rqstp->rq_deferred) return 0; - len = svc_getnl(&buf->head[0]); - if (len & 3) + if (xdr_stream_decode_u32(xdr, &len) < 0) goto unwrap_failed; - if (len > buf->len) + if (len & 3) goto unwrap_failed; - if (xdr_buf_subsegment(buf, &databody_integ, 0, len)) + offset = xdr_stream_pos(xdr); + if (xdr_buf_subsegment(buf, &databody_integ, offset, len)) goto unwrap_failed; - if (xdr_decode_word(buf, len, &checksum.len)) + /* + * The xdr_stream now points to the @seq_num field. The next + * XDR data item is the @arg field, which contains the clear + * text RPC program payload. The checksum, which follows the + * @arg field, is located and decoded without updating the + * xdr_stream. + */ + + offset += len; + if (xdr_decode_word(buf, offset, &checksum.len)) goto unwrap_failed; if (checksum.len > sizeof(gsd->gsd_scratch)) goto unwrap_failed; checksum.data = gsd->gsd_scratch; - if (read_bytes_from_xdr_buf(buf, len + 4, checksum.data, checksum.len)) + if (read_bytes_from_xdr_buf(buf, offset + XDR_UNIT, checksum.data, + checksum.len)) goto unwrap_failed; + maj_stat = gss_verify_mic(ctx, &databody_integ, &checksum); if (maj_stat != GSS_S_COMPLETE) goto bad_mic; - seq_num = svc_getnl(&buf->head[0]); + + /* The received seqno is protected by the checksum. */ + if (xdr_stream_decode_u32(xdr, &seq_num) < 0) + goto unwrap_failed; if (seq_num != seq) goto bad_seqno; - /* trim off the mic and padding at the end before returning */ - xdr_buf_trim(buf, round_up_to_quad(checksum.len) + 4); + + xdr_truncate_decode(xdr, XDR_UNIT + checksum.len); return 0; unwrap_failed: @@ -1652,11 +1667,11 @@ svcauth_gss_accept(struct svc_rqst *rqstp) /* placeholders for length and seq. number: */ svc_putnl(resv, 0); svc_putnl(resv, 0); - if (svcauth_gss_unwrap_integ(rqstp, &rqstp->rq_arg, - gc->gc_seq, rsci->mechctx)) + svcxdr_init_decode(rqstp); + if (svcauth_gss_unwrap_integ(rqstp, gc->gc_seq, + rsci->mechctx)) goto garbage_args; rqstp->rq_auth_slack = RPC_MAX_AUTH_SIZE; - svcxdr_init_decode(rqstp); break; case RPC_GSS_SVC_PRIVACY: /* placeholders for length and seq. number: */ diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index 4845ba2113fd..c7e89921d511 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -1192,6 +1192,21 @@ void xdr_truncate_encode(struct xdr_stream *xdr, size_t len) } EXPORT_SYMBOL(xdr_truncate_encode); +/** + * xdr_truncate_decode - Truncate a decoding stream + * @xdr: pointer to struct xdr_stream + * @len: Number of bytes to remove + * + */ +void xdr_truncate_decode(struct xdr_stream *xdr, size_t len) +{ + unsigned int nbytes = xdr_align_size(len); + + xdr->buf->len -= nbytes; + xdr->nwords -= XDR_QUADLEN(nbytes); +} +EXPORT_SYMBOL_GPL(xdr_truncate_decode); + /** * xdr_restrict_buflen - decrease available buffer space * @xdr: pointer to xdr_stream -- cgit v1.2.3 From 42140718ea26c47fb06c679451a6aa6703545136 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 2 Jan 2023 12:07:07 -0500 Subject: SUNRPC: Convert unwrap_priv_data() to use xdr_stream Done as part of hardening the server-side RPC header decoding path. Reviewed-by: Jeff Layton Signed-off-by: Chuck Lever --- include/linux/sunrpc/xdr.h | 1 - net/sunrpc/auth_gss/svcauth_gss.c | 65 +++++++++++++-------------------------- net/sunrpc/xdr.c | 7 ----- 3 files changed, 21 insertions(+), 52 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index accfe8d6e283..884df67009f4 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -188,7 +188,6 @@ xdr_adjust_iovec(struct kvec *iov, __be32 *p) /* * XDR buffer helper functions */ -extern void xdr_shift_buf(struct xdr_buf *, size_t); extern void xdr_buf_from_iov(const struct kvec *, struct xdr_buf *); extern int xdr_buf_subsegment(const struct xdr_buf *, struct xdr_buf *, unsigned int, unsigned int); extern void xdr_buf_trim(struct xdr_buf *, unsigned int); diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index 03d9067b4fa9..e204b5b60bf0 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -982,17 +982,6 @@ total_buf_len(struct xdr_buf *buf) return buf->head[0].iov_len + buf->page_len + buf->tail[0].iov_len; } -static void -fix_priv_head(struct xdr_buf *buf, int pad) -{ - if (buf->page_len == 0) { - /* We need to adjust head and buf->len in tandem in this - * case to make svc_defer() work--it finds the original - * buffer start using buf->len - buf->head[0].iov_len. */ - buf->head[0].iov_len -= pad; - } -} - /* * RFC 2203, Section 5.3.2.3 * @@ -1005,49 +994,37 @@ fix_priv_head(struct xdr_buf *buf, int pad) * proc_req_arg_t arg; * }; */ -static int -svcauth_gss_unwrap_priv(struct svc_rqst *rqstp, struct xdr_buf *buf, u32 seq, - struct gss_ctx *ctx) +static noinline_for_stack int +svcauth_gss_unwrap_priv(struct svc_rqst *rqstp, u32 seq, struct gss_ctx *ctx) { - u32 len, seq_num, maj_stat; - int pad, remaining_len, offset; + struct xdr_stream *xdr = &rqstp->rq_arg_stream; + u32 len, maj_stat, seq_num, offset; + struct xdr_buf *buf = xdr->buf; + unsigned int saved_len; clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags); - len = svc_getnl(&buf->head[0]); + if (xdr_stream_decode_u32(xdr, &len) < 0) + goto unwrap_failed; if (rqstp->rq_deferred) { /* Already decrypted last time through! The sequence number * check at out_seq is unnecessary but harmless: */ goto out_seq; } - /* buf->len is the number of bytes from the original start of the - * request to the end, where head[0].iov_len is just the bytes - * not yet read from the head, so these two values are different: */ - remaining_len = total_buf_len(buf); - if (len > remaining_len) + if (len > xdr_stream_remaining(xdr)) goto unwrap_failed; - pad = remaining_len - len; - buf->len -= pad; - fix_priv_head(buf, pad); - - maj_stat = gss_unwrap(ctx, 0, len, buf); - pad = len - buf->len; - /* The upper layers assume the buffer is aligned on 4-byte boundaries. - * In the krb5p case, at least, the data ends up offset, so we need to - * move it around. */ - /* XXX: This is very inefficient. It would be better to either do - * this while we encrypt, or maybe in the receive code, if we can peak - * ahead and work out the service and mechanism there. */ - offset = xdr_pad_size(buf->head[0].iov_len); - if (offset) { - buf->buflen = RPCSVC_MAXPAYLOAD; - xdr_shift_buf(buf, offset); - fix_priv_head(buf, pad); - } + offset = xdr_stream_pos(xdr); + + saved_len = buf->len; + maj_stat = gss_unwrap(ctx, offset, offset + len, buf); if (maj_stat != GSS_S_COMPLETE) goto bad_unwrap; + xdr->nwords -= XDR_QUADLEN(saved_len - buf->len); + out_seq: - seq_num = svc_getnl(&buf->head[0]); + /* gss_unwrap() decrypted the sequence number. */ + if (xdr_stream_decode_u32(xdr, &seq_num) < 0) + goto unwrap_failed; if (seq_num != seq) goto bad_seqno; return 0; @@ -1689,11 +1666,11 @@ svcauth_gss_accept(struct svc_rqst *rqstp) /* placeholders for length and seq. number: */ svc_putnl(resv, 0); svc_putnl(resv, 0); - if (svcauth_gss_unwrap_priv(rqstp, &rqstp->rq_arg, - gc->gc_seq, rsci->mechctx)) + svcxdr_init_decode(rqstp); + if (svcauth_gss_unwrap_priv(rqstp, gc->gc_seq, + rsci->mechctx)) goto garbage_args; rqstp->rq_auth_slack = RPC_MAX_AUTH_SIZE * 2; - svcxdr_init_decode(rqstp); break; default: goto auth_err; diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index c7e89921d511..56d87c784c9e 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -863,13 +863,6 @@ static unsigned int xdr_shrink_pagelen(struct xdr_buf *buf, unsigned int len) return shift; } -void -xdr_shift_buf(struct xdr_buf *buf, size_t len) -{ - xdr_shrink_bufhead(buf, buf->head->iov_len - len); -} -EXPORT_SYMBOL_GPL(xdr_shift_buf); - /** * xdr_stream_pos - Return the current offset from the start of the xdr_stream * @xdr: pointer to struct xdr_stream -- cgit v1.2.3 From df24ac7a2e3a9d0bc68f1756a880e50bfe4b4522 Mon Sep 17 00:00:00 2001 From: Dai Ngo Date: Sun, 18 Dec 2022 16:55:53 -0800 Subject: NFSD: enhance inter-server copy cleanup Currently nfsd4_setup_inter_ssc returns the vfsmount of the source server's export when the mount completes. After the copy is done nfsd4_cleanup_inter_ssc is called with the vfsmount of the source server and it searches nfsd_ssc_mount_list for a matching entry to do the clean up. The problems with this approach are (1) the need to search the nfsd_ssc_mount_list and (2) the code has to handle the case where the matching entry is not found which looks ugly. The enhancement is instead of nfsd4_setup_inter_ssc returning the vfsmount, it returns the nfsd4_ssc_umount_item which has the vfsmount embedded in it. When nfsd4_cleanup_inter_ssc is called it's passed with the nfsd4_ssc_umount_item directly to do the clean up so no searching is needed and there is no need to handle the 'not found' case. Signed-off-by: Dai Ngo Signed-off-by: Chuck Lever [ cel: adjusted whitespace and variable/function names ] Reviewed-by: Olga Kornievskaia --- fs/nfsd/nfs4proc.c | 111 +++++++++++++++++++----------------------------- fs/nfsd/xdr4.h | 2 +- include/linux/nfs_ssc.h | 2 +- 3 files changed, 46 insertions(+), 69 deletions(-) (limited to 'include/linux') diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index f189ba7995f5..dbaf33398c82 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1293,15 +1293,15 @@ extern void nfs_sb_deactive(struct super_block *sb); * setup a work entry in the ssc delayed unmount list. */ static __be32 nfsd4_ssc_setup_dul(struct nfsd_net *nn, char *ipaddr, - struct nfsd4_ssc_umount_item **retwork, struct vfsmount **ss_mnt) + struct nfsd4_ssc_umount_item **nsui) { struct nfsd4_ssc_umount_item *ni = NULL; struct nfsd4_ssc_umount_item *work = NULL; struct nfsd4_ssc_umount_item *tmp; DEFINE_WAIT(wait); + __be32 status = 0; - *ss_mnt = NULL; - *retwork = NULL; + *nsui = NULL; work = kzalloc(sizeof(*work), GFP_KERNEL); try_again: spin_lock(&nn->nfsd_ssc_lock); @@ -1325,12 +1325,12 @@ try_again: finish_wait(&nn->nfsd_ssc_waitq, &wait); goto try_again; } - *ss_mnt = ni->nsui_vfsmount; + *nsui = ni; refcount_inc(&ni->nsui_refcnt); spin_unlock(&nn->nfsd_ssc_lock); kfree(work); - /* return vfsmount in ss_mnt */ + /* return vfsmount in (*nsui)->nsui_vfsmount */ return 0; } if (work) { @@ -1338,31 +1338,32 @@ try_again: refcount_set(&work->nsui_refcnt, 2); work->nsui_busy = true; list_add_tail(&work->nsui_list, &nn->nfsd_ssc_mount_list); - *retwork = work; - } + *nsui = work; + } else + status = nfserr_resource; spin_unlock(&nn->nfsd_ssc_lock); - return 0; + return status; } -static void nfsd4_ssc_update_dul_work(struct nfsd_net *nn, - struct nfsd4_ssc_umount_item *work, struct vfsmount *ss_mnt) +static void nfsd4_ssc_update_dul(struct nfsd_net *nn, + struct nfsd4_ssc_umount_item *nsui, + struct vfsmount *ss_mnt) { - /* set nsui_vfsmount, clear busy flag and wakeup waiters */ spin_lock(&nn->nfsd_ssc_lock); - work->nsui_vfsmount = ss_mnt; - work->nsui_busy = false; + nsui->nsui_vfsmount = ss_mnt; + nsui->nsui_busy = false; wake_up_all(&nn->nfsd_ssc_waitq); spin_unlock(&nn->nfsd_ssc_lock); } -static void nfsd4_ssc_cancel_dul_work(struct nfsd_net *nn, - struct nfsd4_ssc_umount_item *work) +static void nfsd4_ssc_cancel_dul(struct nfsd_net *nn, + struct nfsd4_ssc_umount_item *nsui) { spin_lock(&nn->nfsd_ssc_lock); - list_del(&work->nsui_list); + list_del(&nsui->nsui_list); wake_up_all(&nn->nfsd_ssc_waitq); spin_unlock(&nn->nfsd_ssc_lock); - kfree(work); + kfree(nsui); } /* @@ -1370,7 +1371,7 @@ static void nfsd4_ssc_cancel_dul_work(struct nfsd_net *nn, */ static __be32 nfsd4_interssc_connect(struct nl4_server *nss, struct svc_rqst *rqstp, - struct vfsmount **mount) + struct nfsd4_ssc_umount_item **nsui) { struct file_system_type *type; struct vfsmount *ss_mnt; @@ -1381,7 +1382,6 @@ nfsd4_interssc_connect(struct nl4_server *nss, struct svc_rqst *rqstp, char *ipaddr, *dev_name, *raw_data; int len, raw_len; __be32 status = nfserr_inval; - struct nfsd4_ssc_umount_item *work = NULL; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); naddr = &nss->u.nl4_addr; @@ -1389,6 +1389,7 @@ nfsd4_interssc_connect(struct nl4_server *nss, struct svc_rqst *rqstp, naddr->addr_len, (struct sockaddr *)&tmp_addr, sizeof(tmp_addr)); + *nsui = NULL; if (tmp_addrlen == 0) goto out_err; @@ -1431,10 +1432,10 @@ nfsd4_interssc_connect(struct nl4_server *nss, struct svc_rqst *rqstp, goto out_free_rawdata; snprintf(dev_name, len + 5, "%s%s%s:/", startsep, ipaddr, endsep); - status = nfsd4_ssc_setup_dul(nn, ipaddr, &work, &ss_mnt); + status = nfsd4_ssc_setup_dul(nn, ipaddr, nsui); if (status) goto out_free_devname; - if (ss_mnt) + if ((*nsui)->nsui_vfsmount) goto out_done; /* Use an 'internal' mount: SB_KERNMOUNT -> MNT_INTERNAL */ @@ -1442,15 +1443,12 @@ nfsd4_interssc_connect(struct nl4_server *nss, struct svc_rqst *rqstp, module_put(type->owner); if (IS_ERR(ss_mnt)) { status = nfserr_nodev; - if (work) - nfsd4_ssc_cancel_dul_work(nn, work); + nfsd4_ssc_cancel_dul(nn, *nsui); goto out_free_devname; } - if (work) - nfsd4_ssc_update_dul_work(nn, work, ss_mnt); + nfsd4_ssc_update_dul(nn, *nsui, ss_mnt); out_done: status = 0; - *mount = ss_mnt; out_free_devname: kfree(dev_name); @@ -1474,7 +1472,7 @@ out_err: static __be32 nfsd4_setup_inter_ssc(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_copy *copy, struct vfsmount **mount) + struct nfsd4_copy *copy) { struct svc_fh *s_fh = NULL; stateid_t *s_stid = ©->cp_src_stateid; @@ -1487,7 +1485,7 @@ nfsd4_setup_inter_ssc(struct svc_rqst *rqstp, if (status) goto out; - status = nfsd4_interssc_connect(copy->cp_src, rqstp, mount); + status = nfsd4_interssc_connect(copy->cp_src, rqstp, ©->ss_nsui); if (status) goto out; @@ -1505,45 +1503,27 @@ out: } static void -nfsd4_cleanup_inter_ssc(struct vfsmount *ss_mnt, struct file *filp, +nfsd4_cleanup_inter_ssc(struct nfsd4_ssc_umount_item *nsui, struct file *filp, struct nfsd_file *dst) { - bool found = false; - long timeout; - struct nfsd4_ssc_umount_item *tmp; - struct nfsd4_ssc_umount_item *ni = NULL; struct nfsd_net *nn = net_generic(dst->nf_net, nfsd_net_id); + long timeout = msecs_to_jiffies(nfsd4_ssc_umount_timeout); nfs42_ssc_close(filp); nfsd_file_put(dst); fput(filp); - if (!nn) { - mntput(ss_mnt); - return; - } spin_lock(&nn->nfsd_ssc_lock); - timeout = msecs_to_jiffies(nfsd4_ssc_umount_timeout); - list_for_each_entry_safe(ni, tmp, &nn->nfsd_ssc_mount_list, nsui_list) { - if (ni->nsui_vfsmount->mnt_sb == ss_mnt->mnt_sb) { - list_del(&ni->nsui_list); - /* - * vfsmount can be shared by multiple exports, - * decrement refcnt. If the count drops to 1 it - * will be unmounted when nsui_expire expires. - */ - refcount_dec(&ni->nsui_refcnt); - ni->nsui_expire = jiffies + timeout; - list_add_tail(&ni->nsui_list, &nn->nfsd_ssc_mount_list); - found = true; - break; - } - } + list_del(&nsui->nsui_list); + /* + * vfsmount can be shared by multiple exports, + * decrement refcnt. If the count drops to 1 it + * will be unmounted when nsui_expire expires. + */ + refcount_dec(&nsui->nsui_refcnt); + nsui->nsui_expire = jiffies + timeout; + list_add_tail(&nsui->nsui_list, &nn->nfsd_ssc_mount_list); spin_unlock(&nn->nfsd_ssc_lock); - if (!found) { - mntput(ss_mnt); - return; - } } #else /* CONFIG_NFSD_V4_2_INTER_SSC */ @@ -1551,15 +1531,13 @@ nfsd4_cleanup_inter_ssc(struct vfsmount *ss_mnt, struct file *filp, static __be32 nfsd4_setup_inter_ssc(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_copy *copy, - struct vfsmount **mount) + struct nfsd4_copy *copy) { - *mount = NULL; return nfserr_inval; } static void -nfsd4_cleanup_inter_ssc(struct vfsmount *ss_mnt, struct file *filp, +nfsd4_cleanup_inter_ssc(struct nfsd4_ssc_umount_item *nsui, struct file *filp, struct nfsd_file *dst) { } @@ -1700,7 +1678,7 @@ static void dup_copy_fields(struct nfsd4_copy *src, struct nfsd4_copy *dst) memcpy(dst->cp_src, src->cp_src, sizeof(struct nl4_server)); memcpy(&dst->stateid, &src->stateid, sizeof(src->stateid)); memcpy(&dst->c_fh, &src->c_fh, sizeof(src->c_fh)); - dst->ss_mnt = src->ss_mnt; + dst->ss_nsui = src->ss_nsui; } static void cleanup_async_copy(struct nfsd4_copy *copy) @@ -1749,8 +1727,8 @@ static int nfsd4_do_async_copy(void *data) if (nfsd4_ssc_is_inter(copy)) { struct file *filp; - filp = nfs42_ssc_open(copy->ss_mnt, ©->c_fh, - ©->stateid); + filp = nfs42_ssc_open(copy->ss_nsui->nsui_vfsmount, + ©->c_fh, ©->stateid); if (IS_ERR(filp)) { switch (PTR_ERR(filp)) { case -EBADF: @@ -1764,7 +1742,7 @@ static int nfsd4_do_async_copy(void *data) } nfserr = nfsd4_do_copy(copy, filp, copy->nf_dst->nf_file, false); - nfsd4_cleanup_inter_ssc(copy->ss_mnt, filp, copy->nf_dst); + nfsd4_cleanup_inter_ssc(copy->ss_nsui, filp, copy->nf_dst); } else { nfserr = nfsd4_do_copy(copy, copy->nf_src->nf_file, copy->nf_dst->nf_file, false); @@ -1790,8 +1768,7 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, status = nfserr_notsupp; goto out; } - status = nfsd4_setup_inter_ssc(rqstp, cstate, copy, - ©->ss_mnt); + status = nfsd4_setup_inter_ssc(rqstp, cstate, copy); if (status) return nfserr_offload_denied; } else { diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index 4fd2cf6d1d2d..510978e602da 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -571,7 +571,7 @@ struct nfsd4_copy { struct task_struct *copy_task; refcount_t refcount; - struct vfsmount *ss_mnt; + struct nfsd4_ssc_umount_item *ss_nsui; struct nfs_fh c_fh; nfs4_stateid stateid; }; diff --git a/include/linux/nfs_ssc.h b/include/linux/nfs_ssc.h index 75843c00f326..22265b1ff080 100644 --- a/include/linux/nfs_ssc.h +++ b/include/linux/nfs_ssc.h @@ -53,6 +53,7 @@ static inline void nfs42_ssc_close(struct file *filep) if (nfs_ssc_client_tbl.ssc_nfs4_ops) (*nfs_ssc_client_tbl.ssc_nfs4_ops->sco_close)(filep); } +#endif struct nfsd4_ssc_umount_item { struct list_head nsui_list; @@ -66,7 +67,6 @@ struct nfsd4_ssc_umount_item { struct vfsmount *nsui_vfsmount; char nsui_ipaddr[RPC_MAX_ADDRBUFLEN + 1]; }; -#endif /* * NFS_FS -- cgit v1.2.3 From 7b402c8db66414abb4001d0c2676553baa619a2b Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sun, 8 Jan 2023 11:29:38 -0500 Subject: SUNRPC: Add XDR encoding helper for opaque_auth RFC 5531 defines an MSG_ACCEPTED Reply message like this: struct accepted_reply { opaque_auth verf; union switch (accept_stat stat) { case SUCCESS: ... In the current server code, struct opaque_auth encoding is open- coded. Introduce a helper that encodes an opaque_auth data item within the context of a xdr_stream. Done as part of hardening the server-side RPC header decoding and encoding paths. Reviewed-by: Jeff Layton Signed-off-by: Chuck Lever --- include/linux/sunrpc/xdr.h | 2 ++ net/sunrpc/xdr.c | 29 +++++++++++++++++++++++++++++ 2 files changed, 31 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 884df67009f4..f3b6eb9accd7 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -348,6 +348,8 @@ ssize_t xdr_stream_decode_string_dup(struct xdr_stream *xdr, char **str, size_t maxlen, gfp_t gfp_flags); ssize_t xdr_stream_decode_opaque_auth(struct xdr_stream *xdr, u32 *flavor, void **body, unsigned int *body_len); +ssize_t xdr_stream_encode_opaque_auth(struct xdr_stream *xdr, u32 flavor, + void *body, unsigned int body_len); /** * xdr_align_size - Calculate padded size of an object diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index 56d87c784c9e..6b2ec24ec62d 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -2310,3 +2310,32 @@ ssize_t xdr_stream_decode_opaque_auth(struct xdr_stream *xdr, u32 *flavor, return len + ret; } EXPORT_SYMBOL_GPL(xdr_stream_decode_opaque_auth); + +/** + * xdr_stream_encode_opaque_auth - Encode struct opaque_auth (RFC5531 S8.2) + * @xdr: pointer to xdr_stream + * @flavor: verifier flavor to encode + * @body: content of body to encode + * @body_len: length of body to encode + * + * Return values: + * On success, returns length in bytes of XDR buffer consumed + * %-EBADMSG on XDR buffer overflow + * %-EMSGSIZE if the size of @body exceeds 400 octets + */ +ssize_t xdr_stream_encode_opaque_auth(struct xdr_stream *xdr, u32 flavor, + void *body, unsigned int body_len) +{ + ssize_t ret, len; + + if (unlikely(body_len > RPC_MAX_AUTH_SIZE)) + return -EMSGSIZE; + len = xdr_stream_encode_u32(xdr, flavor); + if (unlikely(len < 0)) + return len; + ret = xdr_stream_encode_opaque(xdr, body, body_len); + if (unlikely(ret < 0)) + return ret; + return len + ret; +} +EXPORT_SYMBOL_GPL(xdr_stream_encode_opaque_auth); -- cgit v1.2.3 From 8dd41d70f331c342842e8d349d7a1f73b0ba7ccd Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sun, 8 Jan 2023 11:29:44 -0500 Subject: SUNRPC: Push svcxdr_init_encode() into svc_process_common() Now that all vs_dispatch functions invoke svcxdr_init_encode(), it is common code and can be pushed down into the generic RPC server. Reviewed-by: Jeff Layton Signed-off-by: Chuck Lever --- fs/lockd/svc.c | 1 - fs/nfs/callback_xdr.c | 2 -- fs/nfsd/nfscache.c | 2 +- fs/nfsd/nfssvc.c | 6 ------ include/linux/sunrpc/xdr.h | 21 +++++++++++++++++++++ net/sunrpc/svc.c | 1 + 6 files changed, 23 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index e56d85335599..642e394e7a2d 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -704,7 +704,6 @@ static int nlmsvc_dispatch(struct svc_rqst *rqstp, __be32 *statp) if (*statp != rpc_success) return 1; - svcxdr_init_encode(rqstp); if (!procp->pc_encode(rqstp, &rqstp->rq_res_stream)) goto out_encode_err; diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c index 46d3f5986b4e..b4c3b7182198 100644 --- a/fs/nfs/callback_xdr.c +++ b/fs/nfs/callback_xdr.c @@ -984,8 +984,6 @@ nfs_callback_dispatch(struct svc_rqst *rqstp, __be32 *statp) { const struct svc_procedure *procp = rqstp->rq_procinfo; - svcxdr_init_encode(rqstp); - *statp = procp->pc_func(rqstp); return 1; } diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c index 3e64a3d50a1c..ef5ee548053b 100644 --- a/fs/nfsd/nfscache.c +++ b/fs/nfsd/nfscache.c @@ -488,7 +488,7 @@ found_entry: case RC_NOCACHE: break; case RC_REPLSTAT: - svc_putu32(&rqstp->rq_res.head[0], rp->c_replstat); + xdr_stream_encode_be32(&rqstp->rq_res_stream, rp->c_replstat); rtn = RC_REPLY; break; case RC_REPLBUFF: diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 1ed29eac80ed..dfa8ee6c04d5 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -1052,12 +1052,6 @@ int nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp) goto out_dropit; } - /* - * Need to grab the location to store the status, as - * NFSv4 does some encoding while processing - */ - svcxdr_init_encode(rqstp); - *statp = proc->pc_func(rqstp); if (test_bit(RQ_DROPME, &rqstp->rq_flags)) goto out_update_drop; diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index f3b6eb9accd7..72014c9216fc 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -474,6 +474,27 @@ xdr_stream_encode_u32(struct xdr_stream *xdr, __u32 n) return len; } +/** + * xdr_stream_encode_be32 - Encode a big-endian 32-bit integer + * @xdr: pointer to xdr_stream + * @n: integer to encode + * + * Return values: + * On success, returns length in bytes of XDR buffer consumed + * %-EMSGSIZE on XDR buffer overflow + */ +static inline ssize_t +xdr_stream_encode_be32(struct xdr_stream *xdr, __be32 n) +{ + const size_t len = sizeof(n); + __be32 *p = xdr_reserve_space(xdr, len); + + if (unlikely(!p)) + return -EMSGSIZE; + *p = n; + return len; +} + /** * xdr_stream_encode_u64 - Encode a 64-bit integer * @xdr: pointer to xdr_stream diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 7610e36e51e0..ce75db5eb9bd 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1321,6 +1321,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *resv) */ if (procp->pc_xdrressize) svc_reserve_auth(rqstp, procp->pc_xdrressize<<2); + svcxdr_init_encode(rqstp); /* Call the function that processes the request. */ rc = process.dispatch(rqstp, statp); -- cgit v1.2.3 From 7bb0dfb2234725ba085cacfd35f34c187def92b2 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sun, 8 Jan 2023 11:30:15 -0500 Subject: SUNRPC: Convert unwrap data paths to use xdr_stream for replies We're now moving svcxdr_init_encode() to /before/ the flavor's ->accept method has set rq_auth_slack. Add a helper that can set rq_auth_slack /after/ svcxdr_init_encode() has been called. Reviewed-by: Jeff Layton Signed-off-by: Chuck Lever --- include/linux/sunrpc/svc.h | 26 ++++++++++++++++++++++++-- net/sunrpc/auth_gss/svcauth_gss.c | 18 ++++++++---------- 2 files changed, 32 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index ed722dd33b46..dd9f68acd9f1 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -577,12 +577,34 @@ static inline void svcxdr_init_encode(struct svc_rqst *rqstp) xdr->buf = buf; xdr->iov = resv; xdr->p = resv->iov_base + resv->iov_len; - xdr->end = resv->iov_base + PAGE_SIZE - rqstp->rq_auth_slack; + xdr->end = resv->iov_base + PAGE_SIZE; buf->len = resv->iov_len; xdr->page_ptr = buf->pages - 1; buf->buflen = PAGE_SIZE * (rqstp->rq_page_end - buf->pages); - buf->buflen -= rqstp->rq_auth_slack; xdr->rqst = NULL; } +/** + * svcxdr_set_auth_slack - + * @rqstp: RPC transaction + * @slack: buffer space to reserve for the transaction's security flavor + * + * Set the request's slack space requirement, and set aside that much + * space in the rqstp's rq_res.head for use when the auth wraps the Reply. + */ +static inline void svcxdr_set_auth_slack(struct svc_rqst *rqstp, int slack) +{ + struct xdr_stream *xdr = &rqstp->rq_res_stream; + struct xdr_buf *buf = &rqstp->rq_res; + struct kvec *resv = buf->head; + + rqstp->rq_auth_slack = slack; + + xdr->end -= XDR_QUADLEN(slack); + buf->buflen -= rqstp->rq_auth_slack; + + WARN_ON(xdr->iov != resv); + WARN_ON(xdr->p > xdr->end); +} + #endif /* SUNRPC_SVC_H */ diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index 5c41c34dd83e..7f8cbd6e2d4e 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -1685,24 +1685,22 @@ svcauth_gss_accept(struct svc_rqst *rqstp) svcxdr_init_encode(rqstp); break; case RPC_GSS_SVC_INTEGRITY: - /* placeholders for length and seq. number: */ - svc_putnl(resv, 0); - svc_putnl(resv, 0); + svcxdr_init_encode(rqstp); + /* placeholders for body length and seq. number: */ + xdr_reserve_space(&rqstp->rq_res_stream, XDR_UNIT * 2); if (svcauth_gss_unwrap_integ(rqstp, gc->gc_seq, rsci->mechctx)) goto garbage_args; - rqstp->rq_auth_slack = RPC_MAX_AUTH_SIZE; - svcxdr_init_encode(rqstp); + svcxdr_set_auth_slack(rqstp, RPC_MAX_AUTH_SIZE); break; case RPC_GSS_SVC_PRIVACY: - /* placeholders for length and seq. number: */ - svc_putnl(resv, 0); - svc_putnl(resv, 0); + svcxdr_init_encode(rqstp); + /* placeholders for body length and seq. number: */ + xdr_reserve_space(&rqstp->rq_res_stream, XDR_UNIT * 2); if (svcauth_gss_unwrap_priv(rqstp, gc->gc_seq, rsci->mechctx)) goto garbage_args; - rqstp->rq_auth_slack = RPC_MAX_AUTH_SIZE * 2; - svcxdr_init_encode(rqstp); + svcxdr_set_auth_slack(rqstp, RPC_MAX_AUTH_SIZE * 2); break; default: goto auth_err; -- cgit v1.2.3 From 5df25676de2e13b2cb67140fd43bcbfdd60ef0df Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sun, 8 Jan 2023 11:30:52 -0500 Subject: SUNRPC: Remove no-longer-used helper functions The svc_get/put helpers are no longer used. Reviewed-by: Jeff Layton Signed-off-by: Chuck Lever --- include/linux/sunrpc/svc.h | 66 +--------------------------------------------- 1 file changed, 1 insertion(+), 65 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index dd9f68acd9f1..32eb98e621c3 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -193,40 +193,6 @@ extern u32 svc_max_payload(const struct svc_rqst *rqstp); #define RPCSVC_MAXPAGES ((RPCSVC_MAXPAYLOAD+PAGE_SIZE-1)/PAGE_SIZE \ + 2 + 1) -static inline u32 svc_getnl(struct kvec *iov) -{ - __be32 val, *vp; - vp = iov->iov_base; - val = *vp++; - iov->iov_base = (void*)vp; - iov->iov_len -= sizeof(__be32); - return ntohl(val); -} - -static inline void svc_putnl(struct kvec *iov, u32 val) -{ - __be32 *vp = iov->iov_base + iov->iov_len; - *vp = htonl(val); - iov->iov_len += sizeof(__be32); -} - -static inline __be32 svc_getu32(struct kvec *iov) -{ - __be32 val, *vp; - vp = iov->iov_base; - val = *vp++; - iov->iov_base = (void*)vp; - iov->iov_len -= sizeof(__be32); - return val; -} - -static inline void svc_putu32(struct kvec *iov, __be32 val) -{ - __be32 *vp = iov->iov_base + iov->iov_len; - *vp = val; - iov->iov_len += sizeof(__be32); -} - /* * The context of a single thread, including the request currently being * processed. @@ -345,29 +311,6 @@ static inline struct sockaddr *svc_daddr(const struct svc_rqst *rqst) return (struct sockaddr *) &rqst->rq_daddr; } -/* - * Check buffer bounds after decoding arguments - */ -static inline int -xdr_argsize_check(struct svc_rqst *rqstp, __be32 *p) -{ - char *cp = (char *)p; - struct kvec *vec = &rqstp->rq_arg.head[0]; - return cp >= (char*)vec->iov_base - && cp <= (char*)vec->iov_base + vec->iov_len; -} - -static inline int -xdr_ressize_check(struct svc_rqst *rqstp, __be32 *p) -{ - struct kvec *vec = &rqstp->rq_res.head[0]; - char *cp = (char*)p; - - vec->iov_len = cp - (char*)vec->iov_base; - - return vec->iov_len <= PAGE_SIZE; -} - static inline void svc_free_res_pages(struct svc_rqst *rqstp) { while (rqstp->rq_next_page != rqstp->rq_respages) { @@ -540,9 +483,6 @@ static inline void svc_reserve_auth(struct svc_rqst *rqstp, int space) * svcxdr_init_decode - Prepare an xdr_stream for Call decoding * @rqstp: controlling server RPC transaction context * - * This function currently assumes the RPC header in rq_arg has - * already been decoded. Upon return, xdr->p points to the - * location of the upper layer header. */ static inline void svcxdr_init_decode(struct svc_rqst *rqstp) { @@ -550,11 +490,7 @@ static inline void svcxdr_init_decode(struct svc_rqst *rqstp) struct xdr_buf *buf = &rqstp->rq_arg; struct kvec *argv = buf->head; - /* - * svc_getnl() and friends do not keep the xdr_buf's ::len - * field up to date. Refresh that field before initializing - * the argument decoding stream. - */ + WARN_ON(buf->len != buf->head->iov_len + buf->page_len + buf->tail->iov_len); buf->len = buf->head->iov_len + buf->page_len + buf->tail->iov_len; xdr_init_decode(xdr, buf, argv->iov_base, NULL); -- cgit v1.2.3 From cee4db19452467eef8ab93c6eb6a3a84d11d25d7 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sun, 8 Jan 2023 11:30:59 -0500 Subject: SUNRPC: Refactor RPC server dispatch method Currently, svcauth_gss_accept() pre-reserves response buffer space for the RPC payload length and GSS sequence number before returning to the dispatcher, which then adds the header's accept_stat field. The problem is the accept_stat field is supposed to go before the length and seq_num fields. So svcauth_gss_release() has to relocate the accept_stat value (see svcauth_gss_prepare_to_wrap()). To enable these fields to be added to the response buffer in the correct (final) order, the pointer to the accept_stat has to be made available to svcauth_gss_accept() so that it can set it before reserving space for the length and seq_num fields. As a first step, move the pointer to the location of the accept_stat field into struct svc_rqst. Reviewed-by: Jeff Layton Signed-off-by: Chuck Lever --- fs/lockd/svc.c | 4 ++-- fs/nfs/callback_xdr.c | 4 ++-- fs/nfsd/nfscache.c | 2 +- fs/nfsd/nfsd.h | 2 +- fs/nfsd/nfssvc.c | 4 ++-- include/linux/sunrpc/svc.h | 5 +++-- net/sunrpc/svc.c | 10 +++++----- 7 files changed, 16 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index 642e394e7a2d..0b28a6cf9303 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -685,15 +685,15 @@ module_exit(exit_nlm); /** * nlmsvc_dispatch - Process an NLM Request * @rqstp: incoming request - * @statp: pointer to location of accept_stat field in RPC Reply buffer * * Return values: * %0: Processing complete; do not send a Reply * %1: Processing complete; send Reply in rqstp->rq_res */ -static int nlmsvc_dispatch(struct svc_rqst *rqstp, __be32 *statp) +static int nlmsvc_dispatch(struct svc_rqst *rqstp) { const struct svc_procedure *procp = rqstp->rq_procinfo; + __be32 *statp = rqstp->rq_accept_statp; if (!procp->pc_decode(rqstp, &rqstp->rq_arg_stream)) goto out_decode_err; diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c index b4c3b7182198..13b2af55497d 100644 --- a/fs/nfs/callback_xdr.c +++ b/fs/nfs/callback_xdr.c @@ -980,11 +980,11 @@ out_invalidcred: } static int -nfs_callback_dispatch(struct svc_rqst *rqstp, __be32 *statp) +nfs_callback_dispatch(struct svc_rqst *rqstp) { const struct svc_procedure *procp = rqstp->rq_procinfo; - *statp = procp->pc_func(rqstp); + *rqstp->rq_accept_statp = procp->pc_func(rqstp); return 1; } diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c index ef5ee548053b..041faa13b852 100644 --- a/fs/nfsd/nfscache.c +++ b/fs/nfsd/nfscache.c @@ -509,7 +509,7 @@ out_trace: * nfsd_cache_update - Update an entry in the duplicate reply cache. * @rqstp: svc_rqst with a finished Reply * @cachetype: which cache to update - * @statp: Reply's status code + * @statp: pointer to Reply's NFS status code, or NULL * * This is called from nfsd_dispatch when the procedure has been * executed and the complete reply is in rqstp->rq_res. diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index fa0144a74267..d88498f8b275 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -86,7 +86,7 @@ bool nfssvc_encode_voidres(struct svc_rqst *rqstp, * Function prototypes. */ int nfsd_svc(int nrservs, struct net *net, const struct cred *cred); -int nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp); +int nfsd_dispatch(struct svc_rqst *rqstp); int nfsd_nrthreads(struct net *); int nfsd_nrpools(struct net *); diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index dfa8ee6c04d5..ff10c46b62d3 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -1022,7 +1022,6 @@ out: /** * nfsd_dispatch - Process an NFS or NFSACL Request * @rqstp: incoming request - * @statp: pointer to location of accept_stat field in RPC Reply buffer * * This RPC dispatcher integrates the NFS server's duplicate reply cache. * @@ -1030,9 +1029,10 @@ out: * %0: Processing complete; do not send a Reply * %1: Processing complete; send Reply in rqstp->rq_res */ -int nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp) +int nfsd_dispatch(struct svc_rqst *rqstp) { const struct svc_procedure *proc = rqstp->rq_procinfo; + __be32 *statp = rqstp->rq_accept_statp; /* * Give the xdr decoder a chance to change this if it wants diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 32eb98e621c3..f40a90ca5de6 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -251,6 +251,7 @@ struct svc_rqst { void * rq_argp; /* decoded arguments */ void * rq_resp; /* xdr'd results */ + __be32 *rq_accept_statp; void * rq_auth_data; /* flavor-specific data */ __be32 rq_auth_stat; /* authentication status */ int rq_auth_slack; /* extra space xdr code @@ -337,7 +338,7 @@ struct svc_deferred_req { struct svc_process_info { union { - int (*dispatch)(struct svc_rqst *, __be32 *); + int (*dispatch)(struct svc_rqst *rqstp); struct { unsigned int lovers; unsigned int hivers; @@ -389,7 +390,7 @@ struct svc_version { bool vs_need_cong_ctrl; /* Dispatch function */ - int (*vs_dispatch)(struct svc_rqst *, __be32 *); + int (*vs_dispatch)(struct svc_rqst *rqstp); }; /* diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 167cb928515f..16760bc5191f 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1232,9 +1232,9 @@ svc_process_common(struct svc_rqst *rqstp) const struct svc_procedure *procp = NULL; struct svc_serv *serv = rqstp->rq_server; struct svc_process_info process; - __be32 *p, *statp; int auth_res, rc; unsigned int aoffset; + __be32 *p; /* Will be turned off by GSS integrity and privacy services */ set_bit(RQ_SPLICE_OK, &rqstp->rq_flags); @@ -1314,8 +1314,8 @@ svc_process_common(struct svc_rqst *rqstp) trace_svc_process(rqstp, progp->pg_name); aoffset = xdr_stream_pos(xdr); - statp = xdr_reserve_space(&rqstp->rq_res_stream, XDR_UNIT); - *statp = rpc_success; + rqstp->rq_accept_statp = xdr_reserve_space(&rqstp->rq_res_stream, XDR_UNIT); + *rqstp->rq_accept_statp = rpc_success; /* un-reserve some of the out-queue now that we have a * better idea of reply size @@ -1324,7 +1324,7 @@ svc_process_common(struct svc_rqst *rqstp) svc_reserve_auth(rqstp, procp->pc_xdrressize<<2); /* Call the function that processes the request. */ - rc = process.dispatch(rqstp, statp); + rc = process.dispatch(rqstp); if (procp->pc_release) procp->pc_release(rqstp); if (!rc) @@ -1332,7 +1332,7 @@ svc_process_common(struct svc_rqst *rqstp) if (rqstp->rq_auth_stat != rpc_auth_ok) goto err_bad_auth; - if (*statp != rpc_success) + if (*rqstp->rq_accept_statp != rpc_success) xdr_truncate_encode(xdr, aoffset); if (procp->pc_encode == NULL) -- cgit v1.2.3 From 4bcf0343e8a69eb22f7e83bfa7cfce32a28c9d95 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sun, 8 Jan 2023 11:31:05 -0500 Subject: SUNRPC: Set rq_accept_statp inside ->accept methods To navigate around the space that svcauth_gss_accept() reserves for the RPC payload body length and sequence number fields, svcauth_gss_release() does a little dance with the reply's accept_stat, moving the accept_stat value in the response buffer down by two words. Instead, let's have the ->accept() methods each set the proper final location of the accept_stat to avoid having to move things. Reviewed-by: Jeff Layton Signed-off-by: Chuck Lever --- include/linux/sunrpc/svc.h | 19 +++++++++++++++++++ net/sunrpc/auth_gss/svcauth_gss.c | 21 ++++++++++----------- net/sunrpc/svc.c | 2 -- net/sunrpc/svcauth_unix.c | 6 ++++++ 4 files changed, 35 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index f40a90ca5de6..392d2d2620fa 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -544,4 +544,23 @@ static inline void svcxdr_set_auth_slack(struct svc_rqst *rqstp, int slack) WARN_ON(xdr->p > xdr->end); } +/** + * svcxdr_set_accept_stat - Reserve space for the accept_stat field + * @rqstp: RPC transaction context + * + * Return values: + * %true: Success + * %false: No response buffer space was available + */ +static inline bool svcxdr_set_accept_stat(struct svc_rqst *rqstp) +{ + struct xdr_stream *xdr = &rqstp->rq_res_stream; + + rqstp->rq_accept_statp = xdr_reserve_space(xdr, XDR_UNIT); + if (unlikely(!rqstp->rq_accept_statp)) + return false; + *rqstp->rq_accept_statp = rpc_success; + return true; +} + #endif /* SUNRPC_SVC_H */ diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index 01080d4659c3..7e7fda9a3e4e 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -1220,7 +1220,7 @@ svcauth_gss_legacy_init(struct svc_rqst *rqstp, if (!svcauth_gss_proc_init_verf(sn->rsc_cache, rqstp, &rsip->out_handle, &rsip->major_status, GSS_SEQ_WIN)) goto out; - if (xdr_stream_encode_u32(&rqstp->rq_res_stream, RPC_SUCCESS) < 0) + if (!svcxdr_set_accept_stat(rqstp)) goto out; if (!svcxdr_encode_gss_init_res(&rqstp->rq_res_stream, &rsip->out_handle, &rsip->out_token, rsip->major_status, @@ -1348,7 +1348,7 @@ static int svcauth_gss_proxy_init(struct svc_rqst *rqstp, if (!svcauth_gss_proc_init_verf(sn->rsc_cache, rqstp, &cli_handle, &ud.major_status, GSS_SEQ_WIN)) goto out; - if (xdr_stream_encode_u32(&rqstp->rq_res_stream, RPC_SUCCESS) < 0) + if (!svcxdr_set_accept_stat(rqstp)) goto out; if (!svcxdr_encode_gss_init_res(&rqstp->rq_res_stream, &cli_handle, &ud.out_token, ud.major_status, @@ -1640,16 +1640,18 @@ svcauth_gss_accept(struct svc_rqst *rqstp) case RPC_GSS_PROC_DESTROY: if (!svcauth_gss_encode_verf(rqstp, rsci->mechctx, gc->gc_seq)) goto auth_err; + if (!svcxdr_set_accept_stat(rqstp)) + goto auth_err; /* Delete the entry from the cache_list and call cache_put */ sunrpc_cache_unhash(sn->rsc_cache, &rsci->h); - if (xdr_stream_encode_u32(&rqstp->rq_res_stream, RPC_SUCCESS) < 0) - goto auth_err; goto complete; case RPC_GSS_PROC_DATA: rqstp->rq_auth_stat = rpcsec_gsserr_ctxproblem; svcdata->verf_start = xdr_reserve_space(&rqstp->rq_res_stream, 0); if (!svcauth_gss_encode_verf(rqstp, rsci->mechctx, gc->gc_seq)) goto auth_err; + if (!svcxdr_set_accept_stat(rqstp)) + goto auth_err; rqstp->rq_cred = rsci->cred; get_group_info(rsci->cred.cr_group_info); rqstp->rq_auth_stat = rpc_autherr_badcred; @@ -1706,7 +1708,6 @@ out: static __be32 * svcauth_gss_prepare_to_wrap(struct svc_rqst *rqstp, struct gss_svc_data *gsd) { - struct xdr_buf *resbuf = &rqstp->rq_res; __be32 *p; u32 verf_len; @@ -1721,13 +1722,11 @@ svcauth_gss_prepare_to_wrap(struct svc_rqst *rqstp, struct gss_svc_data *gsd) p += 1; verf_len = ntohl(*p++); p += XDR_QUADLEN(verf_len); - /* move accept_stat to right place: */ - memcpy(p, p + 2, 4); - /* Also don't wrap if the accept stat is nonzero: */ - if (*p != rpc_success) { - resbuf->head[0].iov_len -= 2 * 4; + + /* Also don't wrap if the accept_stat is nonzero: */ + if (*rqstp->rq_accept_statp != rpc_success) return NULL; - } + p++; return p; } diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 16760bc5191f..7b208e063334 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1314,8 +1314,6 @@ svc_process_common(struct svc_rqst *rqstp) trace_svc_process(rqstp, progp->pg_name); aoffset = xdr_stream_pos(xdr); - rqstp->rq_accept_statp = xdr_reserve_space(&rqstp->rq_res_stream, XDR_UNIT); - *rqstp->rq_accept_statp = rpc_success; /* un-reserve some of the out-queue now that we have a * better idea of reply size diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c index b101700d155c..62dfc8cdf8c5 100644 --- a/net/sunrpc/svcauth_unix.c +++ b/net/sunrpc/svcauth_unix.c @@ -775,6 +775,8 @@ svcauth_null_accept(struct svc_rqst *rqstp) if (xdr_stream_encode_opaque_auth(&rqstp->rq_res_stream, RPC_AUTH_NULL, NULL, 0) < 0) return SVC_CLOSE; + if (!svcxdr_set_accept_stat(rqstp)) + return SVC_CLOSE; rqstp->rq_cred.cr_flavor = RPC_AUTH_NULL; return SVC_OK; @@ -866,6 +868,8 @@ svcauth_tls_accept(struct svc_rqst *rqstp) RPC_AUTH_NULL, NULL, 0) < 0) return SVC_CLOSE; } + if (!svcxdr_set_accept_stat(rqstp)) + return SVC_CLOSE; rqstp->rq_cred.cr_flavor = RPC_AUTH_TLS; return SVC_OK; @@ -960,6 +964,8 @@ svcauth_unix_accept(struct svc_rqst *rqstp) if (xdr_stream_encode_opaque_auth(&rqstp->rq_res_stream, RPC_AUTH_NULL, NULL, 0) < 0) return SVC_CLOSE; + if (!svcxdr_set_accept_stat(rqstp)) + return SVC_CLOSE; rqstp->rq_cred.cr_flavor = RPC_AUTH_UNIX; return SVC_OK; -- cgit v1.2.3 From 65ba3d2425bf51165b6e88509c632bd15d12883d Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 10 Jan 2023 10:31:54 -0500 Subject: SUNRPC: Use per-CPU counters to tally server RPC counts - Improves counting accuracy - Reduces cross-CPU memory traffic Signed-off-by: Chuck Lever --- fs/lockd/svc.c | 15 ++++++++++----- fs/nfs/callback_xdr.c | 6 ++++-- fs/nfsd/nfs2acl.c | 5 +++-- fs/nfsd/nfs3acl.c | 5 +++-- fs/nfsd/nfs3proc.c | 5 +++-- fs/nfsd/nfs4proc.c | 7 ++++--- fs/nfsd/nfsproc.c | 6 +++--- include/linux/lockd/lockd.h | 4 ++-- include/linux/sunrpc/svc.h | 2 +- net/sunrpc/stats.c | 11 ++++++++--- net/sunrpc/svc.c | 2 +- 11 files changed, 42 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index 0b28a6cf9303..1da00230860c 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -721,7 +721,7 @@ out_encode_err: /* * Define NLM program and procedures */ -static unsigned int nlmsvc_version1_count[17]; +static DEFINE_PER_CPU_ALIGNED(unsigned long, nlmsvc_version1_count[17]); static const struct svc_version nlmsvc_version1 = { .vs_vers = 1, .vs_nproc = 17, @@ -730,26 +730,31 @@ static const struct svc_version nlmsvc_version1 = { .vs_dispatch = nlmsvc_dispatch, .vs_xdrsize = NLMSVC_XDRSIZE, }; -static unsigned int nlmsvc_version3_count[24]; + +static DEFINE_PER_CPU_ALIGNED(unsigned long, + nlmsvc_version3_count[ARRAY_SIZE(nlmsvc_procedures)]); static const struct svc_version nlmsvc_version3 = { .vs_vers = 3, - .vs_nproc = 24, + .vs_nproc = ARRAY_SIZE(nlmsvc_procedures), .vs_proc = nlmsvc_procedures, .vs_count = nlmsvc_version3_count, .vs_dispatch = nlmsvc_dispatch, .vs_xdrsize = NLMSVC_XDRSIZE, }; + #ifdef CONFIG_LOCKD_V4 -static unsigned int nlmsvc_version4_count[24]; +static DEFINE_PER_CPU_ALIGNED(unsigned long, + nlmsvc_version4_count[ARRAY_SIZE(nlmsvc_procedures4)]); static const struct svc_version nlmsvc_version4 = { .vs_vers = 4, - .vs_nproc = 24, + .vs_nproc = ARRAY_SIZE(nlmsvc_procedures4), .vs_proc = nlmsvc_procedures4, .vs_count = nlmsvc_version4_count, .vs_dispatch = nlmsvc_dispatch, .vs_xdrsize = NLMSVC_XDRSIZE, }; #endif + static const struct svc_version *nlmsvc_version[] = { [1] = &nlmsvc_version1, [3] = &nlmsvc_version3, diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c index 13b2af55497d..321af81c456e 100644 --- a/fs/nfs/callback_xdr.c +++ b/fs/nfs/callback_xdr.c @@ -1069,7 +1069,8 @@ static const struct svc_procedure nfs4_callback_procedures1[] = { } }; -static unsigned int nfs4_callback_count1[ARRAY_SIZE(nfs4_callback_procedures1)]; +static DEFINE_PER_CPU_ALIGNED(unsigned long, + nfs4_callback_count1[ARRAY_SIZE(nfs4_callback_procedures1)]); const struct svc_version nfs4_callback_version1 = { .vs_vers = 1, .vs_nproc = ARRAY_SIZE(nfs4_callback_procedures1), @@ -1081,7 +1082,8 @@ const struct svc_version nfs4_callback_version1 = { .vs_need_cong_ctrl = true, }; -static unsigned int nfs4_callback_count4[ARRAY_SIZE(nfs4_callback_procedures1)]; +static DEFINE_PER_CPU_ALIGNED(unsigned long, + nfs4_callback_count4[ARRAY_SIZE(nfs4_callback_procedures1)]); const struct svc_version nfs4_callback_version4 = { .vs_vers = 4, .vs_nproc = ARRAY_SIZE(nfs4_callback_procedures1), diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c index 1457f59f447a..dea55883e099 100644 --- a/fs/nfsd/nfs2acl.c +++ b/fs/nfsd/nfs2acl.c @@ -377,10 +377,11 @@ static const struct svc_procedure nfsd_acl_procedures2[5] = { }, }; -static unsigned int nfsd_acl_count2[ARRAY_SIZE(nfsd_acl_procedures2)]; +static DEFINE_PER_CPU_ALIGNED(unsigned long, + nfsd_acl_count2[ARRAY_SIZE(nfsd_acl_procedures2)]); const struct svc_version nfsd_acl_version2 = { .vs_vers = 2, - .vs_nproc = 5, + .vs_nproc = ARRAY_SIZE(nfsd_acl_procedures2), .vs_proc = nfsd_acl_procedures2, .vs_count = nfsd_acl_count2, .vs_dispatch = nfsd_dispatch, diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c index 647108138e8a..bf1c52c1bdab 100644 --- a/fs/nfsd/nfs3acl.c +++ b/fs/nfsd/nfs3acl.c @@ -266,10 +266,11 @@ static const struct svc_procedure nfsd_acl_procedures3[3] = { }, }; -static unsigned int nfsd_acl_count3[ARRAY_SIZE(nfsd_acl_procedures3)]; +static DEFINE_PER_CPU_ALIGNED(unsigned long, + nfsd_acl_count3[ARRAY_SIZE(nfsd_acl_procedures3)]); const struct svc_version nfsd_acl_version3 = { .vs_vers = 3, - .vs_nproc = 3, + .vs_nproc = ARRAY_SIZE(nfsd_acl_procedures3), .vs_proc = nfsd_acl_procedures3, .vs_count = nfsd_acl_count3, .vs_dispatch = nfsd_dispatch, diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index d01b29aba662..1c73921c02e0 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -1064,10 +1064,11 @@ static const struct svc_procedure nfsd_procedures3[22] = { }, }; -static unsigned int nfsd_count3[ARRAY_SIZE(nfsd_procedures3)]; +static DEFINE_PER_CPU_ALIGNED(unsigned long, + nfsd_count3[ARRAY_SIZE(nfsd_procedures3)]); const struct svc_version nfsd_version3 = { .vs_vers = 3, - .vs_nproc = 22, + .vs_nproc = ARRAY_SIZE(nfsd_procedures3), .vs_proc = nfsd_procedures3, .vs_dispatch = nfsd_dispatch, .vs_count = nfsd_count3, diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index dbaf33398c82..9435136d7de6 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -3596,12 +3596,13 @@ static const struct svc_procedure nfsd_procedures4[2] = { }, }; -static unsigned int nfsd_count3[ARRAY_SIZE(nfsd_procedures4)]; +static DEFINE_PER_CPU_ALIGNED(unsigned long, + nfsd_count4[ARRAY_SIZE(nfsd_procedures4)]); const struct svc_version nfsd_version4 = { .vs_vers = 4, - .vs_nproc = 2, + .vs_nproc = ARRAY_SIZE(nfsd_procedures4), .vs_proc = nfsd_procedures4, - .vs_count = nfsd_count3, + .vs_count = nfsd_count4, .vs_dispatch = nfsd_dispatch, .vs_xdrsize = NFS4_SVC_XDRSIZE, .vs_rpcb_optnl = true, diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index 9744443c3965..9e6069e9c9f1 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -838,11 +838,11 @@ static const struct svc_procedure nfsd_procedures2[18] = { }, }; - -static unsigned int nfsd_count2[ARRAY_SIZE(nfsd_procedures2)]; +static DEFINE_PER_CPU_ALIGNED(unsigned long, + nfsd_count2[ARRAY_SIZE(nfsd_procedures2)]); const struct svc_version nfsd_version2 = { .vs_vers = 2, - .vs_nproc = 18, + .vs_nproc = ARRAY_SIZE(nfsd_procedures2), .vs_proc = nfsd_procedures2, .vs_count = nfsd_count2, .vs_dispatch = nfsd_dispatch, diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index 70ce419e2709..84de6b7c9948 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -196,9 +196,9 @@ struct nlm_block { * Global variables */ extern const struct rpc_program nlm_program; -extern const struct svc_procedure nlmsvc_procedures[]; +extern const struct svc_procedure nlmsvc_procedures[24]; #ifdef CONFIG_LOCKD_V4 -extern const struct svc_procedure nlmsvc_procedures4[]; +extern const struct svc_procedure nlmsvc_procedures4[24]; #endif extern int nlmsvc_grace_period; extern unsigned long nlmsvc_timeout; diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 392d2d2620fa..1b078c9a2d60 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -377,7 +377,7 @@ struct svc_version { u32 vs_vers; /* version number */ u32 vs_nproc; /* number of procedures */ const struct svc_procedure *vs_proc; /* per-procedure info */ - unsigned int *vs_count; /* call counts */ + unsigned long __percpu *vs_count; /* call counts */ u32 vs_xdrsize; /* xdrsize needed for this version */ /* Don't register with rpcbind */ diff --git a/net/sunrpc/stats.c b/net/sunrpc/stats.c index 52908f9e6eab..65fc1297c6df 100644 --- a/net/sunrpc/stats.c +++ b/net/sunrpc/stats.c @@ -83,7 +83,8 @@ void svc_seq_show(struct seq_file *seq, const struct svc_stat *statp) { const struct svc_program *prog = statp->program; const struct svc_version *vers; - unsigned int i, j; + unsigned int i, j, k; + unsigned long count; seq_printf(seq, "net %u %u %u %u\n", @@ -104,8 +105,12 @@ void svc_seq_show(struct seq_file *seq, const struct svc_stat *statp) if (!vers) continue; seq_printf(seq, "proc%d %u", i, vers->vs_nproc); - for (j = 0; j < vers->vs_nproc; j++) - seq_printf(seq, " %u", vers->vs_count[j]); + for (j = 0; j < vers->vs_nproc; j++) { + count = 0; + for_each_possible_cpu(k) + count += per_cpu(vers->vs_count[j], k); + seq_printf(seq, " %lu", count); + } seq_putc(seq, '\n'); } } diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 7b208e063334..5dc298c30ea8 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1208,7 +1208,7 @@ svc_generic_init_request(struct svc_rqst *rqstp, memset(rqstp->rq_resp, 0, procp->pc_ressize); /* Bump per-procedure stats counter */ - versp->vs_count[rqstp->rq_proc]++; + this_cpu_inc(versp->vs_count[rqstp->rq_proc]); ret->dispatch = versp->vs_dispatch; return rpc_success; -- cgit v1.2.3 From ccf08bed6e7a80519569456edd2ea21b7b1701c6 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 10 Jan 2023 10:32:00 -0500 Subject: SUNRPC: Replace pool stats with per-CPU variables Eliminate the use of bus-locked operations in svc_xprt_enqueue(), which is a hot path. Replace them with per-cpu variables to reduce cross-CPU memory bus traffic. Signed-off-by: Chuck Lever --- include/linux/sunrpc/svc.h | 15 ++++++--------- net/sunrpc/svc.c | 12 ++++++++++++ net/sunrpc/svc_xprt.c | 18 ++++++++---------- 3 files changed, 26 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 1b078c9a2d60..877891536c2f 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -21,14 +21,6 @@ #include #include -/* statistics for svc_pool structures */ -struct svc_pool_stats { - atomic_long_t packets; - unsigned long sockets_queued; - atomic_long_t threads_woken; - atomic_long_t threads_timedout; -}; - /* * * RPC service thread pool. @@ -45,7 +37,12 @@ struct svc_pool { struct list_head sp_sockets; /* pending sockets */ unsigned int sp_nrthreads; /* # of threads in pool */ struct list_head sp_all_threads; /* all server threads */ - struct svc_pool_stats sp_stats; /* statistics on pool operation */ + + /* statistics on pool operation */ + struct percpu_counter sp_sockets_queued; + struct percpu_counter sp_threads_woken; + struct percpu_counter sp_threads_timedout; + #define SP_TASK_PENDING (0) /* still work to do even if no * xprt is queued. */ #define SP_CONGESTED (1) diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 5dc298c30ea8..1fd3f5e57285 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -512,6 +512,10 @@ __svc_create(struct svc_program *prog, unsigned int bufsize, int npools, INIT_LIST_HEAD(&pool->sp_sockets); INIT_LIST_HEAD(&pool->sp_all_threads); spin_lock_init(&pool->sp_lock); + + percpu_counter_init(&pool->sp_sockets_queued, 0, GFP_KERNEL); + percpu_counter_init(&pool->sp_threads_woken, 0, GFP_KERNEL); + percpu_counter_init(&pool->sp_threads_timedout, 0, GFP_KERNEL); } return serv; @@ -565,6 +569,7 @@ void svc_destroy(struct kref *ref) { struct svc_serv *serv = container_of(ref, struct svc_serv, sv_refcnt); + unsigned int i; dprintk("svc: svc_destroy(%s)\n", serv->sv_program->pg_name); timer_shutdown_sync(&serv->sv_temptimer); @@ -580,6 +585,13 @@ svc_destroy(struct kref *ref) svc_pool_map_put(serv->sv_nrpools); + for (i = 0; i < serv->sv_nrpools; i++) { + struct svc_pool *pool = &serv->sv_pools[i]; + + percpu_counter_destroy(&pool->sp_sockets_queued); + percpu_counter_destroy(&pool->sp_threads_woken); + percpu_counter_destroy(&pool->sp_threads_timedout); + } kfree(serv->sv_pools); kfree(serv); } diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index c678fd2d61ef..1574a9429d07 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -462,11 +462,9 @@ void svc_xprt_enqueue(struct svc_xprt *xprt) pool = svc_pool_for_cpu(xprt->xpt_server); - atomic_long_inc(&pool->sp_stats.packets); - + percpu_counter_inc(&pool->sp_sockets_queued); spin_lock_bh(&pool->sp_lock); list_add_tail(&xprt->xpt_ready, &pool->sp_sockets); - pool->sp_stats.sockets_queued++; spin_unlock_bh(&pool->sp_lock); /* find a thread for this xprt */ @@ -474,7 +472,7 @@ void svc_xprt_enqueue(struct svc_xprt *xprt) list_for_each_entry_rcu(rqstp, &pool->sp_all_threads, rq_all) { if (test_and_set_bit(RQ_BUSY, &rqstp->rq_flags)) continue; - atomic_long_inc(&pool->sp_stats.threads_woken); + percpu_counter_inc(&pool->sp_threads_woken); rqstp->rq_qtime = ktime_get(); wake_up_process(rqstp->rq_task); goto out_unlock; @@ -769,7 +767,7 @@ static struct svc_xprt *svc_get_next_xprt(struct svc_rqst *rqstp, long timeout) goto out_found; if (!time_left) - atomic_long_inc(&pool->sp_stats.threads_timedout); + percpu_counter_inc(&pool->sp_threads_timedout); if (signalled() || kthread_should_stop()) return ERR_PTR(-EINTR); @@ -1440,12 +1438,12 @@ static int svc_pool_stats_show(struct seq_file *m, void *p) return 0; } - seq_printf(m, "%u %lu %lu %lu %lu\n", + seq_printf(m, "%u %llu %llu %llu %llu\n", pool->sp_id, - (unsigned long)atomic_long_read(&pool->sp_stats.packets), - pool->sp_stats.sockets_queued, - (unsigned long)atomic_long_read(&pool->sp_stats.threads_woken), - (unsigned long)atomic_long_read(&pool->sp_stats.threads_timedout)); + percpu_counter_sum_positive(&pool->sp_sockets_queued), + percpu_counter_sum_positive(&pool->sp_sockets_queued), + percpu_counter_sum_positive(&pool->sp_threads_woken), + percpu_counter_sum_positive(&pool->sp_threads_timedout)); return 0; } -- cgit v1.2.3 From 97648b94bd9dbb987fe7e4067deecdb47d4fd7e7 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sun, 15 Jan 2023 12:20:22 -0500 Subject: SUNRPC: Add header ifdefs to linux/sunrpc/gss_krb5.h Standard convention: Ensure the contents of the header are included only once per source file. Tested-by: Scott Mayhew Reviewed-by: Simo Sorce Signed-off-by: Chuck Lever --- include/linux/sunrpc/gss_krb5.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/gss_krb5.h b/include/linux/sunrpc/gss_krb5.h index 91f43d86879d..0135139ddf20 100644 --- a/include/linux/sunrpc/gss_krb5.h +++ b/include/linux/sunrpc/gss_krb5.h @@ -1,6 +1,4 @@ /* - * linux/include/linux/sunrpc/gss_krb5_types.h - * * Adapted from MIT Kerberos 5-1.2.1 lib/include/krb5.h, * lib/gssapi/krb5/gssapiP_krb5.h, and others * @@ -36,6 +34,9 @@ * */ +#ifndef _LINUX_SUNRPC_GSS_KRB5_H +#define _LINUX_SUNRPC_GSS_KRB5_H + #include #include #include @@ -316,3 +317,5 @@ gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, u32 len, void gss_krb5_make_confounder(char *p, u32 conflen); + +#endif /* _LINUX_SUNRPC_GSS_KRB5_H */ -- cgit v1.2.3 From f03640a1a9782f4bf7c1db63e2e6a9598c6d2c6e Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sun, 15 Jan 2023 12:20:28 -0500 Subject: SUNRPC: Remove .blocksize field from struct gss_krb5_enctype It is not clear from documenting comments, specifications, or code usage what value the gss_krb5_enctype.blocksize field is supposed to store. The "encryption blocksize" depends only on the cipher being used, so that value can be derived where it's needed instead of stored as a constant. RFC 3961 Section 5.2 says: > cipher block size, c > This is the block size of the block cipher underlying the > encryption and decryption functions indicated above, used for key > derivation and for the size of the message confounder and initial > vector. (If a block cipher is not in use, some comparable > parameter should be determined.) It must be at least 5 octets. > > This is not actually an independent parameter; rather, it is a > property of the functions E and D. It is listed here to clarify > the distinction between it and the message block size, m. In the Linux kernel's implemenation of the SunRPC RPCSEC GSS Kerberos 5 mechanism, the cipher block size, which is dependent on the encryption and decryption transforms, is used only in krb5_derive_key(), so it is straightforward to replace it. Tested-by: Scott Mayhew Reviewed-by: Simo Sorce Signed-off-by: Chuck Lever --- include/linux/sunrpc/gss_krb5.h | 1 - net/sunrpc/auth_gss/gss_krb5_keys.c | 4 +--- net/sunrpc/auth_gss/gss_krb5_mech.c | 4 ---- 3 files changed, 1 insertion(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/gss_krb5.h b/include/linux/sunrpc/gss_krb5.h index 0135139ddf20..9a833825b55b 100644 --- a/include/linux/sunrpc/gss_krb5.h +++ b/include/linux/sunrpc/gss_krb5.h @@ -64,7 +64,6 @@ struct gss_krb5_enctype { const char *cksum_name; /* crypto checksum name */ const u16 signalg; /* signing algorithm */ const u16 sealalg; /* sealing algorithm */ - const u32 blocksize; /* encryption blocksize */ const u32 conflen; /* confounder length (normally the same as the blocksize) */ diff --git a/net/sunrpc/auth_gss/gss_krb5_keys.c b/net/sunrpc/auth_gss/gss_krb5_keys.c index 726c076950c0..554cfd23f288 100644 --- a/net/sunrpc/auth_gss/gss_krb5_keys.c +++ b/net/sunrpc/auth_gss/gss_krb5_keys.c @@ -150,7 +150,6 @@ u32 krb5_derive_key(const struct gss_krb5_enctype *gk5e, struct crypto_sync_skcipher *cipher; u32 ret = EINVAL; - blocksize = gk5e->blocksize; keybytes = gk5e->keybytes; keylength = gk5e->keylength; @@ -160,11 +159,10 @@ u32 krb5_derive_key(const struct gss_krb5_enctype *gk5e, cipher = crypto_alloc_sync_skcipher(gk5e->encrypt_name, 0, 0); if (IS_ERR(cipher)) goto err_return; + blocksize = crypto_sync_skcipher_blocksize(cipher); if (crypto_sync_skcipher_setkey(cipher, inkey->data, inkey->len)) goto err_return; - /* allocate and set up buffers */ - ret = ENOMEM; inblockdata = kmalloc(blocksize, gfp_mask); if (inblockdata == NULL) diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c index 1c092b05c2bb..dd85fc9ca80b 100644 --- a/net/sunrpc/auth_gss/gss_krb5_mech.c +++ b/net/sunrpc/auth_gss/gss_krb5_mech.c @@ -47,7 +47,6 @@ static const struct gss_krb5_enctype supported_gss_krb5_enctypes[] = { .sealalg = SEAL_ALG_DES, .keybytes = 7, .keylength = 8, - .blocksize = 8, .conflen = 8, .cksumlength = 8, .keyed_cksum = 0, @@ -69,7 +68,6 @@ static const struct gss_krb5_enctype supported_gss_krb5_enctypes[] = { .sealalg = SEAL_ALG_DES3KD, .keybytes = 21, .keylength = 24, - .blocksize = 8, .conflen = 8, .cksumlength = 20, .keyed_cksum = 1, @@ -92,7 +90,6 @@ static const struct gss_krb5_enctype supported_gss_krb5_enctypes[] = { .sealalg = -1, .keybytes = 16, .keylength = 16, - .blocksize = 16, .conflen = 16, .cksumlength = 12, .keyed_cksum = 1, @@ -115,7 +112,6 @@ static const struct gss_krb5_enctype supported_gss_krb5_enctypes[] = { .sealalg = -1, .keybytes = 32, .keylength = 32, - .blocksize = 16, .conflen = 16, .cksumlength = 12, .keyed_cksum = 1, -- cgit v1.2.3 From 4be416a5f2803d421c950cc48e8e0c1eaaa8c773 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sun, 15 Jan 2023 12:20:35 -0500 Subject: SUNRPC: Remove .conflen field from struct gss_krb5_enctype Now that arcfour-hmac is gone, the confounder length is again the same as the cipher blocksize for every implemented enctype. The gss_krb5_enctype::conflen field is no longer necessary. Tested-by: Scott Mayhew Reviewed-by: Simo Sorce Signed-off-by: Chuck Lever --- include/linux/sunrpc/gss_krb5.h | 3 --- net/sunrpc/auth_gss/gss_krb5_crypto.c | 9 +++++---- net/sunrpc/auth_gss/gss_krb5_mech.c | 4 ---- net/sunrpc/auth_gss/gss_krb5_wrap.c | 4 ++-- 4 files changed, 7 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/gss_krb5.h b/include/linux/sunrpc/gss_krb5.h index 9a833825b55b..51860e3a0216 100644 --- a/include/linux/sunrpc/gss_krb5.h +++ b/include/linux/sunrpc/gss_krb5.h @@ -64,9 +64,6 @@ struct gss_krb5_enctype { const char *cksum_name; /* crypto checksum name */ const u16 signalg; /* signing algorithm */ const u16 sealalg; /* sealing algorithm */ - const u32 conflen; /* confounder length - (normally the same as - the blocksize) */ const u32 cksumlength; /* checksum length */ const u32 keyed_cksum; /* is it a keyed cksum? */ const u32 keybytes; /* raw key len, in bytes */ diff --git a/net/sunrpc/auth_gss/gss_krb5_crypto.c b/net/sunrpc/auth_gss/gss_krb5_crypto.c index 3ea58175e159..8aa5610ef660 100644 --- a/net/sunrpc/auth_gss/gss_krb5_crypto.c +++ b/net/sunrpc/auth_gss/gss_krb5_crypto.c @@ -610,6 +610,7 @@ gss_krb5_aes_encrypt(struct krb5_ctx *kctx, u32 offset, struct encryptor_desc desc; u32 cbcbytes; unsigned int usage; + unsigned int conflen; if (kctx->initiate) { cipher = kctx->initiator_enc; @@ -623,12 +624,13 @@ gss_krb5_aes_encrypt(struct krb5_ctx *kctx, u32 offset, usage = KG_USAGE_ACCEPTOR_SEAL; } blocksize = crypto_sync_skcipher_blocksize(cipher); + conflen = crypto_sync_skcipher_blocksize(cipher); /* hide the gss token header and insert the confounder */ offset += GSS_KRB5_TOK_HDR_LEN; - if (xdr_extend_head(buf, offset, kctx->gk5e->conflen)) + if (xdr_extend_head(buf, offset, conflen)) return GSS_S_FAILURE; - gss_krb5_make_confounder(buf->head[0].iov_base + offset, kctx->gk5e->conflen); + gss_krb5_make_confounder(buf->head[0].iov_base + offset, conflen); offset -= GSS_KRB5_TOK_HDR_LEN; if (buf->tail[0].iov_base != NULL) { @@ -744,7 +746,6 @@ gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, u32 len, } blocksize = crypto_sync_skcipher_blocksize(cipher); - /* create a segment skipping the header and leaving out the checksum */ xdr_buf_subsegment(buf, &subbuf, offset + GSS_KRB5_TOK_HDR_LEN, (len - offset - GSS_KRB5_TOK_HDR_LEN - @@ -801,7 +802,7 @@ gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, u32 len, ret = GSS_S_BAD_SIG; goto out_err; } - *headskip = kctx->gk5e->conflen; + *headskip = blocksize; *tailskip = kctx->gk5e->cksumlength; out_err: if (ret && ret != GSS_S_BAD_SIG) diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c index dd85fc9ca80b..08a86ece665e 100644 --- a/net/sunrpc/auth_gss/gss_krb5_mech.c +++ b/net/sunrpc/auth_gss/gss_krb5_mech.c @@ -47,7 +47,6 @@ static const struct gss_krb5_enctype supported_gss_krb5_enctypes[] = { .sealalg = SEAL_ALG_DES, .keybytes = 7, .keylength = 8, - .conflen = 8, .cksumlength = 8, .keyed_cksum = 0, }, @@ -68,7 +67,6 @@ static const struct gss_krb5_enctype supported_gss_krb5_enctypes[] = { .sealalg = SEAL_ALG_DES3KD, .keybytes = 21, .keylength = 24, - .conflen = 8, .cksumlength = 20, .keyed_cksum = 1, }, @@ -90,7 +88,6 @@ static const struct gss_krb5_enctype supported_gss_krb5_enctypes[] = { .sealalg = -1, .keybytes = 16, .keylength = 16, - .conflen = 16, .cksumlength = 12, .keyed_cksum = 1, }, @@ -112,7 +109,6 @@ static const struct gss_krb5_enctype supported_gss_krb5_enctypes[] = { .sealalg = -1, .keybytes = 32, .keylength = 32, - .conflen = 16, .cksumlength = 12, .keyed_cksum = 1, }, diff --git a/net/sunrpc/auth_gss/gss_krb5_wrap.c b/net/sunrpc/auth_gss/gss_krb5_wrap.c index 48337687848c..bd068e936947 100644 --- a/net/sunrpc/auth_gss/gss_krb5_wrap.c +++ b/net/sunrpc/auth_gss/gss_krb5_wrap.c @@ -168,7 +168,7 @@ gss_wrap_kerberos_v1(struct krb5_ctx *kctx, int offset, struct page **tmp_pages; u32 seq_send; u8 *cksumkey; - u32 conflen = kctx->gk5e->conflen; + u32 conflen = crypto_sync_skcipher_blocksize(kctx->enc); dprintk("RPC: %s\n", __func__); @@ -261,7 +261,7 @@ gss_unwrap_kerberos_v1(struct krb5_ctx *kctx, int offset, int len, void *data_start, *orig_start; int data_len; int blocksize; - u32 conflen = kctx->gk5e->conflen; + u32 conflen = crypto_sync_skcipher_blocksize(kctx->enc); int crypt_offset; u8 *cksumkey; unsigned int saved_len = buf->len; -- cgit v1.2.3 From 7f675ca7757bfeb70e19d187dc3be44deb836da8 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sun, 15 Jan 2023 12:20:41 -0500 Subject: SUNRPC: Improve Kerberos confounder generation Other common Kerberos implementations use a fully random confounder for encryption. The reason for this is explained in the new comment added by this patch. The current get_random_bytes() implementation does not exhaust system entropy. Since confounder generation is part of Kerberos itself rather than the GSS-API Kerberos mechanism, the function is renamed and moved. Note that light top-down analysis shows that the SHA-1 transform is by far the most CPU-intensive part of encryption. Thus we do not expect this change to result in a significant performance impact. However, eventually it might be necessary to generate an independent stream of confounders for each Kerberos context to help improve I/O parallelism. Reviewed-by: Simo Sorce Signed-off-by: Chuck Lever --- include/linux/sunrpc/gss_krb5.h | 3 --- net/sunrpc/auth_gss/gss_krb5_crypto.c | 33 +++++++++++++++++++++++++++- net/sunrpc/auth_gss/gss_krb5_internal.h | 13 +++++++++++ net/sunrpc/auth_gss/gss_krb5_mech.c | 15 ++++++------- net/sunrpc/auth_gss/gss_krb5_wrap.c | 38 +++------------------------------ 5 files changed, 55 insertions(+), 47 deletions(-) create mode 100644 net/sunrpc/auth_gss/gss_krb5_internal.h (limited to 'include/linux') diff --git a/include/linux/sunrpc/gss_krb5.h b/include/linux/sunrpc/gss_krb5.h index 51860e3a0216..f0fac1e69731 100644 --- a/include/linux/sunrpc/gss_krb5.h +++ b/include/linux/sunrpc/gss_krb5.h @@ -311,7 +311,4 @@ gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, u32 len, struct xdr_buf *buf, u32 *plainoffset, u32 *plainlen); -void -gss_krb5_make_confounder(char *p, u32 conflen); - #endif /* _LINUX_SUNRPC_GSS_KRB5_H */ diff --git a/net/sunrpc/auth_gss/gss_krb5_crypto.c b/net/sunrpc/auth_gss/gss_krb5_crypto.c index 8aa5610ef660..7c06c11e452c 100644 --- a/net/sunrpc/auth_gss/gss_krb5_crypto.c +++ b/net/sunrpc/auth_gss/gss_krb5_crypto.c @@ -47,10 +47,41 @@ #include #include +#include "gss_krb5_internal.h" + #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_AUTH #endif +/** + * krb5_make_confounder - Generate a confounder string + * @p: memory location into which to write the string + * @conflen: string length to write, in octets + * + * RFCs 1964 and 3961 mention only "a random confounder" without going + * into detail about its function or cryptographic requirements. The + * assumed purpose is to prevent repeated encryption of a plaintext with + * the same key from generating the same ciphertext. It is also used to + * pad minimum plaintext length to at least a single cipher block. + * + * However, in situations like the GSS Kerberos 5 mechanism, where the + * encryption IV is always all zeroes, the confounder also effectively + * functions like an IV. Thus, not only must it be unique from message + * to message, but it must also be difficult to predict. Otherwise an + * attacker can correlate the confounder to previous or future values, + * making the encryption easier to break. + * + * Given that the primary consumer of this encryption mechanism is a + * network storage protocol, a type of traffic that often carries + * predictable payloads (eg, all zeroes when reading unallocated blocks + * from a file), our confounder generation has to be cryptographically + * strong. + */ +void krb5_make_confounder(u8 *p, int conflen) +{ + get_random_bytes(p, conflen); +} + u32 krb5_encrypt( struct crypto_sync_skcipher *tfm, @@ -630,7 +661,7 @@ gss_krb5_aes_encrypt(struct krb5_ctx *kctx, u32 offset, offset += GSS_KRB5_TOK_HDR_LEN; if (xdr_extend_head(buf, offset, conflen)) return GSS_S_FAILURE; - gss_krb5_make_confounder(buf->head[0].iov_base + offset, conflen); + krb5_make_confounder(buf->head[0].iov_base + offset, conflen); offset -= GSS_KRB5_TOK_HDR_LEN; if (buf->tail[0].iov_base != NULL) { diff --git a/net/sunrpc/auth_gss/gss_krb5_internal.h b/net/sunrpc/auth_gss/gss_krb5_internal.h new file mode 100644 index 000000000000..16a83d507075 --- /dev/null +++ b/net/sunrpc/auth_gss/gss_krb5_internal.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 or BSD-3-Clause */ +/* + * SunRPC GSS Kerberos 5 mechanism internal definitions + * + * Copyright (c) 2022 Oracle and/or its affiliates. + */ + +#ifndef _NET_SUNRPC_AUTH_GSS_KRB5_INTERNAL_H +#define _NET_SUNRPC_AUTH_GSS_KRB5_INTERNAL_H + +void krb5_make_confounder(u8 *p, int conflen); + +#endif /* _NET_SUNRPC_AUTH_GSS_KRB5_INTERNAL_H */ diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c index 08a86ece665e..76a0d83fe500 100644 --- a/net/sunrpc/auth_gss/gss_krb5_mech.c +++ b/net/sunrpc/auth_gss/gss_krb5_mech.c @@ -550,16 +550,15 @@ gss_import_sec_context_kerberos(const void *p, size_t len, ret = gss_import_v1_context(p, end, ctx); else ret = gss_import_v2_context(p, end, ctx, gfp_mask); - - if (ret == 0) { - ctx_id->internal_ctx_id = ctx; - if (endtime) - *endtime = ctx->endtime; - } else + if (ret) { kfree(ctx); + return ret; + } - dprintk("RPC: %s: returning %d\n", __func__, ret); - return ret; + ctx_id->internal_ctx_id = ctx; + if (endtime) + *endtime = ctx->endtime; + return 0; } static void diff --git a/net/sunrpc/auth_gss/gss_krb5_wrap.c b/net/sunrpc/auth_gss/gss_krb5_wrap.c index bd068e936947..66e65e4c6336 100644 --- a/net/sunrpc/auth_gss/gss_krb5_wrap.c +++ b/net/sunrpc/auth_gss/gss_krb5_wrap.c @@ -32,9 +32,10 @@ #include #include #include -#include #include +#include "gss_krb5_internal.h" + #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_AUTH #endif @@ -113,39 +114,6 @@ out: return 0; } -void -gss_krb5_make_confounder(char *p, u32 conflen) -{ - static u64 i = 0; - u64 *q = (u64 *)p; - - /* rfc1964 claims this should be "random". But all that's really - * necessary is that it be unique. And not even that is necessary in - * our case since our "gssapi" implementation exists only to support - * rpcsec_gss, so we know that the only buffers we will ever encrypt - * already begin with a unique sequence number. Just to hedge my bets - * I'll make a half-hearted attempt at something unique, but ensuring - * uniqueness would mean worrying about atomicity and rollover, and I - * don't care enough. */ - - /* initialize to random value */ - if (i == 0) { - i = get_random_u32(); - i = (i << 32) | get_random_u32(); - } - - switch (conflen) { - case 16: - *q++ = i++; - fallthrough; - case 8: - *q++ = i++; - break; - default: - BUG(); - } -} - /* Assumptions: the head and tail of inbuf are ours to play with. * The pages, however, may be real pages in the page cache and we replace * them with scratch pages from **pages before writing to them. */ @@ -211,7 +179,7 @@ gss_wrap_kerberos_v1(struct krb5_ctx *kctx, int offset, ptr[6] = 0xff; ptr[7] = 0xff; - gss_krb5_make_confounder(msg_start, conflen); + krb5_make_confounder(msg_start, conflen); if (kctx->gk5e->keyed_cksum) cksumkey = kctx->cksum; -- cgit v1.2.3 From 7989a4f4ab5437ec82b0b59984594f848f12b36a Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sun, 15 Jan 2023 12:20:54 -0500 Subject: SUNRPC: Refactor set-up for aux_cipher Hoist the name of the aux_cipher into struct gss_krb5_enctype to prepare for obscuring the encryption keys just after they are derived. Tested-by: Scott Mayhew Reviewed-by: Simo Sorce Signed-off-by: Chuck Lever --- include/linux/sunrpc/gss_krb5.h | 1 + net/sunrpc/auth_gss/gss_krb5_mech.c | 50 ++++++++++++++++++------------------- 2 files changed, 26 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/gss_krb5.h b/include/linux/sunrpc/gss_krb5.h index f0fac1e69731..34d54714c6a3 100644 --- a/include/linux/sunrpc/gss_krb5.h +++ b/include/linux/sunrpc/gss_krb5.h @@ -61,6 +61,7 @@ struct gss_krb5_enctype { const u32 ctype; /* checksum type */ const char *name; /* "friendly" name */ const char *encrypt_name; /* crypto encrypt name */ + const char *aux_cipher; /* aux encrypt cipher name */ const char *cksum_name; /* crypto checksum name */ const u16 signalg; /* signing algorithm */ const u16 sealalg; /* sealing algorithm */ diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c index b982c9d495f2..afa6a692ccdd 100644 --- a/net/sunrpc/auth_gss/gss_krb5_mech.c +++ b/net/sunrpc/auth_gss/gss_krb5_mech.c @@ -78,6 +78,7 @@ static const struct gss_krb5_enctype supported_gss_krb5_enctypes[] = { .ctype = CKSUMTYPE_HMAC_SHA1_96_AES128, .name = "aes128-cts", .encrypt_name = "cts(cbc(aes))", + .aux_cipher = "cbc(aes)", .cksum_name = "hmac(sha1)", .encrypt = krb5_encrypt, .decrypt = krb5_decrypt, @@ -99,6 +100,7 @@ static const struct gss_krb5_enctype supported_gss_krb5_enctypes[] = { .ctype = CKSUMTYPE_HMAC_SHA1_96_AES256, .name = "aes256-cts", .encrypt_name = "cts(cbc(aes))", + .aux_cipher = "cbc(aes)", .cksum_name = "hmac(sha1)", .encrypt = krb5_encrypt, .decrypt = krb5_decrypt, @@ -373,6 +375,13 @@ context_derive_keys_new(struct krb5_ctx *ctx, gfp_t gfp_mask) ctx->initiator_seal); if (ctx->initiator_enc == NULL) goto out_err; + if (ctx->gk5e->aux_cipher) { + ctx->initiator_enc_aux = + context_v2_alloc_cipher(ctx, ctx->gk5e->aux_cipher, + ctx->initiator_seal); + if (ctx->initiator_enc_aux == NULL) + goto out_free; + } /* acceptor seal encryption */ set_cdata(cdata, KG_USAGE_ACCEPTOR_SEAL, KEY_USAGE_SEED_ENCRYPTION); @@ -381,13 +390,20 @@ context_derive_keys_new(struct krb5_ctx *ctx, gfp_t gfp_mask) if (err) { dprintk("%s: Error %d deriving acceptor_seal key\n", __func__, err); - goto out_free_initiator_enc; + goto out_free; } ctx->acceptor_enc = context_v2_alloc_cipher(ctx, ctx->gk5e->encrypt_name, ctx->acceptor_seal); if (ctx->acceptor_enc == NULL) - goto out_free_initiator_enc; + goto out_free; + if (ctx->gk5e->aux_cipher) { + ctx->acceptor_enc_aux = + context_v2_alloc_cipher(ctx, ctx->gk5e->aux_cipher, + ctx->acceptor_seal); + if (ctx->acceptor_enc_aux == NULL) + goto out_free; + } /* initiator sign checksum */ set_cdata(cdata, KG_USAGE_INITIATOR_SIGN, KEY_USAGE_SEED_CHECKSUM); @@ -396,7 +412,7 @@ context_derive_keys_new(struct krb5_ctx *ctx, gfp_t gfp_mask) if (err) { dprintk("%s: Error %d deriving initiator_sign key\n", __func__, err); - goto out_free_acceptor_enc; + goto out_free; } /* acceptor sign checksum */ @@ -406,7 +422,7 @@ context_derive_keys_new(struct krb5_ctx *ctx, gfp_t gfp_mask) if (err) { dprintk("%s: Error %d deriving acceptor_sign key\n", __func__, err); - goto out_free_acceptor_enc; + goto out_free; } /* initiator seal integrity */ @@ -416,7 +432,7 @@ context_derive_keys_new(struct krb5_ctx *ctx, gfp_t gfp_mask) if (err) { dprintk("%s: Error %d deriving initiator_integ key\n", __func__, err); - goto out_free_acceptor_enc; + goto out_free; } /* acceptor seal integrity */ @@ -426,31 +442,15 @@ context_derive_keys_new(struct krb5_ctx *ctx, gfp_t gfp_mask) if (err) { dprintk("%s: Error %d deriving acceptor_integ key\n", __func__, err); - goto out_free_acceptor_enc; - } - - switch (ctx->enctype) { - case ENCTYPE_AES128_CTS_HMAC_SHA1_96: - case ENCTYPE_AES256_CTS_HMAC_SHA1_96: - ctx->initiator_enc_aux = - context_v2_alloc_cipher(ctx, "cbc(aes)", - ctx->initiator_seal); - if (ctx->initiator_enc_aux == NULL) - goto out_free_acceptor_enc; - ctx->acceptor_enc_aux = - context_v2_alloc_cipher(ctx, "cbc(aes)", - ctx->acceptor_seal); - if (ctx->acceptor_enc_aux == NULL) { - crypto_free_sync_skcipher(ctx->initiator_enc_aux); - goto out_free_acceptor_enc; - } + goto out_free; } return 0; -out_free_acceptor_enc: +out_free: + crypto_free_sync_skcipher(ctx->acceptor_enc_aux); crypto_free_sync_skcipher(ctx->acceptor_enc); -out_free_initiator_enc: + crypto_free_sync_skcipher(ctx->initiator_enc_aux); crypto_free_sync_skcipher(ctx->initiator_enc); out_err: return -EINVAL; -- cgit v1.2.3 From 9f0b49f933ab1ec5e7140a43eec72b0c5181cabf Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sun, 15 Jan 2023 12:21:01 -0500 Subject: SUNRPC: Obscure Kerberos encryption keys The encryption subkeys are not used after the cipher transforms have been allocated and keyed. There is no need to retain them in struct krb5_ctx. Tested-by: Scott Mayhew Reviewed-by: Simo Sorce Signed-off-by: Chuck Lever --- include/linux/sunrpc/gss_krb5.h | 2 -- net/sunrpc/auth_gss/gss_krb5_mech.c | 43 ++++++++++++++++++++++--------------- 2 files changed, 26 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/gss_krb5.h b/include/linux/sunrpc/gss_krb5.h index 34d54714c6a3..46eaa2ee9c21 100644 --- a/include/linux/sunrpc/gss_krb5.h +++ b/include/linux/sunrpc/gss_krb5.h @@ -110,8 +110,6 @@ struct krb5_ctx { struct xdr_netobj mech_used; u8 initiator_sign[GSS_KRB5_MAX_KEYLEN]; u8 acceptor_sign[GSS_KRB5_MAX_KEYLEN]; - u8 initiator_seal[GSS_KRB5_MAX_KEYLEN]; - u8 acceptor_seal[GSS_KRB5_MAX_KEYLEN]; u8 initiator_integ[GSS_KRB5_MAX_KEYLEN]; u8 acceptor_integ[GSS_KRB5_MAX_KEYLEN]; }; diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c index afa6a692ccdd..8bc24c0684cb 100644 --- a/net/sunrpc/auth_gss/gss_krb5_mech.c +++ b/net/sunrpc/auth_gss/gss_krb5_mech.c @@ -350,42 +350,49 @@ out_err: static int context_derive_keys_new(struct krb5_ctx *ctx, gfp_t gfp_mask) { - struct xdr_netobj c, keyin, keyout; u8 cdata[GSS_KRB5_K5CLENGTH]; + struct xdr_netobj c = { + .len = sizeof(cdata), + .data = cdata, + }; + struct xdr_netobj keyin = { + .len = ctx->gk5e->keylength, + .data = ctx->Ksess, + }; + struct xdr_netobj keyout; + int ret = -EINVAL; + void *subkey; u32 err; - c.len = GSS_KRB5_K5CLENGTH; - c.data = cdata; - - keyin.data = ctx->Ksess; - keyin.len = ctx->gk5e->keylength; + subkey = kmalloc(ctx->gk5e->keylength, gfp_mask); + if (!subkey) + return -ENOMEM; keyout.len = ctx->gk5e->keylength; + keyout.data = subkey; /* initiator seal encryption */ set_cdata(cdata, KG_USAGE_INITIATOR_SEAL, KEY_USAGE_SEED_ENCRYPTION); - keyout.data = ctx->initiator_seal; err = krb5_derive_key(ctx->gk5e, &keyin, &keyout, &c, gfp_mask); if (err) { dprintk("%s: Error %d deriving initiator_seal key\n", __func__, err); - goto out_err; + goto out; } ctx->initiator_enc = context_v2_alloc_cipher(ctx, ctx->gk5e->encrypt_name, - ctx->initiator_seal); + subkey); if (ctx->initiator_enc == NULL) - goto out_err; + goto out; if (ctx->gk5e->aux_cipher) { ctx->initiator_enc_aux = context_v2_alloc_cipher(ctx, ctx->gk5e->aux_cipher, - ctx->initiator_seal); + subkey); if (ctx->initiator_enc_aux == NULL) goto out_free; } /* acceptor seal encryption */ set_cdata(cdata, KG_USAGE_ACCEPTOR_SEAL, KEY_USAGE_SEED_ENCRYPTION); - keyout.data = ctx->acceptor_seal; err = krb5_derive_key(ctx->gk5e, &keyin, &keyout, &c, gfp_mask); if (err) { dprintk("%s: Error %d deriving acceptor_seal key\n", @@ -394,13 +401,13 @@ context_derive_keys_new(struct krb5_ctx *ctx, gfp_t gfp_mask) } ctx->acceptor_enc = context_v2_alloc_cipher(ctx, ctx->gk5e->encrypt_name, - ctx->acceptor_seal); + subkey); if (ctx->acceptor_enc == NULL) goto out_free; if (ctx->gk5e->aux_cipher) { ctx->acceptor_enc_aux = context_v2_alloc_cipher(ctx, ctx->gk5e->aux_cipher, - ctx->acceptor_seal); + subkey); if (ctx->acceptor_enc_aux == NULL) goto out_free; } @@ -445,15 +452,17 @@ context_derive_keys_new(struct krb5_ctx *ctx, gfp_t gfp_mask) goto out_free; } - return 0; + ret = 0; +out: + kfree_sensitive(subkey); + return ret; out_free: crypto_free_sync_skcipher(ctx->acceptor_enc_aux); crypto_free_sync_skcipher(ctx->acceptor_enc); crypto_free_sync_skcipher(ctx->initiator_enc_aux); crypto_free_sync_skcipher(ctx->initiator_enc); -out_err: - return -EINVAL; + goto out; } static int -- cgit v1.2.3 From 2dbe0cac3cd6d747579b0b347145326eddfd4e5c Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sun, 15 Jan 2023 12:21:07 -0500 Subject: SUNRPC: Obscure Kerberos signing keys There's no need to keep the signing keys around if we instead allocate and key an ahash and keep that. This not only enables the subkeys to be destroyed immediately after deriving them, but it makes the Kerberos signing code path more efficient. Tested-by: Scott Mayhew Reviewed-by: Simo Sorce Signed-off-by: Chuck Lever --- include/linux/sunrpc/gss_krb5.h | 5 +-- net/sunrpc/auth_gss/gss_krb5_crypto.c | 70 +++++++++++++++++++++++++++++++++ net/sunrpc/auth_gss/gss_krb5_internal.h | 4 ++ net/sunrpc/auth_gss/gss_krb5_mech.c | 37 ++++++++++++----- net/sunrpc/auth_gss/gss_krb5_seal.c | 30 ++++++-------- net/sunrpc/auth_gss/gss_krb5_unseal.c | 29 ++++++-------- 6 files changed, 127 insertions(+), 48 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/gss_krb5.h b/include/linux/sunrpc/gss_krb5.h index 46eaa2ee9c21..9d897f1ac85a 100644 --- a/include/linux/sunrpc/gss_krb5.h +++ b/include/linux/sunrpc/gss_krb5.h @@ -102,14 +102,14 @@ struct krb5_ctx { struct crypto_sync_skcipher *initiator_enc; struct crypto_sync_skcipher *acceptor_enc_aux; struct crypto_sync_skcipher *initiator_enc_aux; + struct crypto_ahash *acceptor_sign; + struct crypto_ahash *initiator_sign; u8 Ksess[GSS_KRB5_MAX_KEYLEN]; /* session key */ u8 cksum[GSS_KRB5_MAX_KEYLEN]; atomic_t seq_send; atomic64_t seq_send64; time64_t endtime; struct xdr_netobj mech_used; - u8 initiator_sign[GSS_KRB5_MAX_KEYLEN]; - u8 acceptor_sign[GSS_KRB5_MAX_KEYLEN]; u8 initiator_integ[GSS_KRB5_MAX_KEYLEN]; u8 acceptor_integ[GSS_KRB5_MAX_KEYLEN]; }; @@ -252,7 +252,6 @@ u32 gss_unwrap_kerberos(struct gss_ctx *ctx_id, int offset, int len, struct xdr_buf *buf); - u32 krb5_encrypt(struct crypto_sync_skcipher *key, void *iv, void *in, void *out, int length); diff --git a/net/sunrpc/auth_gss/gss_krb5_crypto.c b/net/sunrpc/auth_gss/gss_krb5_crypto.c index 7c06c11e452c..44dfcd5f6cbe 100644 --- a/net/sunrpc/auth_gss/gss_krb5_crypto.c +++ b/net/sunrpc/auth_gss/gss_krb5_crypto.c @@ -346,6 +346,76 @@ out_free_cksum: return err ? GSS_S_FAILURE : 0; } +/** + * gss_krb5_checksum - Compute the MAC for a GSS Wrap or MIC token + * @tfm: an initialized hash transform + * @header: pointer to a buffer containing the token header, or NULL + * @hdrlen: number of octets in @header + * @body: xdr_buf containing an RPC message (body.len is the message length) + * @body_offset: byte offset into @body to start checksumming + * @cksumout: OUT: a buffer to be filled in with the computed HMAC + * + * Usually expressed as H = HMAC(K, message)[1..h] . + * + * Caller provides the truncation length of the output token (h) in + * cksumout.len. + * + * Return values: + * %GSS_S_COMPLETE: Digest computed, @cksumout filled in + * %GSS_S_FAILURE: Call failed + */ +u32 +gss_krb5_checksum(struct crypto_ahash *tfm, char *header, int hdrlen, + const struct xdr_buf *body, int body_offset, + struct xdr_netobj *cksumout) +{ + struct ahash_request *req; + int err = -ENOMEM; + u8 *checksumdata; + + checksumdata = kmalloc(crypto_ahash_digestsize(tfm), GFP_KERNEL); + if (!checksumdata) + return GSS_S_FAILURE; + + req = ahash_request_alloc(tfm, GFP_KERNEL); + if (!req) + goto out_free_cksum; + ahash_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP, NULL, NULL); + err = crypto_ahash_init(req); + if (err) + goto out_free_ahash; + + /* + * Per RFC 4121 Section 4.2.4, the checksum is performed over the + * data body first, then over the octets in "header". + */ + err = xdr_process_buf(body, body_offset, body->len - body_offset, + checksummer, req); + if (err) + goto out_free_ahash; + if (header) { + struct scatterlist sg[1]; + + sg_init_one(sg, header, hdrlen); + ahash_request_set_crypt(req, sg, NULL, hdrlen); + err = crypto_ahash_update(req); + if (err) + goto out_free_ahash; + } + + ahash_request_set_crypt(req, NULL, checksumdata, 0); + err = crypto_ahash_final(req); + if (err) + goto out_free_ahash; + memcpy(cksumout->data, checksumdata, cksumout->len); + +out_free_ahash: + ahash_request_free(req); +out_free_cksum: + kfree_sensitive(checksumdata); + return err ? GSS_S_FAILURE : GSS_S_COMPLETE; +} + struct encryptor_desc { u8 iv[GSS_KRB5_MAX_BLOCKSIZE]; struct skcipher_request *req; diff --git a/net/sunrpc/auth_gss/gss_krb5_internal.h b/net/sunrpc/auth_gss/gss_krb5_internal.h index 16a83d507075..42f7fd0bbf3a 100644 --- a/net/sunrpc/auth_gss/gss_krb5_internal.h +++ b/net/sunrpc/auth_gss/gss_krb5_internal.h @@ -10,4 +10,8 @@ void krb5_make_confounder(u8 *p, int conflen); +u32 gss_krb5_checksum(struct crypto_ahash *tfm, char *header, int hdrlen, + const struct xdr_buf *body, int body_offset, + struct xdr_netobj *cksumout); + #endif /* _NET_SUNRPC_AUTH_GSS_KRB5_INTERNAL_H */ diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c index 8bc24c0684cb..5478f741287e 100644 --- a/net/sunrpc/auth_gss/gss_krb5_mech.c +++ b/net/sunrpc/auth_gss/gss_krb5_mech.c @@ -347,6 +347,21 @@ out_err: return -EINVAL; } +static struct crypto_ahash * +gss_krb5_alloc_hash_v2(struct krb5_ctx *kctx, const struct xdr_netobj *key) +{ + struct crypto_ahash *tfm; + + tfm = crypto_alloc_ahash(kctx->gk5e->cksum_name, 0, CRYPTO_ALG_ASYNC); + if (IS_ERR(tfm)) + return NULL; + if (crypto_ahash_setkey(tfm, key->data, key->len)) { + crypto_free_ahash(tfm); + return NULL; + } + return tfm; +} + static int context_derive_keys_new(struct krb5_ctx *ctx, gfp_t gfp_mask) { @@ -414,23 +429,21 @@ context_derive_keys_new(struct krb5_ctx *ctx, gfp_t gfp_mask) /* initiator sign checksum */ set_cdata(cdata, KG_USAGE_INITIATOR_SIGN, KEY_USAGE_SEED_CHECKSUM); - keyout.data = ctx->initiator_sign; err = krb5_derive_key(ctx->gk5e, &keyin, &keyout, &c, gfp_mask); - if (err) { - dprintk("%s: Error %d deriving initiator_sign key\n", - __func__, err); + if (err) + goto out_free; + ctx->initiator_sign = gss_krb5_alloc_hash_v2(ctx, &keyout); + if (ctx->initiator_sign == NULL) goto out_free; - } /* acceptor sign checksum */ set_cdata(cdata, KG_USAGE_ACCEPTOR_SIGN, KEY_USAGE_SEED_CHECKSUM); - keyout.data = ctx->acceptor_sign; err = krb5_derive_key(ctx->gk5e, &keyin, &keyout, &c, gfp_mask); - if (err) { - dprintk("%s: Error %d deriving acceptor_sign key\n", - __func__, err); + if (err) + goto out_free; + ctx->acceptor_sign = gss_krb5_alloc_hash_v2(ctx, &keyout); + if (ctx->acceptor_sign == NULL) goto out_free; - } /* initiator seal integrity */ set_cdata(cdata, KG_USAGE_INITIATOR_SEAL, KEY_USAGE_SEED_INTEGRITY); @@ -458,6 +471,8 @@ out: return ret; out_free: + crypto_free_ahash(ctx->acceptor_sign); + crypto_free_ahash(ctx->initiator_sign); crypto_free_sync_skcipher(ctx->acceptor_enc_aux); crypto_free_sync_skcipher(ctx->acceptor_enc); crypto_free_sync_skcipher(ctx->initiator_enc_aux); @@ -581,6 +596,8 @@ gss_delete_sec_context_kerberos(void *internal_ctx) { crypto_free_sync_skcipher(kctx->initiator_enc); crypto_free_sync_skcipher(kctx->acceptor_enc_aux); crypto_free_sync_skcipher(kctx->initiator_enc_aux); + crypto_free_ahash(kctx->acceptor_sign); + crypto_free_ahash(kctx->initiator_sign); kfree(kctx->mech_used.data); kfree(kctx); } diff --git a/net/sunrpc/auth_gss/gss_krb5_seal.c b/net/sunrpc/auth_gss/gss_krb5_seal.c index 33061417ec97..1d6f8a345354 100644 --- a/net/sunrpc/auth_gss/gss_krb5_seal.c +++ b/net/sunrpc/auth_gss/gss_krb5_seal.c @@ -65,6 +65,8 @@ #include #include +#include "gss_krb5_internal.h" + #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_AUTH #endif @@ -166,14 +168,14 @@ static u32 gss_get_mic_v2(struct krb5_ctx *ctx, struct xdr_buf *text, struct xdr_netobj *token) { - char cksumdata[GSS_KRB5_MAX_CKSUM_LEN]; - struct xdr_netobj cksumobj = { .len = sizeof(cksumdata), - .data = cksumdata}; + struct crypto_ahash *tfm = ctx->initiate ? + ctx->initiator_sign : ctx->acceptor_sign; + struct xdr_netobj cksumobj = { + .len = ctx->gk5e->cksumlength, + }; + __be64 seq_send_be64; void *krb5_hdr; time64_t now; - u8 *cksumkey; - unsigned int cksum_usage; - __be64 seq_send_be64; dprintk("RPC: %s\n", __func__); @@ -184,22 +186,12 @@ gss_get_mic_v2(struct krb5_ctx *ctx, struct xdr_buf *text, seq_send_be64 = cpu_to_be64(atomic64_fetch_inc(&ctx->seq_send64)); memcpy(krb5_hdr + 8, (char *) &seq_send_be64, 8); - if (ctx->initiate) { - cksumkey = ctx->initiator_sign; - cksum_usage = KG_USAGE_INITIATOR_SIGN; - } else { - cksumkey = ctx->acceptor_sign; - cksum_usage = KG_USAGE_ACCEPTOR_SIGN; - } - - if (make_checksum_v2(ctx, krb5_hdr, GSS_KRB5_TOK_HDR_LEN, - text, 0, cksumkey, cksum_usage, &cksumobj)) + cksumobj.data = krb5_hdr + GSS_KRB5_TOK_HDR_LEN; + if (gss_krb5_checksum(tfm, krb5_hdr, GSS_KRB5_TOK_HDR_LEN, + text, 0, &cksumobj)) return GSS_S_FAILURE; - memcpy(krb5_hdr + GSS_KRB5_TOK_HDR_LEN, cksumobj.data, cksumobj.len); - now = ktime_get_real_seconds(); - return (ctx->endtime < now) ? GSS_S_CONTEXT_EXPIRED : GSS_S_COMPLETE; } diff --git a/net/sunrpc/auth_gss/gss_krb5_unseal.c b/net/sunrpc/auth_gss/gss_krb5_unseal.c index ba04e3ec970a..d52103f1203b 100644 --- a/net/sunrpc/auth_gss/gss_krb5_unseal.c +++ b/net/sunrpc/auth_gss/gss_krb5_unseal.c @@ -57,11 +57,14 @@ * WARRANTIES OF MERCHANTIBILITY AND FITNESS FOR A PARTICULAR PURPOSE. */ +#include #include #include #include #include +#include "gss_krb5_internal.h" + #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_AUTH #endif @@ -146,16 +149,18 @@ static u32 gss_verify_mic_v2(struct krb5_ctx *ctx, struct xdr_buf *message_buffer, struct xdr_netobj *read_token) { + struct crypto_ahash *tfm = ctx->initiate ? + ctx->acceptor_sign : ctx->initiator_sign; char cksumdata[GSS_KRB5_MAX_CKSUM_LEN]; - struct xdr_netobj cksumobj = {.len = sizeof(cksumdata), - .data = cksumdata}; - time64_t now; + struct xdr_netobj cksumobj = { + .len = ctx->gk5e->cksumlength, + .data = cksumdata, + }; u8 *ptr = read_token->data; - u8 *cksumkey; + __be16 be16_ptr; + time64_t now; u8 flags; int i; - unsigned int cksum_usage; - __be16 be16_ptr; dprintk("RPC: %s\n", __func__); @@ -177,16 +182,8 @@ gss_verify_mic_v2(struct krb5_ctx *ctx, if (ptr[i] != 0xff) return GSS_S_DEFECTIVE_TOKEN; - if (ctx->initiate) { - cksumkey = ctx->acceptor_sign; - cksum_usage = KG_USAGE_ACCEPTOR_SIGN; - } else { - cksumkey = ctx->initiator_sign; - cksum_usage = KG_USAGE_INITIATOR_SIGN; - } - - if (make_checksum_v2(ctx, ptr, GSS_KRB5_TOK_HDR_LEN, message_buffer, 0, - cksumkey, cksum_usage, &cksumobj)) + if (gss_krb5_checksum(tfm, ptr, GSS_KRB5_TOK_HDR_LEN, + message_buffer, 0, &cksumobj)) return GSS_S_FAILURE; if (memcmp(cksumobj.data, ptr + GSS_KRB5_TOK_HDR_LEN, -- cgit v1.2.3 From 8270dbfcebea5b68037a84ad1710e2cfa499b82f Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sun, 15 Jan 2023 12:21:13 -0500 Subject: SUNRPC: Obscure Kerberos integrity keys There's no need to keep the integrity keys around if we instead allocate and key a pair of ahashes and keep those. This not only enables the subkeys to be destroyed immediately after deriving them, but it makes the Kerberos integrity code path more efficient. Tested-by: Scott Mayhew Reviewed-by: Simo Sorce Signed-off-by: Chuck Lever --- include/linux/sunrpc/gss_krb5.h | 9 +-- net/sunrpc/auth_gss/gss_krb5_crypto.c | 116 +++------------------------------- net/sunrpc/auth_gss/gss_krb5_mech.c | 22 ++++--- 3 files changed, 23 insertions(+), 124 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/gss_krb5.h b/include/linux/sunrpc/gss_krb5.h index 9d897f1ac85a..85e65232bb61 100644 --- a/include/linux/sunrpc/gss_krb5.h +++ b/include/linux/sunrpc/gss_krb5.h @@ -104,14 +104,14 @@ struct krb5_ctx { struct crypto_sync_skcipher *initiator_enc_aux; struct crypto_ahash *acceptor_sign; struct crypto_ahash *initiator_sign; + struct crypto_ahash *initiator_integ; + struct crypto_ahash *acceptor_integ; u8 Ksess[GSS_KRB5_MAX_KEYLEN]; /* session key */ u8 cksum[GSS_KRB5_MAX_KEYLEN]; atomic_t seq_send; atomic64_t seq_send64; time64_t endtime; struct xdr_netobj mech_used; - u8 initiator_integ[GSS_KRB5_MAX_KEYLEN]; - u8 acceptor_integ[GSS_KRB5_MAX_KEYLEN]; }; /* The length of the Kerberos GSS token header */ @@ -233,11 +233,6 @@ make_checksum(struct krb5_ctx *kctx, char *header, int hdrlen, struct xdr_buf *body, int body_offset, u8 *cksumkey, unsigned int usage, struct xdr_netobj *cksumout); -u32 -make_checksum_v2(struct krb5_ctx *, char *header, int hdrlen, - struct xdr_buf *body, int body_offset, u8 *key, - unsigned int usage, struct xdr_netobj *cksum); - u32 gss_get_mic_kerberos(struct gss_ctx *, struct xdr_buf *, struct xdr_netobj *); diff --git a/net/sunrpc/auth_gss/gss_krb5_crypto.c b/net/sunrpc/auth_gss/gss_krb5_crypto.c index 44dfcd5f6cbe..098faaf02fe6 100644 --- a/net/sunrpc/auth_gss/gss_krb5_crypto.c +++ b/net/sunrpc/auth_gss/gss_krb5_crypto.c @@ -259,93 +259,6 @@ out_free_cksum: return err ? GSS_S_FAILURE : 0; } -/* - * checksum the plaintext data and hdrlen bytes of the token header - * Per rfc4121, sec. 4.2.4, the checksum is performed over the data - * body then over the first 16 octets of the MIC token - * Inclusion of the header data in the calculation of the - * checksum is optional. - */ -u32 -make_checksum_v2(struct krb5_ctx *kctx, char *header, int hdrlen, - struct xdr_buf *body, int body_offset, u8 *cksumkey, - unsigned int usage, struct xdr_netobj *cksumout) -{ - struct crypto_ahash *tfm; - struct ahash_request *req; - struct scatterlist sg[1]; - int err = -1; - u8 *checksumdata; - - if (kctx->gk5e->keyed_cksum == 0) { - dprintk("%s: expected keyed hash for %s\n", - __func__, kctx->gk5e->name); - return GSS_S_FAILURE; - } - if (cksumkey == NULL) { - dprintk("%s: no key supplied for %s\n", - __func__, kctx->gk5e->name); - return GSS_S_FAILURE; - } - - checksumdata = kmalloc(GSS_KRB5_MAX_CKSUM_LEN, GFP_KERNEL); - if (!checksumdata) - return GSS_S_FAILURE; - - tfm = crypto_alloc_ahash(kctx->gk5e->cksum_name, 0, CRYPTO_ALG_ASYNC); - if (IS_ERR(tfm)) - goto out_free_cksum; - - req = ahash_request_alloc(tfm, GFP_KERNEL); - if (!req) - goto out_free_ahash; - - ahash_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP, NULL, NULL); - - err = crypto_ahash_setkey(tfm, cksumkey, kctx->gk5e->keylength); - if (err) - goto out; - - err = crypto_ahash_init(req); - if (err) - goto out; - err = xdr_process_buf(body, body_offset, body->len - body_offset, - checksummer, req); - if (err) - goto out; - if (header != NULL) { - sg_init_one(sg, header, hdrlen); - ahash_request_set_crypt(req, sg, NULL, hdrlen); - err = crypto_ahash_update(req); - if (err) - goto out; - } - ahash_request_set_crypt(req, NULL, checksumdata, 0); - err = crypto_ahash_final(req); - if (err) - goto out; - - cksumout->len = kctx->gk5e->cksumlength; - - switch (kctx->gk5e->ctype) { - case CKSUMTYPE_HMAC_SHA1_96_AES128: - case CKSUMTYPE_HMAC_SHA1_96_AES256: - /* note that this truncates the hash */ - memcpy(cksumout->data, checksumdata, kctx->gk5e->cksumlength); - break; - default: - BUG(); - break; - } -out: - ahash_request_free(req); -out_free_ahash: - crypto_free_ahash(tfm); -out_free_cksum: - kfree(checksumdata); - return err ? GSS_S_FAILURE : 0; -} - /** * gss_krb5_checksum - Compute the MAC for a GSS Wrap or MIC token * @tfm: an initialized hash transform @@ -702,27 +615,24 @@ gss_krb5_aes_encrypt(struct krb5_ctx *kctx, u32 offset, { u32 err; struct xdr_netobj hmac; - u8 *cksumkey; u8 *ecptr; struct crypto_sync_skcipher *cipher, *aux_cipher; + struct crypto_ahash *ahash; int blocksize; struct page **save_pages; int nblocks, nbytes; struct encryptor_desc desc; u32 cbcbytes; - unsigned int usage; unsigned int conflen; if (kctx->initiate) { cipher = kctx->initiator_enc; aux_cipher = kctx->initiator_enc_aux; - cksumkey = kctx->initiator_integ; - usage = KG_USAGE_INITIATOR_SEAL; + ahash = kctx->initiator_integ; } else { cipher = kctx->acceptor_enc; aux_cipher = kctx->acceptor_enc_aux; - cksumkey = kctx->acceptor_integ; - usage = KG_USAGE_ACCEPTOR_SEAL; + ahash = kctx->acceptor_integ; } blocksize = crypto_sync_skcipher_blocksize(cipher); conflen = crypto_sync_skcipher_blocksize(cipher); @@ -762,9 +672,8 @@ gss_krb5_aes_encrypt(struct krb5_ctx *kctx, u32 offset, save_pages = buf->pages; buf->pages = pages; - err = make_checksum_v2(kctx, NULL, 0, buf, - offset + GSS_KRB5_TOK_HDR_LEN, - cksumkey, usage, &hmac); + err = gss_krb5_checksum(ahash, NULL, 0, buf, + offset + GSS_KRB5_TOK_HDR_LEN, &hmac); buf->pages = save_pages; if (err) return GSS_S_FAILURE; @@ -825,25 +734,22 @@ gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, u32 len, { struct xdr_buf subbuf; u32 ret = 0; - u8 *cksum_key; struct crypto_sync_skcipher *cipher, *aux_cipher; + struct crypto_ahash *ahash; struct xdr_netobj our_hmac_obj; u8 our_hmac[GSS_KRB5_MAX_CKSUM_LEN]; u8 pkt_hmac[GSS_KRB5_MAX_CKSUM_LEN]; int nblocks, blocksize, cbcbytes; struct decryptor_desc desc; - unsigned int usage; if (kctx->initiate) { cipher = kctx->acceptor_enc; aux_cipher = kctx->acceptor_enc_aux; - cksum_key = kctx->acceptor_integ; - usage = KG_USAGE_ACCEPTOR_SEAL; + ahash = kctx->acceptor_integ; } else { cipher = kctx->initiator_enc; aux_cipher = kctx->initiator_enc_aux; - cksum_key = kctx->initiator_integ; - usage = KG_USAGE_INITIATOR_SEAL; + ahash = kctx->initiator_integ; } blocksize = crypto_sync_skcipher_blocksize(cipher); @@ -883,13 +789,9 @@ gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, u32 len, if (ret) goto out_err; - - /* Calculate our hmac over the plaintext data */ our_hmac_obj.len = sizeof(our_hmac); our_hmac_obj.data = our_hmac; - - ret = make_checksum_v2(kctx, NULL, 0, &subbuf, 0, - cksum_key, usage, &our_hmac_obj); + ret = gss_krb5_checksum(ahash, NULL, 0, &subbuf, 0, &our_hmac_obj); if (ret) goto out_err; diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c index 5478f741287e..2237f640cef4 100644 --- a/net/sunrpc/auth_gss/gss_krb5_mech.c +++ b/net/sunrpc/auth_gss/gss_krb5_mech.c @@ -447,23 +447,21 @@ context_derive_keys_new(struct krb5_ctx *ctx, gfp_t gfp_mask) /* initiator seal integrity */ set_cdata(cdata, KG_USAGE_INITIATOR_SEAL, KEY_USAGE_SEED_INTEGRITY); - keyout.data = ctx->initiator_integ; err = krb5_derive_key(ctx->gk5e, &keyin, &keyout, &c, gfp_mask); - if (err) { - dprintk("%s: Error %d deriving initiator_integ key\n", - __func__, err); + if (err) + goto out_free; + ctx->initiator_integ = gss_krb5_alloc_hash_v2(ctx, &keyout); + if (ctx->initiator_integ == NULL) goto out_free; - } /* acceptor seal integrity */ set_cdata(cdata, KG_USAGE_ACCEPTOR_SEAL, KEY_USAGE_SEED_INTEGRITY); - keyout.data = ctx->acceptor_integ; err = krb5_derive_key(ctx->gk5e, &keyin, &keyout, &c, gfp_mask); - if (err) { - dprintk("%s: Error %d deriving acceptor_integ key\n", - __func__, err); + if (err) + goto out_free; + ctx->acceptor_integ = gss_krb5_alloc_hash_v2(ctx, &keyout); + if (ctx->acceptor_integ == NULL) goto out_free; - } ret = 0; out: @@ -471,6 +469,8 @@ out: return ret; out_free: + crypto_free_ahash(ctx->acceptor_integ); + crypto_free_ahash(ctx->initiator_integ); crypto_free_ahash(ctx->acceptor_sign); crypto_free_ahash(ctx->initiator_sign); crypto_free_sync_skcipher(ctx->acceptor_enc_aux); @@ -598,6 +598,8 @@ gss_delete_sec_context_kerberos(void *internal_ctx) { crypto_free_sync_skcipher(kctx->initiator_enc_aux); crypto_free_ahash(kctx->acceptor_sign); crypto_free_ahash(kctx->initiator_sign); + crypto_free_ahash(kctx->acceptor_integ); + crypto_free_ahash(kctx->initiator_integ); kfree(kctx->mech_used.data); kfree(kctx); } -- cgit v1.2.3 From e01b2c79f4af1298b961116aba3e64367fe73286 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sun, 15 Jan 2023 12:21:20 -0500 Subject: SUNRPC: Refactor the GSS-API Per Message calls in the Kerberos mechanism Replace a number of switches on encryption type so that all of them don't have to be modified when adding or removing support for an enctype. Tested-by: Scott Mayhew Reviewed-by: Simo Sorce Signed-off-by: Chuck Lever --- include/linux/sunrpc/gss_krb5.h | 23 +++--- net/sunrpc/auth_gss/gss_krb5_internal.h | 30 ++++++++ net/sunrpc/auth_gss/gss_krb5_mech.c | 126 +++++++++++++++++++++++++++++--- net/sunrpc/auth_gss/gss_krb5_seal.c | 30 ++------ net/sunrpc/auth_gss/gss_krb5_unseal.c | 31 ++------ net/sunrpc/auth_gss/gss_krb5_wrap.c | 66 ++++------------- 6 files changed, 180 insertions(+), 126 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/gss_krb5.h b/include/linux/sunrpc/gss_krb5.h index 85e65232bb61..f1201478fdd5 100644 --- a/include/linux/sunrpc/gss_krb5.h +++ b/include/linux/sunrpc/gss_krb5.h @@ -84,6 +84,15 @@ struct gss_krb5_enctype { u32 (*decrypt_v2) (struct krb5_ctx *kctx, u32 offset, u32 len, struct xdr_buf *buf, u32 *headskip, u32 *tailskip); /* v2 decryption function */ + u32 (*get_mic)(struct krb5_ctx *kctx, struct xdr_buf *text, + struct xdr_netobj *token); + u32 (*verify_mic)(struct krb5_ctx *kctx, struct xdr_buf *message_buffer, + struct xdr_netobj *read_token); + u32 (*wrap)(struct krb5_ctx *kctx, int offset, + struct xdr_buf *buf, struct page **pages); + u32 (*unwrap)(struct krb5_ctx *kctx, int offset, int len, + struct xdr_buf *buf, unsigned int *slack, + unsigned int *align); }; /* krb5_ctx flags definitions */ @@ -233,20 +242,6 @@ make_checksum(struct krb5_ctx *kctx, char *header, int hdrlen, struct xdr_buf *body, int body_offset, u8 *cksumkey, unsigned int usage, struct xdr_netobj *cksumout); -u32 gss_get_mic_kerberos(struct gss_ctx *, struct xdr_buf *, - struct xdr_netobj *); - -u32 gss_verify_mic_kerberos(struct gss_ctx *, struct xdr_buf *, - struct xdr_netobj *); - -u32 -gss_wrap_kerberos(struct gss_ctx *ctx_id, int offset, - struct xdr_buf *outbuf, struct page **pages); - -u32 -gss_unwrap_kerberos(struct gss_ctx *ctx_id, int offset, int len, - struct xdr_buf *buf); - u32 krb5_encrypt(struct crypto_sync_skcipher *key, void *iv, void *in, void *out, int length); diff --git a/net/sunrpc/auth_gss/gss_krb5_internal.h b/net/sunrpc/auth_gss/gss_krb5_internal.h index 42f7fd0bbf3a..04d2781e2ce2 100644 --- a/net/sunrpc/auth_gss/gss_krb5_internal.h +++ b/net/sunrpc/auth_gss/gss_krb5_internal.h @@ -8,6 +8,36 @@ #ifndef _NET_SUNRPC_AUTH_GSS_KRB5_INTERNAL_H #define _NET_SUNRPC_AUTH_GSS_KRB5_INTERNAL_H +/* + * GSS Kerberos 5 mechanism Per-Message calls. + */ + +u32 gss_krb5_get_mic_v1(struct krb5_ctx *ctx, struct xdr_buf *text, + struct xdr_netobj *token); +u32 gss_krb5_get_mic_v2(struct krb5_ctx *ctx, struct xdr_buf *text, + struct xdr_netobj *token); + +u32 gss_krb5_verify_mic_v1(struct krb5_ctx *ctx, struct xdr_buf *message_buffer, + struct xdr_netobj *read_token); +u32 gss_krb5_verify_mic_v2(struct krb5_ctx *ctx, struct xdr_buf *message_buffer, + struct xdr_netobj *read_token); + +u32 gss_krb5_wrap_v1(struct krb5_ctx *kctx, int offset, + struct xdr_buf *buf, struct page **pages); +u32 gss_krb5_wrap_v2(struct krb5_ctx *kctx, int offset, + struct xdr_buf *buf, struct page **pages); + +u32 gss_krb5_unwrap_v1(struct krb5_ctx *kctx, int offset, int len, + struct xdr_buf *buf, unsigned int *slack, + unsigned int *align); +u32 gss_krb5_unwrap_v2(struct krb5_ctx *kctx, int offset, int len, + struct xdr_buf *buf, unsigned int *slack, + unsigned int *align); + +/* + * Implementation internal functions + */ + void krb5_make_confounder(u8 *p, int conflen); u32 gss_krb5_checksum(struct crypto_ahash *tfm, char *header, int hdrlen, diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c index 2237f640cef4..0a831b5cea6b 100644 --- a/net/sunrpc/auth_gss/gss_krb5_mech.c +++ b/net/sunrpc/auth_gss/gss_krb5_mech.c @@ -22,6 +22,7 @@ #include #include "auth_gss_internal.h" +#include "gss_krb5_internal.h" #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_AUTH @@ -43,6 +44,10 @@ static const struct gss_krb5_enctype supported_gss_krb5_enctypes[] = { .encrypt = krb5_encrypt, .decrypt = krb5_decrypt, .mk_key = NULL, + .get_mic = gss_krb5_get_mic_v1, + .verify_mic = gss_krb5_verify_mic_v1, + .wrap = gss_krb5_wrap_v1, + .unwrap = gss_krb5_unwrap_v1, .signalg = SGN_ALG_DES_MAC_MD5, .sealalg = SEAL_ALG_DES, .keybytes = 7, @@ -63,6 +68,10 @@ static const struct gss_krb5_enctype supported_gss_krb5_enctypes[] = { .encrypt = krb5_encrypt, .decrypt = krb5_decrypt, .mk_key = gss_krb5_des3_make_key, + .get_mic = gss_krb5_get_mic_v1, + .verify_mic = gss_krb5_verify_mic_v1, + .wrap = gss_krb5_wrap_v1, + .unwrap = gss_krb5_unwrap_v1, .signalg = SGN_ALG_HMAC_SHA1_DES3_KD, .sealalg = SEAL_ALG_DES3KD, .keybytes = 21, @@ -85,6 +94,12 @@ static const struct gss_krb5_enctype supported_gss_krb5_enctypes[] = { .mk_key = gss_krb5_aes_make_key, .encrypt_v2 = gss_krb5_aes_encrypt, .decrypt_v2 = gss_krb5_aes_decrypt, + + .get_mic = gss_krb5_get_mic_v2, + .verify_mic = gss_krb5_verify_mic_v2, + .wrap = gss_krb5_wrap_v2, + .unwrap = gss_krb5_unwrap_v2, + .signalg = -1, .sealalg = -1, .keybytes = 16, @@ -107,6 +122,12 @@ static const struct gss_krb5_enctype supported_gss_krb5_enctypes[] = { .mk_key = gss_krb5_aes_make_key, .encrypt_v2 = gss_krb5_aes_encrypt, .decrypt_v2 = gss_krb5_aes_decrypt, + + .get_mic = gss_krb5_get_mic_v2, + .verify_mic = gss_krb5_verify_mic_v2, + .wrap = gss_krb5_wrap_v2, + .unwrap = gss_krb5_unwrap_v2, + .signalg = -1, .sealalg = -1, .keybytes = 32, @@ -557,10 +578,8 @@ out_err: } static int -gss_import_sec_context_kerberos(const void *p, size_t len, - struct gss_ctx *ctx_id, - time64_t *endtime, - gfp_t gfp_mask) +gss_krb5_import_sec_context(const void *p, size_t len, struct gss_ctx *ctx_id, + time64_t *endtime, gfp_t gfp_mask) { const void *end = (const void *)((const char *)p + len); struct krb5_ctx *ctx; @@ -587,7 +606,8 @@ gss_import_sec_context_kerberos(const void *p, size_t len, } static void -gss_delete_sec_context_kerberos(void *internal_ctx) { +gss_krb5_delete_sec_context(void *internal_ctx) +{ struct krb5_ctx *kctx = internal_ctx; crypto_free_sync_skcipher(kctx->seq); @@ -604,13 +624,97 @@ gss_delete_sec_context_kerberos(void *internal_ctx) { kfree(kctx); } +/** + * gss_krb5_get_mic - get_mic for the Kerberos GSS mechanism + * @gctx: GSS context + * @text: plaintext to checksum + * @token: buffer into which to write the computed checksum + * + * Return values: + * %GSS_S_COMPLETE - success, and @token is filled in + * %GSS_S_FAILURE - checksum could not be generated + * %GSS_S_CONTEXT_EXPIRED - Kerberos context is no longer valid + */ +static u32 gss_krb5_get_mic(struct gss_ctx *gctx, struct xdr_buf *text, + struct xdr_netobj *token) +{ + struct krb5_ctx *kctx = gctx->internal_ctx_id; + + return kctx->gk5e->get_mic(kctx, text, token); +} + +/** + * gss_krb5_verify_mic - verify_mic for the Kerberos GSS mechanism + * @gctx: GSS context + * @message_buffer: plaintext to check + * @read_token: received checksum to check + * + * Return values: + * %GSS_S_COMPLETE - computed and received checksums match + * %GSS_S_DEFECTIVE_TOKEN - received checksum is not valid + * %GSS_S_BAD_SIG - computed and received checksums do not match + * %GSS_S_FAILURE - received checksum could not be checked + * %GSS_S_CONTEXT_EXPIRED - Kerberos context is no longer valid + */ +static u32 gss_krb5_verify_mic(struct gss_ctx *gctx, + struct xdr_buf *message_buffer, + struct xdr_netobj *read_token) +{ + struct krb5_ctx *kctx = gctx->internal_ctx_id; + + return kctx->gk5e->verify_mic(kctx, message_buffer, read_token); +} + +/** + * gss_krb5_wrap - gss_wrap for the Kerberos GSS mechanism + * @gctx: initialized GSS context + * @offset: byte offset in @buf to start writing the cipher text + * @buf: OUT: send buffer + * @pages: plaintext to wrap + * + * Return values: + * %GSS_S_COMPLETE - success, @buf has been updated + * %GSS_S_FAILURE - @buf could not be wrapped + * %GSS_S_CONTEXT_EXPIRED - Kerberos context is no longer valid + */ +static u32 gss_krb5_wrap(struct gss_ctx *gctx, int offset, + struct xdr_buf *buf, struct page **pages) +{ + struct krb5_ctx *kctx = gctx->internal_ctx_id; + + return kctx->gk5e->wrap(kctx, offset, buf, pages); +} + +/** + * gss_krb5_unwrap - gss_unwrap for the Kerberos GSS mechanism + * @gctx: initialized GSS context + * @offset: starting byte offset into @buf + * @len: size of ciphertext to unwrap + * @buf: ciphertext to unwrap + * + * Return values: + * %GSS_S_COMPLETE - success, @buf has been updated + * %GSS_S_DEFECTIVE_TOKEN - received blob is not valid + * %GSS_S_BAD_SIG - computed and received checksums do not match + * %GSS_S_FAILURE - @buf could not be unwrapped + * %GSS_S_CONTEXT_EXPIRED - Kerberos context is no longer valid + */ +static u32 gss_krb5_unwrap(struct gss_ctx *gctx, int offset, + int len, struct xdr_buf *buf) +{ + struct krb5_ctx *kctx = gctx->internal_ctx_id; + + return kctx->gk5e->unwrap(kctx, offset, len, buf, + &gctx->slack, &gctx->align); +} + static const struct gss_api_ops gss_kerberos_ops = { - .gss_import_sec_context = gss_import_sec_context_kerberos, - .gss_get_mic = gss_get_mic_kerberos, - .gss_verify_mic = gss_verify_mic_kerberos, - .gss_wrap = gss_wrap_kerberos, - .gss_unwrap = gss_unwrap_kerberos, - .gss_delete_sec_context = gss_delete_sec_context_kerberos, + .gss_import_sec_context = gss_krb5_import_sec_context, + .gss_get_mic = gss_krb5_get_mic, + .gss_verify_mic = gss_krb5_verify_mic, + .gss_wrap = gss_krb5_wrap, + .gss_unwrap = gss_krb5_unwrap, + .gss_delete_sec_context = gss_krb5_delete_sec_context, }; static struct pf_desc gss_kerberos_pfs[] = { diff --git a/net/sunrpc/auth_gss/gss_krb5_seal.c b/net/sunrpc/auth_gss/gss_krb5_seal.c index 1d6f8a345354..f74125407588 100644 --- a/net/sunrpc/auth_gss/gss_krb5_seal.c +++ b/net/sunrpc/auth_gss/gss_krb5_seal.c @@ -125,9 +125,9 @@ setup_token_v2(struct krb5_ctx *ctx, struct xdr_netobj *token) return krb5_hdr; } -static u32 -gss_get_mic_v1(struct krb5_ctx *ctx, struct xdr_buf *text, - struct xdr_netobj *token) +u32 +gss_krb5_get_mic_v1(struct krb5_ctx *ctx, struct xdr_buf *text, + struct xdr_netobj *token) { char cksumdata[GSS_KRB5_MAX_CKSUM_LEN]; struct xdr_netobj md5cksum = {.len = sizeof(cksumdata), @@ -164,9 +164,9 @@ gss_get_mic_v1(struct krb5_ctx *ctx, struct xdr_buf *text, return (ctx->endtime < now) ? GSS_S_CONTEXT_EXPIRED : GSS_S_COMPLETE; } -static u32 -gss_get_mic_v2(struct krb5_ctx *ctx, struct xdr_buf *text, - struct xdr_netobj *token) +u32 +gss_krb5_get_mic_v2(struct krb5_ctx *ctx, struct xdr_buf *text, + struct xdr_netobj *token) { struct crypto_ahash *tfm = ctx->initiate ? ctx->initiator_sign : ctx->acceptor_sign; @@ -194,21 +194,3 @@ gss_get_mic_v2(struct krb5_ctx *ctx, struct xdr_buf *text, now = ktime_get_real_seconds(); return (ctx->endtime < now) ? GSS_S_CONTEXT_EXPIRED : GSS_S_COMPLETE; } - -u32 -gss_get_mic_kerberos(struct gss_ctx *gss_ctx, struct xdr_buf *text, - struct xdr_netobj *token) -{ - struct krb5_ctx *ctx = gss_ctx->internal_ctx_id; - - switch (ctx->enctype) { - default: - BUG(); - case ENCTYPE_DES_CBC_RAW: - case ENCTYPE_DES3_CBC_RAW: - return gss_get_mic_v1(ctx, text, token); - case ENCTYPE_AES128_CTS_HMAC_SHA1_96: - case ENCTYPE_AES256_CTS_HMAC_SHA1_96: - return gss_get_mic_v2(ctx, text, token); - } -} diff --git a/net/sunrpc/auth_gss/gss_krb5_unseal.c b/net/sunrpc/auth_gss/gss_krb5_unseal.c index d52103f1203b..939d199eb7b7 100644 --- a/net/sunrpc/auth_gss/gss_krb5_unseal.c +++ b/net/sunrpc/auth_gss/gss_krb5_unseal.c @@ -73,9 +73,9 @@ /* read_token is a mic token, and message_buffer is the data that the mic was * supposedly taken over. */ -static u32 -gss_verify_mic_v1(struct krb5_ctx *ctx, - struct xdr_buf *message_buffer, struct xdr_netobj *read_token) +u32 +gss_krb5_verify_mic_v1(struct krb5_ctx *ctx, struct xdr_buf *message_buffer, + struct xdr_netobj *read_token) { int signalg; int sealalg; @@ -145,9 +145,9 @@ gss_verify_mic_v1(struct krb5_ctx *ctx, return GSS_S_COMPLETE; } -static u32 -gss_verify_mic_v2(struct krb5_ctx *ctx, - struct xdr_buf *message_buffer, struct xdr_netobj *read_token) +u32 +gss_krb5_verify_mic_v2(struct krb5_ctx *ctx, struct xdr_buf *message_buffer, + struct xdr_netobj *read_token) { struct crypto_ahash *tfm = ctx->initiate ? ctx->acceptor_sign : ctx->initiator_sign; @@ -202,22 +202,3 @@ gss_verify_mic_v2(struct krb5_ctx *ctx, return GSS_S_COMPLETE; } - -u32 -gss_verify_mic_kerberos(struct gss_ctx *gss_ctx, - struct xdr_buf *message_buffer, - struct xdr_netobj *read_token) -{ - struct krb5_ctx *ctx = gss_ctx->internal_ctx_id; - - switch (ctx->enctype) { - default: - BUG(); - case ENCTYPE_DES_CBC_RAW: - case ENCTYPE_DES3_CBC_RAW: - return gss_verify_mic_v1(ctx, message_buffer, read_token); - case ENCTYPE_AES128_CTS_HMAC_SHA1_96: - case ENCTYPE_AES256_CTS_HMAC_SHA1_96: - return gss_verify_mic_v2(ctx, message_buffer, read_token); - } -} diff --git a/net/sunrpc/auth_gss/gss_krb5_wrap.c b/net/sunrpc/auth_gss/gss_krb5_wrap.c index 66e65e4c6336..d983da6f9530 100644 --- a/net/sunrpc/auth_gss/gss_krb5_wrap.c +++ b/net/sunrpc/auth_gss/gss_krb5_wrap.c @@ -122,9 +122,9 @@ out: /* XXX factor out common code with seal/unseal. */ -static u32 -gss_wrap_kerberos_v1(struct krb5_ctx *kctx, int offset, - struct xdr_buf *buf, struct page **pages) +u32 +gss_krb5_wrap_v1(struct krb5_ctx *kctx, int offset, + struct xdr_buf *buf, struct page **pages) { char cksumdata[GSS_KRB5_MAX_CKSUM_LEN]; struct xdr_netobj md5cksum = {.len = sizeof(cksumdata), @@ -211,10 +211,10 @@ gss_wrap_kerberos_v1(struct krb5_ctx *kctx, int offset, return (kctx->endtime < now) ? GSS_S_CONTEXT_EXPIRED : GSS_S_COMPLETE; } -static u32 -gss_unwrap_kerberos_v1(struct krb5_ctx *kctx, int offset, int len, - struct xdr_buf *buf, unsigned int *slack, - unsigned int *align) +u32 +gss_krb5_unwrap_v1(struct krb5_ctx *kctx, int offset, int len, + struct xdr_buf *buf, unsigned int *slack, + unsigned int *align) { int signalg; int sealalg; @@ -373,9 +373,9 @@ static void rotate_left(u32 base, struct xdr_buf *buf, unsigned int shift) _rotate_left(&subbuf, shift); } -static u32 -gss_wrap_kerberos_v2(struct krb5_ctx *kctx, u32 offset, - struct xdr_buf *buf, struct page **pages) +u32 +gss_krb5_wrap_v2(struct krb5_ctx *kctx, int offset, + struct xdr_buf *buf, struct page **pages) { u8 *ptr; time64_t now; @@ -424,10 +424,10 @@ gss_wrap_kerberos_v2(struct krb5_ctx *kctx, u32 offset, return (kctx->endtime < now) ? GSS_S_CONTEXT_EXPIRED : GSS_S_COMPLETE; } -static u32 -gss_unwrap_kerberos_v2(struct krb5_ctx *kctx, int offset, int len, - struct xdr_buf *buf, unsigned int *slack, - unsigned int *align) +u32 +gss_krb5_unwrap_v2(struct krb5_ctx *kctx, int offset, int len, + struct xdr_buf *buf, unsigned int *slack, + unsigned int *align) { time64_t now; u8 *ptr; @@ -524,41 +524,3 @@ gss_unwrap_kerberos_v2(struct krb5_ctx *kctx, int offset, int len, *slack = *align + XDR_QUADLEN(ec + GSS_KRB5_TOK_HDR_LEN + tailskip); return GSS_S_COMPLETE; } - -u32 -gss_wrap_kerberos(struct gss_ctx *gctx, int offset, - struct xdr_buf *buf, struct page **pages) -{ - struct krb5_ctx *kctx = gctx->internal_ctx_id; - - switch (kctx->enctype) { - default: - BUG(); - case ENCTYPE_DES_CBC_RAW: - case ENCTYPE_DES3_CBC_RAW: - return gss_wrap_kerberos_v1(kctx, offset, buf, pages); - case ENCTYPE_AES128_CTS_HMAC_SHA1_96: - case ENCTYPE_AES256_CTS_HMAC_SHA1_96: - return gss_wrap_kerberos_v2(kctx, offset, buf, pages); - } -} - -u32 -gss_unwrap_kerberos(struct gss_ctx *gctx, int offset, - int len, struct xdr_buf *buf) -{ - struct krb5_ctx *kctx = gctx->internal_ctx_id; - - switch (kctx->enctype) { - default: - BUG(); - case ENCTYPE_DES_CBC_RAW: - case ENCTYPE_DES3_CBC_RAW: - return gss_unwrap_kerberos_v1(kctx, offset, len, buf, - &gctx->slack, &gctx->align); - case ENCTYPE_AES128_CTS_HMAC_SHA1_96: - case ENCTYPE_AES256_CTS_HMAC_SHA1_96: - return gss_unwrap_kerberos_v2(kctx, offset, len, buf, - &gctx->slack, &gctx->align); - } -} -- cgit v1.2.3 From 279a67cdd491a53028eb0b52508383098c6d992b Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sun, 15 Jan 2023 12:21:26 -0500 Subject: SUNRPC: Remove another switch on ctx->enctype Replace another switch on encryption type so that it does not have to be modified when adding or removing support for an enctype. Tested-by: Scott Mayhew Reviewed-by: Simo Sorce Signed-off-by: Chuck Lever --- include/linux/sunrpc/gss_krb5.h | 1 + net/sunrpc/auth_gss/gss_krb5_mech.c | 30 ++++++++++++++++++------------ 2 files changed, 19 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/gss_krb5.h b/include/linux/sunrpc/gss_krb5.h index f1201478fdd5..68ae0c3d4cf7 100644 --- a/include/linux/sunrpc/gss_krb5.h +++ b/include/linux/sunrpc/gss_krb5.h @@ -75,6 +75,7 @@ struct gss_krb5_enctype { u32 (*decrypt) (struct crypto_sync_skcipher *tfm, void *iv, void *in, void *out, int length); /* decryption function */ + int (*import_ctx)(struct krb5_ctx *ctx, gfp_t gfp_mask); u32 (*mk_key) (const struct gss_krb5_enctype *gk5e, struct xdr_netobj *in, struct xdr_netobj *out); /* complete key generation */ diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c index 0a831b5cea6b..e33575216a01 100644 --- a/net/sunrpc/auth_gss/gss_krb5_mech.c +++ b/net/sunrpc/auth_gss/gss_krb5_mech.c @@ -28,7 +28,11 @@ # define RPCDBG_FACILITY RPCDBG_AUTH #endif -static struct gss_api_mech gss_kerberos_mech; /* forward declaration */ +static struct gss_api_mech gss_kerberos_mech; + +static int gss_krb5_import_ctx_des(struct krb5_ctx *ctx, gfp_t gfp_mask); +static int gss_krb5_import_ctx_v1(struct krb5_ctx *ctx, gfp_t gfp_mask); +static int gss_krb5_import_ctx_v2(struct krb5_ctx *ctx, gfp_t gfp_mask); static const struct gss_krb5_enctype supported_gss_krb5_enctypes[] = { #ifndef CONFIG_SUNRPC_DISABLE_INSECURE_ENCTYPES @@ -43,6 +47,7 @@ static const struct gss_krb5_enctype supported_gss_krb5_enctypes[] = { .cksum_name = "md5", .encrypt = krb5_encrypt, .decrypt = krb5_decrypt, + .import_ctx = gss_krb5_import_ctx_des, .mk_key = NULL, .get_mic = gss_krb5_get_mic_v1, .verify_mic = gss_krb5_verify_mic_v1, @@ -67,6 +72,7 @@ static const struct gss_krb5_enctype supported_gss_krb5_enctypes[] = { .cksum_name = "hmac(sha1)", .encrypt = krb5_encrypt, .decrypt = krb5_decrypt, + .import_ctx = gss_krb5_import_ctx_v1, .mk_key = gss_krb5_des3_make_key, .get_mic = gss_krb5_get_mic_v1, .verify_mic = gss_krb5_verify_mic_v1, @@ -91,6 +97,7 @@ static const struct gss_krb5_enctype supported_gss_krb5_enctypes[] = { .cksum_name = "hmac(sha1)", .encrypt = krb5_encrypt, .decrypt = krb5_decrypt, + .import_ctx = gss_krb5_import_ctx_v2, .mk_key = gss_krb5_aes_make_key, .encrypt_v2 = gss_krb5_aes_encrypt, .decrypt_v2 = gss_krb5_aes_decrypt, @@ -119,6 +126,7 @@ static const struct gss_krb5_enctype supported_gss_krb5_enctypes[] = { .cksum_name = "hmac(sha1)", .encrypt = krb5_encrypt, .decrypt = krb5_decrypt, + .import_ctx = gss_krb5_import_ctx_v2, .mk_key = gss_krb5_aes_make_key, .encrypt_v2 = gss_krb5_aes_encrypt, .decrypt_v2 = gss_krb5_aes_decrypt, @@ -324,7 +332,13 @@ set_cdata(u8 cdata[GSS_KRB5_K5CLENGTH], u32 usage, u8 seed) } static int -context_derive_keys_des3(struct krb5_ctx *ctx, gfp_t gfp_mask) +gss_krb5_import_ctx_des(struct krb5_ctx *ctx, gfp_t gfp_mask) +{ + return -EINVAL; +} + +static int +gss_krb5_import_ctx_v1(struct krb5_ctx *ctx, gfp_t gfp_mask) { struct xdr_netobj c, keyin, keyout; u8 cdata[GSS_KRB5_K5CLENGTH]; @@ -384,7 +398,7 @@ gss_krb5_alloc_hash_v2(struct krb5_ctx *kctx, const struct xdr_netobj *key) } static int -context_derive_keys_new(struct krb5_ctx *ctx, gfp_t gfp_mask) +gss_krb5_import_ctx_v2(struct krb5_ctx *ctx, gfp_t gfp_mask) { u8 cdata[GSS_KRB5_K5CLENGTH]; struct xdr_netobj c = { @@ -563,15 +577,7 @@ gss_import_v2_context(const void *p, const void *end, struct krb5_ctx *ctx, } ctx->mech_used.len = gss_kerberos_mech.gm_oid.len; - switch (ctx->enctype) { - case ENCTYPE_DES3_CBC_RAW: - return context_derive_keys_des3(ctx, gfp_mask); - case ENCTYPE_AES128_CTS_HMAC_SHA1_96: - case ENCTYPE_AES256_CTS_HMAC_SHA1_96: - return context_derive_keys_new(ctx, gfp_mask); - default: - return -EINVAL; - } + return ctx->gk5e->import_ctx(ctx, gfp_mask); out_err: return PTR_ERR(p); -- cgit v1.2.3 From 17781b2ce41a8915163d7cdada021f809ccd49f0 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sun, 15 Jan 2023 12:21:45 -0500 Subject: SUNRPC: Replace KRB5_SUPPORTED_ENCTYPES macro Now that all consumers of the KRB5_SUPPORTED_ENCTYPES macro are within the SunRPC layer, the macro can be replaced with something private and more flexible. Tested-by: Scott Mayhew Reviewed-by: Simo Sorce Signed-off-by: Chuck Lever --- include/linux/sunrpc/gss_krb5_enctypes.h | 41 -------------------------------- net/sunrpc/auth_gss/gss_krb5_mech.c | 41 ++++++++++++++++++++++++++++++-- 2 files changed, 39 insertions(+), 43 deletions(-) delete mode 100644 include/linux/sunrpc/gss_krb5_enctypes.h (limited to 'include/linux') diff --git a/include/linux/sunrpc/gss_krb5_enctypes.h b/include/linux/sunrpc/gss_krb5_enctypes.h deleted file mode 100644 index 87eea679d750..000000000000 --- a/include/linux/sunrpc/gss_krb5_enctypes.h +++ /dev/null @@ -1,41 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Define the string that exports the set of kernel-supported - * Kerberos enctypes. This list is sent via upcall to gssd, and - * is also exposed via the nfsd /proc API. The consumers generally - * treat this as an ordered list, where the first item in the list - * is the most preferred. - */ - -#ifndef _LINUX_SUNRPC_GSS_KRB5_ENCTYPES_H -#define _LINUX_SUNRPC_GSS_KRB5_ENCTYPES_H - -#ifdef CONFIG_SUNRPC_DISABLE_INSECURE_ENCTYPES - -/* - * NB: This list includes DES3_CBC_SHA1, which was deprecated by RFC 8429. - * - * ENCTYPE_AES256_CTS_HMAC_SHA1_96 - * ENCTYPE_AES128_CTS_HMAC_SHA1_96 - * ENCTYPE_DES3_CBC_SHA1 - */ -#define KRB5_SUPPORTED_ENCTYPES "18,17,16" - -#else /* CONFIG_SUNRPC_DISABLE_INSECURE_ENCTYPES */ - -/* - * NB: This list includes encryption types that were deprecated - * by RFC 8429 and RFC 6649. - * - * ENCTYPE_AES256_CTS_HMAC_SHA1_96 - * ENCTYPE_AES128_CTS_HMAC_SHA1_96 - * ENCTYPE_DES3_CBC_SHA1 - * ENCTYPE_DES_CBC_MD5 - * ENCTYPE_DES_CBC_CRC - * ENCTYPE_DES_CBC_MD4 - */ -#define KRB5_SUPPORTED_ENCTYPES "18,17,16,3,1,2" - -#endif /* CONFIG_SUNRPC_DISABLE_INSECURE_ENCTYPES */ - -#endif /* _LINUX_SUNRPC_GSS_KRB5_ENCTYPES_H */ diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c index e33575216a01..2553d18fd288 100644 --- a/net/sunrpc/auth_gss/gss_krb5_mech.c +++ b/net/sunrpc/auth_gss/gss_krb5_mech.c @@ -19,7 +19,6 @@ #include #include #include -#include #include "auth_gss_internal.h" #include "gss_krb5_internal.h" @@ -145,6 +144,43 @@ static const struct gss_krb5_enctype supported_gss_krb5_enctypes[] = { }, }; +/* + * The list of advertised enctypes is specified in order of most + * preferred to least. + */ +static char gss_krb5_enctype_priority_list[64]; + +static void gss_krb5_prepare_enctype_priority_list(void) +{ + static const u32 gss_krb5_enctypes[] = { + ENCTYPE_AES256_CTS_HMAC_SHA1_96, + ENCTYPE_AES128_CTS_HMAC_SHA1_96, + ENCTYPE_DES3_CBC_SHA1, +#ifndef CONFIG_SUNRPC_DISABLE_INSECURE_ENCTYPES + ENCTYPE_DES_CBC_MD5, + ENCTYPE_DES_CBC_CRC, + ENCTYPE_DES_CBC_MD4, +#endif + }; + size_t total, i; + char buf[16]; + char *sep; + int n; + + sep = ""; + gss_krb5_enctype_priority_list[0] = '\0'; + for (total = 0, i = 0; i < ARRAY_SIZE(gss_krb5_enctypes); i++) { + n = sprintf(buf, "%s%u", sep, gss_krb5_enctypes[i]); + if (n < 0) + break; + if (total + n >= sizeof(gss_krb5_enctype_priority_list)) + break; + strcat(gss_krb5_enctype_priority_list, buf); + sep = ","; + total += n; + } +} + static const int num_supported_enctypes = ARRAY_SIZE(supported_gss_krb5_enctypes); @@ -761,13 +797,14 @@ static struct gss_api_mech gss_kerberos_mech = { .gm_ops = &gss_kerberos_ops, .gm_pf_num = ARRAY_SIZE(gss_kerberos_pfs), .gm_pfs = gss_kerberos_pfs, - .gm_upcall_enctypes = KRB5_SUPPORTED_ENCTYPES, + .gm_upcall_enctypes = gss_krb5_enctype_priority_list, }; static int __init init_kerberos_module(void) { int status; + gss_krb5_prepare_enctype_priority_list(); status = gss_mech_register(&gss_kerberos_mech); if (status) printk("Failed to register kerberos gss mechanism!\n"); -- cgit v1.2.3 From d50b8152c992ac88c5f1f0cc8ade6ee0aa0a3704 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sun, 15 Jan 2023 12:21:58 -0500 Subject: SUNRPC: Remove ->encrypt and ->decrypt methods from struct gss_krb5_enctype Clean up: ->encrypt is set to only one value. Replace the two remaining call sites with direct calls to krb5_encrypt(). There have never been any call sites for the ->decrypt() method. Tested-by: Scott Mayhew Reviewed-by: Simo Sorce Signed-off-by: Chuck Lever --- include/linux/sunrpc/gss_krb5.h | 14 ------------- net/sunrpc/auth_gss/gss_krb5_crypto.c | 36 +++++++++++++++++++++++++++++++-- net/sunrpc/auth_gss/gss_krb5_internal.h | 6 ++++++ net/sunrpc/auth_gss/gss_krb5_keys.c | 6 ++++-- net/sunrpc/auth_gss/gss_krb5_mech.c | 8 -------- net/sunrpc/auth_gss/gss_krb5_seqnum.c | 2 ++ 6 files changed, 46 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/gss_krb5.h b/include/linux/sunrpc/gss_krb5.h index 68ae0c3d4cf7..a0646df12beb 100644 --- a/include/linux/sunrpc/gss_krb5.h +++ b/include/linux/sunrpc/gss_krb5.h @@ -69,12 +69,6 @@ struct gss_krb5_enctype { const u32 keyed_cksum; /* is it a keyed cksum? */ const u32 keybytes; /* raw key len, in bytes */ const u32 keylength; /* final key len, in bytes */ - u32 (*encrypt) (struct crypto_sync_skcipher *tfm, - void *iv, void *in, void *out, - int length); /* encryption function */ - u32 (*decrypt) (struct crypto_sync_skcipher *tfm, - void *iv, void *in, void *out, - int length); /* decryption function */ int (*import_ctx)(struct krb5_ctx *ctx, gfp_t gfp_mask); u32 (*mk_key) (const struct gss_krb5_enctype *gk5e, struct xdr_netobj *in, @@ -243,14 +237,6 @@ make_checksum(struct krb5_ctx *kctx, char *header, int hdrlen, struct xdr_buf *body, int body_offset, u8 *cksumkey, unsigned int usage, struct xdr_netobj *cksumout); -u32 -krb5_encrypt(struct crypto_sync_skcipher *key, - void *iv, void *in, void *out, int length); - -u32 -krb5_decrypt(struct crypto_sync_skcipher *key, - void *iv, void *in, void *out, int length); - int gss_encrypt_xdr_buf(struct crypto_sync_skcipher *tfm, struct xdr_buf *outbuf, int offset, struct page **pages); diff --git a/net/sunrpc/auth_gss/gss_krb5_crypto.c b/net/sunrpc/auth_gss/gss_krb5_crypto.c index 098faaf02fe6..c5845fdda527 100644 --- a/net/sunrpc/auth_gss/gss_krb5_crypto.c +++ b/net/sunrpc/auth_gss/gss_krb5_crypto.c @@ -82,6 +82,22 @@ void krb5_make_confounder(u8 *p, int conflen) get_random_bytes(p, conflen); } +/** + * krb5_encrypt - simple encryption of an RPCSEC GSS payload + * @tfm: initialized cipher transform + * @iv: pointer to an IV + * @in: plaintext to encrypt + * @out: OUT: ciphertext + * @length: length of input and output buffers, in bytes + * + * @iv may be NULL to force the use of an all-zero IV. + * The buffer containing the IV must be as large as the + * cipher's ivsize. + * + * Return values: + * %0: @in successfully encrypted into @out + * negative errno: @in not encrypted + */ u32 krb5_encrypt( struct crypto_sync_skcipher *tfm, @@ -121,6 +137,22 @@ out: return ret; } +/** + * krb5_decrypt - simple decryption of an RPCSEC GSS payload + * @tfm: initialized cipher transform + * @iv: pointer to an IV + * @in: ciphertext to decrypt + * @out: OUT: plaintext + * @length: length of input and output buffers, in bytes + * + * @iv may be NULL to force the use of an all-zero IV. + * The buffer containing the IV must be as large as the + * cipher's ivsize. + * + * Return values: + * %0: @in successfully decrypted into @out + * negative errno: @in not decrypted + */ u32 krb5_decrypt( struct crypto_sync_skcipher *tfm, @@ -234,8 +266,8 @@ make_checksum(struct krb5_ctx *kctx, char *header, int hdrlen, switch (kctx->gk5e->ctype) { case CKSUMTYPE_RSA_MD5: - err = kctx->gk5e->encrypt(kctx->seq, NULL, checksumdata, - checksumdata, checksumlen); + err = krb5_encrypt(kctx->seq, NULL, checksumdata, + checksumdata, checksumlen); if (err) goto out; memcpy(cksumout->data, diff --git a/net/sunrpc/auth_gss/gss_krb5_internal.h b/net/sunrpc/auth_gss/gss_krb5_internal.h index 04d2781e2ce2..a4b752af6951 100644 --- a/net/sunrpc/auth_gss/gss_krb5_internal.h +++ b/net/sunrpc/auth_gss/gss_krb5_internal.h @@ -44,4 +44,10 @@ u32 gss_krb5_checksum(struct crypto_ahash *tfm, char *header, int hdrlen, const struct xdr_buf *body, int body_offset, struct xdr_netobj *cksumout); +u32 krb5_encrypt(struct crypto_sync_skcipher *key, void *iv, void *in, + void *out, int length); + +u32 krb5_decrypt(struct crypto_sync_skcipher *key, void *iv, void *in, + void *out, int length); + #endif /* _NET_SUNRPC_AUTH_GSS_KRB5_INTERNAL_H */ diff --git a/net/sunrpc/auth_gss/gss_krb5_keys.c b/net/sunrpc/auth_gss/gss_krb5_keys.c index 554cfd23f288..a7c6866dad96 100644 --- a/net/sunrpc/auth_gss/gss_krb5_keys.c +++ b/net/sunrpc/auth_gss/gss_krb5_keys.c @@ -61,6 +61,8 @@ #include #include +#include "gss_krb5_internal.h" + #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_AUTH #endif @@ -195,8 +197,8 @@ u32 krb5_derive_key(const struct gss_krb5_enctype *gk5e, n = 0; while (n < keybytes) { - (*(gk5e->encrypt))(cipher, NULL, inblock.data, - outblock.data, inblock.len); + krb5_encrypt(cipher, NULL, inblock.data, outblock.data, + inblock.len); if ((keybytes - n) <= outblock.len) { memcpy(rawkey + n, outblock.data, (keybytes - n)); diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c index 9ddc6fc7077f..47c065aa4a14 100644 --- a/net/sunrpc/auth_gss/gss_krb5_mech.c +++ b/net/sunrpc/auth_gss/gss_krb5_mech.c @@ -48,8 +48,6 @@ static const struct gss_krb5_enctype supported_gss_krb5_enctypes[] = { .name = "des-cbc-crc", .encrypt_name = "cbc(des)", .cksum_name = "md5", - .encrypt = krb5_encrypt, - .decrypt = krb5_decrypt, .import_ctx = gss_krb5_import_ctx_des, .mk_key = NULL, .get_mic = gss_krb5_get_mic_v1, @@ -72,8 +70,6 @@ static const struct gss_krb5_enctype supported_gss_krb5_enctypes[] = { .name = "des3-hmac-sha1", .encrypt_name = "cbc(des3_ede)", .cksum_name = "hmac(sha1)", - .encrypt = krb5_encrypt, - .decrypt = krb5_decrypt, .import_ctx = gss_krb5_import_ctx_v1, .mk_key = gss_krb5_des3_make_key, .get_mic = gss_krb5_get_mic_v1, @@ -100,8 +96,6 @@ static const struct gss_krb5_enctype supported_gss_krb5_enctypes[] = { .encrypt_name = "cts(cbc(aes))", .aux_cipher = "cbc(aes)", .cksum_name = "hmac(sha1)", - .encrypt = krb5_encrypt, - .decrypt = krb5_decrypt, .import_ctx = gss_krb5_import_ctx_v2, .mk_key = gss_krb5_aes_make_key, .encrypt_v2 = gss_krb5_aes_encrypt, @@ -129,8 +123,6 @@ static const struct gss_krb5_enctype supported_gss_krb5_enctypes[] = { .encrypt_name = "cts(cbc(aes))", .aux_cipher = "cbc(aes)", .cksum_name = "hmac(sha1)", - .encrypt = krb5_encrypt, - .decrypt = krb5_decrypt, .import_ctx = gss_krb5_import_ctx_v2, .mk_key = gss_krb5_aes_make_key, .encrypt_v2 = gss_krb5_aes_encrypt, diff --git a/net/sunrpc/auth_gss/gss_krb5_seqnum.c b/net/sunrpc/auth_gss/gss_krb5_seqnum.c index 3200b971a814..1babc3474e10 100644 --- a/net/sunrpc/auth_gss/gss_krb5_seqnum.c +++ b/net/sunrpc/auth_gss/gss_krb5_seqnum.c @@ -35,6 +35,8 @@ #include #include +#include "gss_krb5_internal.h" + #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_AUTH #endif -- cgit v1.2.3 From ae6ad5d0b7901b301234143e93624417ac9fd9ef Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sun, 15 Jan 2023 12:22:04 -0500 Subject: SUNRPC: Rename .encrypt_v2 and .decrypt_v2 methods Clean up: there is now only one encrypt and only one decrypt method, thus there is no longer a need for the v2-suffixed method names. Tested-by: Scott Mayhew Reviewed-by: Simo Sorce Signed-off-by: Chuck Lever --- include/linux/sunrpc/gss_krb5.h | 20 ++++---------------- net/sunrpc/auth_gss/gss_krb5_internal.h | 6 ++++++ net/sunrpc/auth_gss/gss_krb5_mech.c | 8 ++++---- net/sunrpc/auth_gss/gss_krb5_wrap.c | 12 +++--------- 4 files changed, 17 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/gss_krb5.h b/include/linux/sunrpc/gss_krb5.h index a0646df12beb..85fce36c242d 100644 --- a/include/linux/sunrpc/gss_krb5.h +++ b/include/linux/sunrpc/gss_krb5.h @@ -73,12 +73,10 @@ struct gss_krb5_enctype { u32 (*mk_key) (const struct gss_krb5_enctype *gk5e, struct xdr_netobj *in, struct xdr_netobj *out); /* complete key generation */ - u32 (*encrypt_v2) (struct krb5_ctx *kctx, u32 offset, - struct xdr_buf *buf, - struct page **pages); /* v2 encryption function */ - u32 (*decrypt_v2) (struct krb5_ctx *kctx, u32 offset, u32 len, - struct xdr_buf *buf, u32 *headskip, - u32 *tailskip); /* v2 decryption function */ + u32 (*encrypt)(struct krb5_ctx *kctx, u32 offset, + struct xdr_buf *buf, struct page **pages); + u32 (*decrypt)(struct krb5_ctx *kctx, u32 offset, u32 len, + struct xdr_buf *buf, u32 *headskip, u32 *tailskip); u32 (*get_mic)(struct krb5_ctx *kctx, struct xdr_buf *text, struct xdr_netobj *token); u32 (*verify_mic)(struct krb5_ctx *kctx, struct xdr_buf *message_buffer, @@ -276,14 +274,4 @@ gss_krb5_aes_make_key(const struct gss_krb5_enctype *gk5e, struct xdr_netobj *randombits, struct xdr_netobj *key); -u32 -gss_krb5_aes_encrypt(struct krb5_ctx *kctx, u32 offset, - struct xdr_buf *buf, - struct page **pages); - -u32 -gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, u32 len, - struct xdr_buf *buf, u32 *plainoffset, - u32 *plainlen); - #endif /* _LINUX_SUNRPC_GSS_KRB5_H */ diff --git a/net/sunrpc/auth_gss/gss_krb5_internal.h b/net/sunrpc/auth_gss/gss_krb5_internal.h index a4b752af6951..837bcfa3742f 100644 --- a/net/sunrpc/auth_gss/gss_krb5_internal.h +++ b/net/sunrpc/auth_gss/gss_krb5_internal.h @@ -50,4 +50,10 @@ u32 krb5_encrypt(struct crypto_sync_skcipher *key, void *iv, void *in, u32 krb5_decrypt(struct crypto_sync_skcipher *key, void *iv, void *in, void *out, int length); +u32 gss_krb5_aes_encrypt(struct krb5_ctx *kctx, u32 offset, + struct xdr_buf *buf, struct page **pages); + +u32 gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, u32 len, + struct xdr_buf *buf, u32 *plainoffset, u32 *plainlen); + #endif /* _NET_SUNRPC_AUTH_GSS_KRB5_INTERNAL_H */ diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c index 47c065aa4a14..9f393175a276 100644 --- a/net/sunrpc/auth_gss/gss_krb5_mech.c +++ b/net/sunrpc/auth_gss/gss_krb5_mech.c @@ -98,8 +98,8 @@ static const struct gss_krb5_enctype supported_gss_krb5_enctypes[] = { .cksum_name = "hmac(sha1)", .import_ctx = gss_krb5_import_ctx_v2, .mk_key = gss_krb5_aes_make_key, - .encrypt_v2 = gss_krb5_aes_encrypt, - .decrypt_v2 = gss_krb5_aes_decrypt, + .encrypt = gss_krb5_aes_encrypt, + .decrypt = gss_krb5_aes_decrypt, .get_mic = gss_krb5_get_mic_v2, .verify_mic = gss_krb5_verify_mic_v2, @@ -125,8 +125,8 @@ static const struct gss_krb5_enctype supported_gss_krb5_enctypes[] = { .cksum_name = "hmac(sha1)", .import_ctx = gss_krb5_import_ctx_v2, .mk_key = gss_krb5_aes_make_key, - .encrypt_v2 = gss_krb5_aes_encrypt, - .decrypt_v2 = gss_krb5_aes_decrypt, + .encrypt = gss_krb5_aes_encrypt, + .decrypt = gss_krb5_aes_decrypt, .get_mic = gss_krb5_get_mic_v2, .verify_mic = gss_krb5_verify_mic_v2, diff --git a/net/sunrpc/auth_gss/gss_krb5_wrap.c b/net/sunrpc/auth_gss/gss_krb5_wrap.c index 7dabf379406b..6d6b082380b2 100644 --- a/net/sunrpc/auth_gss/gss_krb5_wrap.c +++ b/net/sunrpc/auth_gss/gss_krb5_wrap.c @@ -390,9 +390,6 @@ gss_krb5_wrap_v2(struct krb5_ctx *kctx, int offset, dprintk("RPC: %s\n", __func__); - if (kctx->gk5e->encrypt_v2 == NULL) - return GSS_S_FAILURE; - /* make room for gss token header */ if (xdr_extend_head(buf, offset, GSS_KRB5_TOK_HDR_LEN)) return GSS_S_FAILURE; @@ -420,7 +417,7 @@ gss_krb5_wrap_v2(struct krb5_ctx *kctx, int offset, be64ptr = (__be64 *)be16ptr; *be64ptr = cpu_to_be64(atomic64_fetch_inc(&kctx->seq_send64)); - err = (*kctx->gk5e->encrypt_v2)(kctx, offset, buf, pages); + err = (*kctx->gk5e->encrypt)(kctx, offset, buf, pages); if (err) return err; @@ -445,9 +442,6 @@ gss_krb5_unwrap_v2(struct krb5_ctx *kctx, int offset, int len, dprintk("RPC: %s\n", __func__); - if (kctx->gk5e->decrypt_v2 == NULL) - return GSS_S_FAILURE; - ptr = buf->head[0].iov_base + offset; if (be16_to_cpu(*((__be16 *)ptr)) != KG2_TOK_WRAP) @@ -477,8 +471,8 @@ gss_krb5_unwrap_v2(struct krb5_ctx *kctx, int offset, int len, if (rrc != 0) rotate_left(offset + 16, buf, rrc); - err = (*kctx->gk5e->decrypt_v2)(kctx, offset, len, buf, - &headskip, &tailskip); + err = (*kctx->gk5e->decrypt)(kctx, offset, len, buf, + &headskip, &tailskip); if (err) return GSS_S_FAILURE; -- cgit v1.2.3 From 2691a27d9b3e6a48adeb87a9dcf4e8a0ca84a26e Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sun, 15 Jan 2023 12:22:11 -0500 Subject: SUNRPC: Hoist KDF into struct gss_krb5_enctype Each Kerberos enctype can have a different KDF. Refactor the key derivation path to support different KDFs for the enctypes introduced in subsequent patches. In particular, expose the key derivation function in struct gss_krb5_enctype instead of the enctype's preferred random-to-key function. The latter is usually the identity function and is only ever called during key derivation, so have each KDF call it directly. A couple of extra clean-ups: - Deduplicate the set_cdata() helper - Have ->derive_key return negative errnos, in accordance with usual kernel coding conventions This patch is a little bigger than I'd like, but these are all mechanical changes and they are all to the same areas of code. No behavior change is intended. Tested-by: Scott Mayhew Reviewed-by: Simo Sorce Signed-off-by: Chuck Lever --- include/linux/sunrpc/gss_krb5.h | 25 ++---- net/sunrpc/auth_gss/gss_krb5_internal.h | 46 +++++++++++ net/sunrpc/auth_gss/gss_krb5_keys.c | 131 +++++++++++++++++++++----------- net/sunrpc/auth_gss/gss_krb5_mech.c | 76 +++++------------- 4 files changed, 156 insertions(+), 122 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/gss_krb5.h b/include/linux/sunrpc/gss_krb5.h index 85fce36c242d..04addef79177 100644 --- a/include/linux/sunrpc/gss_krb5.h +++ b/include/linux/sunrpc/gss_krb5.h @@ -70,9 +70,11 @@ struct gss_krb5_enctype { const u32 keybytes; /* raw key len, in bytes */ const u32 keylength; /* final key len, in bytes */ int (*import_ctx)(struct krb5_ctx *ctx, gfp_t gfp_mask); - u32 (*mk_key) (const struct gss_krb5_enctype *gk5e, - struct xdr_netobj *in, - struct xdr_netobj *out); /* complete key generation */ + int (*derive_key)(const struct gss_krb5_enctype *gk5e, + const struct xdr_netobj *in, + struct xdr_netobj *out, + const struct xdr_netobj *label, + gfp_t gfp_mask); u32 (*encrypt)(struct krb5_ctx *kctx, u32 offset, struct xdr_buf *buf, struct page **pages); u32 (*decrypt)(struct krb5_ctx *kctx, u32 offset, u32 len, @@ -257,21 +259,4 @@ krb5_get_seq_num(struct krb5_ctx *kctx, int xdr_extend_head(struct xdr_buf *buf, unsigned int base, unsigned int shiftlen); -u32 -krb5_derive_key(const struct gss_krb5_enctype *gk5e, - const struct xdr_netobj *inkey, - struct xdr_netobj *outkey, - const struct xdr_netobj *in_constant, - gfp_t gfp_mask); - -u32 -gss_krb5_des3_make_key(const struct gss_krb5_enctype *gk5e, - struct xdr_netobj *randombits, - struct xdr_netobj *key); - -u32 -gss_krb5_aes_make_key(const struct gss_krb5_enctype *gk5e, - struct xdr_netobj *randombits, - struct xdr_netobj *key); - #endif /* _LINUX_SUNRPC_GSS_KRB5_H */ diff --git a/net/sunrpc/auth_gss/gss_krb5_internal.h b/net/sunrpc/auth_gss/gss_krb5_internal.h index 837bcfa3742f..c7580026adc7 100644 --- a/net/sunrpc/auth_gss/gss_krb5_internal.h +++ b/net/sunrpc/auth_gss/gss_krb5_internal.h @@ -38,6 +38,52 @@ u32 gss_krb5_unwrap_v2(struct krb5_ctx *kctx, int offset, int len, * Implementation internal functions */ +/* Key Derivation Functions */ + +int krb5_derive_key_v1(const struct gss_krb5_enctype *gk5e, + const struct xdr_netobj *inkey, + struct xdr_netobj *outkey, + const struct xdr_netobj *label, + gfp_t gfp_mask); + +int krb5_derive_key_v2(const struct gss_krb5_enctype *gk5e, + const struct xdr_netobj *inkey, + struct xdr_netobj *outkey, + const struct xdr_netobj *label, + gfp_t gfp_mask); + +/** + * krb5_derive_key - Derive a subkey from a protocol key + * @kctx: Kerberos 5 context + * @inkey: base protocol key + * @outkey: OUT: derived key + * @usage: key usage value + * @seed: key usage seed (one octet) + * @gfp_mask: memory allocation control flags + * + * Caller sets @outkey->len to the desired length of the derived key. + * + * On success, returns 0 and fills in @outkey. A negative errno value + * is returned on failure. + */ +static inline int krb5_derive_key(struct krb5_ctx *kctx, + const struct xdr_netobj *inkey, + struct xdr_netobj *outkey, + u32 usage, u8 seed, gfp_t gfp_mask) +{ + const struct gss_krb5_enctype *gk5e = kctx->gk5e; + u8 label_data[GSS_KRB5_K5CLENGTH]; + struct xdr_netobj label = { + .len = sizeof(label_data), + .data = label_data, + }; + __be32 *p = (__be32 *)label_data; + + *p = cpu_to_be32(usage); + label_data[4] = seed; + return gk5e->derive_key(gk5e, inkey, outkey, &label, gfp_mask); +} + void krb5_make_confounder(u8 *p, int conflen); u32 gss_krb5_checksum(struct crypto_ahash *tfm, char *header, int hdrlen, diff --git a/net/sunrpc/auth_gss/gss_krb5_keys.c b/net/sunrpc/auth_gss/gss_krb5_keys.c index a7c6866dad96..f6de4fdd63ae 100644 --- a/net/sunrpc/auth_gss/gss_krb5_keys.c +++ b/net/sunrpc/auth_gss/gss_krb5_keys.c @@ -139,23 +139,20 @@ static void krb5_nfold(u32 inbits, const u8 *in, * This is the DK (derive_key) function as described in rfc3961, sec 5.1 * Taken from MIT Kerberos and modified. */ - -u32 krb5_derive_key(const struct gss_krb5_enctype *gk5e, - const struct xdr_netobj *inkey, - struct xdr_netobj *outkey, - const struct xdr_netobj *in_constant, - gfp_t gfp_mask) +static int krb5_DK(const struct gss_krb5_enctype *gk5e, + const struct xdr_netobj *inkey, u8 *rawkey, + const struct xdr_netobj *in_constant, gfp_t gfp_mask) { size_t blocksize, keybytes, keylength, n; - unsigned char *inblockdata, *outblockdata, *rawkey; + unsigned char *inblockdata, *outblockdata; struct xdr_netobj inblock, outblock; struct crypto_sync_skcipher *cipher; - u32 ret = EINVAL; + int ret = -EINVAL; keybytes = gk5e->keybytes; keylength = gk5e->keylength; - if ((inkey->len != keylength) || (outkey->len != keylength)) + if (inkey->len != keylength) goto err_return; cipher = crypto_alloc_sync_skcipher(gk5e->encrypt_name, 0, 0); @@ -165,7 +162,7 @@ u32 krb5_derive_key(const struct gss_krb5_enctype *gk5e, if (crypto_sync_skcipher_setkey(cipher, inkey->data, inkey->len)) goto err_return; - ret = ENOMEM; + ret = -ENOMEM; inblockdata = kmalloc(blocksize, gfp_mask); if (inblockdata == NULL) goto err_free_cipher; @@ -174,10 +171,6 @@ u32 krb5_derive_key(const struct gss_krb5_enctype *gk5e, if (outblockdata == NULL) goto err_free_in; - rawkey = kmalloc(keybytes, gfp_mask); - if (rawkey == NULL) - goto err_free_out; - inblock.data = (char *) inblockdata; inblock.len = blocksize; @@ -210,26 +203,8 @@ u32 krb5_derive_key(const struct gss_krb5_enctype *gk5e, n += outblock.len; } - /* postprocess the key */ - - inblock.data = (char *) rawkey; - inblock.len = keybytes; - - BUG_ON(gk5e->mk_key == NULL); - ret = (*(gk5e->mk_key))(gk5e, &inblock, outkey); - if (ret) { - dprintk("%s: got %d from mk_key function for '%s'\n", - __func__, ret, gk5e->encrypt_name); - goto err_free_raw; - } - - /* clean memory, free resources and exit */ - ret = 0; -err_free_raw: - kfree_sensitive(rawkey); -err_free_out: kfree_sensitive(outblockdata); err_free_in: kfree_sensitive(inblockdata); @@ -252,15 +227,11 @@ static void mit_des_fixup_key_parity(u8 key[8]) } } -/* - * This is the des3 key derivation postprocess function - */ -u32 gss_krb5_des3_make_key(const struct gss_krb5_enctype *gk5e, - struct xdr_netobj *randombits, - struct xdr_netobj *key) +static int krb5_random_to_key_v1(const struct gss_krb5_enctype *gk5e, + struct xdr_netobj *randombits, + struct xdr_netobj *key) { - int i; - u32 ret = EINVAL; + int i, ret = -EINVAL; if (key->len != 24) { dprintk("%s: key->len is %d\n", __func__, key->len); @@ -292,14 +263,49 @@ err_out: return ret; } +/** + * krb5_derive_key_v1 - Derive a subkey for an RFC 3961 enctype + * @gk5e: Kerberos 5 enctype profile + * @inkey: base protocol key + * @outkey: OUT: derived key + * @label: subkey usage label + * @gfp_mask: memory allocation control flags + * + * Caller sets @outkey->len to the desired length of the derived key. + * + * On success, returns 0 and fills in @outkey. A negative errno value + * is returned on failure. + */ +int krb5_derive_key_v1(const struct gss_krb5_enctype *gk5e, + const struct xdr_netobj *inkey, + struct xdr_netobj *outkey, + const struct xdr_netobj *label, + gfp_t gfp_mask) +{ + struct xdr_netobj inblock; + int ret; + + inblock.len = gk5e->keybytes; + inblock.data = kmalloc(inblock.len, gfp_mask); + if (!inblock.data) + return -ENOMEM; + + ret = krb5_DK(gk5e, inkey, inblock.data, label, gfp_mask); + if (!ret) + ret = krb5_random_to_key_v1(gk5e, &inblock, outkey); + + kfree_sensitive(inblock.data); + return ret; +} + /* - * This is the aes key derivation postprocess function + * This is the identity function, with some sanity checking. */ -u32 gss_krb5_aes_make_key(const struct gss_krb5_enctype *gk5e, - struct xdr_netobj *randombits, - struct xdr_netobj *key) +static int krb5_random_to_key_v2(const struct gss_krb5_enctype *gk5e, + struct xdr_netobj *randombits, + struct xdr_netobj *key) { - u32 ret = EINVAL; + int ret = -EINVAL; if (key->len != 16 && key->len != 32) { dprintk("%s: key->len is %d\n", __func__, key->len); @@ -320,3 +326,38 @@ u32 gss_krb5_aes_make_key(const struct gss_krb5_enctype *gk5e, err_out: return ret; } + +/** + * krb5_derive_key_v2 - Derive a subkey for an RFC 3962 enctype + * @gk5e: Kerberos 5 enctype profile + * @inkey: base protocol key + * @outkey: OUT: derived key + * @label: subkey usage label + * @gfp_mask: memory allocation control flags + * + * Caller sets @outkey->len to the desired length of the derived key. + * + * On success, returns 0 and fills in @outkey. A negative errno value + * is returned on failure. + */ +int krb5_derive_key_v2(const struct gss_krb5_enctype *gk5e, + const struct xdr_netobj *inkey, + struct xdr_netobj *outkey, + const struct xdr_netobj *label, + gfp_t gfp_mask) +{ + struct xdr_netobj inblock; + int ret; + + inblock.len = gk5e->keybytes; + inblock.data = kmalloc(inblock.len, gfp_mask); + if (!inblock.data) + return -ENOMEM; + + ret = krb5_DK(gk5e, inkey, inblock.data, label, gfp_mask); + if (!ret) + ret = krb5_random_to_key_v2(gk5e, &inblock, outkey); + + kfree_sensitive(inblock.data); + return ret; +} diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c index 9f393175a276..9e9551b224f6 100644 --- a/net/sunrpc/auth_gss/gss_krb5_mech.c +++ b/net/sunrpc/auth_gss/gss_krb5_mech.c @@ -49,7 +49,6 @@ static const struct gss_krb5_enctype supported_gss_krb5_enctypes[] = { .encrypt_name = "cbc(des)", .cksum_name = "md5", .import_ctx = gss_krb5_import_ctx_des, - .mk_key = NULL, .get_mic = gss_krb5_get_mic_v1, .verify_mic = gss_krb5_verify_mic_v1, .wrap = gss_krb5_wrap_v1, @@ -71,7 +70,7 @@ static const struct gss_krb5_enctype supported_gss_krb5_enctypes[] = { .encrypt_name = "cbc(des3_ede)", .cksum_name = "hmac(sha1)", .import_ctx = gss_krb5_import_ctx_v1, - .mk_key = gss_krb5_des3_make_key, + .derive_key = krb5_derive_key_v1, .get_mic = gss_krb5_get_mic_v1, .verify_mic = gss_krb5_verify_mic_v1, .wrap = gss_krb5_wrap_v1, @@ -97,7 +96,7 @@ static const struct gss_krb5_enctype supported_gss_krb5_enctypes[] = { .aux_cipher = "cbc(aes)", .cksum_name = "hmac(sha1)", .import_ctx = gss_krb5_import_ctx_v2, - .mk_key = gss_krb5_aes_make_key, + .derive_key = krb5_derive_key_v2, .encrypt = gss_krb5_aes_encrypt, .decrypt = gss_krb5_aes_decrypt, @@ -124,7 +123,7 @@ static const struct gss_krb5_enctype supported_gss_krb5_enctypes[] = { .aux_cipher = "cbc(aes)", .cksum_name = "hmac(sha1)", .import_ctx = gss_krb5_import_ctx_v2, - .mk_key = gss_krb5_aes_make_key, + .derive_key = krb5_derive_key_v2, .encrypt = gss_krb5_aes_encrypt, .decrypt = gss_krb5_aes_decrypt, @@ -358,16 +357,6 @@ context_v2_alloc_cipher(struct krb5_ctx *ctx, const char *cname, u8 *key) return cp; } -static inline void -set_cdata(u8 cdata[GSS_KRB5_K5CLENGTH], u32 usage, u8 seed) -{ - cdata[0] = (usage>>24)&0xff; - cdata[1] = (usage>>16)&0xff; - cdata[2] = (usage>>8)&0xff; - cdata[3] = usage&0xff; - cdata[4] = seed; -} - #if defined(CONFIG_RPCSEC_GSS_KRB5_SIMPLIFIED) static int gss_krb5_import_ctx_des(struct krb5_ctx *ctx, gfp_t gfp_mask) @@ -378,16 +367,10 @@ gss_krb5_import_ctx_des(struct krb5_ctx *ctx, gfp_t gfp_mask) static int gss_krb5_import_ctx_v1(struct krb5_ctx *ctx, gfp_t gfp_mask) { - struct xdr_netobj c, keyin, keyout; - u8 cdata[GSS_KRB5_K5CLENGTH]; - u32 err; - - c.len = GSS_KRB5_K5CLENGTH; - c.data = cdata; + struct xdr_netobj keyin, keyout; keyin.data = ctx->Ksess; keyin.len = ctx->gk5e->keylength; - keyout.len = ctx->gk5e->keylength; /* seq uses the raw key */ ctx->seq = context_v2_alloc_cipher(ctx, ctx->gk5e->encrypt_name, @@ -401,14 +384,11 @@ gss_krb5_import_ctx_v1(struct krb5_ctx *ctx, gfp_t gfp_mask) goto out_free_seq; /* derive cksum */ - set_cdata(cdata, KG_USAGE_SIGN, KEY_USAGE_SEED_CHECKSUM); keyout.data = ctx->cksum; - err = krb5_derive_key(ctx->gk5e, &keyin, &keyout, &c, gfp_mask); - if (err) { - dprintk("%s: Error %d deriving cksum key\n", - __func__, err); + keyout.len = ctx->gk5e->keylength; + if (krb5_derive_key(ctx, &keyin, &keyout, KG_USAGE_SIGN, + KEY_USAGE_SEED_CHECKSUM, gfp_mask)) goto out_free_enc; - } return 0; @@ -441,11 +421,6 @@ gss_krb5_alloc_hash_v2(struct krb5_ctx *kctx, const struct xdr_netobj *key) static int gss_krb5_import_ctx_v2(struct krb5_ctx *ctx, gfp_t gfp_mask) { - u8 cdata[GSS_KRB5_K5CLENGTH]; - struct xdr_netobj c = { - .len = sizeof(cdata), - .data = cdata, - }; struct xdr_netobj keyin = { .len = ctx->gk5e->keylength, .data = ctx->Ksess, @@ -453,7 +428,6 @@ gss_krb5_import_ctx_v2(struct krb5_ctx *ctx, gfp_t gfp_mask) struct xdr_netobj keyout; int ret = -EINVAL; void *subkey; - u32 err; subkey = kmalloc(ctx->gk5e->keylength, gfp_mask); if (!subkey) @@ -462,13 +436,9 @@ gss_krb5_import_ctx_v2(struct krb5_ctx *ctx, gfp_t gfp_mask) keyout.data = subkey; /* initiator seal encryption */ - set_cdata(cdata, KG_USAGE_INITIATOR_SEAL, KEY_USAGE_SEED_ENCRYPTION); - err = krb5_derive_key(ctx->gk5e, &keyin, &keyout, &c, gfp_mask); - if (err) { - dprintk("%s: Error %d deriving initiator_seal key\n", - __func__, err); + if (krb5_derive_key(ctx, &keyin, &keyout, KG_USAGE_INITIATOR_SEAL, + KEY_USAGE_SEED_ENCRYPTION, gfp_mask)) goto out; - } ctx->initiator_enc = context_v2_alloc_cipher(ctx, ctx->gk5e->encrypt_name, subkey); @@ -483,13 +453,9 @@ gss_krb5_import_ctx_v2(struct krb5_ctx *ctx, gfp_t gfp_mask) } /* acceptor seal encryption */ - set_cdata(cdata, KG_USAGE_ACCEPTOR_SEAL, KEY_USAGE_SEED_ENCRYPTION); - err = krb5_derive_key(ctx->gk5e, &keyin, &keyout, &c, gfp_mask); - if (err) { - dprintk("%s: Error %d deriving acceptor_seal key\n", - __func__, err); + if (krb5_derive_key(ctx, &keyin, &keyout, KG_USAGE_ACCEPTOR_SEAL, + KEY_USAGE_SEED_ENCRYPTION, gfp_mask)) goto out_free; - } ctx->acceptor_enc = context_v2_alloc_cipher(ctx, ctx->gk5e->encrypt_name, subkey); @@ -504,36 +470,32 @@ gss_krb5_import_ctx_v2(struct krb5_ctx *ctx, gfp_t gfp_mask) } /* initiator sign checksum */ - set_cdata(cdata, KG_USAGE_INITIATOR_SIGN, KEY_USAGE_SEED_CHECKSUM); - err = krb5_derive_key(ctx->gk5e, &keyin, &keyout, &c, gfp_mask); - if (err) + if (krb5_derive_key(ctx, &keyin, &keyout, KG_USAGE_INITIATOR_SIGN, + KEY_USAGE_SEED_CHECKSUM, gfp_mask)) goto out_free; ctx->initiator_sign = gss_krb5_alloc_hash_v2(ctx, &keyout); if (ctx->initiator_sign == NULL) goto out_free; /* acceptor sign checksum */ - set_cdata(cdata, KG_USAGE_ACCEPTOR_SIGN, KEY_USAGE_SEED_CHECKSUM); - err = krb5_derive_key(ctx->gk5e, &keyin, &keyout, &c, gfp_mask); - if (err) + if (krb5_derive_key(ctx, &keyin, &keyout, KG_USAGE_ACCEPTOR_SIGN, + KEY_USAGE_SEED_CHECKSUM, gfp_mask)) goto out_free; ctx->acceptor_sign = gss_krb5_alloc_hash_v2(ctx, &keyout); if (ctx->acceptor_sign == NULL) goto out_free; /* initiator seal integrity */ - set_cdata(cdata, KG_USAGE_INITIATOR_SEAL, KEY_USAGE_SEED_INTEGRITY); - err = krb5_derive_key(ctx->gk5e, &keyin, &keyout, &c, gfp_mask); - if (err) + if (krb5_derive_key(ctx, &keyin, &keyout, KG_USAGE_INITIATOR_SEAL, + KEY_USAGE_SEED_INTEGRITY, gfp_mask)) goto out_free; ctx->initiator_integ = gss_krb5_alloc_hash_v2(ctx, &keyout); if (ctx->initiator_integ == NULL) goto out_free; /* acceptor seal integrity */ - set_cdata(cdata, KG_USAGE_ACCEPTOR_SEAL, KEY_USAGE_SEED_INTEGRITY); - err = krb5_derive_key(ctx->gk5e, &keyin, &keyout, &c, gfp_mask); - if (err) + if (krb5_derive_key(ctx, &keyin, &keyout, KG_USAGE_ACCEPTOR_SEAL, + KEY_USAGE_SEED_INTEGRITY, gfp_mask)) goto out_free; ctx->acceptor_integ = gss_krb5_alloc_hash_v2(ctx, &keyout); if (ctx->acceptor_integ == NULL) -- cgit v1.2.3 From af664fc9023e69d1a90800c0f815c296bf727e18 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sun, 15 Jan 2023 12:22:30 -0500 Subject: SUNRPC: Add new subkey length fields The aes256-cts-hmac-sha384-192 enctype specifies the length of its checksum and integrity subkeys as 192 bits, but the length of its encryption subkey (Ke) as 256 bits. Add new fields to struct gss_krb5_enctype that specify the key lengths individually, and where needed, use the correct new field instead of ->keylength. Tested-by: Scott Mayhew Reviewed-by: Simo Sorce Signed-off-by: Chuck Lever --- include/linux/sunrpc/gss_krb5.h | 14 ++++++++++++-- net/sunrpc/auth_gss/gss_krb5_mech.c | 20 ++++++++++++++------ 2 files changed, 26 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/gss_krb5.h b/include/linux/sunrpc/gss_krb5.h index 04addef79177..3e97d2a7c87d 100644 --- a/include/linux/sunrpc/gss_krb5.h +++ b/include/linux/sunrpc/gss_krb5.h @@ -42,10 +42,16 @@ #include #include +/* + * The RFCs often specify payload lengths in bits. This helper + * converts a specified bit-length to the number of octets/bytes. + */ +#define BITS2OCTETS(x) ((x) / 8) + /* Length of constant used in key derivation */ #define GSS_KRB5_K5CLENGTH (5) -/* Maximum key length (in bytes) for the supported crypto algorithms*/ +/* Maximum key length (in bytes) for the supported crypto algorithms */ #define GSS_KRB5_MAX_KEYLEN (32) /* Maximum checksum function output for the supported crypto algorithms */ @@ -68,7 +74,11 @@ struct gss_krb5_enctype { const u32 cksumlength; /* checksum length */ const u32 keyed_cksum; /* is it a keyed cksum? */ const u32 keybytes; /* raw key len, in bytes */ - const u32 keylength; /* final key len, in bytes */ + const u32 keylength; /* protocol key length, in octets */ + const u32 Kc_length; /* checksum subkey length, in octets */ + const u32 Ke_length; /* encryption subkey length, in octets */ + const u32 Ki_length; /* integrity subkey length, in octets */ + int (*import_ctx)(struct krb5_ctx *ctx, gfp_t gfp_mask); int (*derive_key)(const struct gss_krb5_enctype *gk5e, const struct xdr_netobj *in, diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c index 45f461f9b5ba..ec3cca8fadc5 100644 --- a/net/sunrpc/auth_gss/gss_krb5_mech.c +++ b/net/sunrpc/auth_gss/gss_krb5_mech.c @@ -108,8 +108,11 @@ static const struct gss_krb5_enctype supported_gss_krb5_enctypes[] = { .signalg = -1, .sealalg = -1, .keybytes = 16, - .keylength = 16, - .cksumlength = 12, + .keylength = BITS2OCTETS(128), + .Kc_length = BITS2OCTETS(128), + .Ke_length = BITS2OCTETS(128), + .Ki_length = BITS2OCTETS(128), + .cksumlength = BITS2OCTETS(96), .keyed_cksum = 1, }, /* @@ -135,8 +138,11 @@ static const struct gss_krb5_enctype supported_gss_krb5_enctypes[] = { .signalg = -1, .sealalg = -1, .keybytes = 32, - .keylength = 32, - .cksumlength = 12, + .keylength = BITS2OCTETS(256), + .Kc_length = BITS2OCTETS(256), + .Ke_length = BITS2OCTETS(256), + .Ki_length = BITS2OCTETS(256), + .cksumlength = BITS2OCTETS(96), .keyed_cksum = 1, }, #endif @@ -423,12 +429,12 @@ gss_krb5_import_ctx_v2(struct krb5_ctx *ctx, gfp_t gfp_mask) struct xdr_netobj keyout; int ret = -EINVAL; - keyout.data = kmalloc(ctx->gk5e->keylength, gfp_mask); + keyout.data = kmalloc(GSS_KRB5_MAX_KEYLEN, gfp_mask); if (!keyout.data) return -ENOMEM; - keyout.len = ctx->gk5e->keylength; /* initiator seal encryption */ + keyout.len = ctx->gk5e->Ke_length; if (krb5_derive_key(ctx, &keyin, &keyout, KG_USAGE_INITIATOR_SEAL, KEY_USAGE_SEED_ENCRYPTION, gfp_mask)) goto out; @@ -461,6 +467,7 @@ gss_krb5_import_ctx_v2(struct krb5_ctx *ctx, gfp_t gfp_mask) } /* initiator sign checksum */ + keyout.len = ctx->gk5e->Kc_length; if (krb5_derive_key(ctx, &keyin, &keyout, KG_USAGE_INITIATOR_SIGN, KEY_USAGE_SEED_CHECKSUM, gfp_mask)) goto out_free; @@ -477,6 +484,7 @@ gss_krb5_import_ctx_v2(struct krb5_ctx *ctx, gfp_t gfp_mask) goto out_free; /* initiator seal integrity */ + keyout.len = ctx->gk5e->Ki_length; if (krb5_derive_key(ctx, &keyin, &keyout, KG_USAGE_INITIATOR_SEAL, KEY_USAGE_SEED_INTEGRITY, gfp_mask)) goto out_free; -- cgit v1.2.3 From a40cf7530d3104793f9361e69e84ada7960724f2 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sun, 15 Jan 2023 12:22:43 -0500 Subject: SUNRPC: Add gk5e definitions for RFC 8009 encryption types Fill in entries in the supported_gss_krb5_enctypes array for the encryption types defined in RFC 8009. These new enctypes use the SHA-256 and SHA-384 message digest algorithms (as defined in FIPS-180) instead of the deprecated SHA-1 algorithm, and are thus more secure. Note that NIST has scheduled SHA-1 for deprecation: https://www.nist.gov/news-events/news/2022/12/nist-retires-sha-1-cryptographic-algorithm Thus these new encryption types are placed under a separate CONFIG option to enable distributors to separately introduce support for the AES-SHA2 enctypes and deprecate support for the current set of AES-SHA1 encryption types as their user space allows. As this implementation is still a "beta", the default is to not build it automatically. Tested-by: Scott Mayhew Reviewed-by: Simo Sorce Signed-off-by: Chuck Lever --- include/linux/sunrpc/gss_krb5.h | 19 ++++++++++++-- net/sunrpc/Kconfig | 14 ++++++++++ net/sunrpc/auth_gss/gss_krb5_mech.c | 51 +++++++++++++++++++++++++++++++++++++ 3 files changed, 82 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/gss_krb5.h b/include/linux/sunrpc/gss_krb5.h index 3e97d2a7c87d..8ff397b5c04b 100644 --- a/include/linux/sunrpc/gss_krb5.h +++ b/include/linux/sunrpc/gss_krb5.h @@ -54,8 +54,8 @@ /* Maximum key length (in bytes) for the supported crypto algorithms */ #define GSS_KRB5_MAX_KEYLEN (32) -/* Maximum checksum function output for the supported crypto algorithms */ -#define GSS_KRB5_MAX_CKSUM_LEN (20) +/* Maximum checksum function output for the supported enctypes */ +#define GSS_KRB5_MAX_CKSUM_LEN (24) /* Maximum blocksize for the supported crypto algorithms */ #define GSS_KRB5_MAX_BLOCKSIZE (16) @@ -160,6 +160,12 @@ enum seal_alg { SEAL_ALG_DES3KD = 0x0002 }; +/* + * These values are assigned by IANA and published via the + * subregistry at the link below: + * + * https://www.iana.org/assignments/kerberos-parameters/kerberos-parameters.xhtml#kerberos-parameters-2 + */ #define CKSUMTYPE_CRC32 0x0001 #define CKSUMTYPE_RSA_MD4 0x0002 #define CKSUMTYPE_RSA_MD4_DES 0x0003 @@ -170,6 +176,8 @@ enum seal_alg { #define CKSUMTYPE_HMAC_SHA1_DES3 0x000c #define CKSUMTYPE_HMAC_SHA1_96_AES128 0x000f #define CKSUMTYPE_HMAC_SHA1_96_AES256 0x0010 +#define CKSUMTYPE_HMAC_SHA256_128_AES128 0x0013 +#define CKSUMTYPE_HMAC_SHA384_192_AES256 0x0014 #define CKSUMTYPE_HMAC_MD5_ARCFOUR -138 /* Microsoft md5 hmac cksumtype */ /* from gssapi_err_krb5.h */ @@ -190,6 +198,11 @@ enum seal_alg { /* per Kerberos v5 protocol spec crypto types from the wire. * these get mapped to linux kernel crypto routines. + * + * These values are assigned by IANA and published via the + * subregistry at the link below: + * + * https://www.iana.org/assignments/kerberos-parameters/kerberos-parameters.xhtml#kerberos-parameters-1 */ #define ENCTYPE_NULL 0x0000 #define ENCTYPE_DES_CBC_CRC 0x0001 /* DES cbc mode with CRC-32 */ @@ -203,6 +216,8 @@ enum seal_alg { #define ENCTYPE_DES3_CBC_SHA1 0x0010 #define ENCTYPE_AES128_CTS_HMAC_SHA1_96 0x0011 #define ENCTYPE_AES256_CTS_HMAC_SHA1_96 0x0012 +#define ENCTYPE_AES128_CTS_HMAC_SHA256_128 0x0013 +#define ENCTYPE_AES256_CTS_HMAC_SHA384_192 0x0014 #define ENCTYPE_ARCFOUR_HMAC 0x0017 #define ENCTYPE_ARCFOUR_HMAC_EXP 0x0018 #define ENCTYPE_UNKNOWN 0x01ff diff --git a/net/sunrpc/Kconfig b/net/sunrpc/Kconfig index 82ecb534795a..420b40279986 100644 --- a/net/sunrpc/Kconfig +++ b/net/sunrpc/Kconfig @@ -80,6 +80,20 @@ config RPCSEC_GSS_KRB5_ENCTYPES_AES_SHA1 SHA-1 digests. These include aes128-cts-hmac-sha1-96 and aes256-cts-hmac-sha1-96. +config RPCSEC_GSS_KRB5_ENCTYPES_AES_SHA2 + bool "Enable Kerberos enctypes based on AES and SHA-2" + depends on RPCSEC_GSS_KRB5 + depends on CRYPTO_CBC && CRYPTO_CTS + depends on CRYPTO_HMAC && CRYPTO_SHA256 && CRYPTO_SHA512 + depends on CRYPTO_AES + default n + select RPCSEC_GSS_KRB5_CRYPTOSYSTEM + help + Choose Y to enable the use of Kerberos 5 encryption types + that utilize Advanced Encryption Standard (AES) ciphers and + SHA-2 digests. These include aes128-cts-hmac-sha256-128 and + aes256-cts-hmac-sha384-192. + config SUNRPC_DEBUG bool "RPC: Enable dprintk debugging" depends on SUNRPC && SYSCTL diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c index ec3cca8fadc5..1951867f3fa8 100644 --- a/net/sunrpc/auth_gss/gss_krb5_mech.c +++ b/net/sunrpc/auth_gss/gss_krb5_mech.c @@ -146,6 +146,57 @@ static const struct gss_krb5_enctype supported_gss_krb5_enctypes[] = { .keyed_cksum = 1, }, #endif + +#if defined(CONFIG_RPCSEC_GSS_KRB5_ENCTYPES_AES_SHA2) + /* + * AES-128 with SHA-256 (RFC 8009) + */ + { + .etype = ENCTYPE_AES128_CTS_HMAC_SHA256_128, + .ctype = CKSUMTYPE_HMAC_SHA256_128_AES128, + .name = "aes128-cts-hmac-sha256-128", + .encrypt_name = "cts(cbc(aes))", + .aux_cipher = "cbc(aes)", + .cksum_name = "hmac(sha256)", + .cksumlength = BITS2OCTETS(128), + .keyed_cksum = 1, + .keylength = BITS2OCTETS(128), + .Kc_length = BITS2OCTETS(128), + .Ke_length = BITS2OCTETS(128), + .Ki_length = BITS2OCTETS(128), + + .import_ctx = gss_krb5_import_ctx_v2, + + .get_mic = gss_krb5_get_mic_v2, + .verify_mic = gss_krb5_verify_mic_v2, + .wrap = gss_krb5_wrap_v2, + .unwrap = gss_krb5_unwrap_v2, + }, + /* + * AES-256 with SHA-384 (RFC 8009) + */ + { + .etype = ENCTYPE_AES256_CTS_HMAC_SHA384_192, + .ctype = CKSUMTYPE_HMAC_SHA384_192_AES256, + .name = "aes256-cts-hmac-sha384-192", + .encrypt_name = "cts(cbc(aes))", + .aux_cipher = "cbc(aes)", + .cksum_name = "hmac(sha384)", + .cksumlength = BITS2OCTETS(192), + .keyed_cksum = 1, + .keylength = BITS2OCTETS(256), + .Kc_length = BITS2OCTETS(192), + .Ke_length = BITS2OCTETS(256), + .Ki_length = BITS2OCTETS(192), + + .import_ctx = gss_krb5_import_ctx_v2, + + .get_mic = gss_krb5_get_mic_v2, + .verify_mic = gss_krb5_verify_mic_v2, + .wrap = gss_krb5_wrap_v2, + .unwrap = gss_krb5_unwrap_v2, + }, +#endif }; /* -- cgit v1.2.3 From 3394682fba3b9010c6147e94f37633f044876e5e Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sun, 15 Jan 2023 12:23:08 -0500 Subject: SUNRPC: Support the Camellia enctypes RFC 6803 defines two encryption types that use Camellia ciphers (RFC 3713) and CMAC digests. Implement support for those in SunRPC's GSS Kerberos 5 mechanism. There has not been an explicit request to support these enctypes. However, this new set of enctypes provides a good alternative to the AES-SHA1 enctypes that are to be deprecated at some point. As this implementation is still a "beta", the default is to not build it automatically. Tested-by: Scott Mayhew Signed-off-by: Chuck Lever --- include/linux/sunrpc/gss_krb5.h | 4 +++ net/sunrpc/Kconfig | 13 +++++++++ net/sunrpc/auth_gss/gss_krb5_mech.c | 55 +++++++++++++++++++++++++++++++++++++ 3 files changed, 72 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/gss_krb5.h b/include/linux/sunrpc/gss_krb5.h index 8ff397b5c04b..cbb6c8192890 100644 --- a/include/linux/sunrpc/gss_krb5.h +++ b/include/linux/sunrpc/gss_krb5.h @@ -176,6 +176,8 @@ enum seal_alg { #define CKSUMTYPE_HMAC_SHA1_DES3 0x000c #define CKSUMTYPE_HMAC_SHA1_96_AES128 0x000f #define CKSUMTYPE_HMAC_SHA1_96_AES256 0x0010 +#define CKSUMTYPE_CMAC_CAMELLIA128 0x0011 +#define CKSUMTYPE_CMAC_CAMELLIA256 0x0012 #define CKSUMTYPE_HMAC_SHA256_128_AES128 0x0013 #define CKSUMTYPE_HMAC_SHA384_192_AES256 0x0014 #define CKSUMTYPE_HMAC_MD5_ARCFOUR -138 /* Microsoft md5 hmac cksumtype */ @@ -220,6 +222,8 @@ enum seal_alg { #define ENCTYPE_AES256_CTS_HMAC_SHA384_192 0x0014 #define ENCTYPE_ARCFOUR_HMAC 0x0017 #define ENCTYPE_ARCFOUR_HMAC_EXP 0x0018 +#define ENCTYPE_CAMELLIA128_CTS_CMAC 0x0019 +#define ENCTYPE_CAMELLIA256_CTS_CMAC 0x001A #define ENCTYPE_UNKNOWN 0x01ff /* diff --git a/net/sunrpc/Kconfig b/net/sunrpc/Kconfig index 420b40279986..b8e1819a8dd0 100644 --- a/net/sunrpc/Kconfig +++ b/net/sunrpc/Kconfig @@ -80,6 +80,19 @@ config RPCSEC_GSS_KRB5_ENCTYPES_AES_SHA1 SHA-1 digests. These include aes128-cts-hmac-sha1-96 and aes256-cts-hmac-sha1-96. +config RPCSEC_GSS_KRB5_ENCTYPES_CAMELLIA + bool "Enable Kerberos encryption types based on Camellia and CMAC" + depends on RPCSEC_GSS_KRB5 + depends on CRYPTO_CBC && CRYPTO_CTS && CRYPTO_CAMELLIA + depends on CRYPTO_CMAC + default n + select RPCSEC_GSS_KRB5_CRYPTOSYSTEM + help + Choose Y to enable the use of Kerberos 5 encryption types + that utilize Camellia ciphers (RFC 3713) and CMAC digests + (NIST Special Publication 800-38B). These include + camellia128-cts-cmac and camellia256-cts-cmac. + config RPCSEC_GSS_KRB5_ENCTYPES_AES_SHA2 bool "Enable Kerberos enctypes based on AES and SHA-2" depends on RPCSEC_GSS_KRB5 diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c index 97a365608233..4e7cb49a06de 100644 --- a/net/sunrpc/auth_gss/gss_krb5_mech.c +++ b/net/sunrpc/auth_gss/gss_krb5_mech.c @@ -147,6 +147,61 @@ static const struct gss_krb5_enctype supported_gss_krb5_enctypes[] = { }, #endif +#if defined(CONFIG_RPCSEC_GSS_KRB5_ENCTYPES_CAMELLIA) + /* + * Camellia-128 with CMAC (RFC 6803) + */ + { + .etype = ENCTYPE_CAMELLIA128_CTS_CMAC, + .ctype = CKSUMTYPE_CMAC_CAMELLIA128, + .name = "camellia128-cts-cmac", + .encrypt_name = "cts(cbc(camellia))", + .aux_cipher = "cbc(camellia)", + .cksum_name = "cmac(camellia)", + .cksumlength = BITS2OCTETS(128), + .keyed_cksum = 1, + .keylength = BITS2OCTETS(128), + .Kc_length = BITS2OCTETS(128), + .Ke_length = BITS2OCTETS(128), + .Ki_length = BITS2OCTETS(128), + + .import_ctx = gss_krb5_import_ctx_v2, + .encrypt = gss_krb5_aes_encrypt, + .decrypt = gss_krb5_aes_decrypt, + + .get_mic = gss_krb5_get_mic_v2, + .verify_mic = gss_krb5_verify_mic_v2, + .wrap = gss_krb5_wrap_v2, + .unwrap = gss_krb5_unwrap_v2, + }, + /* + * Camellia-256 with CMAC (RFC 6803) + */ + { + .etype = ENCTYPE_CAMELLIA256_CTS_CMAC, + .ctype = CKSUMTYPE_CMAC_CAMELLIA256, + .name = "camellia256-cts-cmac", + .encrypt_name = "cts(cbc(camellia))", + .aux_cipher = "cbc(camellia)", + .cksum_name = "cmac(camellia)", + .cksumlength = BITS2OCTETS(128), + .keyed_cksum = 1, + .keylength = BITS2OCTETS(256), + .Kc_length = BITS2OCTETS(256), + .Ke_length = BITS2OCTETS(256), + .Ki_length = BITS2OCTETS(256), + + .import_ctx = gss_krb5_import_ctx_v2, + .encrypt = gss_krb5_aes_encrypt, + .decrypt = gss_krb5_aes_decrypt, + + .get_mic = gss_krb5_get_mic_v2, + .verify_mic = gss_krb5_verify_mic_v2, + .wrap = gss_krb5_wrap_v2, + .unwrap = gss_krb5_unwrap_v2, + }, +#endif + #if defined(CONFIG_RPCSEC_GSS_KRB5_ENCTYPES_AES_SHA2) /* * AES-128 with SHA-256 (RFC 8009) -- cgit v1.2.3 From 6e460c230d2dfb0e5a02b6e0995546bb4b9d208e Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sun, 15 Jan 2023 12:23:27 -0500 Subject: SUNRPC: Move remaining internal definitions to gss_krb5_internal.h The goal is to leave only protocol-defined items in gss_krb5.h so that it can be easily replaced by a generic header. Implementation specific items are moved to the new internal header. Tested-by: Scott Mayhew Reviewed-by: Simo Sorce Signed-off-by: Chuck Lever --- include/linux/sunrpc/gss_krb5.h | 117 -------------------------------- net/sunrpc/auth_gss/auth_gss.c | 17 +++++ net/sunrpc/auth_gss/gss_krb5_crypto.c | 1 - net/sunrpc/auth_gss/gss_krb5_internal.h | 94 +++++++++++++++++++++++++ 4 files changed, 111 insertions(+), 118 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/gss_krb5.h b/include/linux/sunrpc/gss_krb5.h index cbb6c8192890..78a80bf3fdcb 100644 --- a/include/linux/sunrpc/gss_krb5.h +++ b/include/linux/sunrpc/gss_krb5.h @@ -42,12 +42,6 @@ #include #include -/* - * The RFCs often specify payload lengths in bits. This helper - * converts a specified bit-length to the number of octets/bytes. - */ -#define BITS2OCTETS(x) ((x) / 8) - /* Length of constant used in key derivation */ #define GSS_KRB5_K5CLENGTH (5) @@ -60,74 +54,6 @@ /* Maximum blocksize for the supported crypto algorithms */ #define GSS_KRB5_MAX_BLOCKSIZE (16) -struct krb5_ctx; - -struct gss_krb5_enctype { - const u32 etype; /* encryption (key) type */ - const u32 ctype; /* checksum type */ - const char *name; /* "friendly" name */ - const char *encrypt_name; /* crypto encrypt name */ - const char *aux_cipher; /* aux encrypt cipher name */ - const char *cksum_name; /* crypto checksum name */ - const u16 signalg; /* signing algorithm */ - const u16 sealalg; /* sealing algorithm */ - const u32 cksumlength; /* checksum length */ - const u32 keyed_cksum; /* is it a keyed cksum? */ - const u32 keybytes; /* raw key len, in bytes */ - const u32 keylength; /* protocol key length, in octets */ - const u32 Kc_length; /* checksum subkey length, in octets */ - const u32 Ke_length; /* encryption subkey length, in octets */ - const u32 Ki_length; /* integrity subkey length, in octets */ - - int (*import_ctx)(struct krb5_ctx *ctx, gfp_t gfp_mask); - int (*derive_key)(const struct gss_krb5_enctype *gk5e, - const struct xdr_netobj *in, - struct xdr_netobj *out, - const struct xdr_netobj *label, - gfp_t gfp_mask); - u32 (*encrypt)(struct krb5_ctx *kctx, u32 offset, - struct xdr_buf *buf, struct page **pages); - u32 (*decrypt)(struct krb5_ctx *kctx, u32 offset, u32 len, - struct xdr_buf *buf, u32 *headskip, u32 *tailskip); - u32 (*get_mic)(struct krb5_ctx *kctx, struct xdr_buf *text, - struct xdr_netobj *token); - u32 (*verify_mic)(struct krb5_ctx *kctx, struct xdr_buf *message_buffer, - struct xdr_netobj *read_token); - u32 (*wrap)(struct krb5_ctx *kctx, int offset, - struct xdr_buf *buf, struct page **pages); - u32 (*unwrap)(struct krb5_ctx *kctx, int offset, int len, - struct xdr_buf *buf, unsigned int *slack, - unsigned int *align); -}; - -/* krb5_ctx flags definitions */ -#define KRB5_CTX_FLAG_INITIATOR 0x00000001 -#define KRB5_CTX_FLAG_CFX 0x00000002 -#define KRB5_CTX_FLAG_ACCEPTOR_SUBKEY 0x00000004 - -struct krb5_ctx { - int initiate; /* 1 = initiating, 0 = accepting */ - u32 enctype; - u32 flags; - const struct gss_krb5_enctype *gk5e; /* enctype-specific info */ - struct crypto_sync_skcipher *enc; - struct crypto_sync_skcipher *seq; - struct crypto_sync_skcipher *acceptor_enc; - struct crypto_sync_skcipher *initiator_enc; - struct crypto_sync_skcipher *acceptor_enc_aux; - struct crypto_sync_skcipher *initiator_enc_aux; - struct crypto_ahash *acceptor_sign; - struct crypto_ahash *initiator_sign; - struct crypto_ahash *initiator_integ; - struct crypto_ahash *acceptor_integ; - u8 Ksess[GSS_KRB5_MAX_KEYLEN]; /* session key */ - u8 cksum[GSS_KRB5_MAX_KEYLEN]; - atomic_t seq_send; - atomic64_t seq_send64; - time64_t endtime; - struct xdr_netobj mech_used; -}; - /* The length of the Kerberos GSS token header */ #define GSS_KRB5_TOK_HDR_LEN (16) @@ -245,47 +171,4 @@ enum seal_alg { #define KG_USAGE_INITIATOR_SEAL (24) #define KG_USAGE_INITIATOR_SIGN (25) -/* - * This compile-time check verifies that we will not exceed the - * slack space allotted by the client and server auth_gss code - * before they call gss_wrap(). - */ -#define GSS_KRB5_MAX_SLACK_NEEDED \ - (GSS_KRB5_TOK_HDR_LEN /* gss token header */ \ - + GSS_KRB5_MAX_CKSUM_LEN /* gss token checksum */ \ - + GSS_KRB5_MAX_BLOCKSIZE /* confounder */ \ - + GSS_KRB5_MAX_BLOCKSIZE /* possible padding */ \ - + GSS_KRB5_TOK_HDR_LEN /* encrypted hdr in v2 token */\ - + GSS_KRB5_MAX_CKSUM_LEN /* encryption hmac */ \ - + 4 + 4 /* RPC verifier */ \ - + GSS_KRB5_TOK_HDR_LEN \ - + GSS_KRB5_MAX_CKSUM_LEN) - -u32 -make_checksum(struct krb5_ctx *kctx, char *header, int hdrlen, - struct xdr_buf *body, int body_offset, u8 *cksumkey, - unsigned int usage, struct xdr_netobj *cksumout); - -int -gss_encrypt_xdr_buf(struct crypto_sync_skcipher *tfm, struct xdr_buf *outbuf, - int offset, struct page **pages); - -int -gss_decrypt_xdr_buf(struct crypto_sync_skcipher *tfm, struct xdr_buf *inbuf, - int offset); - -s32 -krb5_make_seq_num(struct krb5_ctx *kctx, - struct crypto_sync_skcipher *key, - int direction, - u32 seqnum, unsigned char *cksum, unsigned char *buf); - -s32 -krb5_get_seq_num(struct krb5_ctx *kctx, - unsigned char *cksum, - unsigned char *buf, int *direction, u32 *seqnum); - -int -xdr_extend_head(struct xdr_buf *buf, unsigned int base, unsigned int shiftlen); - #endif /* _LINUX_SUNRPC_GSS_KRB5_H */ diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 2d7b1e03110a..1af71fbb0d80 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -49,6 +49,22 @@ static unsigned int gss_key_expire_timeo = GSS_KEY_EXPIRE_TIMEO; # define RPCDBG_FACILITY RPCDBG_AUTH #endif +/* + * This compile-time check verifies that we will not exceed the + * slack space allotted by the client and server auth_gss code + * before they call gss_wrap(). + */ +#define GSS_KRB5_MAX_SLACK_NEEDED \ + (GSS_KRB5_TOK_HDR_LEN /* gss token header */ \ + + GSS_KRB5_MAX_CKSUM_LEN /* gss token checksum */ \ + + GSS_KRB5_MAX_BLOCKSIZE /* confounder */ \ + + GSS_KRB5_MAX_BLOCKSIZE /* possible padding */ \ + + GSS_KRB5_TOK_HDR_LEN /* encrypted hdr in v2 token */ \ + + GSS_KRB5_MAX_CKSUM_LEN /* encryption hmac */ \ + + XDR_UNIT * 2 /* RPC verifier */ \ + + GSS_KRB5_TOK_HDR_LEN \ + + GSS_KRB5_MAX_CKSUM_LEN) + #define GSS_CRED_SLACK (RPC_MAX_AUTH_SIZE * 2) /* length of a krb5 verifier (48), plus data added before arguments when * using integrity (two 4-byte integers): */ @@ -1042,6 +1058,7 @@ gss_create_new(const struct rpc_auth_create_args *args, struct rpc_clnt *clnt) goto err_put_mech; auth = &gss_auth->rpc_auth; auth->au_cslack = GSS_CRED_SLACK >> 2; + BUILD_BUG_ON(GSS_KRB5_MAX_SLACK_NEEDED > RPC_MAX_AUTH_SIZE); auth->au_rslack = GSS_KRB5_MAX_SLACK_NEEDED >> 2; auth->au_verfsize = GSS_VERF_SLACK >> 2; auth->au_ralign = GSS_VERF_SLACK >> 2; diff --git a/net/sunrpc/auth_gss/gss_krb5_crypto.c b/net/sunrpc/auth_gss/gss_krb5_crypto.c index 4f29216d414a..5c811b554fd1 100644 --- a/net/sunrpc/auth_gss/gss_krb5_crypto.c +++ b/net/sunrpc/auth_gss/gss_krb5_crypto.c @@ -572,7 +572,6 @@ xdr_extend_head(struct xdr_buf *buf, unsigned int base, unsigned int shiftlen) if (shiftlen == 0) return 0; - BUILD_BUG_ON(GSS_KRB5_MAX_SLACK_NEEDED > RPC_MAX_AUTH_SIZE); BUG_ON(shiftlen > RPC_MAX_AUTH_SIZE); p = buf->head[0].iov_base + base; diff --git a/net/sunrpc/auth_gss/gss_krb5_internal.h b/net/sunrpc/auth_gss/gss_krb5_internal.h index c955e7b76c4d..850748f6733a 100644 --- a/net/sunrpc/auth_gss/gss_krb5_internal.h +++ b/net/sunrpc/auth_gss/gss_krb5_internal.h @@ -8,6 +8,79 @@ #ifndef _NET_SUNRPC_AUTH_GSS_KRB5_INTERNAL_H #define _NET_SUNRPC_AUTH_GSS_KRB5_INTERNAL_H +/* + * The RFCs often specify payload lengths in bits. This helper + * converts a specified bit-length to the number of octets/bytes. + */ +#define BITS2OCTETS(x) ((x) / 8) + +struct krb5_ctx; + +struct gss_krb5_enctype { + const u32 etype; /* encryption (key) type */ + const u32 ctype; /* checksum type */ + const char *name; /* "friendly" name */ + const char *encrypt_name; /* crypto encrypt name */ + const char *aux_cipher; /* aux encrypt cipher name */ + const char *cksum_name; /* crypto checksum name */ + const u16 signalg; /* signing algorithm */ + const u16 sealalg; /* sealing algorithm */ + const u32 cksumlength; /* checksum length */ + const u32 keyed_cksum; /* is it a keyed cksum? */ + const u32 keybytes; /* raw key len, in bytes */ + const u32 keylength; /* protocol key length, in octets */ + const u32 Kc_length; /* checksum subkey length, in octets */ + const u32 Ke_length; /* encryption subkey length, in octets */ + const u32 Ki_length; /* integrity subkey length, in octets */ + + int (*import_ctx)(struct krb5_ctx *ctx, gfp_t gfp_mask); + int (*derive_key)(const struct gss_krb5_enctype *gk5e, + const struct xdr_netobj *in, + struct xdr_netobj *out, + const struct xdr_netobj *label, + gfp_t gfp_mask); + u32 (*encrypt)(struct krb5_ctx *kctx, u32 offset, + struct xdr_buf *buf, struct page **pages); + u32 (*decrypt)(struct krb5_ctx *kctx, u32 offset, u32 len, + struct xdr_buf *buf, u32 *headskip, u32 *tailskip); + u32 (*get_mic)(struct krb5_ctx *kctx, struct xdr_buf *text, + struct xdr_netobj *token); + u32 (*verify_mic)(struct krb5_ctx *kctx, struct xdr_buf *message_buffer, + struct xdr_netobj *read_token); + u32 (*wrap)(struct krb5_ctx *kctx, int offset, + struct xdr_buf *buf, struct page **pages); + u32 (*unwrap)(struct krb5_ctx *kctx, int offset, int len, + struct xdr_buf *buf, unsigned int *slack, + unsigned int *align); +}; + +/* krb5_ctx flags definitions */ +#define KRB5_CTX_FLAG_INITIATOR 0x00000001 +#define KRB5_CTX_FLAG_ACCEPTOR_SUBKEY 0x00000004 + +struct krb5_ctx { + int initiate; /* 1 = initiating, 0 = accepting */ + u32 enctype; + u32 flags; + const struct gss_krb5_enctype *gk5e; /* enctype-specific info */ + struct crypto_sync_skcipher *enc; + struct crypto_sync_skcipher *seq; + struct crypto_sync_skcipher *acceptor_enc; + struct crypto_sync_skcipher *initiator_enc; + struct crypto_sync_skcipher *acceptor_enc_aux; + struct crypto_sync_skcipher *initiator_enc_aux; + struct crypto_ahash *acceptor_sign; + struct crypto_ahash *initiator_sign; + struct crypto_ahash *initiator_integ; + struct crypto_ahash *acceptor_integ; + u8 Ksess[GSS_KRB5_MAX_KEYLEN]; /* session key */ + u8 cksum[GSS_KRB5_MAX_KEYLEN]; + atomic_t seq_send; + atomic64_t seq_send64; + time64_t endtime; + struct xdr_netobj mech_used; +}; + /* * GSS Kerberos 5 mechanism Per-Message calls. */ @@ -96,8 +169,19 @@ static inline int krb5_derive_key(struct krb5_ctx *kctx, return gk5e->derive_key(gk5e, inkey, outkey, &label, gfp_mask); } +s32 krb5_make_seq_num(struct krb5_ctx *kctx, struct crypto_sync_skcipher *key, + int direction, u32 seqnum, unsigned char *cksum, + unsigned char *buf); + +s32 krb5_get_seq_num(struct krb5_ctx *kctx, unsigned char *cksum, + unsigned char *buf, int *direction, u32 *seqnum); + void krb5_make_confounder(u8 *p, int conflen); +u32 make_checksum(struct krb5_ctx *kctx, char *header, int hdrlen, + struct xdr_buf *body, int body_offset, u8 *cksumkey, + unsigned int usage, struct xdr_netobj *cksumout); + u32 gss_krb5_checksum(struct crypto_ahash *tfm, char *header, int hdrlen, const struct xdr_buf *body, int body_offset, struct xdr_netobj *cksumout); @@ -108,6 +192,16 @@ u32 krb5_encrypt(struct crypto_sync_skcipher *key, void *iv, void *in, u32 krb5_decrypt(struct crypto_sync_skcipher *key, void *iv, void *in, void *out, int length); +int xdr_extend_head(struct xdr_buf *buf, unsigned int base, + unsigned int shiftlen); + +int gss_encrypt_xdr_buf(struct crypto_sync_skcipher *tfm, + struct xdr_buf *outbuf, int offset, + struct page **pages); + +int gss_decrypt_xdr_buf(struct crypto_sync_skcipher *tfm, + struct xdr_buf *inbuf, int offset); + u32 gss_krb5_aes_encrypt(struct krb5_ctx *kctx, u32 offset, struct xdr_buf *buf, struct page **pages); -- cgit v1.2.3 From 319951eba0fc412a78a8fe3d2ee5e143cc318c14 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 24 Jan 2023 15:40:22 -0500 Subject: SUNRPC: Remove ->xpo_secure_port() There's no need for the cost of this extra virtual function call during every RPC transaction: the RQ_SECURE bit can be set properly in ->xpo_recvfrom() instead. Reviewed-by: Jeff Layton Signed-off-by: Chuck Lever --- include/linux/sunrpc/svc_xprt.h | 1 - net/sunrpc/svc_xprt.c | 1 - net/sunrpc/svcsock.c | 4 ++-- net/sunrpc/xprtrdma/svc_rdma_recvfrom.c | 1 + net/sunrpc/xprtrdma/svc_rdma_transport.c | 7 ------- 5 files changed, 3 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index d42a75b3be10..775368802762 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -26,7 +26,6 @@ struct svc_xprt_ops { void (*xpo_release_rqst)(struct svc_rqst *); void (*xpo_detach)(struct svc_xprt *); void (*xpo_free)(struct svc_xprt *); - void (*xpo_secure_port)(struct svc_rqst *rqstp); void (*xpo_kill_temp_xprt)(struct svc_xprt *); void (*xpo_start_tls)(struct svc_xprt *); }; diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 1574a9429d07..ba629297da4e 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -886,7 +886,6 @@ int svc_recv(struct svc_rqst *rqstp, long timeout) clear_bit(XPT_OLD, &xprt->xpt_flags); - xprt->xpt_ops->xpo_secure_port(rqstp); rqstp->rq_chandle.defer = svc_defer; if (serv->sv_stats) diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 815baf308236..81bdcb6f73bb 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -508,6 +508,7 @@ static int svc_udp_recvfrom(struct svc_rqst *rqstp) if (serv->sv_stats) serv->sv_stats->netudpcnt++; + svc_sock_secure_port(rqstp); svc_xprt_received(rqstp->rq_xprt); return len; @@ -636,7 +637,6 @@ static const struct svc_xprt_ops svc_udp_ops = { .xpo_free = svc_sock_free, .xpo_has_wspace = svc_udp_has_wspace, .xpo_accept = svc_udp_accept, - .xpo_secure_port = svc_sock_secure_port, .xpo_kill_temp_xprt = svc_udp_kill_temp_xprt, }; @@ -1028,6 +1028,7 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp) if (serv->sv_stats) serv->sv_stats->nettcpcnt++; + svc_sock_secure_port(rqstp); svc_xprt_received(rqstp->rq_xprt); return rqstp->rq_arg.len; @@ -1209,7 +1210,6 @@ static const struct svc_xprt_ops svc_tcp_ops = { .xpo_free = svc_sock_free, .xpo_has_wspace = svc_tcp_has_wspace, .xpo_accept = svc_tcp_accept, - .xpo_secure_port = svc_sock_secure_port, .xpo_kill_temp_xprt = svc_tcp_kill_temp_xprt, }; diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index 5242ad121450..1c658fa43063 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -847,6 +847,7 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp) rqstp->rq_xprt_ctxt = ctxt; rqstp->rq_prot = IPPROTO_MAX; svc_xprt_copy_addrs(rqstp, xprt); + set_bit(RQ_SECURE, &rqstp->rq_flags); return rqstp->rq_arg.len; out_err: diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index 94b20fb47135..416b298f74dd 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -73,7 +73,6 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt); static void svc_rdma_detach(struct svc_xprt *xprt); static void svc_rdma_free(struct svc_xprt *xprt); static int svc_rdma_has_wspace(struct svc_xprt *xprt); -static void svc_rdma_secure_port(struct svc_rqst *); static void svc_rdma_kill_temp_xprt(struct svc_xprt *); static const struct svc_xprt_ops svc_rdma_ops = { @@ -86,7 +85,6 @@ static const struct svc_xprt_ops svc_rdma_ops = { .xpo_free = svc_rdma_free, .xpo_has_wspace = svc_rdma_has_wspace, .xpo_accept = svc_rdma_accept, - .xpo_secure_port = svc_rdma_secure_port, .xpo_kill_temp_xprt = svc_rdma_kill_temp_xprt, }; @@ -600,11 +598,6 @@ static int svc_rdma_has_wspace(struct svc_xprt *xprt) return 1; } -static void svc_rdma_secure_port(struct svc_rqst *rqstp) -{ - set_bit(RQ_SECURE, &rqstp->rq_flags); -} - static void svc_rdma_kill_temp_xprt(struct svc_xprt *xprt) { } -- cgit v1.2.3 From 225a05043cd87a37455bfbff8c35d4e276519387 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox (Oracle) Date: Wed, 8 Feb 2023 14:56:11 +0000 Subject: filemap: Remove lock_page_killable() There are no more callers; remove this function before any more appear. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: David Howells Signed-off-by: Steve French --- include/linux/pagemap.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 29e1f9e76eb6..2f5b36f446cc 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -977,16 +977,6 @@ static inline int folio_lock_killable(struct folio *folio) return 0; } -/* - * lock_page_killable is like lock_page but can be interrupted by fatal - * signals. It returns 0 if it locked the page and -EINTR if it was - * killed while waiting. - */ -static inline int lock_page_killable(struct page *page) -{ - return folio_lock_killable(page_folio(page)); -} - /* * folio_lock_or_retry - Lock the folio, unless this would block and the * caller indicated that it can handle a retry. -- cgit v1.2.3 From 9747b9e92418b61c2281561e0651803f1fad0159 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Wed, 15 Feb 2023 18:39:36 +0800 Subject: mm: hugetlb: change to return bool for isolate_hugetlb() Now the isolate_hugetlb() only returns 0 or -EBUSY, and most users did not care about the negative value, thus we can convert the isolate_hugetlb() to return a boolean value to make code more clear when checking the hugetlb isolation state. Moreover converts 2 users which will consider the negative value returned by isolate_hugetlb(). No functional changes intended. [akpm@linux-foundation.org: shorten locked section, per SeongJae Park] Link: https://lkml.kernel.org/r/12a287c5bebc13df304387087bbecc6421510849.1676424378.git.baolin.wang@linux.alibaba.com Signed-off-by: Baolin Wang Acked-by: David Hildenbrand Reviewed-by: Matthew Wilcox (Oracle) Reviewed-by: Mike Kravetz Acked-by: Linus Torvalds Reviewed-by: SeongJae Park Signed-off-by: Andrew Morton --- include/linux/hugetlb.h | 6 +++--- mm/hugetlb.c | 13 ++++++++----- mm/memory-failure.c | 2 +- mm/mempolicy.c | 2 +- mm/migrate.c | 7 +++---- 5 files changed, 16 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index df6dd624ccfe..5f5e4177b2e0 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -171,7 +171,7 @@ bool hugetlb_reserve_pages(struct inode *inode, long from, long to, vm_flags_t vm_flags); long hugetlb_unreserve_pages(struct inode *inode, long start, long end, long freed); -int isolate_hugetlb(struct folio *folio, struct list_head *list); +bool isolate_hugetlb(struct folio *folio, struct list_head *list); int get_hwpoison_hugetlb_folio(struct folio *folio, bool *hugetlb, bool unpoison); int get_huge_page_for_hwpoison(unsigned long pfn, int flags, bool *migratable_cleared); @@ -413,9 +413,9 @@ static inline pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, return NULL; } -static inline int isolate_hugetlb(struct folio *folio, struct list_head *list) +static inline bool isolate_hugetlb(struct folio *folio, struct list_head *list) { - return -EBUSY; + return false; } static inline int get_hwpoison_hugetlb_folio(struct folio *folio, bool *hugetlb, bool unpoison) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 3a01a9dbf445..07abcb6eb203 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2925,12 +2925,15 @@ retry: */ goto free_new; } else if (folio_ref_count(old_folio)) { + bool isolated; + /* * Someone has grabbed the folio, try to isolate it here. * Fail with -EBUSY if not possible. */ spin_unlock_irq(&hugetlb_lock); - ret = isolate_hugetlb(old_folio, list); + isolated = isolate_hugetlb(old_folio, list); + ret = isolated ? 0 : -EBUSY; spin_lock_irq(&hugetlb_lock); goto free_new; } else if (!folio_test_hugetlb_freed(old_folio)) { @@ -3005,7 +3008,7 @@ int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list) if (hstate_is_gigantic(h)) return -ENOMEM; - if (folio_ref_count(folio) && !isolate_hugetlb(folio, list)) + if (folio_ref_count(folio) && isolate_hugetlb(folio, list)) ret = 0; else if (!folio_ref_count(folio)) ret = alloc_and_dissolve_hugetlb_folio(h, folio, list); @@ -7251,15 +7254,15 @@ __weak unsigned long hugetlb_mask_last_page(struct hstate *h) * These functions are overwritable if your architecture needs its own * behavior. */ -int isolate_hugetlb(struct folio *folio, struct list_head *list) +bool isolate_hugetlb(struct folio *folio, struct list_head *list) { - int ret = 0; + bool ret = true; spin_lock_irq(&hugetlb_lock); if (!folio_test_hugetlb(folio) || !folio_test_hugetlb_migratable(folio) || !folio_try_get(folio)) { - ret = -EBUSY; + ret = false; goto unlock; } folio_clear_hugetlb_migratable(folio); diff --git a/mm/memory-failure.c b/mm/memory-failure.c index e504362fdb23..8604753bc644 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -2508,7 +2508,7 @@ static bool isolate_page(struct page *page, struct list_head *pagelist) bool isolated = false; if (PageHuge(page)) { - isolated = !isolate_hugetlb(page_folio(page), pagelist); + isolated = isolate_hugetlb(page_folio(page), pagelist); } else { bool lru = !__PageMovable(page); diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 2751bc3310fd..a256a241fd1d 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -609,7 +609,7 @@ static int queue_folios_hugetlb(pte_t *pte, unsigned long hmask, if (flags & (MPOL_MF_MOVE_ALL) || (flags & MPOL_MF_MOVE && folio_estimated_sharers(folio) == 1 && !hugetlb_pmd_shared(pte))) { - if (isolate_hugetlb(folio, qp->pagelist) && + if (!isolate_hugetlb(folio, qp->pagelist) && (flags & MPOL_MF_STRICT)) /* * Failed to isolate folio but allow migrating pages diff --git a/mm/migrate.c b/mm/migrate.c index 53010a142e7f..2db546a0618c 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -2095,6 +2095,7 @@ static int add_page_for_migration(struct mm_struct *mm, unsigned long addr, struct vm_area_struct *vma; struct page *page; int err; + bool isolated; mmap_read_lock(mm); err = -EFAULT; @@ -2126,13 +2127,11 @@ static int add_page_for_migration(struct mm_struct *mm, unsigned long addr, if (PageHuge(page)) { if (PageHead(page)) { - err = isolate_hugetlb(page_folio(page), pagelist); - if (!err) - err = 1; + isolated = isolate_hugetlb(page_folio(page), pagelist); + err = isolated ? 1 : -EBUSY; } } else { struct page *head; - bool isolated; head = compound_head(page); isolated = isolate_lru_page(head); -- cgit v1.2.3 From cd7755800eb54e8522f5e51f4e71e6494c1f1572 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Wed, 15 Feb 2023 18:39:37 +0800 Subject: mm: change to return bool for isolate_movable_page() Now the isolate_movable_page() can only return 0 or -EBUSY, and no users will care about the negative return value, thus we can convert the isolate_movable_page() to return a boolean value to make the code more clear when checking the movable page isolation state. No functional changes intended. [akpm@linux-foundation.org: remove unneeded comment, per Matthew] Link: https://lkml.kernel.org/r/cb877f73f4fff8d309611082ec740a7065b1ade0.1676424378.git.baolin.wang@linux.alibaba.com Signed-off-by: Baolin Wang Acked-by: David Hildenbrand Reviewed-by: Matthew Wilcox (Oracle) Acked-by: Linus Torvalds Reviewed-by: SeongJae Park Signed-off-by: Andrew Morton --- include/linux/migrate.h | 6 +++--- mm/compaction.c | 2 +- mm/memory-failure.c | 4 ++-- mm/memory_hotplug.c | 10 +++++----- mm/migrate.c | 6 +++--- 5 files changed, 14 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/migrate.h b/include/linux/migrate.h index c88b96b48be7..6b252f519c86 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -71,7 +71,7 @@ extern int migrate_pages(struct list_head *l, new_page_t new, free_page_t free, unsigned long private, enum migrate_mode mode, int reason, unsigned int *ret_succeeded); extern struct page *alloc_migration_target(struct page *page, unsigned long private); -extern int isolate_movable_page(struct page *page, isolate_mode_t mode); +extern bool isolate_movable_page(struct page *page, isolate_mode_t mode); int migrate_huge_page_move_mapping(struct address_space *mapping, struct folio *dst, struct folio *src); @@ -92,8 +92,8 @@ static inline int migrate_pages(struct list_head *l, new_page_t new, static inline struct page *alloc_migration_target(struct page *page, unsigned long private) { return NULL; } -static inline int isolate_movable_page(struct page *page, isolate_mode_t mode) - { return -EBUSY; } +static inline bool isolate_movable_page(struct page *page, isolate_mode_t mode) + { return false; } static inline int migrate_huge_page_move_mapping(struct address_space *mapping, struct folio *dst, struct folio *src) diff --git a/mm/compaction.c b/mm/compaction.c index d73578af44cc..ad7409f70519 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -976,7 +976,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, locked = NULL; } - if (!isolate_movable_page(page, mode)) + if (isolate_movable_page(page, mode)) goto isolate_success; } diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 8604753bc644..a1ede7bdce95 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -2515,8 +2515,8 @@ static bool isolate_page(struct page *page, struct list_head *pagelist) if (lru) isolated = isolate_lru_page(page); else - isolated = !isolate_movable_page(page, - ISOLATE_UNEVICTABLE); + isolated = isolate_movable_page(page, + ISOLATE_UNEVICTABLE); if (isolated) { list_add(&page->lru, pagelist); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 5fc2dcf4e3ab..5f73fd894b89 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1668,18 +1668,18 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) * We can skip free pages. And we can deal with pages on * LRU and non-lru movable pages. */ - if (PageLRU(page)) { + if (PageLRU(page)) isolated = isolate_lru_page(page); - ret = isolated ? 0 : -EBUSY; - } else - ret = isolate_movable_page(page, ISOLATE_UNEVICTABLE); - if (!ret) { /* Success */ + else + isolated = isolate_movable_page(page, ISOLATE_UNEVICTABLE); + if (isolated) { list_add_tail(&page->lru, &source); if (!__PageMovable(page)) inc_node_page_state(page, NR_ISOLATED_ANON + page_is_file_lru(page)); } else { + ret = -EBUSY; if (__ratelimit(&migrate_rs)) { pr_warn("failed to isolate pfn %lx\n", pfn); dump_page(page, "isolation failed"); diff --git a/mm/migrate.c b/mm/migrate.c index 2db546a0618c..9a101c7bb8ff 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -58,7 +58,7 @@ #include "internal.h" -int isolate_movable_page(struct page *page, isolate_mode_t mode) +bool isolate_movable_page(struct page *page, isolate_mode_t mode) { struct folio *folio = folio_get_nontail_page(page); const struct movable_operations *mops; @@ -119,14 +119,14 @@ int isolate_movable_page(struct page *page, isolate_mode_t mode) folio_set_isolated(folio); folio_unlock(folio); - return 0; + return true; out_no_isolated: folio_unlock(folio); out_putfolio: folio_put(folio); out: - return -EBUSY; + return false; } static void putback_movable_folio(struct folio *folio) -- cgit v1.2.3 From f9366f4c2a29d14f5992b195e268240c2deb116e Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Thu, 16 Feb 2023 14:44:24 -0800 Subject: include/linux/migrate.h: remove unneeded externs As suggested by Matthew. Suggested-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- include/linux/migrate.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 6b252f519c86..6241a1596a75 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -62,16 +62,16 @@ extern const char *migrate_reason_names[MR_TYPES]; #ifdef CONFIG_MIGRATION -extern void putback_movable_pages(struct list_head *l); +void putback_movable_pages(struct list_head *l); int migrate_folio_extra(struct address_space *mapping, struct folio *dst, struct folio *src, enum migrate_mode mode, int extra_count); int migrate_folio(struct address_space *mapping, struct folio *dst, struct folio *src, enum migrate_mode mode); -extern int migrate_pages(struct list_head *l, new_page_t new, free_page_t free, - unsigned long private, enum migrate_mode mode, int reason, - unsigned int *ret_succeeded); -extern struct page *alloc_migration_target(struct page *page, unsigned long private); -extern bool isolate_movable_page(struct page *page, isolate_mode_t mode); +int migrate_pages(struct list_head *l, new_page_t new, free_page_t free, + unsigned long private, enum migrate_mode mode, int reason, + unsigned int *ret_succeeded); +struct page *alloc_migration_target(struct page *page, unsigned long private); +bool isolate_movable_page(struct page *page, isolate_mode_t mode); int migrate_huge_page_move_mapping(struct address_space *mapping, struct folio *dst, struct folio *src); @@ -142,8 +142,8 @@ const struct movable_operations *page_movable_ops(struct page *page) } #ifdef CONFIG_NUMA_BALANCING -extern int migrate_misplaced_page(struct page *page, - struct vm_area_struct *vma, int node); +int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, + int node); #else static inline int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, int node) -- cgit v1.2.3 From d9194e009efef9613f48022f3c885191c48120f9 Mon Sep 17 00:00:00 2001 From: Frank Rowand Date: Mon, 13 Feb 2023 12:57:02 -0600 Subject: of: dynamic: add lifecycle docbook info to node creation functions The existing docbook comments for the functions related to creating a devicetree node do not explain the reference count of a newly created node, how decrementing the reference count to zero will free the associated memory, and the caller's responsibility to call of_node_put() on the node. Explain what happens when the reference count is decremented to zero. Signed-off-by: Frank Rowand Link: https://lore.kernel.org/r/20230213185702.395776-8-frowand.list@gmail.com Signed-off-by: Rob Herring --- drivers/of/dynamic.c | 3 ++- include/linux/of.h | 11 +++++++++++ 2 files changed, 13 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/of/dynamic.c b/drivers/of/dynamic.c index 657a65006056..12aa99018969 100644 --- a/drivers/of/dynamic.c +++ b/drivers/of/dynamic.c @@ -443,7 +443,8 @@ struct property *__of_prop_dup(const struct property *prop, gfp_t allocflags) * another node. The node data are dynamically allocated and all the node * flags have the OF_DYNAMIC & OF_DETACHED bits set. * - * Return: The newly allocated node or NULL on out of memory error. + * Return: The newly allocated node or NULL on out of memory error. Use + * of_node_put() on it when done to free the memory allocated for it. */ struct device_node *__of_node_dup(const struct device_node *np, const char *full_name) diff --git a/include/linux/of.h b/include/linux/of.h index 37afd04f36eb..1cb659e682f5 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -100,6 +100,17 @@ struct of_reconfig_data { struct property *old_prop; }; +/** + * of_node_init - initialize a devicetree node + * @node: Pointer to device node that has been created by kzalloc() + * @phandle_name: Name of property holding a phandle value + * + * On return the device_node refcount is set to one. Use of_node_put() + * on @node when done to free the memory allocated for it. If the node + * is NOT a dynamic node the memory will not be freed. The decision of + * whether to free the memory will be done by node->release(), which is + * of_node_release(). + */ /* initialize a node */ extern const struct kobj_type of_node_ktype; extern const struct fwnode_operations of_fwnode_ops; -- cgit v1.2.3 From 07073eb01c5f630344bc1c3e56b0e0d94aedf919 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 14 Feb 2023 15:01:42 +0000 Subject: splice: Add a func to do a splice from a buffered file without ITER_PIPE Provide a function to do splice read from a buffered file, pulling the folios out of the pagecache directly by calling filemap_get_pages() to do any required reading and then pasting the returned folios into the pipe. A helper function is provided to do the actual folio pasting and will handle multipage folios by splicing as many of the relevant subpages as will fit into the pipe. The code is loosely based on filemap_read() and might belong in mm/filemap.c with that as it needs to use filemap_get_pages(). Signed-off-by: David Howells Reviewed-by: Jens Axboe cc: Christoph Hellwig cc: Al Viro cc: David Hildenbrand cc: John Hubbard cc: linux-mm@kvack.org cc: linux-block@vger.kernel.org cc: linux-fsdevel@vger.kernel.org Signed-off-by: Steve French --- include/linux/fs.h | 3 ++ include/linux/pipe_fs_i.h | 20 +++++++ lib/iov_iter.c | 6 --- mm/filemap.c | 129 ++++++++++++++++++++++++++++++++++++++++++++++ mm/internal.h | 6 +++ 5 files changed, 158 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index c1769a2c5d70..28743e38df91 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3163,6 +3163,9 @@ ssize_t vfs_iocb_iter_write(struct file *file, struct kiocb *iocb, struct iov_iter *iter); /* fs/splice.c */ +ssize_t filemap_splice_read(struct file *in, loff_t *ppos, + struct pipe_inode_info *pipe, + size_t len, unsigned int flags); extern ssize_t generic_file_splice_read(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int); extern ssize_t iter_file_splice_write(struct pipe_inode_info *, diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index 6cb65df3e3ba..d2c3f16cf6b1 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -156,6 +156,26 @@ static inline bool pipe_full(unsigned int head, unsigned int tail, return pipe_occupancy(head, tail) >= limit; } +/** + * pipe_buf - Return the pipe buffer for the specified slot in the pipe ring + * @pipe: The pipe to access + * @slot: The slot of interest + */ +static inline struct pipe_buffer *pipe_buf(const struct pipe_inode_info *pipe, + unsigned int slot) +{ + return &pipe->bufs[slot & (pipe->ring_size - 1)]; +} + +/** + * pipe_head_buf - Return the pipe buffer at the head of the pipe ring + * @pipe: The pipe to access + */ +static inline struct pipe_buffer *pipe_head_buf(const struct pipe_inode_info *pipe) +{ + return pipe_buf(pipe, pipe->head); +} + /** * pipe_buf_get - get a reference to a pipe_buffer * @pipe: the pipe that the buffer belongs to diff --git a/lib/iov_iter.c b/lib/iov_iter.c index f9a3ff37ecd1..47c484551c59 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -186,12 +186,6 @@ static int copyin(void *to, const void __user *from, size_t n) return res; } -static inline struct pipe_buffer *pipe_buf(const struct pipe_inode_info *pipe, - unsigned int slot) -{ - return &pipe->bufs[slot & (pipe->ring_size - 1)]; -} - #ifdef PIPE_PARANOIA static bool sanity(const struct iov_iter *i) { diff --git a/mm/filemap.c b/mm/filemap.c index 2d5377012284..162b4daaeb99 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -42,6 +42,8 @@ #include #include #include +#include +#include #include #include #include "internal.h" @@ -2843,6 +2845,133 @@ generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) } EXPORT_SYMBOL(generic_file_read_iter); +/* + * Splice subpages from a folio into a pipe. + */ +size_t splice_folio_into_pipe(struct pipe_inode_info *pipe, + struct folio *folio, loff_t fpos, size_t size) +{ + struct page *page; + size_t spliced = 0, offset = offset_in_folio(folio, fpos); + + page = folio_page(folio, offset / PAGE_SIZE); + size = min(size, folio_size(folio) - offset); + offset %= PAGE_SIZE; + + while (spliced < size && + !pipe_full(pipe->head, pipe->tail, pipe->max_usage)) { + struct pipe_buffer *buf = pipe_head_buf(pipe); + size_t part = min_t(size_t, PAGE_SIZE - offset, size - spliced); + + *buf = (struct pipe_buffer) { + .ops = &page_cache_pipe_buf_ops, + .page = page, + .offset = offset, + .len = part, + }; + folio_get(folio); + pipe->head++; + page++; + spliced += part; + offset = 0; + } + + return spliced; +} + +/* + * Splice folios from the pagecache of a buffered (ie. non-O_DIRECT) file into + * a pipe. + */ +ssize_t filemap_splice_read(struct file *in, loff_t *ppos, + struct pipe_inode_info *pipe, + size_t len, unsigned int flags) +{ + struct folio_batch fbatch; + struct kiocb iocb; + size_t total_spliced = 0, used, npages; + loff_t isize, end_offset; + bool writably_mapped; + int i, error = 0; + + init_sync_kiocb(&iocb, in); + iocb.ki_pos = *ppos; + + /* Work out how much data we can actually add into the pipe */ + used = pipe_occupancy(pipe->head, pipe->tail); + npages = max_t(ssize_t, pipe->max_usage - used, 0); + len = min_t(size_t, len, npages * PAGE_SIZE); + + folio_batch_init(&fbatch); + + do { + cond_resched(); + + if (*ppos >= i_size_read(file_inode(in))) + break; + + iocb.ki_pos = *ppos; + error = filemap_get_pages(&iocb, len, &fbatch, true); + if (error < 0) + break; + + /* + * i_size must be checked after we know the pages are Uptodate. + * + * Checking i_size after the check allows us to calculate + * the correct value for "nr", which means the zero-filled + * part of the page is not copied back to userspace (unless + * another truncate extends the file - this is desired though). + */ + isize = i_size_read(file_inode(in)); + if (unlikely(*ppos >= isize)) + break; + end_offset = min_t(loff_t, isize, *ppos + len); + + /* + * Once we start copying data, we don't want to be touching any + * cachelines that might be contended: + */ + writably_mapped = mapping_writably_mapped(in->f_mapping); + + for (i = 0; i < folio_batch_count(&fbatch); i++) { + struct folio *folio = fbatch.folios[i]; + size_t n; + + if (folio_pos(folio) >= end_offset) + goto out; + folio_mark_accessed(folio); + + /* + * If users can be writing to this folio using arbitrary + * virtual addresses, take care of potential aliasing + * before reading the folio on the kernel side. + */ + if (writably_mapped) + flush_dcache_folio(folio); + + n = min_t(loff_t, len, isize - *ppos); + n = splice_folio_into_pipe(pipe, folio, *ppos, n); + if (!n) + goto out; + len -= n; + total_spliced += n; + *ppos += n; + in->f_ra.prev_pos = *ppos; + if (pipe_full(pipe->head, pipe->tail, pipe->max_usage)) + goto out; + } + + folio_batch_release(&fbatch); + } while (len); + +out: + folio_batch_release(&fbatch); + file_accessed(in); + + return total_spliced ? total_spliced : error; +} + static inline loff_t folio_seek_hole_data(struct xa_state *xas, struct address_space *mapping, struct folio *folio, loff_t start, loff_t end, bool seek_data) diff --git a/mm/internal.h b/mm/internal.h index bcf75a8b032d..6d4ca98f3844 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -794,6 +794,12 @@ struct migration_target_control { gfp_t gfp_mask; }; +/* + * mm/filemap.c + */ +size_t splice_folio_into_pipe(struct pipe_inode_info *pipe, + struct folio *folio, loff_t fpos, size_t size); + /* * mm/vmalloc.c */ -- cgit v1.2.3 From 33b3b041543e8b3abf9a692d0f8c2ab0e07c50cd Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 7 Feb 2023 10:45:40 +0000 Subject: splice: Add a func to do a splice from an O_DIRECT file without ITER_PIPE Implement a function, direct_file_splice(), that deals with this by using an ITER_BVEC iterator instead of an ITER_PIPE iterator as the former won't free its buffers when reverted. The function bulk allocates all the buffers it thinks it is going to use in advance, does the read synchronously and only then trims the buffer down. The pages we did use get pushed into the pipe. This fixes a problem with the upcoming iov_iter_extract_pages() function, whereby pages extracted from a non-user-backed iterator such as ITER_PIPE aren't pinned. __iomap_dio_rw(), however, calls iov_iter_revert() to shorten the iterator to just the bufferage it is going to use - which has the side-effect of freeing the excess pipe buffers, even though they're attached to a bio and may get written to by DMA (thanks to Hillf Danton for spotting this[1]). This then causes memory corruption that is particularly noticeable when the syzbot test[2] is run. The test boils down to: out = creat(argv[1], 0666); ftruncate(out, 0x800); lseek(out, 0x200, SEEK_SET); in = open(argv[1], O_RDONLY | O_DIRECT | O_NOFOLLOW); sendfile(out, in, NULL, 0x1dd00); run repeatedly in parallel. What I think is happening is that ftruncate() occasionally shortens the DIO read that's about to be made by sendfile's splice core by reducing i_size. This should be more efficient for DIO read by virtue of doing a bulk page allocation, but slightly less efficient by ignoring any partial page in the pipe. Reported-by: syzbot+a440341a59e3b7142895@syzkaller.appspotmail.com Signed-off-by: David Howells Reviewed-by: Jens Axboe cc: Christoph Hellwig cc: Al Viro cc: David Hildenbrand cc: John Hubbard cc: linux-mm@kvack.org cc: linux-block@vger.kernel.org cc: linux-fsdevel@vger.kernel.org Link: https://lore.kernel.org/r/20230207094731.1390-1-hdanton@sina.com/ [1] Link: https://lore.kernel.org/r/000000000000b0b3c005f3a09383@google.com/ [2] Signed-off-by: Steve French --- fs/splice.c | 92 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/fs.h | 3 ++ 2 files changed, 95 insertions(+) (limited to 'include/linux') diff --git a/fs/splice.c b/fs/splice.c index 5969b7a1d353..4c6332854b63 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -282,6 +282,98 @@ void splice_shrink_spd(struct splice_pipe_desc *spd) kfree(spd->partial); } +/* + * Splice data from an O_DIRECT file into pages and then add them to the output + * pipe. + */ +ssize_t direct_splice_read(struct file *in, loff_t *ppos, + struct pipe_inode_info *pipe, + size_t len, unsigned int flags) +{ + struct iov_iter to; + struct bio_vec *bv; + struct kiocb kiocb; + struct page **pages; + ssize_t ret; + size_t used, npages, chunk, remain, reclaim; + int i; + + /* Work out how much data we can actually add into the pipe */ + used = pipe_occupancy(pipe->head, pipe->tail); + npages = max_t(ssize_t, pipe->max_usage - used, 0); + len = min_t(size_t, len, npages * PAGE_SIZE); + npages = DIV_ROUND_UP(len, PAGE_SIZE); + + bv = kzalloc(array_size(npages, sizeof(bv[0])) + + array_size(npages, sizeof(struct page *)), GFP_KERNEL); + if (!bv) + return -ENOMEM; + + pages = (void *)(bv + npages); + npages = alloc_pages_bulk_array(GFP_USER, npages, pages); + if (!npages) { + kfree(bv); + return -ENOMEM; + } + + remain = len = min_t(size_t, len, npages * PAGE_SIZE); + + for (i = 0; i < npages; i++) { + chunk = min_t(size_t, PAGE_SIZE, remain); + bv[i].bv_page = pages[i]; + bv[i].bv_offset = 0; + bv[i].bv_len = chunk; + remain -= chunk; + } + + /* Do the I/O */ + iov_iter_bvec(&to, ITER_DEST, bv, npages, len); + init_sync_kiocb(&kiocb, in); + kiocb.ki_pos = *ppos; + ret = call_read_iter(in, &kiocb, &to); + + reclaim = npages * PAGE_SIZE; + remain = 0; + if (ret > 0) { + reclaim -= ret; + remain = ret; + *ppos = kiocb.ki_pos; + file_accessed(in); + } else if (ret < 0) { + /* + * callers of ->splice_read() expect -EAGAIN on + * "can't put anything in there", rather than -EFAULT. + */ + if (ret == -EFAULT) + ret = -EAGAIN; + } + + /* Free any pages that didn't get touched at all. */ + reclaim /= PAGE_SIZE; + if (reclaim) { + npages -= reclaim; + release_pages(pages + npages, reclaim); + } + + /* Push the remaining pages into the pipe. */ + for (i = 0; i < npages; i++) { + struct pipe_buffer *buf = pipe_head_buf(pipe); + + chunk = min_t(size_t, remain, PAGE_SIZE); + *buf = (struct pipe_buffer) { + .ops = &default_pipe_buf_ops, + .page = bv[i].bv_page, + .offset = 0, + .len = chunk, + }; + pipe->head++; + remain -= chunk; + } + + kfree(bv); + return ret; +} + /** * generic_file_splice_read - splice data from file to a pipe * @in: file to splice from diff --git a/include/linux/fs.h b/include/linux/fs.h index 28743e38df91..551c9403f9b3 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3166,6 +3166,9 @@ ssize_t vfs_iocb_iter_write(struct file *file, struct kiocb *iocb, ssize_t filemap_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); +ssize_t direct_splice_read(struct file *in, loff_t *ppos, + struct pipe_inode_info *pipe, + size_t len, unsigned int flags); extern ssize_t generic_file_splice_read(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int); extern ssize_t iter_file_splice_write(struct pipe_inode_info *, -- cgit v1.2.3 From f62e52d1276b6cd329fe72d36bdf912b2ce4caaf Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 19 Jan 2023 12:47:23 +0000 Subject: iov_iter: Define flags to qualify page extraction. Define flags to qualify page extraction to pass into iov_iter_*_pages*() rather than passing in FOLL_* flags. For now only a flag to allow peer-to-peer DMA is supported. Signed-off-by: David Howells Reviewed-by: Christoph Hellwig Reviewed-by: John Hubbard Reviewed-by: Jens Axboe cc: Al Viro cc: Logan Gunthorpe cc: linux-fsdevel@vger.kernel.org cc: linux-block@vger.kernel.org Signed-off-by: Steve French --- block/bio.c | 6 +++--- block/blk-map.c | 8 ++++---- include/linux/uio.h | 10 ++++++++-- lib/iov_iter.c | 14 ++++++++------ 4 files changed, 23 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/block/bio.c b/block/bio.c index ab59a491a883..b97f3991c904 100644 --- a/block/bio.c +++ b/block/bio.c @@ -1245,11 +1245,11 @@ static int bio_iov_add_zone_append_page(struct bio *bio, struct page *page, */ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) { + iov_iter_extraction_t extraction_flags = 0; unsigned short nr_pages = bio->bi_max_vecs - bio->bi_vcnt; unsigned short entries_left = bio->bi_max_vecs - bio->bi_vcnt; struct bio_vec *bv = bio->bi_io_vec + bio->bi_vcnt; struct page **pages = (struct page **)bv; - unsigned int gup_flags = 0; ssize_t size, left; unsigned len, i = 0; size_t offset, trim; @@ -1264,7 +1264,7 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) pages += entries_left * (PAGE_PTRS_PER_BVEC - 1); if (bio->bi_bdev && blk_queue_pci_p2pdma(bio->bi_bdev->bd_disk->queue)) - gup_flags |= FOLL_PCI_P2PDMA; + extraction_flags |= ITER_ALLOW_P2PDMA; /* * Each segment in the iov is required to be a block size multiple. @@ -1275,7 +1275,7 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) */ size = iov_iter_get_pages(iter, pages, UINT_MAX - bio->bi_iter.bi_size, - nr_pages, &offset, gup_flags); + nr_pages, &offset, extraction_flags); if (unlikely(size <= 0)) return size ? size : -EFAULT; diff --git a/block/blk-map.c b/block/blk-map.c index 19940c978c73..080dd60485be 100644 --- a/block/blk-map.c +++ b/block/blk-map.c @@ -265,9 +265,9 @@ static struct bio *blk_rq_map_bio_alloc(struct request *rq, static int bio_map_user_iov(struct request *rq, struct iov_iter *iter, gfp_t gfp_mask) { + iov_iter_extraction_t extraction_flags = 0; unsigned int max_sectors = queue_max_hw_sectors(rq->q); unsigned int nr_vecs = iov_iter_npages(iter, BIO_MAX_VECS); - unsigned int gup_flags = 0; struct bio *bio; int ret; int j; @@ -280,7 +280,7 @@ static int bio_map_user_iov(struct request *rq, struct iov_iter *iter, return -ENOMEM; if (blk_queue_pci_p2pdma(rq->q)) - gup_flags |= FOLL_PCI_P2PDMA; + extraction_flags |= ITER_ALLOW_P2PDMA; while (iov_iter_count(iter)) { struct page **pages, *stack_pages[UIO_FASTIOV]; @@ -291,10 +291,10 @@ static int bio_map_user_iov(struct request *rq, struct iov_iter *iter, if (nr_vecs <= ARRAY_SIZE(stack_pages)) { pages = stack_pages; bytes = iov_iter_get_pages(iter, pages, LONG_MAX, - nr_vecs, &offs, gup_flags); + nr_vecs, &offs, extraction_flags); } else { bytes = iov_iter_get_pages_alloc(iter, &pages, - LONG_MAX, &offs, gup_flags); + LONG_MAX, &offs, extraction_flags); } if (unlikely(bytes <= 0)) { ret = bytes ? bytes : -EFAULT; diff --git a/include/linux/uio.h b/include/linux/uio.h index 9f158238edba..eec6ed8a627a 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -13,6 +13,8 @@ struct page; struct pipe_inode_info; +typedef unsigned int __bitwise iov_iter_extraction_t; + struct kvec { void *iov_base; /* and that should *never* hold a userland pointer */ size_t iov_len; @@ -252,12 +254,12 @@ void iov_iter_xarray(struct iov_iter *i, unsigned int direction, struct xarray * loff_t start, size_t count); ssize_t iov_iter_get_pages(struct iov_iter *i, struct page **pages, size_t maxsize, unsigned maxpages, size_t *start, - unsigned gup_flags); + iov_iter_extraction_t extraction_flags); ssize_t iov_iter_get_pages2(struct iov_iter *i, struct page **pages, size_t maxsize, unsigned maxpages, size_t *start); ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, struct page ***pages, size_t maxsize, size_t *start, - unsigned gup_flags); + iov_iter_extraction_t extraction_flags); ssize_t iov_iter_get_pages_alloc2(struct iov_iter *i, struct page ***pages, size_t maxsize, size_t *start); int iov_iter_npages(const struct iov_iter *i, int maxpages); @@ -360,4 +362,8 @@ static inline void iov_iter_ubuf(struct iov_iter *i, unsigned int direction, }; } +/* Flags for iov_iter_get/extract_pages*() */ +/* Allow P2PDMA on the extracted pages */ +#define ITER_ALLOW_P2PDMA ((__force iov_iter_extraction_t)0x01) + #endif diff --git a/lib/iov_iter.c b/lib/iov_iter.c index 47c484551c59..9d4949ea9b27 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -1426,9 +1426,9 @@ static struct page *first_bvec_segment(const struct iov_iter *i, static ssize_t __iov_iter_get_pages_alloc(struct iov_iter *i, struct page ***pages, size_t maxsize, unsigned int maxpages, size_t *start, - unsigned int gup_flags) + iov_iter_extraction_t extraction_flags) { - unsigned int n; + unsigned int n, gup_flags = 0; if (maxsize > i->count) maxsize = i->count; @@ -1436,6 +1436,8 @@ static ssize_t __iov_iter_get_pages_alloc(struct iov_iter *i, return 0; if (maxsize > MAX_RW_COUNT) maxsize = MAX_RW_COUNT; + if (extraction_flags & ITER_ALLOW_P2PDMA) + gup_flags |= FOLL_PCI_P2PDMA; if (likely(user_backed_iter(i))) { unsigned long addr; @@ -1489,14 +1491,14 @@ static ssize_t __iov_iter_get_pages_alloc(struct iov_iter *i, ssize_t iov_iter_get_pages(struct iov_iter *i, struct page **pages, size_t maxsize, unsigned maxpages, - size_t *start, unsigned gup_flags) + size_t *start, iov_iter_extraction_t extraction_flags) { if (!maxpages) return 0; BUG_ON(!pages); return __iov_iter_get_pages_alloc(i, &pages, maxsize, maxpages, - start, gup_flags); + start, extraction_flags); } EXPORT_SYMBOL_GPL(iov_iter_get_pages); @@ -1509,14 +1511,14 @@ EXPORT_SYMBOL(iov_iter_get_pages2); ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, struct page ***pages, size_t maxsize, - size_t *start, unsigned gup_flags) + size_t *start, iov_iter_extraction_t extraction_flags) { ssize_t len; *pages = NULL; len = __iov_iter_get_pages_alloc(i, pages, maxsize, ~0U, start, - gup_flags); + extraction_flags); if (len <= 0) { kvfree(*pages); *pages = NULL; -- cgit v1.2.3 From 7d58fe731028128f3a7e20b9c492be48aae133ee Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 28 Oct 2022 21:50:30 +0100 Subject: iov_iter: Add a function to extract a page list from an iterator Add a function, iov_iter_extract_pages(), to extract a list of pages from an iterator. The pages may be returned with a pin added or nothing, depending on the type of iterator. Add a second function, iov_iter_extract_will_pin(), to determine how the cleanup should be done. There are two cases: (1) ITER_IOVEC or ITER_UBUF iterator. Extracted pages will have pins (FOLL_PIN) obtained on them so that a concurrent fork() will forcibly copy the page so that DMA is done to/from the parent's buffer and is unavailable to/unaffected by the child process. iov_iter_extract_will_pin() will return true for this case. The caller should use something like unpin_user_page() to dispose of the page. (2) Any other sort of iterator. No refs or pins are obtained on the page, the assumption is made that the caller will manage page retention. iov_iter_extract_will_pin() will return false. The pages don't need additional disposal. Signed-off-by: David Howells Reviewed-by: Christoph Hellwig Reviewed-by: Jens Axboe cc: Al Viro cc: John Hubbard cc: David Hildenbrand cc: Matthew Wilcox cc: linux-fsdevel@vger.kernel.org cc: linux-mm@kvack.org Signed-off-by: Steve French --- include/linux/uio.h | 27 +++++- lib/iov_iter.c | 264 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 290 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/uio.h b/include/linux/uio.h index eec6ed8a627a..514e3b7b06b8 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -361,9 +361,34 @@ static inline void iov_iter_ubuf(struct iov_iter *i, unsigned int direction, .count = count }; } - /* Flags for iov_iter_get/extract_pages*() */ /* Allow P2PDMA on the extracted pages */ #define ITER_ALLOW_P2PDMA ((__force iov_iter_extraction_t)0x01) +ssize_t iov_iter_extract_pages(struct iov_iter *i, struct page ***pages, + size_t maxsize, unsigned int maxpages, + iov_iter_extraction_t extraction_flags, + size_t *offset0); + +/** + * iov_iter_extract_will_pin - Indicate how pages from the iterator will be retained + * @iter: The iterator + * + * Examine the iterator and indicate by returning true or false as to how, if + * at all, pages extracted from the iterator will be retained by the extraction + * function. + * + * %true indicates that the pages will have a pin placed in them that the + * caller must unpin. This is must be done for DMA/async DIO to force fork() + * to forcibly copy a page for the child (the parent must retain the original + * page). + * + * %false indicates that no measures are taken and that it's up to the caller + * to retain the pages. + */ +static inline bool iov_iter_extract_will_pin(const struct iov_iter *iter) +{ + return user_backed_iter(iter); +} + #endif diff --git a/lib/iov_iter.c b/lib/iov_iter.c index 9d4949ea9b27..e53b16235385 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -1910,3 +1910,267 @@ void iov_iter_restore(struct iov_iter *i, struct iov_iter_state *state) i->iov -= state->nr_segs - i->nr_segs; i->nr_segs = state->nr_segs; } + +/* + * Extract a list of contiguous pages from an ITER_XARRAY iterator. This does not + * get references on the pages, nor does it get a pin on them. + */ +static ssize_t iov_iter_extract_xarray_pages(struct iov_iter *i, + struct page ***pages, size_t maxsize, + unsigned int maxpages, + iov_iter_extraction_t extraction_flags, + size_t *offset0) +{ + struct page *page, **p; + unsigned int nr = 0, offset; + loff_t pos = i->xarray_start + i->iov_offset; + pgoff_t index = pos >> PAGE_SHIFT; + XA_STATE(xas, i->xarray, index); + + offset = pos & ~PAGE_MASK; + *offset0 = offset; + + maxpages = want_pages_array(pages, maxsize, offset, maxpages); + if (!maxpages) + return -ENOMEM; + p = *pages; + + rcu_read_lock(); + for (page = xas_load(&xas); page; page = xas_next(&xas)) { + if (xas_retry(&xas, page)) + continue; + + /* Has the page moved or been split? */ + if (unlikely(page != xas_reload(&xas))) { + xas_reset(&xas); + continue; + } + + p[nr++] = find_subpage(page, xas.xa_index); + if (nr == maxpages) + break; + } + rcu_read_unlock(); + + maxsize = min_t(size_t, nr * PAGE_SIZE - offset, maxsize); + iov_iter_advance(i, maxsize); + return maxsize; +} + +/* + * Extract a list of contiguous pages from an ITER_BVEC iterator. This does + * not get references on the pages, nor does it get a pin on them. + */ +static ssize_t iov_iter_extract_bvec_pages(struct iov_iter *i, + struct page ***pages, size_t maxsize, + unsigned int maxpages, + iov_iter_extraction_t extraction_flags, + size_t *offset0) +{ + struct page **p, *page; + size_t skip = i->iov_offset, offset; + int k; + + for (;;) { + if (i->nr_segs == 0) + return 0; + maxsize = min(maxsize, i->bvec->bv_len - skip); + if (maxsize) + break; + i->iov_offset = 0; + i->nr_segs--; + i->bvec++; + skip = 0; + } + + skip += i->bvec->bv_offset; + page = i->bvec->bv_page + skip / PAGE_SIZE; + offset = skip % PAGE_SIZE; + *offset0 = offset; + + maxpages = want_pages_array(pages, maxsize, offset, maxpages); + if (!maxpages) + return -ENOMEM; + p = *pages; + for (k = 0; k < maxpages; k++) + p[k] = page + k; + + maxsize = min_t(size_t, maxsize, maxpages * PAGE_SIZE - offset); + iov_iter_advance(i, maxsize); + return maxsize; +} + +/* + * Extract a list of virtually contiguous pages from an ITER_KVEC iterator. + * This does not get references on the pages, nor does it get a pin on them. + */ +static ssize_t iov_iter_extract_kvec_pages(struct iov_iter *i, + struct page ***pages, size_t maxsize, + unsigned int maxpages, + iov_iter_extraction_t extraction_flags, + size_t *offset0) +{ + struct page **p, *page; + const void *kaddr; + size_t skip = i->iov_offset, offset, len; + int k; + + for (;;) { + if (i->nr_segs == 0) + return 0; + maxsize = min(maxsize, i->kvec->iov_len - skip); + if (maxsize) + break; + i->iov_offset = 0; + i->nr_segs--; + i->kvec++; + skip = 0; + } + + kaddr = i->kvec->iov_base + skip; + offset = (unsigned long)kaddr & ~PAGE_MASK; + *offset0 = offset; + + maxpages = want_pages_array(pages, maxsize, offset, maxpages); + if (!maxpages) + return -ENOMEM; + p = *pages; + + kaddr -= offset; + len = offset + maxsize; + for (k = 0; k < maxpages; k++) { + size_t seg = min_t(size_t, len, PAGE_SIZE); + + if (is_vmalloc_or_module_addr(kaddr)) + page = vmalloc_to_page(kaddr); + else + page = virt_to_page(kaddr); + + p[k] = page; + len -= seg; + kaddr += PAGE_SIZE; + } + + maxsize = min_t(size_t, maxsize, maxpages * PAGE_SIZE - offset); + iov_iter_advance(i, maxsize); + return maxsize; +} + +/* + * Extract a list of contiguous pages from a user iterator and get a pin on + * each of them. This should only be used if the iterator is user-backed + * (IOBUF/UBUF). + * + * It does not get refs on the pages, but the pages must be unpinned by the + * caller once the transfer is complete. + * + * This is safe to be used where background IO/DMA *is* going to be modifying + * the buffer; using a pin rather than a ref makes forces fork() to give the + * child a copy of the page. + */ +static ssize_t iov_iter_extract_user_pages(struct iov_iter *i, + struct page ***pages, + size_t maxsize, + unsigned int maxpages, + iov_iter_extraction_t extraction_flags, + size_t *offset0) +{ + unsigned long addr; + unsigned int gup_flags = 0; + size_t offset; + int res; + + if (i->data_source == ITER_DEST) + gup_flags |= FOLL_WRITE; + if (extraction_flags & ITER_ALLOW_P2PDMA) + gup_flags |= FOLL_PCI_P2PDMA; + if (i->nofault) + gup_flags |= FOLL_NOFAULT; + + addr = first_iovec_segment(i, &maxsize); + *offset0 = offset = addr % PAGE_SIZE; + addr &= PAGE_MASK; + maxpages = want_pages_array(pages, maxsize, offset, maxpages); + if (!maxpages) + return -ENOMEM; + res = pin_user_pages_fast(addr, maxpages, gup_flags, *pages); + if (unlikely(res <= 0)) + return res; + maxsize = min_t(size_t, maxsize, res * PAGE_SIZE - offset); + iov_iter_advance(i, maxsize); + return maxsize; +} + +/** + * iov_iter_extract_pages - Extract a list of contiguous pages from an iterator + * @i: The iterator to extract from + * @pages: Where to return the list of pages + * @maxsize: The maximum amount of iterator to extract + * @maxpages: The maximum size of the list of pages + * @extraction_flags: Flags to qualify request + * @offset0: Where to return the starting offset into (*@pages)[0] + * + * Extract a list of contiguous pages from the current point of the iterator, + * advancing the iterator. The maximum number of pages and the maximum amount + * of page contents can be set. + * + * If *@pages is NULL, a page list will be allocated to the required size and + * *@pages will be set to its base. If *@pages is not NULL, it will be assumed + * that the caller allocated a page list at least @maxpages in size and this + * will be filled in. + * + * @extraction_flags can have ITER_ALLOW_P2PDMA set to request peer-to-peer DMA + * be allowed on the pages extracted. + * + * The iov_iter_extract_will_pin() function can be used to query how cleanup + * should be performed. + * + * Extra refs or pins on the pages may be obtained as follows: + * + * (*) If the iterator is user-backed (ITER_IOVEC/ITER_UBUF), pins will be + * added to the pages, but refs will not be taken. + * iov_iter_extract_will_pin() will return true. + * + * (*) If the iterator is ITER_KVEC, ITER_BVEC or ITER_XARRAY, the pages are + * merely listed; no extra refs or pins are obtained. + * iov_iter_extract_will_pin() will return 0. + * + * Note also: + * + * (*) Use with ITER_DISCARD is not supported as that has no content. + * + * On success, the function sets *@pages to the new pagelist, if allocated, and + * sets *offset0 to the offset into the first page. + * + * It may also return -ENOMEM and -EFAULT. + */ +ssize_t iov_iter_extract_pages(struct iov_iter *i, + struct page ***pages, + size_t maxsize, + unsigned int maxpages, + iov_iter_extraction_t extraction_flags, + size_t *offset0) +{ + maxsize = min_t(size_t, min_t(size_t, maxsize, i->count), MAX_RW_COUNT); + if (!maxsize) + return 0; + + if (likely(user_backed_iter(i))) + return iov_iter_extract_user_pages(i, pages, maxsize, + maxpages, extraction_flags, + offset0); + if (iov_iter_is_kvec(i)) + return iov_iter_extract_kvec_pages(i, pages, maxsize, + maxpages, extraction_flags, + offset0); + if (iov_iter_is_bvec(i)) + return iov_iter_extract_bvec_pages(i, pages, maxsize, + maxpages, extraction_flags, + offset0); + if (iov_iter_is_xarray(i)) + return iov_iter_extract_xarray_pages(i, pages, maxsize, + maxpages, extraction_flags, + offset0); + return -EFAULT; +} +EXPORT_SYMBOL_GPL(iov_iter_extract_pages); -- cgit v1.2.3 From 85dd2c8ff368b1446be9febde84afe1d7aec4261 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 20 Oct 2022 16:16:32 +0100 Subject: netfs: Add a function to extract a UBUF or IOVEC into a BVEC iterator Add a function to extract the pages from a user-space supplied iterator (UBUF- or IOVEC-type) into a BVEC-type iterator, retaining the pages by getting a pin on them (as FOLL_PIN) as we go. This is useful in three situations: (1) A userspace thread may have a sibling that unmaps or remaps the process's VM during the operation, changing the assignment of the pages and potentially causing an error. Retaining the pages keeps some pages around, even if this occurs; futher, we find out at the point of extraction if EFAULT is going to be incurred. (2) Pages might get swapped out/discarded if not retained, so we want to retain them to avoid the reload causing a deadlock due to a DIO from/to an mmapped region on the same file. (3) The iterator may get passed to sendmsg() by the filesystem. If a fault occurs, we may get a short write to a TCP stream that's then tricky to recover from. We don't deal with other types of iterator here, leaving it to other mechanisms to retain the pages (eg. PG_locked, PG_writeback and the pipe lock). Signed-off-by: David Howells cc: Jeff Layton cc: Steve French cc: Shyam Prasad N cc: Rohith Surabattula cc: linux-cachefs@redhat.com cc: linux-cifs@vger.kernel.org cc: linux-fsdevel@vger.kernel.org Signed-off-by: Steve French --- fs/netfs/Makefile | 1 + fs/netfs/iterator.c | 103 ++++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/netfs.h | 4 ++ 3 files changed, 108 insertions(+) create mode 100644 fs/netfs/iterator.c (limited to 'include/linux') diff --git a/fs/netfs/Makefile b/fs/netfs/Makefile index f684c0cd1ec5..386d6fb92793 100644 --- a/fs/netfs/Makefile +++ b/fs/netfs/Makefile @@ -3,6 +3,7 @@ netfs-y := \ buffered_read.o \ io.o \ + iterator.o \ main.o \ objects.o diff --git a/fs/netfs/iterator.c b/fs/netfs/iterator.c new file mode 100644 index 000000000000..6f0d79080abc --- /dev/null +++ b/fs/netfs/iterator.c @@ -0,0 +1,103 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* Iterator helpers. + * + * Copyright (C) 2022 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#include +#include +#include +#include +#include "internal.h" + +/** + * netfs_extract_user_iter - Extract the pages from a user iterator into a bvec + * @orig: The original iterator + * @orig_len: The amount of iterator to copy + * @new: The iterator to be set up + * @extraction_flags: Flags to qualify the request + * + * Extract the page fragments from the given amount of the source iterator and + * build up a second iterator that refers to all of those bits. This allows + * the original iterator to disposed of. + * + * @extraction_flags can have ITER_ALLOW_P2PDMA set to request peer-to-peer DMA be + * allowed on the pages extracted. + * + * On success, the number of elements in the bvec is returned, the original + * iterator will have been advanced by the amount extracted. + * + * The iov_iter_extract_mode() function should be used to query how cleanup + * should be performed. + */ +ssize_t netfs_extract_user_iter(struct iov_iter *orig, size_t orig_len, + struct iov_iter *new, + iov_iter_extraction_t extraction_flags) +{ + struct bio_vec *bv = NULL; + struct page **pages; + unsigned int cur_npages; + unsigned int max_pages; + unsigned int npages = 0; + unsigned int i; + ssize_t ret; + size_t count = orig_len, offset, len; + size_t bv_size, pg_size; + + if (WARN_ON_ONCE(!iter_is_ubuf(orig) && !iter_is_iovec(orig))) + return -EIO; + + max_pages = iov_iter_npages(orig, INT_MAX); + bv_size = array_size(max_pages, sizeof(*bv)); + bv = kvmalloc(bv_size, GFP_KERNEL); + if (!bv) + return -ENOMEM; + + /* Put the page list at the end of the bvec list storage. bvec + * elements are larger than page pointers, so as long as we work + * 0->last, we should be fine. + */ + pg_size = array_size(max_pages, sizeof(*pages)); + pages = (void *)bv + bv_size - pg_size; + + while (count && npages < max_pages) { + ret = iov_iter_extract_pages(orig, &pages, count, + max_pages - npages, extraction_flags, + &offset); + if (ret < 0) { + pr_err("Couldn't get user pages (rc=%zd)\n", ret); + break; + } + + if (ret > count) { + pr_err("get_pages rc=%zd more than %zu\n", ret, count); + break; + } + + count -= ret; + ret += offset; + cur_npages = DIV_ROUND_UP(ret, PAGE_SIZE); + + if (npages + cur_npages > max_pages) { + pr_err("Out of bvec array capacity (%u vs %u)\n", + npages + cur_npages, max_pages); + break; + } + + for (i = 0; i < cur_npages; i++) { + len = ret > PAGE_SIZE ? PAGE_SIZE : ret; + bv[npages + i].bv_page = *pages++; + bv[npages + i].bv_offset = offset; + bv[npages + i].bv_len = len - offset; + ret -= len; + offset = 0; + } + + npages += cur_npages; + } + + iov_iter_bvec(new, orig->data_source, bv, npages, orig_len - count); + return npages; +} +EXPORT_SYMBOL_GPL(netfs_extract_user_iter); diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 4c76ddfb6a67..b11a84f6c32b 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -17,6 +17,7 @@ #include #include #include +#include enum netfs_sreq_ref_trace; @@ -296,6 +297,9 @@ void netfs_get_subrequest(struct netfs_io_subrequest *subreq, void netfs_put_subrequest(struct netfs_io_subrequest *subreq, bool was_async, enum netfs_sreq_ref_trace what); void netfs_stats_show(struct seq_file *); +ssize_t netfs_extract_user_iter(struct iov_iter *orig, size_t orig_len, + struct iov_iter *new, + iov_iter_extraction_t extraction_flags); /** * netfs_inode - Get the netfs inode context from the inode -- cgit v1.2.3 From 0185846975339a5c348373aa450a977f5242366b Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 27 Oct 2022 16:19:44 +0100 Subject: netfs: Add a function to extract an iterator into a scatterlist Provide a function for filling in a scatterlist from the list of pages contained in an iterator. If the iterator is UBUF- or IOBUF-type, the pages have a pin taken on them (as FOLL_PIN). If the iterator is BVEC-, KVEC- or XARRAY-type, no pin is taken on the pages and it is left to the caller to manage their lifetime. It cannot be assumed that a ref can be validly taken, particularly in the case of a KVEC iterator. Signed-off-by: David Howells cc: Jeff Layton cc: Steve French cc: Shyam Prasad N cc: Rohith Surabattula cc: linux-cachefs@redhat.com cc: linux-cifs@vger.kernel.org cc: linux-fsdevel@vger.kernel.org Signed-off-by: Steve French --- fs/netfs/iterator.c | 268 ++++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/netfs.h | 4 + mm/vmalloc.c | 1 + 3 files changed, 273 insertions(+) (limited to 'include/linux') diff --git a/fs/netfs/iterator.c b/fs/netfs/iterator.c index 6f0d79080abc..80d7ff440cac 100644 --- a/fs/netfs/iterator.c +++ b/fs/netfs/iterator.c @@ -7,7 +7,9 @@ #include #include +#include #include +#include #include #include "internal.h" @@ -101,3 +103,269 @@ ssize_t netfs_extract_user_iter(struct iov_iter *orig, size_t orig_len, return npages; } EXPORT_SYMBOL_GPL(netfs_extract_user_iter); + +/* + * Extract and pin a list of up to sg_max pages from UBUF- or IOVEC-class + * iterators, and add them to the scatterlist. + */ +static ssize_t netfs_extract_user_to_sg(struct iov_iter *iter, + ssize_t maxsize, + struct sg_table *sgtable, + unsigned int sg_max, + iov_iter_extraction_t extraction_flags) +{ + struct scatterlist *sg = sgtable->sgl + sgtable->nents; + struct page **pages; + unsigned int npages; + ssize_t ret = 0, res; + size_t len, off; + + /* We decant the page list into the tail of the scatterlist */ + pages = (void *)sgtable->sgl + array_size(sg_max, sizeof(struct scatterlist)); + pages -= sg_max; + + do { + res = iov_iter_extract_pages(iter, &pages, maxsize, sg_max, + extraction_flags, &off); + if (res < 0) + goto failed; + + len = res; + maxsize -= len; + ret += len; + npages = DIV_ROUND_UP(off + len, PAGE_SIZE); + sg_max -= npages; + + for (; npages < 0; npages--) { + struct page *page = *pages; + size_t seg = min_t(size_t, PAGE_SIZE - off, len); + + *pages++ = NULL; + sg_set_page(sg, page, len, off); + sgtable->nents++; + sg++; + len -= seg; + off = 0; + } + } while (maxsize > 0 && sg_max > 0); + + return ret; + +failed: + while (sgtable->nents > sgtable->orig_nents) + put_page(sg_page(&sgtable->sgl[--sgtable->nents])); + return res; +} + +/* + * Extract up to sg_max pages from a BVEC-type iterator and add them to the + * scatterlist. The pages are not pinned. + */ +static ssize_t netfs_extract_bvec_to_sg(struct iov_iter *iter, + ssize_t maxsize, + struct sg_table *sgtable, + unsigned int sg_max, + iov_iter_extraction_t extraction_flags) +{ + const struct bio_vec *bv = iter->bvec; + struct scatterlist *sg = sgtable->sgl + sgtable->nents; + unsigned long start = iter->iov_offset; + unsigned int i; + ssize_t ret = 0; + + for (i = 0; i < iter->nr_segs; i++) { + size_t off, len; + + len = bv[i].bv_len; + if (start >= len) { + start -= len; + continue; + } + + len = min_t(size_t, maxsize, len - start); + off = bv[i].bv_offset + start; + + sg_set_page(sg, bv[i].bv_page, len, off); + sgtable->nents++; + sg++; + sg_max--; + + ret += len; + maxsize -= len; + if (maxsize <= 0 || sg_max == 0) + break; + start = 0; + } + + if (ret > 0) + iov_iter_advance(iter, ret); + return ret; +} + +/* + * Extract up to sg_max pages from a KVEC-type iterator and add them to the + * scatterlist. This can deal with vmalloc'd buffers as well as kmalloc'd or + * static buffers. The pages are not pinned. + */ +static ssize_t netfs_extract_kvec_to_sg(struct iov_iter *iter, + ssize_t maxsize, + struct sg_table *sgtable, + unsigned int sg_max, + iov_iter_extraction_t extraction_flags) +{ + const struct kvec *kv = iter->kvec; + struct scatterlist *sg = sgtable->sgl + sgtable->nents; + unsigned long start = iter->iov_offset; + unsigned int i; + ssize_t ret = 0; + + for (i = 0; i < iter->nr_segs; i++) { + struct page *page; + unsigned long kaddr; + size_t off, len, seg; + + len = kv[i].iov_len; + if (start >= len) { + start -= len; + continue; + } + + kaddr = (unsigned long)kv[i].iov_base + start; + off = kaddr & ~PAGE_MASK; + len = min_t(size_t, maxsize, len - start); + kaddr &= PAGE_MASK; + + maxsize -= len; + ret += len; + do { + seg = min_t(size_t, len, PAGE_SIZE - off); + if (is_vmalloc_or_module_addr((void *)kaddr)) + page = vmalloc_to_page((void *)kaddr); + else + page = virt_to_page(kaddr); + + sg_set_page(sg, page, len, off); + sgtable->nents++; + sg++; + sg_max--; + + len -= seg; + kaddr += PAGE_SIZE; + off = 0; + } while (len > 0 && sg_max > 0); + + if (maxsize <= 0 || sg_max == 0) + break; + start = 0; + } + + if (ret > 0) + iov_iter_advance(iter, ret); + return ret; +} + +/* + * Extract up to sg_max folios from an XARRAY-type iterator and add them to + * the scatterlist. The pages are not pinned. + */ +static ssize_t netfs_extract_xarray_to_sg(struct iov_iter *iter, + ssize_t maxsize, + struct sg_table *sgtable, + unsigned int sg_max, + iov_iter_extraction_t extraction_flags) +{ + struct scatterlist *sg = sgtable->sgl + sgtable->nents; + struct xarray *xa = iter->xarray; + struct folio *folio; + loff_t start = iter->xarray_start + iter->iov_offset; + pgoff_t index = start / PAGE_SIZE; + ssize_t ret = 0; + size_t offset, len; + XA_STATE(xas, xa, index); + + rcu_read_lock(); + + xas_for_each(&xas, folio, ULONG_MAX) { + if (xas_retry(&xas, folio)) + continue; + if (WARN_ON(xa_is_value(folio))) + break; + if (WARN_ON(folio_test_hugetlb(folio))) + break; + + offset = offset_in_folio(folio, start); + len = min_t(size_t, maxsize, folio_size(folio) - offset); + + sg_set_page(sg, folio_page(folio, 0), len, offset); + sgtable->nents++; + sg++; + sg_max--; + + maxsize -= len; + ret += len; + if (maxsize <= 0 || sg_max == 0) + break; + } + + rcu_read_unlock(); + if (ret > 0) + iov_iter_advance(iter, ret); + return ret; +} + +/** + * netfs_extract_iter_to_sg - Extract pages from an iterator and add ot an sglist + * @iter: The iterator to extract from + * @maxsize: The amount of iterator to copy + * @sgtable: The scatterlist table to fill in + * @sg_max: Maximum number of elements in @sgtable that may be filled + * @extraction_flags: Flags to qualify the request + * + * Extract the page fragments from the given amount of the source iterator and + * add them to a scatterlist that refers to all of those bits, to a maximum + * addition of @sg_max elements. + * + * The pages referred to by UBUF- and IOVEC-type iterators are extracted and + * pinned; BVEC-, KVEC- and XARRAY-type are extracted but aren't pinned; PIPE- + * and DISCARD-type are not supported. + * + * No end mark is placed on the scatterlist; that's left to the caller. + * + * @extraction_flags can have ITER_ALLOW_P2PDMA set to request peer-to-peer DMA + * be allowed on the pages extracted. + * + * If successul, @sgtable->nents is updated to include the number of elements + * added and the number of bytes added is returned. @sgtable->orig_nents is + * left unaltered. + * + * The iov_iter_extract_mode() function should be used to query how cleanup + * should be performed. + */ +ssize_t netfs_extract_iter_to_sg(struct iov_iter *iter, size_t maxsize, + struct sg_table *sgtable, unsigned int sg_max, + iov_iter_extraction_t extraction_flags) +{ + if (maxsize == 0) + return 0; + + switch (iov_iter_type(iter)) { + case ITER_UBUF: + case ITER_IOVEC: + return netfs_extract_user_to_sg(iter, maxsize, sgtable, sg_max, + extraction_flags); + case ITER_BVEC: + return netfs_extract_bvec_to_sg(iter, maxsize, sgtable, sg_max, + extraction_flags); + case ITER_KVEC: + return netfs_extract_kvec_to_sg(iter, maxsize, sgtable, sg_max, + extraction_flags); + case ITER_XARRAY: + return netfs_extract_xarray_to_sg(iter, maxsize, sgtable, sg_max, + extraction_flags); + default: + pr_err("%s(%u) unsupported\n", __func__, iov_iter_type(iter)); + WARN_ON_ONCE(1); + return -EIO; + } +} +EXPORT_SYMBOL_GPL(netfs_extract_iter_to_sg); diff --git a/include/linux/netfs.h b/include/linux/netfs.h index b11a84f6c32b..a1f3522daa69 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -300,6 +300,10 @@ void netfs_stats_show(struct seq_file *); ssize_t netfs_extract_user_iter(struct iov_iter *orig, size_t orig_len, struct iov_iter *new, iov_iter_extraction_t extraction_flags); +struct sg_table; +ssize_t netfs_extract_iter_to_sg(struct iov_iter *iter, size_t len, + struct sg_table *sgtable, unsigned int sg_max, + iov_iter_extraction_t extraction_flags); /** * netfs_inode - Get the netfs inode context from the inode diff --git a/mm/vmalloc.c b/mm/vmalloc.c index ca71de7c9d77..61f5bec0f2b6 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -656,6 +656,7 @@ int is_vmalloc_or_module_addr(const void *x) #endif return is_vmalloc_addr(x); } +EXPORT_SYMBOL_GPL(is_vmalloc_or_module_addr); /* * Walk a vmap address to the struct page it maps. Huge vmap mappings will -- cgit v1.2.3 From 868a6fc0ca2407622d2833adefe1c4d284766c4c Mon Sep 17 00:00:00 2001 From: Yang Jihong Date: Tue, 21 Feb 2023 08:49:16 +0900 Subject: x86/kprobes: Fix __recover_optprobed_insn check optimizing logic Since the following commit: commit f66c0447cca1 ("kprobes: Set unoptimized flag after unoptimizing code") modified the update timing of the KPROBE_FLAG_OPTIMIZED, a optimized_kprobe may be in the optimizing or unoptimizing state when op.kp->flags has KPROBE_FLAG_OPTIMIZED and op->list is not empty. The __recover_optprobed_insn check logic is incorrect, a kprobe in the unoptimizing state may be incorrectly determined as unoptimizing. As a result, incorrect instructions are copied. The optprobe_queued_unopt function needs to be exported for invoking in arch directory. Link: https://lore.kernel.org/all/20230216034247.32348-2-yangjihong1@huawei.com/ Fixes: f66c0447cca1 ("kprobes: Set unoptimized flag after unoptimizing code") Cc: stable@vger.kernel.org Signed-off-by: Yang Jihong Acked-by: Masami Hiramatsu (Google) Signed-off-by: Masami Hiramatsu (Google) --- arch/x86/kernel/kprobes/opt.c | 4 ++-- include/linux/kprobes.h | 1 + kernel/kprobes.c | 2 +- 3 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index e57e07b0edb6..f406bfa9a8cd 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -46,8 +46,8 @@ unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsigned long addr) /* This function only handles jump-optimized kprobe */ if (kp && kprobe_optimized(kp)) { op = container_of(kp, struct optimized_kprobe, kp); - /* If op->list is not empty, op is under optimizing */ - if (list_empty(&op->list)) + /* If op is optimized or under unoptimizing */ + if (list_empty(&op->list) || optprobe_queued_unopt(op)) goto found; } } diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index a0b92be98984..ab39285f71a6 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -378,6 +378,7 @@ extern void opt_pre_handler(struct kprobe *p, struct pt_regs *regs); DEFINE_INSN_CACHE_OPS(optinsn); extern void wait_for_kprobe_optimizer(void); +bool optprobe_queued_unopt(struct optimized_kprobe *op); #else /* !CONFIG_OPTPROBES */ static inline void wait_for_kprobe_optimizer(void) { } #endif /* CONFIG_OPTPROBES */ diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 6b6aff00b3b6..55e1807ca054 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -660,7 +660,7 @@ void wait_for_kprobe_optimizer(void) mutex_unlock(&kprobe_mutex); } -static bool optprobe_queued_unopt(struct optimized_kprobe *op) +bool optprobe_queued_unopt(struct optimized_kprobe *op) { struct optimized_kprobe *_op; -- cgit v1.2.3 From f1c97a1b4ef709e3f066f82e3ba3108c3b133ae6 Mon Sep 17 00:00:00 2001 From: Yang Jihong Date: Tue, 21 Feb 2023 08:49:16 +0900 Subject: x86/kprobes: Fix arch_check_optimized_kprobe check within optimized_kprobe range When arch_prepare_optimized_kprobe calculating jump destination address, it copies original instructions from jmp-optimized kprobe (see __recover_optprobed_insn), and calculated based on length of original instruction. arch_check_optimized_kprobe does not check KPROBE_FLAG_OPTIMATED when checking whether jmp-optimized kprobe exists. As a result, setup_detour_execution may jump to a range that has been overwritten by jump destination address, resulting in an inval opcode error. For example, assume that register two kprobes whose addresses are and in "func" function. The original code of "func" function is as follows: 0xffffffff816cb5e9 <+9>: push %r12 0xffffffff816cb5eb <+11>: xor %r12d,%r12d 0xffffffff816cb5ee <+14>: test %rdi,%rdi 0xffffffff816cb5f1 <+17>: setne %r12b 0xffffffff816cb5f5 <+21>: push %rbp 1.Register the kprobe for , assume that is kp1, corresponding optimized_kprobe is op1. After the optimization, "func" code changes to: 0xffffffff816cc079 <+9>: push %r12 0xffffffff816cc07b <+11>: jmp 0xffffffffa0210000 0xffffffff816cc080 <+16>: incl 0xf(%rcx) 0xffffffff816cc083 <+19>: xchg %eax,%ebp 0xffffffff816cc084 <+20>: (bad) 0xffffffff816cc085 <+21>: push %rbp Now op1->flags == KPROBE_FLAG_OPTIMATED; 2. Register the kprobe for , assume that is kp2, corresponding optimized_kprobe is op2. register_kprobe(kp2) register_aggr_kprobe alloc_aggr_kprobe __prepare_optimized_kprobe arch_prepare_optimized_kprobe __recover_optprobed_insn // copy original bytes from kp1->optinsn.copied_insn, // jump address = 3. disable kp1: disable_kprobe(kp1) __disable_kprobe ... if (p == orig_p || aggr_kprobe_disabled(orig_p)) { ret = disarm_kprobe(orig_p, true) // add op1 in unoptimizing_list, not unoptimized orig_p->flags |= KPROBE_FLAG_DISABLED; // op1->flags == KPROBE_FLAG_OPTIMATED | KPROBE_FLAG_DISABLED ... 4. unregister kp2 __unregister_kprobe_top ... if (!kprobe_disabled(ap) && !kprobes_all_disarmed) { optimize_kprobe(op) ... if (arch_check_optimized_kprobe(op) < 0) // because op1 has KPROBE_FLAG_DISABLED, here not return return; p->kp.flags |= KPROBE_FLAG_OPTIMIZED; // now op2 has KPROBE_FLAG_OPTIMIZED } "func" code now is: 0xffffffff816cc079 <+9>: int3 0xffffffff816cc07a <+10>: push %rsp 0xffffffff816cc07b <+11>: jmp 0xffffffffa0210000 0xffffffff816cc080 <+16>: incl 0xf(%rcx) 0xffffffff816cc083 <+19>: xchg %eax,%ebp 0xffffffff816cc084 <+20>: (bad) 0xffffffff816cc085 <+21>: push %rbp 5. if call "func", int3 handler call setup_detour_execution: if (p->flags & KPROBE_FLAG_OPTIMIZED) { ... regs->ip = (unsigned long)op->optinsn.insn + TMPL_END_IDX; ... } The code for the destination address is 0xffffffffa021072c: push %r12 0xffffffffa021072e: xor %r12d,%r12d 0xffffffffa0210731: jmp 0xffffffff816cb5ee However, is not a valid start instruction address. As a result, an error occurs. Link: https://lore.kernel.org/all/20230216034247.32348-3-yangjihong1@huawei.com/ Fixes: f66c0447cca1 ("kprobes: Set unoptimized flag after unoptimizing code") Signed-off-by: Yang Jihong Cc: stable@vger.kernel.org Acked-by: Masami Hiramatsu (Google) Signed-off-by: Masami Hiramatsu (Google) --- arch/x86/kernel/kprobes/opt.c | 2 +- include/linux/kprobes.h | 1 + kernel/kprobes.c | 2 +- 3 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index f406bfa9a8cd..57b0037d0a99 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -353,7 +353,7 @@ int arch_check_optimized_kprobe(struct optimized_kprobe *op) for (i = 1; i < op->optinsn.size; i++) { p = get_kprobe(op->kp.addr + i); - if (p && !kprobe_disabled(p)) + if (p && !kprobe_disarmed(p)) return -EEXIST; } diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index ab39285f71a6..85a64cb95d75 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -379,6 +379,7 @@ DEFINE_INSN_CACHE_OPS(optinsn); extern void wait_for_kprobe_optimizer(void); bool optprobe_queued_unopt(struct optimized_kprobe *op); +bool kprobe_disarmed(struct kprobe *p); #else /* !CONFIG_OPTPROBES */ static inline void wait_for_kprobe_optimizer(void) { } #endif /* CONFIG_OPTPROBES */ diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 55e1807ca054..00e177de91cc 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -458,7 +458,7 @@ static inline int kprobe_optready(struct kprobe *p) } /* Return true if the kprobe is disarmed. Note: p must be on hash list */ -static inline bool kprobe_disarmed(struct kprobe *p) +bool kprobe_disarmed(struct kprobe *p) { struct optimized_kprobe *op; -- cgit v1.2.3 From db6c4dee4c104f50ed163af71c53bfdb878a8318 Mon Sep 17 00:00:00 2001 From: Alvaro Karsz Date: Tue, 10 Jan 2023 18:56:36 +0200 Subject: PCI: Add SolidRun vendor ID Add SolidRun vendor ID to pci_ids.h The vendor ID is used in 2 different source files, the SNET vDPA driver and PCI quirks. Signed-off-by: Alvaro Karsz Acked-by: Bjorn Helgaas Message-Id: <20230110165638.123745-2-alvaro.karsz@solid-run.com> Signed-off-by: Michael S. Tsirkin --- include/linux/pci_ids.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index b362d90eb9b0..6716e6371a18 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -3092,6 +3092,8 @@ #define PCI_VENDOR_ID_3COM_2 0xa727 +#define PCI_VENDOR_ID_SOLIDRUN 0xd063 + #define PCI_VENDOR_ID_DIGIUM 0xd161 #define PCI_DEVICE_ID_DIGIUM_HFC4S 0xb410 -- cgit v1.2.3 From 1538a8a49ecbe6d3302cd7f347632338e56857f8 Mon Sep 17 00:00:00 2001 From: Sebastien Boeuf Date: Tue, 3 Jan 2023 11:51:05 +0100 Subject: vdpa: Add resume operation Add a new operation to allow a vDPA device to be resumed after it has been suspended. Trying to resume a device that wasn't suspended will result in a no-op. This operation is optional. If it's not implemented, the associated backend feature bit will not be exposed. And if the feature bit is not exposed, invoking this operation will return an error. Acked-by: Jason Wang Signed-off-by: Sebastien Boeuf Message-Id: <6e05c4b31b47f3e29cb2bd7ebd56c81f84b8f48a.1672742878.git.sebastien.boeuf@intel.com> Signed-off-by: Michael S. Tsirkin Reviewed-by: Stefano Garzarella --- include/linux/vdpa.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 6d0f5e4e82c2..96d308cbf97b 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -219,7 +219,10 @@ struct vdpa_map_file { * @reset: Reset device * @vdev: vdpa device * Returns integer: success (0) or error (< 0) - * @suspend: Suspend or resume the device (optional) + * @suspend: Suspend the device (optional) + * @vdev: vdpa device + * Returns integer: success (0) or error (< 0) + * @resume: Resume the device (optional) * @vdev: vdpa device * Returns integer: success (0) or error (< 0) * @get_config_size: Get the size of the configuration space includes @@ -324,6 +327,7 @@ struct vdpa_config_ops { void (*set_status)(struct vdpa_device *vdev, u8 status); int (*reset)(struct vdpa_device *vdev); int (*suspend)(struct vdpa_device *vdev); + int (*resume)(struct vdpa_device *vdev); size_t (*get_config_size)(struct vdpa_device *vdev); void (*get_config)(struct vdpa_device *vdev, unsigned int offset, void *buf, unsigned int len); -- cgit v1.2.3 From 2713ea3c7d930aa1ff5ef7d4a57a1e4fcc3b9985 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Thu, 19 Jan 2023 14:15:21 +0800 Subject: virtio_ring: per virtqueue dma device This patch introduces a per virtqueue dma device. This will be used for virtio devices whose virtqueue are backed by different underlayer devices. One example is the vDPA that where the control virtqueue could be implemented through software mediation. Some of the work are actually done before since the helper like vring_dma_device(). This work left are: - Let vring_dma_device() return the per virtqueue dma device instead of the vdev's parent. - Allow passing a dma_device when creating the virtqueue through a new helper, old vring creation helper will keep using vdev's parent. Reviewed-by: Eli Cohen Tested-by: Eli Cohen Signed-off-by: Jason Wang Message-Id: <20230119061525.75068-2-jasowang@redhat.com> Signed-off-by: Michael S. Tsirkin --- drivers/virtio/virtio_ring.c | 133 ++++++++++++++++++++++++++++++------------- include/linux/virtio_ring.h | 16 ++++++ 2 files changed, 109 insertions(+), 40 deletions(-) (limited to 'include/linux') diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index 723c4e29e1d3..41144b5246a8 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -202,6 +202,9 @@ struct vring_virtqueue { /* DMA, allocation, and size information */ bool we_own_ring; + /* Device used for doing DMA */ + struct device *dma_dev; + #ifdef DEBUG /* They're supposed to lock for us. */ unsigned int in_use; @@ -219,7 +222,8 @@ static struct virtqueue *__vring_new_virtqueue(unsigned int index, bool context, bool (*notify)(struct virtqueue *), void (*callback)(struct virtqueue *), - const char *name); + const char *name, + struct device *dma_dev); static struct vring_desc_extra *vring_alloc_desc_extra(unsigned int num); static void vring_free(struct virtqueue *_vq); @@ -297,10 +301,11 @@ size_t virtio_max_dma_size(struct virtio_device *vdev) EXPORT_SYMBOL_GPL(virtio_max_dma_size); static void *vring_alloc_queue(struct virtio_device *vdev, size_t size, - dma_addr_t *dma_handle, gfp_t flag) + dma_addr_t *dma_handle, gfp_t flag, + struct device *dma_dev) { if (vring_use_dma_api(vdev)) { - return dma_alloc_coherent(vdev->dev.parent, size, + return dma_alloc_coherent(dma_dev, size, dma_handle, flag); } else { void *queue = alloc_pages_exact(PAGE_ALIGN(size), flag); @@ -330,10 +335,11 @@ static void *vring_alloc_queue(struct virtio_device *vdev, size_t size, } static void vring_free_queue(struct virtio_device *vdev, size_t size, - void *queue, dma_addr_t dma_handle) + void *queue, dma_addr_t dma_handle, + struct device *dma_dev) { if (vring_use_dma_api(vdev)) - dma_free_coherent(vdev->dev.parent, size, queue, dma_handle); + dma_free_coherent(dma_dev, size, queue, dma_handle); else free_pages_exact(queue, PAGE_ALIGN(size)); } @@ -341,11 +347,11 @@ static void vring_free_queue(struct virtio_device *vdev, size_t size, /* * The DMA ops on various arches are rather gnarly right now, and * making all of the arch DMA ops work on the vring device itself - * is a mess. For now, we use the parent device for DMA ops. + * is a mess. */ static inline struct device *vring_dma_dev(const struct vring_virtqueue *vq) { - return vq->vq.vdev->dev.parent; + return vq->dma_dev; } /* Map one sg entry. */ @@ -1032,11 +1038,12 @@ err_state: } static void vring_free_split(struct vring_virtqueue_split *vring_split, - struct virtio_device *vdev) + struct virtio_device *vdev, struct device *dma_dev) { vring_free_queue(vdev, vring_split->queue_size_in_bytes, vring_split->vring.desc, - vring_split->queue_dma_addr); + vring_split->queue_dma_addr, + dma_dev); kfree(vring_split->desc_state); kfree(vring_split->desc_extra); @@ -1046,7 +1053,8 @@ static int vring_alloc_queue_split(struct vring_virtqueue_split *vring_split, struct virtio_device *vdev, u32 num, unsigned int vring_align, - bool may_reduce_num) + bool may_reduce_num, + struct device *dma_dev) { void *queue = NULL; dma_addr_t dma_addr; @@ -1061,7 +1069,8 @@ static int vring_alloc_queue_split(struct vring_virtqueue_split *vring_split, for (; num && vring_size(num, vring_align) > PAGE_SIZE; num /= 2) { queue = vring_alloc_queue(vdev, vring_size(num, vring_align), &dma_addr, - GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO); + GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO, + dma_dev); if (queue) break; if (!may_reduce_num) @@ -1074,7 +1083,8 @@ static int vring_alloc_queue_split(struct vring_virtqueue_split *vring_split, if (!queue) { /* Try to get a single page. You are my only hope! */ queue = vring_alloc_queue(vdev, vring_size(num, vring_align), - &dma_addr, GFP_KERNEL | __GFP_ZERO); + &dma_addr, GFP_KERNEL | __GFP_ZERO, + dma_dev); } if (!queue) return -ENOMEM; @@ -1100,21 +1110,22 @@ static struct virtqueue *vring_create_virtqueue_split( bool context, bool (*notify)(struct virtqueue *), void (*callback)(struct virtqueue *), - const char *name) + const char *name, + struct device *dma_dev) { struct vring_virtqueue_split vring_split = {}; struct virtqueue *vq; int err; err = vring_alloc_queue_split(&vring_split, vdev, num, vring_align, - may_reduce_num); + may_reduce_num, dma_dev); if (err) return NULL; vq = __vring_new_virtqueue(index, &vring_split, vdev, weak_barriers, - context, notify, callback, name); + context, notify, callback, name, dma_dev); if (!vq) { - vring_free_split(&vring_split, vdev); + vring_free_split(&vring_split, vdev, dma_dev); return NULL; } @@ -1132,7 +1143,8 @@ static int virtqueue_resize_split(struct virtqueue *_vq, u32 num) err = vring_alloc_queue_split(&vring_split, vdev, num, vq->split.vring_align, - vq->split.may_reduce_num); + vq->split.may_reduce_num, + vring_dma_dev(vq)); if (err) goto err; @@ -1150,7 +1162,7 @@ static int virtqueue_resize_split(struct virtqueue *_vq, u32 num) return 0; err_state_extra: - vring_free_split(&vring_split, vdev); + vring_free_split(&vring_split, vdev, vring_dma_dev(vq)); err: virtqueue_reinit_split(vq); return -ENOMEM; @@ -1841,22 +1853,26 @@ static struct vring_desc_extra *vring_alloc_desc_extra(unsigned int num) } static void vring_free_packed(struct vring_virtqueue_packed *vring_packed, - struct virtio_device *vdev) + struct virtio_device *vdev, + struct device *dma_dev) { if (vring_packed->vring.desc) vring_free_queue(vdev, vring_packed->ring_size_in_bytes, vring_packed->vring.desc, - vring_packed->ring_dma_addr); + vring_packed->ring_dma_addr, + dma_dev); if (vring_packed->vring.driver) vring_free_queue(vdev, vring_packed->event_size_in_bytes, vring_packed->vring.driver, - vring_packed->driver_event_dma_addr); + vring_packed->driver_event_dma_addr, + dma_dev); if (vring_packed->vring.device) vring_free_queue(vdev, vring_packed->event_size_in_bytes, vring_packed->vring.device, - vring_packed->device_event_dma_addr); + vring_packed->device_event_dma_addr, + dma_dev); kfree(vring_packed->desc_state); kfree(vring_packed->desc_extra); @@ -1864,7 +1880,7 @@ static void vring_free_packed(struct vring_virtqueue_packed *vring_packed, static int vring_alloc_queue_packed(struct vring_virtqueue_packed *vring_packed, struct virtio_device *vdev, - u32 num) + u32 num, struct device *dma_dev) { struct vring_packed_desc *ring; struct vring_packed_desc_event *driver, *device; @@ -1875,7 +1891,8 @@ static int vring_alloc_queue_packed(struct vring_virtqueue_packed *vring_packed, ring = vring_alloc_queue(vdev, ring_size_in_bytes, &ring_dma_addr, - GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO); + GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO, + dma_dev); if (!ring) goto err; @@ -1887,7 +1904,8 @@ static int vring_alloc_queue_packed(struct vring_virtqueue_packed *vring_packed, driver = vring_alloc_queue(vdev, event_size_in_bytes, &driver_event_dma_addr, - GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO); + GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO, + dma_dev); if (!driver) goto err; @@ -1897,7 +1915,8 @@ static int vring_alloc_queue_packed(struct vring_virtqueue_packed *vring_packed, device = vring_alloc_queue(vdev, event_size_in_bytes, &device_event_dma_addr, - GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO); + GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO, + dma_dev); if (!device) goto err; @@ -1909,7 +1928,7 @@ static int vring_alloc_queue_packed(struct vring_virtqueue_packed *vring_packed, return 0; err: - vring_free_packed(vring_packed, vdev); + vring_free_packed(vring_packed, vdev, dma_dev); return -ENOMEM; } @@ -1987,13 +2006,14 @@ static struct virtqueue *vring_create_virtqueue_packed( bool context, bool (*notify)(struct virtqueue *), void (*callback)(struct virtqueue *), - const char *name) + const char *name, + struct device *dma_dev) { struct vring_virtqueue_packed vring_packed = {}; struct vring_virtqueue *vq; int err; - if (vring_alloc_queue_packed(&vring_packed, vdev, num)) + if (vring_alloc_queue_packed(&vring_packed, vdev, num, dma_dev)) goto err_ring; vq = kmalloc(sizeof(*vq), GFP_KERNEL); @@ -2014,6 +2034,7 @@ static struct virtqueue *vring_create_virtqueue_packed( vq->broken = false; #endif vq->packed_ring = true; + vq->dma_dev = dma_dev; vq->use_dma_api = vring_use_dma_api(vdev); vq->indirect = virtio_has_feature(vdev, VIRTIO_RING_F_INDIRECT_DESC) && @@ -2040,7 +2061,7 @@ static struct virtqueue *vring_create_virtqueue_packed( err_state_extra: kfree(vq); err_vq: - vring_free_packed(&vring_packed, vdev); + vring_free_packed(&vring_packed, vdev, dma_dev); err_ring: return NULL; } @@ -2052,7 +2073,7 @@ static int virtqueue_resize_packed(struct virtqueue *_vq, u32 num) struct virtio_device *vdev = _vq->vdev; int err; - if (vring_alloc_queue_packed(&vring_packed, vdev, num)) + if (vring_alloc_queue_packed(&vring_packed, vdev, num, vring_dma_dev(vq))) goto err_ring; err = vring_alloc_state_extra_packed(&vring_packed); @@ -2069,7 +2090,7 @@ static int virtqueue_resize_packed(struct virtqueue *_vq, u32 num) return 0; err_state_extra: - vring_free_packed(&vring_packed, vdev); + vring_free_packed(&vring_packed, vdev, vring_dma_dev(vq)); err_ring: virtqueue_reinit_packed(vq); return -ENOMEM; @@ -2481,7 +2502,8 @@ static struct virtqueue *__vring_new_virtqueue(unsigned int index, bool context, bool (*notify)(struct virtqueue *), void (*callback)(struct virtqueue *), - const char *name) + const char *name, + struct device *dma_dev) { struct vring_virtqueue *vq; int err; @@ -2507,6 +2529,7 @@ static struct virtqueue *__vring_new_virtqueue(unsigned int index, #else vq->broken = false; #endif + vq->dma_dev = dma_dev; vq->use_dma_api = vring_use_dma_api(vdev); vq->indirect = virtio_has_feature(vdev, VIRTIO_RING_F_INDIRECT_DESC) && @@ -2549,14 +2572,39 @@ struct virtqueue *vring_create_virtqueue( if (virtio_has_feature(vdev, VIRTIO_F_RING_PACKED)) return vring_create_virtqueue_packed(index, num, vring_align, vdev, weak_barriers, may_reduce_num, - context, notify, callback, name); + context, notify, callback, name, vdev->dev.parent); return vring_create_virtqueue_split(index, num, vring_align, vdev, weak_barriers, may_reduce_num, - context, notify, callback, name); + context, notify, callback, name, vdev->dev.parent); } EXPORT_SYMBOL_GPL(vring_create_virtqueue); +struct virtqueue *vring_create_virtqueue_dma( + unsigned int index, + unsigned int num, + unsigned int vring_align, + struct virtio_device *vdev, + bool weak_barriers, + bool may_reduce_num, + bool context, + bool (*notify)(struct virtqueue *), + void (*callback)(struct virtqueue *), + const char *name, + struct device *dma_dev) +{ + + if (virtio_has_feature(vdev, VIRTIO_F_RING_PACKED)) + return vring_create_virtqueue_packed(index, num, vring_align, + vdev, weak_barriers, may_reduce_num, + context, notify, callback, name, dma_dev); + + return vring_create_virtqueue_split(index, num, vring_align, + vdev, weak_barriers, may_reduce_num, + context, notify, callback, name, dma_dev); +} +EXPORT_SYMBOL_GPL(vring_create_virtqueue_dma); + /** * virtqueue_resize - resize the vring of vq * @_vq: the struct virtqueue we're talking about. @@ -2645,7 +2693,8 @@ struct virtqueue *vring_new_virtqueue(unsigned int index, vring_init(&vring_split.vring, num, pages, vring_align); return __vring_new_virtqueue(index, &vring_split, vdev, weak_barriers, - context, notify, callback, name); + context, notify, callback, name, + vdev->dev.parent); } EXPORT_SYMBOL_GPL(vring_new_virtqueue); @@ -2658,17 +2707,20 @@ static void vring_free(struct virtqueue *_vq) vring_free_queue(vq->vq.vdev, vq->packed.ring_size_in_bytes, vq->packed.vring.desc, - vq->packed.ring_dma_addr); + vq->packed.ring_dma_addr, + vring_dma_dev(vq)); vring_free_queue(vq->vq.vdev, vq->packed.event_size_in_bytes, vq->packed.vring.driver, - vq->packed.driver_event_dma_addr); + vq->packed.driver_event_dma_addr, + vring_dma_dev(vq)); vring_free_queue(vq->vq.vdev, vq->packed.event_size_in_bytes, vq->packed.vring.device, - vq->packed.device_event_dma_addr); + vq->packed.device_event_dma_addr, + vring_dma_dev(vq)); kfree(vq->packed.desc_state); kfree(vq->packed.desc_extra); @@ -2676,7 +2728,8 @@ static void vring_free(struct virtqueue *_vq) vring_free_queue(vq->vq.vdev, vq->split.queue_size_in_bytes, vq->split.vring.desc, - vq->split.queue_dma_addr); + vq->split.queue_dma_addr, + vring_dma_dev(vq)); } } if (!vq->packed_ring) { diff --git a/include/linux/virtio_ring.h b/include/linux/virtio_ring.h index 8b8af1a38991..8b95b69ef694 100644 --- a/include/linux/virtio_ring.h +++ b/include/linux/virtio_ring.h @@ -76,6 +76,22 @@ struct virtqueue *vring_create_virtqueue(unsigned int index, void (*callback)(struct virtqueue *vq), const char *name); +/* + * Creates a virtqueue and allocates the descriptor ring with per + * virtqueue DMA device. + */ +struct virtqueue *vring_create_virtqueue_dma(unsigned int index, + unsigned int num, + unsigned int vring_align, + struct virtio_device *vdev, + bool weak_barriers, + bool may_reduce_num, + bool ctx, + bool (*notify)(struct virtqueue *vq), + void (*callback)(struct virtqueue *vq), + const char *name, + struct device *dma_dev); + /* * Creates a virtqueue with a standard layout but a caller-allocated * ring. -- cgit v1.2.3 From 25da258fa61b1a902c781406a4e24a8284fc3d8a Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Thu, 19 Jan 2023 14:15:22 +0800 Subject: vdpa: introduce get_vq_dma_device() This patch introduces a new method to query the dma device that is use for a specific virtqueue. Reviewed-by: Eli Cohen Tested-by: Eli Cohen Signed-off-by: Jason Wang Message-Id: <20230119061525.75068-3-jasowang@redhat.com> Signed-off-by: Michael S. Tsirkin --- include/linux/vdpa.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 96d308cbf97b..43f59ef10cc9 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -285,6 +285,11 @@ struct vdpa_map_file { * @iova: iova to be unmapped * @size: size of the area * Returns integer: success (0) or error (< 0) + * @get_vq_dma_dev: Get the dma device for a specific + * virtqueue (optional) + * @vdev: vdpa device + * @idx: virtqueue index + * Returns pointer to structure device or error (NULL) * @free: Free resources that belongs to vDPA (optional) * @vdev: vdpa device */ @@ -345,6 +350,7 @@ struct vdpa_config_ops { u64 iova, u64 size); int (*set_group_asid)(struct vdpa_device *vdev, unsigned int group, unsigned int asid); + struct device *(*get_vq_dma_dev)(struct vdpa_device *vdev, u16 idx); /* Free device resources */ void (*free)(struct vdpa_device *vdev); -- cgit v1.2.3 From 2e44ca3f1f0ba2022f949003f02cc091144e54a3 Mon Sep 17 00:00:00 2001 From: Shunsuke Mie Date: Thu, 2 Feb 2023 19:42:48 +0900 Subject: vringh: fix a typo in comments for vringh_kiov Probably it is a simple copy error from struct vring_iov. Signed-off-by: Shunsuke Mie Message-Id: <20230202104248.2040652-1-mie@igel.co.jp> Signed-off-by: Michael S. Tsirkin --- include/linux/vringh.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/vringh.h b/include/linux/vringh.h index 212892cf9822..1991a02c6431 100644 --- a/include/linux/vringh.h +++ b/include/linux/vringh.h @@ -92,7 +92,7 @@ struct vringh_iov { }; /** - * struct vringh_iov - kvec mangler. + * struct vringh_kiov - kvec mangler. * * Mangles kvec in place, and restores it. * Remaining data is iov + i, of used - i elements. -- cgit v1.2.3 From 9e0c7efa5ea231d85c0d41693a5115b3b971717c Mon Sep 17 00:00:00 2001 From: Juhyung Park Date: Fri, 3 Feb 2023 11:40:29 +0900 Subject: block: remove more NULL checks after bdev_get_queue() bdev_get_queue() never returns NULL. Several commits [1][2] have been made before to remove such superfluous checks, but some still remained. For places where bdev_get_queue() is called solely for NULL checks, it is removed entirely. [1] commit ec9fd2a13d74 ("blk-lib: don't check bdev_get_queue() NULL check") [2] commit fea127b36c93 ("block: remove superfluous check for request queue in bdev_is_zoned()") Signed-off-by: Juhyung Park Reviewed-by: Pankaj Raghav Link: https://lore.kernel.org/r/20230203024029.48260-1-qkrwngud825@gmail.com Signed-off-by: Jens Axboe --- block/blk-zoned.c | 10 ---------- include/linux/blkdev.h | 7 +------ kernel/trace/blktrace.c | 6 +----- 3 files changed, 2 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/block/blk-zoned.c b/block/blk-zoned.c index 614b575be899..fce9082384d6 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -334,17 +334,12 @@ int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode, { void __user *argp = (void __user *)arg; struct zone_report_args args; - struct request_queue *q; struct blk_zone_report rep; int ret; if (!argp) return -EINVAL; - q = bdev_get_queue(bdev); - if (!q) - return -ENXIO; - if (!bdev_is_zoned(bdev)) return -ENOTTY; @@ -391,7 +386,6 @@ int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) { void __user *argp = (void __user *)arg; - struct request_queue *q; struct blk_zone_range zrange; enum req_op op; int ret; @@ -399,10 +393,6 @@ int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode, if (!argp) return -EINVAL; - q = bdev_get_queue(bdev); - if (!q) - return -ENXIO; - if (!bdev_is_zoned(bdev)) return -ENOTTY; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index b9637d63e6f0..89dd9b02b45b 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1276,12 +1276,7 @@ static inline bool bdev_nowait(struct block_device *bdev) static inline enum blk_zoned_model bdev_zoned_model(struct block_device *bdev) { - struct request_queue *q = bdev_get_queue(bdev); - - if (q) - return blk_queue_zoned_model(q); - - return BLK_ZONED_NONE; + return blk_queue_zoned_model(bdev_get_queue(bdev)); } static inline bool bdev_is_zoned(struct block_device *bdev) diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 5743be559415..d5d94510afd3 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -729,14 +729,10 @@ EXPORT_SYMBOL_GPL(blk_trace_startstop); **/ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg) { - struct request_queue *q; + struct request_queue *q = bdev_get_queue(bdev); int ret, start = 0; char b[BDEVNAME_SIZE]; - q = bdev_get_queue(bdev); - if (!q) - return -ENXIO; - mutex_lock(&q->debugfs_mutex); switch (cmd) { -- cgit v1.2.3 From 6c40624930c58529185a257380442547580ed837 Mon Sep 17 00:00:00 2001 From: Souradeep Chowdhury Date: Wed, 22 Feb 2023 08:27:49 +0900 Subject: bootconfig: Increase max nodes of bootconfig from 1024 to 8192 for DCC support The Data Capture and Compare(DCC) is a debugging tool that uses the bootconfig for configuring the register values during boot-time. Increase the max nodes supported by bootconfig to cater to the requirements of the Data Capture and Compare Driver. Link: https://lore.kernel.org/all/1674536682-18404-1-git-send-email-quic_schowdhu@quicinc.com/ Signed-off-by: Souradeep Chowdhury Acked-by: Masami Hiramatsu (Google) Signed-off-by: Masami Hiramatsu (Google) --- include/linux/bootconfig.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bootconfig.h b/include/linux/bootconfig.h index 1611f9db878e..ca73940e26df 100644 --- a/include/linux/bootconfig.h +++ b/include/linux/bootconfig.h @@ -59,7 +59,7 @@ struct xbc_node { /* Maximum size of boot config is 32KB - 1 */ #define XBC_DATA_MAX (XBC_VALUE - 1) -#define XBC_NODE_MAX 1024 +#define XBC_NODE_MAX 8192 #define XBC_KEYLEN_MAX 256 #define XBC_DEPTH_MAX 16 -- cgit v1.2.3 From fdf6491193e411087ae77bcbc6468e3e1cff99ed Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 20 Feb 2023 17:24:00 +0100 Subject: netfilter: ctnetlink: make event listener tracking global pernet tracking doesn't work correctly because other netns might have set NETLINK_LISTEN_ALL_NSID on its event socket. In this case its expected that events originating in other net namespaces are also received. Making pernet-tracking work while also honoring NETLINK_LISTEN_ALL_NSID requires much more intrusive changes both in netlink and nfnetlink, f.e. adding a 'setsockopt' callback that lets nfnetlink know that the event socket entered (or left) ALL_NSID mode. Move to global tracking instead: if there is an event socket anywhere on the system, all net namespaces which have conntrack enabled and use autobind mode will allocate the ecache extension. netlink_has_listeners() returns false only if the given group has no subscribers in any net namespace, the 'net' argument passed to nfnetlink_has_listeners is only used to derive the protocol (nfnetlink), it has no other effect. For proper NETLINK_LISTEN_ALL_NSID-aware pernet tracking of event listeners a new netlink_has_net_listeners() is also needed. Fixes: 90d1daa45849 ("netfilter: conntrack: add nf_conntrack_events autodetect mode") Reported-by: Bryce Kahle Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 5 +++++ include/net/netns/conntrack.h | 1 - net/netfilter/core.c | 3 +++ net/netfilter/nf_conntrack_ecache.c | 2 +- net/netfilter/nfnetlink.c | 9 +++++---- 5 files changed, 14 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index d8817d381c14..bef8db9d6c08 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -488,4 +488,9 @@ extern const struct nfnl_ct_hook __rcu *nfnl_ct_hook; */ DECLARE_PER_CPU(bool, nf_skb_duplicated); +/** + * Contains bitmask of ctnetlink event subscribers, if any. + * Can't be pernet due to NETLINK_LISTEN_ALL_NSID setsockopt flag. + */ +extern u8 nf_ctnetlink_has_listener; #endif /*__LINUX_NETFILTER_H*/ diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h index e1290c159184..1f463b3957c7 100644 --- a/include/net/netns/conntrack.h +++ b/include/net/netns/conntrack.h @@ -95,7 +95,6 @@ struct nf_ip_net { struct netns_ct { #ifdef CONFIG_NF_CONNTRACK_EVENTS - u8 ctnetlink_has_listener; bool ecache_dwork_pending; #endif u8 sysctl_log_invalid; /* Log invalid packets */ diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 5a6705a0e4ec..6e80f0f6149e 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -669,6 +669,9 @@ const struct nf_ct_hook __rcu *nf_ct_hook __read_mostly; EXPORT_SYMBOL_GPL(nf_ct_hook); #if IS_ENABLED(CONFIG_NF_CONNTRACK) +u8 nf_ctnetlink_has_listener; +EXPORT_SYMBOL_GPL(nf_ctnetlink_has_listener); + const struct nf_nat_hook __rcu *nf_nat_hook __read_mostly; EXPORT_SYMBOL_GPL(nf_nat_hook); diff --git a/net/netfilter/nf_conntrack_ecache.c b/net/netfilter/nf_conntrack_ecache.c index 8698b3424646..69948e1d6974 100644 --- a/net/netfilter/nf_conntrack_ecache.c +++ b/net/netfilter/nf_conntrack_ecache.c @@ -309,7 +309,7 @@ bool nf_ct_ecache_ext_add(struct nf_conn *ct, u16 ctmask, u16 expmask, gfp_t gfp break; return true; case 2: /* autodetect: no event listener, don't allocate extension. */ - if (!READ_ONCE(net->ct.ctnetlink_has_listener)) + if (!READ_ONCE(nf_ctnetlink_has_listener)) return true; fallthrough; case 1: diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 6d18fb346868..81c7737c803a 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -29,6 +29,7 @@ #include #include +#include #include MODULE_LICENSE("GPL"); @@ -685,12 +686,12 @@ static void nfnetlink_bind_event(struct net *net, unsigned int group) group_bit = (1 << group); spin_lock(&nfnl_grp_active_lock); - v = READ_ONCE(net->ct.ctnetlink_has_listener); + v = READ_ONCE(nf_ctnetlink_has_listener); if ((v & group_bit) == 0) { v |= group_bit; /* read concurrently without nfnl_grp_active_lock held. */ - WRITE_ONCE(net->ct.ctnetlink_has_listener, v); + WRITE_ONCE(nf_ctnetlink_has_listener, v); } spin_unlock(&nfnl_grp_active_lock); @@ -744,12 +745,12 @@ static void nfnetlink_unbind(struct net *net, int group) spin_lock(&nfnl_grp_active_lock); if (!nfnetlink_has_listeners(net, group)) { - u8 v = READ_ONCE(net->ct.ctnetlink_has_listener); + u8 v = READ_ONCE(nf_ctnetlink_has_listener); v &= ~group_bit; /* read concurrently without nfnl_grp_active_lock held. */ - WRITE_ONCE(net->ct.ctnetlink_has_listener, v); + WRITE_ONCE(nf_ctnetlink_has_listener, v); } spin_unlock(&nfnl_grp_active_lock); #endif -- cgit v1.2.3 From 8781ba7f45695af3ab8e8d1b55a31f527c9201a3 Mon Sep 17 00:00:00 2001 From: Aren Moynihan Date: Thu, 8 Dec 2022 17:02:26 -0500 Subject: mfd: axp20x: Fix order of pek rise and fall events The power button can get "stuck" if the rising edge and falling edge irq are read in the same pass. This can often be triggered when resuming from suspend if the power button is released before the kernel handles the interrupt. Swapping the order of the rise and fall events makes sure that the press event is handled first, which prevents this situation. Signed-off-by: Aren Moynihan Reviewed-by: Samuel Holland Tested-by: Samuel Holland Acked-by: Chen-Yu Tsai Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20221208220225.635414-1-aren@peacevolution.org --- include/linux/mfd/axp20x.h | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/axp20x.h b/include/linux/mfd/axp20x.h index 9ab0e2fca7ea..2058194807bd 100644 --- a/include/linux/mfd/axp20x.h +++ b/include/linux/mfd/axp20x.h @@ -432,8 +432,9 @@ enum { AXP152_IRQ_PEK_SHORT, AXP152_IRQ_PEK_LONG, AXP152_IRQ_TIMER, - AXP152_IRQ_PEK_RIS_EDGE, + /* out of bit order to make sure the press event is handled first */ AXP152_IRQ_PEK_FAL_EDGE, + AXP152_IRQ_PEK_RIS_EDGE, AXP152_IRQ_GPIO3_INPUT, AXP152_IRQ_GPIO2_INPUT, AXP152_IRQ_GPIO1_INPUT, @@ -472,8 +473,9 @@ enum { AXP20X_IRQ_LOW_PWR_LVL1, AXP20X_IRQ_LOW_PWR_LVL2, AXP20X_IRQ_TIMER, - AXP20X_IRQ_PEK_RIS_EDGE, + /* out of bit order to make sure the press event is handled first */ AXP20X_IRQ_PEK_FAL_EDGE, + AXP20X_IRQ_PEK_RIS_EDGE, AXP20X_IRQ_GPIO3_INPUT, AXP20X_IRQ_GPIO2_INPUT, AXP20X_IRQ_GPIO1_INPUT, @@ -502,8 +504,9 @@ enum axp22x_irqs { AXP22X_IRQ_LOW_PWR_LVL1, AXP22X_IRQ_LOW_PWR_LVL2, AXP22X_IRQ_TIMER, - AXP22X_IRQ_PEK_RIS_EDGE, + /* out of bit order to make sure the press event is handled first */ AXP22X_IRQ_PEK_FAL_EDGE, + AXP22X_IRQ_PEK_RIS_EDGE, AXP22X_IRQ_GPIO1_INPUT, AXP22X_IRQ_GPIO0_INPUT, }; @@ -571,8 +574,9 @@ enum axp803_irqs { AXP803_IRQ_LOW_PWR_LVL1, AXP803_IRQ_LOW_PWR_LVL2, AXP803_IRQ_TIMER, - AXP803_IRQ_PEK_RIS_EDGE, + /* out of bit order to make sure the press event is handled first */ AXP803_IRQ_PEK_FAL_EDGE, + AXP803_IRQ_PEK_RIS_EDGE, AXP803_IRQ_PEK_SHORT, AXP803_IRQ_PEK_LONG, AXP803_IRQ_PEK_OVER_OFF, @@ -623,8 +627,9 @@ enum axp809_irqs { AXP809_IRQ_LOW_PWR_LVL1, AXP809_IRQ_LOW_PWR_LVL2, AXP809_IRQ_TIMER, - AXP809_IRQ_PEK_RIS_EDGE, + /* out of bit order to make sure the press event is handled first */ AXP809_IRQ_PEK_FAL_EDGE, + AXP809_IRQ_PEK_RIS_EDGE, AXP809_IRQ_PEK_SHORT, AXP809_IRQ_PEK_LONG, AXP809_IRQ_PEK_OVER_OFF, -- cgit v1.2.3 From ccc91b3ed3f641efa8e9050c587ef509b0e2be3a Mon Sep 17 00:00:00 2001 From: Andreas Kemnade Date: Thu, 8 Dec 2022 22:57:23 +0100 Subject: mfd: twl: Fix TWL6032 phy vbus detection TWL6032 has a few charging registers prepended before the charging registers the TWL6030 has. To be able to use common register defines declare the additional registers as additional module. At the moment this affects the access to CHARGERUSB_CTRL1 in phy-twl6030-usb. Without this patch, it is accessing the wrong register on TWL6032. The consequence is that presence of Vbus is not reported. Cc: Bin Liu Cc: Tony Lindgren Signed-off-by: Andreas Kemnade Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20221208215723.217557-1-andreas@kemnade.info --- drivers/mfd/twl-core.c | 9 ++++----- include/linux/mfd/twl.h | 2 ++ 2 files changed, 6 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/mfd/twl-core.c b/drivers/mfd/twl-core.c index 62be2326c9b2..e2d9a93be43b 100644 --- a/drivers/mfd/twl-core.c +++ b/drivers/mfd/twl-core.c @@ -110,8 +110,8 @@ #define TWL6030_BASEADD_PWM 0x00BA #define TWL6030_BASEADD_GASGAUGE 0x00C0 #define TWL6030_BASEADD_PIH 0x00D0 -#define TWL6030_BASEADD_CHARGER 0x00E0 #define TWL6032_BASEADD_CHARGER 0x00DA +#define TWL6030_BASEADD_CHARGER 0x00E0 #define TWL6030_BASEADD_LED 0x00F4 /* subchip/slave 2 0x4A - DFT */ @@ -353,6 +353,9 @@ static struct twl_mapping twl6030_map[] = { { 2, TWL6030_BASEADD_ZERO }, { 1, TWL6030_BASEADD_GPADC_CTRL }, { 1, TWL6030_BASEADD_GASGAUGE }, + + /* TWL6032 specific charger registers */ + { 1, TWL6032_BASEADD_CHARGER }, }; static const struct regmap_config twl6030_regmap_config[3] = { @@ -803,10 +806,6 @@ twl_probe(struct i2c_client *client) if ((id->driver_data) & TWL6030_CLASS) { twl_priv->twl_id = TWL6030_CLASS_ID; twl_priv->twl_map = &twl6030_map[0]; - /* The charger base address is different in twl6032 */ - if ((id->driver_data) & TWL6032_SUBCLASS) - twl_priv->twl_map[TWL_MODULE_MAIN_CHARGE].base = - TWL6032_BASEADD_CHARGER; twl_regmap_config = twl6030_regmap_config; } else { twl_priv->twl_id = TWL4030_CLASS_ID; diff --git a/include/linux/mfd/twl.h b/include/linux/mfd/twl.h index eaa233038254..6e3d99b7a0ee 100644 --- a/include/linux/mfd/twl.h +++ b/include/linux/mfd/twl.h @@ -69,6 +69,8 @@ enum twl6030_module_ids { TWL6030_MODULE_GPADC, TWL6030_MODULE_GASGAUGE, + /* A few extra registers before the registers shared with the 6030 */ + TWL6032_MODULE_CHARGE, TWL6030_MODULE_LAST, }; -- cgit v1.2.3 From 88a32c2c5e98d72765846db83c1739e7b036770a Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 9 Jan 2023 14:33:22 +0100 Subject: mfd: core: Spelling s/compement/complement/ Fix a misspelling of "complement". Signed-off-by: Geert Uytterhoeven Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/aa7abd7103a0e4be954ea63de78f12e8251b2964.1673271092.git.geert+renesas@glider.be --- include/linux/mfd/core.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/core.h b/include/linux/mfd/core.h index 0bc7cba798a3..14ca7b471576 100644 --- a/include/linux/mfd/core.h +++ b/include/linux/mfd/core.h @@ -88,7 +88,7 @@ struct mfd_cell { const char *of_compatible; /* - * Address as defined in Device Tree. Used to compement 'of_compatible' + * Address as defined in Device Tree. Used to complement 'of_compatible' * (above) when matching OF nodes with devices that have identical * compatible strings */ -- cgit v1.2.3 From 5a7fbe452ad9e4a8988d4c20d7acf148383f8106 Mon Sep 17 00:00:00 2001 From: Uwe Kleine-König Date: Thu, 17 Nov 2022 08:21:51 +0100 Subject: backlight: pwm_bl: Drop support for legacy PWM probing There is no in-tree user left which relies on legacy probing. So drop support for it which removes another user of the deprecated pwm_request() function. Signed-off-by: Uwe Kleine-König Reviewed-by: Daniel Thompson Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20221117072151.3789691-1-u.kleine-koenig@pengutronix.de --- drivers/video/backlight/pwm_bl.c | 12 ------------ include/linux/pwm_backlight.h | 1 - 2 files changed, 13 deletions(-) (limited to 'include/linux') diff --git a/drivers/video/backlight/pwm_bl.c b/drivers/video/backlight/pwm_bl.c index c0523a0269ee..d0b22158cd70 100644 --- a/drivers/video/backlight/pwm_bl.c +++ b/drivers/video/backlight/pwm_bl.c @@ -28,7 +28,6 @@ struct pwm_bl_data { struct regulator *power_supply; struct gpio_desc *enable_gpio; unsigned int scale; - bool legacy; unsigned int post_pwm_on_delay; unsigned int pwm_off_delay; int (*notify)(struct device *, @@ -455,7 +454,6 @@ static int pwm_backlight_probe(struct platform_device *pdev) struct platform_pwm_backlight_data defdata; struct backlight_properties props; struct backlight_device *bl; - struct device_node *node = pdev->dev.of_node; struct pwm_bl_data *pb; struct pwm_state state; unsigned int i; @@ -506,12 +504,6 @@ static int pwm_backlight_probe(struct platform_device *pdev) } pb->pwm = devm_pwm_get(&pdev->dev, NULL); - if (IS_ERR(pb->pwm) && PTR_ERR(pb->pwm) != -EPROBE_DEFER && !node) { - dev_err(&pdev->dev, "unable to request PWM, trying legacy API\n"); - pb->legacy = true; - pb->pwm = pwm_request(data->pwm_id, "pwm-backlight"); - } - if (IS_ERR(pb->pwm)) { ret = PTR_ERR(pb->pwm); if (ret != -EPROBE_DEFER) @@ -604,8 +596,6 @@ static int pwm_backlight_probe(struct platform_device *pdev) if (IS_ERR(bl)) { dev_err(&pdev->dev, "failed to register backlight\n"); ret = PTR_ERR(bl); - if (pb->legacy) - pwm_free(pb->pwm); goto err_alloc; } @@ -639,8 +629,6 @@ static int pwm_backlight_remove(struct platform_device *pdev) if (pb->exit) pb->exit(&pdev->dev); - if (pb->legacy) - pwm_free(pb->pwm); return 0; } diff --git a/include/linux/pwm_backlight.h b/include/linux/pwm_backlight.h index 06086cb93b6f..cdd2ac366bc7 100644 --- a/include/linux/pwm_backlight.h +++ b/include/linux/pwm_backlight.h @@ -8,7 +8,6 @@ #include struct platform_pwm_backlight_data { - int pwm_id; unsigned int max_brightness; unsigned int dft_brightness; unsigned int lth_brightness; -- cgit v1.2.3 From ca78476e4888f1f1caac26c48ec715e546baf432 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 5 Jan 2023 14:46:13 +0100 Subject: mfd: Remove toshiba tmio drivers Four separate mfd drivers are in the "tmio" family, and all of them were used in now-removed PXA machines (eseries, tosa, and hx4700), so the mfd drivers and all its children can be removed as well. Signed-off-by: Arnd Bergmann Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230105134622.254560-19-arnd@kernel.org --- drivers/mfd/Kconfig | 38 -- drivers/mfd/Makefile | 4 - drivers/mfd/asic3.c | 1071 ------------------------------------------ drivers/mfd/t7l66xb.c | 427 ----------------- drivers/mfd/tc6387xb.c | 228 --------- drivers/mfd/tc6393xb.c | 907 ----------------------------------- drivers/mfd/tmio_core.c | 70 --- include/linux/mfd/asic3.h | 313 ------------ include/linux/mfd/t7l66xb.h | 29 -- include/linux/mfd/tc6387xb.h | 19 - include/linux/mfd/tc6393xb.h | 53 --- include/linux/mfd/tmio.h | 5 - 12 files changed, 3164 deletions(-) delete mode 100644 drivers/mfd/asic3.c delete mode 100644 drivers/mfd/t7l66xb.c delete mode 100644 drivers/mfd/tc6387xb.c delete mode 100644 drivers/mfd/tc6393xb.c delete mode 100644 drivers/mfd/tmio_core.c delete mode 100644 include/linux/mfd/asic3.h delete mode 100644 include/linux/mfd/t7l66xb.h delete mode 100644 include/linux/mfd/tc6387xb.h delete mode 100644 include/linux/mfd/tc6393xb.h (limited to 'include/linux') diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig index d90b4258fc44..d4fc4ca9fdbd 100644 --- a/drivers/mfd/Kconfig +++ b/drivers/mfd/Kconfig @@ -301,15 +301,6 @@ config MFD_CS47L92 help Support for Cirrus Logic CS42L92, CS47L92 and CS47L93 Smart Codecs -config MFD_ASIC3 - bool "Compaq ASIC3" - depends on GPIOLIB - depends on ARM || COMPILE_TEST - select MFD_CORE - help - This driver supports the ASIC3 multifunction chip found on many - PDAs (mainly iPAQ and HTC based ones) - config PMIC_DA903X bool "Dialog Semiconductor DA9030/DA9034 PMIC Support" depends on I2C=y @@ -1796,35 +1787,6 @@ config MFD_TC3589X additional drivers must be enabled in order to use the functionality of the device. -config MFD_TMIO - bool - default n - -config MFD_T7L66XB - bool "Toshiba T7L66XB" - depends on ARM && HAVE_CLK - select MFD_CORE - select MFD_TMIO - help - Support for Toshiba Mobile IO Controller T7L66XB - -config MFD_TC6387XB - bool "Toshiba TC6387XB" - depends on ARM && HAVE_CLK - select MFD_CORE - select MFD_TMIO - help - Support for Toshiba Mobile IO Controller TC6387XB - -config MFD_TC6393XB - bool "Toshiba TC6393XB" - depends on ARM && HAVE_CLK - select GPIOLIB - select MFD_CORE - select MFD_TMIO - help - Support for Toshiba Mobile IO Controller TC6393XB - config MFD_TQMX86 tristate "TQ-Systems IO controller TQMX86" select MFD_CORE diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile index 81c30d7cf5d4..48cf532848c4 100644 --- a/drivers/mfd/Makefile +++ b/drivers/mfd/Makefile @@ -9,7 +9,6 @@ obj-$(CONFIG_MFD_88PM800) += 88pm800.o 88pm80x.o obj-$(CONFIG_MFD_88PM805) += 88pm805.o 88pm80x.o obj-$(CONFIG_MFD_ACT8945A) += act8945a.o obj-$(CONFIG_MFD_SM501) += sm501.o -obj-$(CONFIG_MFD_ASIC3) += asic3.o tmio_core.o obj-$(CONFIG_ARCH_BCM2835) += bcm2835-pm.o obj-$(CONFIG_MFD_BCM590XX) += bcm590xx.o obj-$(CONFIG_MFD_BD9571MWV) += bd9571mwv.o @@ -30,9 +29,6 @@ obj-$(CONFIG_STMPE_I2C) += stmpe-i2c.o obj-$(CONFIG_STMPE_SPI) += stmpe-spi.o obj-$(CONFIG_MFD_SUN6I_PRCM) += sun6i-prcm.o obj-$(CONFIG_MFD_TC3589X) += tc3589x.o -obj-$(CONFIG_MFD_T7L66XB) += t7l66xb.o tmio_core.o -obj-$(CONFIG_MFD_TC6387XB) += tc6387xb.o tmio_core.o -obj-$(CONFIG_MFD_TC6393XB) += tc6393xb.o tmio_core.o obj-$(CONFIG_MFD_TQMX86) += tqmx86.o obj-$(CONFIG_MFD_LOCHNAGAR) += lochnagar-i2c.o diff --git a/drivers/mfd/asic3.c b/drivers/mfd/asic3.c deleted file mode 100644 index 4fb7e35eb5ed..000000000000 --- a/drivers/mfd/asic3.c +++ /dev/null @@ -1,1071 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * driver/mfd/asic3.c - * - * Compaq ASIC3 support. - * - * Copyright 2001 Compaq Computer Corporation. - * Copyright 2004-2005 Phil Blundell - * Copyright 2007-2008 OpenedHand Ltd. - * - * Authors: Phil Blundell , - * Samuel Ortiz - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include -#include - -#include - -enum { - ASIC3_CLOCK_SPI, - ASIC3_CLOCK_OWM, - ASIC3_CLOCK_PWM0, - ASIC3_CLOCK_PWM1, - ASIC3_CLOCK_LED0, - ASIC3_CLOCK_LED1, - ASIC3_CLOCK_LED2, - ASIC3_CLOCK_SD_HOST, - ASIC3_CLOCK_SD_BUS, - ASIC3_CLOCK_SMBUS, - ASIC3_CLOCK_EX0, - ASIC3_CLOCK_EX1, -}; - -struct asic3_clk { - int enabled; - unsigned int cdex; - unsigned long rate; -}; - -#define INIT_CDEX(_name, _rate) \ - [ASIC3_CLOCK_##_name] = { \ - .cdex = CLOCK_CDEX_##_name, \ - .rate = _rate, \ - } - -static struct asic3_clk asic3_clk_init[] __initdata = { - INIT_CDEX(SPI, 0), - INIT_CDEX(OWM, 5000000), - INIT_CDEX(PWM0, 0), - INIT_CDEX(PWM1, 0), - INIT_CDEX(LED0, 0), - INIT_CDEX(LED1, 0), - INIT_CDEX(LED2, 0), - INIT_CDEX(SD_HOST, 24576000), - INIT_CDEX(SD_BUS, 12288000), - INIT_CDEX(SMBUS, 0), - INIT_CDEX(EX0, 32768), - INIT_CDEX(EX1, 24576000), -}; - -struct asic3 { - void __iomem *mapping; - unsigned int bus_shift; - unsigned int irq_nr; - unsigned int irq_base; - raw_spinlock_t lock; - u16 irq_bothedge[4]; - struct gpio_chip gpio; - struct device *dev; - void __iomem *tmio_cnf; - - struct asic3_clk clocks[ARRAY_SIZE(asic3_clk_init)]; -}; - -static int asic3_gpio_get(struct gpio_chip *chip, unsigned offset); - -void asic3_write_register(struct asic3 *asic, unsigned int reg, u32 value) -{ - iowrite16(value, asic->mapping + - (reg >> asic->bus_shift)); -} -EXPORT_SYMBOL_GPL(asic3_write_register); - -u32 asic3_read_register(struct asic3 *asic, unsigned int reg) -{ - return ioread16(asic->mapping + - (reg >> asic->bus_shift)); -} -EXPORT_SYMBOL_GPL(asic3_read_register); - -static void asic3_set_register(struct asic3 *asic, u32 reg, u32 bits, bool set) -{ - unsigned long flags; - u32 val; - - raw_spin_lock_irqsave(&asic->lock, flags); - val = asic3_read_register(asic, reg); - if (set) - val |= bits; - else - val &= ~bits; - asic3_write_register(asic, reg, val); - raw_spin_unlock_irqrestore(&asic->lock, flags); -} - -/* IRQs */ -#define MAX_ASIC_ISR_LOOPS 20 -#define ASIC3_GPIO_BASE_INCR \ - (ASIC3_GPIO_B_BASE - ASIC3_GPIO_A_BASE) - -static void asic3_irq_flip_edge(struct asic3 *asic, - u32 base, int bit) -{ - u16 edge; - unsigned long flags; - - raw_spin_lock_irqsave(&asic->lock, flags); - edge = asic3_read_register(asic, - base + ASIC3_GPIO_EDGE_TRIGGER); - edge ^= bit; - asic3_write_register(asic, - base + ASIC3_GPIO_EDGE_TRIGGER, edge); - raw_spin_unlock_irqrestore(&asic->lock, flags); -} - -static void asic3_irq_demux(struct irq_desc *desc) -{ - struct asic3 *asic = irq_desc_get_handler_data(desc); - struct irq_data *data = irq_desc_get_irq_data(desc); - int iter, i; - unsigned long flags; - - data->chip->irq_ack(data); - - for (iter = 0 ; iter < MAX_ASIC_ISR_LOOPS; iter++) { - u32 status; - int bank; - - raw_spin_lock_irqsave(&asic->lock, flags); - status = asic3_read_register(asic, - ASIC3_OFFSET(INTR, P_INT_STAT)); - raw_spin_unlock_irqrestore(&asic->lock, flags); - - /* Check all ten register bits */ - if ((status & 0x3ff) == 0) - break; - - /* Handle GPIO IRQs */ - for (bank = 0; bank < ASIC3_NUM_GPIO_BANKS; bank++) { - if (status & (1 << bank)) { - unsigned long base, istat; - - base = ASIC3_GPIO_A_BASE - + bank * ASIC3_GPIO_BASE_INCR; - raw_spin_lock_irqsave(&asic->lock, flags); - istat = asic3_read_register(asic, - base + - ASIC3_GPIO_INT_STATUS); - /* Clearing IntStatus */ - asic3_write_register(asic, - base + - ASIC3_GPIO_INT_STATUS, 0); - raw_spin_unlock_irqrestore(&asic->lock, flags); - - for (i = 0; i < ASIC3_GPIOS_PER_BANK; i++) { - int bit = (1 << i); - unsigned int irqnr; - - if (!(istat & bit)) - continue; - - irqnr = asic->irq_base + - (ASIC3_GPIOS_PER_BANK * bank) - + i; - generic_handle_irq(irqnr); - if (asic->irq_bothedge[bank] & bit) - asic3_irq_flip_edge(asic, base, - bit); - } - } - } - - /* Handle remaining IRQs in the status register */ - for (i = ASIC3_NUM_GPIOS; i < ASIC3_NR_IRQS; i++) { - /* They start at bit 4 and go up */ - if (status & (1 << (i - ASIC3_NUM_GPIOS + 4))) - generic_handle_irq(asic->irq_base + i); - } - } - - if (iter >= MAX_ASIC_ISR_LOOPS) - dev_err(asic->dev, "interrupt processing overrun\n"); -} - -static inline int asic3_irq_to_bank(struct asic3 *asic, int irq) -{ - int n; - - n = (irq - asic->irq_base) >> 4; - - return (n * (ASIC3_GPIO_B_BASE - ASIC3_GPIO_A_BASE)); -} - -static inline int asic3_irq_to_index(struct asic3 *asic, int irq) -{ - return (irq - asic->irq_base) & 0xf; -} - -static void asic3_mask_gpio_irq(struct irq_data *data) -{ - struct asic3 *asic = irq_data_get_irq_chip_data(data); - u32 val, bank, index; - unsigned long flags; - - bank = asic3_irq_to_bank(asic, data->irq); - index = asic3_irq_to_index(asic, data->irq); - - raw_spin_lock_irqsave(&asic->lock, flags); - val = asic3_read_register(asic, bank + ASIC3_GPIO_MASK); - val |= 1 << index; - asic3_write_register(asic, bank + ASIC3_GPIO_MASK, val); - raw_spin_unlock_irqrestore(&asic->lock, flags); -} - -static void asic3_mask_irq(struct irq_data *data) -{ - struct asic3 *asic = irq_data_get_irq_chip_data(data); - int regval; - unsigned long flags; - - raw_spin_lock_irqsave(&asic->lock, flags); - regval = asic3_read_register(asic, - ASIC3_INTR_BASE + - ASIC3_INTR_INT_MASK); - - regval &= ~(ASIC3_INTMASK_MASK0 << - (data->irq - (asic->irq_base + ASIC3_NUM_GPIOS))); - - asic3_write_register(asic, - ASIC3_INTR_BASE + - ASIC3_INTR_INT_MASK, - regval); - raw_spin_unlock_irqrestore(&asic->lock, flags); -} - -static void asic3_unmask_gpio_irq(struct irq_data *data) -{ - struct asic3 *asic = irq_data_get_irq_chip_data(data); - u32 val, bank, index; - unsigned long flags; - - bank = asic3_irq_to_bank(asic, data->irq); - index = asic3_irq_to_index(asic, data->irq); - - raw_spin_lock_irqsave(&asic->lock, flags); - val = asic3_read_register(asic, bank + ASIC3_GPIO_MASK); - val &= ~(1 << index); - asic3_write_register(asic, bank + ASIC3_GPIO_MASK, val); - raw_spin_unlock_irqrestore(&asic->lock, flags); -} - -static void asic3_unmask_irq(struct irq_data *data) -{ - struct asic3 *asic = irq_data_get_irq_chip_data(data); - int regval; - unsigned long flags; - - raw_spin_lock_irqsave(&asic->lock, flags); - regval = asic3_read_register(asic, - ASIC3_INTR_BASE + - ASIC3_INTR_INT_MASK); - - regval |= (ASIC3_INTMASK_MASK0 << - (data->irq - (asic->irq_base + ASIC3_NUM_GPIOS))); - - asic3_write_register(asic, - ASIC3_INTR_BASE + - ASIC3_INTR_INT_MASK, - regval); - raw_spin_unlock_irqrestore(&asic->lock, flags); -} - -static int asic3_gpio_irq_type(struct irq_data *data, unsigned int type) -{ - struct asic3 *asic = irq_data_get_irq_chip_data(data); - u32 bank, index; - u16 trigger, level, edge, bit; - unsigned long flags; - - bank = asic3_irq_to_bank(asic, data->irq); - index = asic3_irq_to_index(asic, data->irq); - bit = 1<lock, flags); - level = asic3_read_register(asic, - bank + ASIC3_GPIO_LEVEL_TRIGGER); - edge = asic3_read_register(asic, - bank + ASIC3_GPIO_EDGE_TRIGGER); - trigger = asic3_read_register(asic, - bank + ASIC3_GPIO_TRIGGER_TYPE); - asic->irq_bothedge[(data->irq - asic->irq_base) >> 4] &= ~bit; - - if (type == IRQ_TYPE_EDGE_RISING) { - trigger |= bit; - edge |= bit; - } else if (type == IRQ_TYPE_EDGE_FALLING) { - trigger |= bit; - edge &= ~bit; - } else if (type == IRQ_TYPE_EDGE_BOTH) { - trigger |= bit; - if (asic3_gpio_get(&asic->gpio, data->irq - asic->irq_base)) - edge &= ~bit; - else - edge |= bit; - asic->irq_bothedge[(data->irq - asic->irq_base) >> 4] |= bit; - } else if (type == IRQ_TYPE_LEVEL_LOW) { - trigger &= ~bit; - level &= ~bit; - } else if (type == IRQ_TYPE_LEVEL_HIGH) { - trigger &= ~bit; - level |= bit; - } else { - /* - * if type == IRQ_TYPE_NONE, we should mask interrupts, but - * be careful to not unmask them if mask was also called. - * Probably need internal state for mask. - */ - dev_notice(asic->dev, "irq type not changed\n"); - } - asic3_write_register(asic, bank + ASIC3_GPIO_LEVEL_TRIGGER, - level); - asic3_write_register(asic, bank + ASIC3_GPIO_EDGE_TRIGGER, - edge); - asic3_write_register(asic, bank + ASIC3_GPIO_TRIGGER_TYPE, - trigger); - raw_spin_unlock_irqrestore(&asic->lock, flags); - return 0; -} - -static int asic3_gpio_irq_set_wake(struct irq_data *data, unsigned int on) -{ - struct asic3 *asic = irq_data_get_irq_chip_data(data); - u32 bank, index; - u16 bit; - - bank = asic3_irq_to_bank(asic, data->irq); - index = asic3_irq_to_index(asic, data->irq); - bit = 1<irq_nr = ret; - - /* turn on clock to IRQ controller */ - clksel |= CLOCK_SEL_CX; - asic3_write_register(asic, ASIC3_OFFSET(CLOCK, SEL), - clksel); - - irq_base = asic->irq_base; - - for (irq = irq_base; irq < irq_base + ASIC3_NR_IRQS; irq++) { - if (irq < asic->irq_base + ASIC3_NUM_GPIOS) - irq_set_chip(irq, &asic3_gpio_irq_chip); - else - irq_set_chip(irq, &asic3_irq_chip); - - irq_set_chip_data(irq, asic); - irq_set_handler(irq, handle_level_irq); - irq_clear_status_flags(irq, IRQ_NOREQUEST | IRQ_NOPROBE); - } - - asic3_write_register(asic, ASIC3_OFFSET(INTR, INT_MASK), - ASIC3_INTMASK_GINTMASK); - - irq_set_chained_handler_and_data(asic->irq_nr, asic3_irq_demux, asic); - irq_set_irq_type(asic->irq_nr, IRQ_TYPE_EDGE_RISING); - - return 0; -} - -static void asic3_irq_remove(struct platform_device *pdev) -{ - struct asic3 *asic = platform_get_drvdata(pdev); - unsigned int irq, irq_base; - - irq_base = asic->irq_base; - - for (irq = irq_base; irq < irq_base + ASIC3_NR_IRQS; irq++) { - irq_set_status_flags(irq, IRQ_NOREQUEST | IRQ_NOPROBE); - irq_set_chip_and_handler(irq, NULL, NULL); - irq_set_chip_data(irq, NULL); - } - irq_set_chained_handler(asic->irq_nr, NULL); -} - -/* GPIOs */ -static int asic3_gpio_direction(struct gpio_chip *chip, - unsigned offset, int out) -{ - u32 mask = ASIC3_GPIO_TO_MASK(offset), out_reg; - unsigned int gpio_base; - unsigned long flags; - struct asic3 *asic; - - asic = gpiochip_get_data(chip); - gpio_base = ASIC3_GPIO_TO_BASE(offset); - - if (gpio_base > ASIC3_GPIO_D_BASE) { - dev_err(asic->dev, "Invalid base (0x%x) for gpio %d\n", - gpio_base, offset); - return -EINVAL; - } - - raw_spin_lock_irqsave(&asic->lock, flags); - - out_reg = asic3_read_register(asic, gpio_base + ASIC3_GPIO_DIRECTION); - - /* Input is 0, Output is 1 */ - if (out) - out_reg |= mask; - else - out_reg &= ~mask; - - asic3_write_register(asic, gpio_base + ASIC3_GPIO_DIRECTION, out_reg); - - raw_spin_unlock_irqrestore(&asic->lock, flags); - - return 0; - -} - -static int asic3_gpio_direction_input(struct gpio_chip *chip, - unsigned offset) -{ - return asic3_gpio_direction(chip, offset, 0); -} - -static int asic3_gpio_direction_output(struct gpio_chip *chip, - unsigned offset, int value) -{ - return asic3_gpio_direction(chip, offset, 1); -} - -static int asic3_gpio_get(struct gpio_chip *chip, - unsigned offset) -{ - unsigned int gpio_base; - u32 mask = ASIC3_GPIO_TO_MASK(offset); - struct asic3 *asic; - - asic = gpiochip_get_data(chip); - gpio_base = ASIC3_GPIO_TO_BASE(offset); - - if (gpio_base > ASIC3_GPIO_D_BASE) { - dev_err(asic->dev, "Invalid base (0x%x) for gpio %d\n", - gpio_base, offset); - return -EINVAL; - } - - return !!(asic3_read_register(asic, - gpio_base + ASIC3_GPIO_STATUS) & mask); -} - -static void asic3_gpio_set(struct gpio_chip *chip, - unsigned offset, int value) -{ - u32 mask, out_reg; - unsigned int gpio_base; - unsigned long flags; - struct asic3 *asic; - - asic = gpiochip_get_data(chip); - gpio_base = ASIC3_GPIO_TO_BASE(offset); - - if (gpio_base > ASIC3_GPIO_D_BASE) { - dev_err(asic->dev, "Invalid base (0x%x) for gpio %d\n", - gpio_base, offset); - return; - } - - mask = ASIC3_GPIO_TO_MASK(offset); - - raw_spin_lock_irqsave(&asic->lock, flags); - - out_reg = asic3_read_register(asic, gpio_base + ASIC3_GPIO_OUT); - - if (value) - out_reg |= mask; - else - out_reg &= ~mask; - - asic3_write_register(asic, gpio_base + ASIC3_GPIO_OUT, out_reg); - - raw_spin_unlock_irqrestore(&asic->lock, flags); -} - -static int asic3_gpio_to_irq(struct gpio_chip *chip, unsigned offset) -{ - struct asic3 *asic = gpiochip_get_data(chip); - - return asic->irq_base + offset; -} - -static __init int asic3_gpio_probe(struct platform_device *pdev, - u16 *gpio_config, int num) -{ - struct asic3 *asic = platform_get_drvdata(pdev); - u16 alt_reg[ASIC3_NUM_GPIO_BANKS]; - u16 out_reg[ASIC3_NUM_GPIO_BANKS]; - u16 dir_reg[ASIC3_NUM_GPIO_BANKS]; - int i; - - memset(alt_reg, 0, ASIC3_NUM_GPIO_BANKS * sizeof(u16)); - memset(out_reg, 0, ASIC3_NUM_GPIO_BANKS * sizeof(u16)); - memset(dir_reg, 0, ASIC3_NUM_GPIO_BANKS * sizeof(u16)); - - /* Enable all GPIOs */ - asic3_write_register(asic, ASIC3_GPIO_OFFSET(A, MASK), 0xffff); - asic3_write_register(asic, ASIC3_GPIO_OFFSET(B, MASK), 0xffff); - asic3_write_register(asic, ASIC3_GPIO_OFFSET(C, MASK), 0xffff); - asic3_write_register(asic, ASIC3_GPIO_OFFSET(D, MASK), 0xffff); - - for (i = 0; i < num; i++) { - u8 alt, pin, dir, init, bank_num, bit_num; - u16 config = gpio_config[i]; - - pin = ASIC3_CONFIG_GPIO_PIN(config); - alt = ASIC3_CONFIG_GPIO_ALT(config); - dir = ASIC3_CONFIG_GPIO_DIR(config); - init = ASIC3_CONFIG_GPIO_INIT(config); - - bank_num = ASIC3_GPIO_TO_BANK(pin); - bit_num = ASIC3_GPIO_TO_BIT(pin); - - alt_reg[bank_num] |= (alt << bit_num); - out_reg[bank_num] |= (init << bit_num); - dir_reg[bank_num] |= (dir << bit_num); - } - - for (i = 0; i < ASIC3_NUM_GPIO_BANKS; i++) { - asic3_write_register(asic, - ASIC3_BANK_TO_BASE(i) + - ASIC3_GPIO_DIRECTION, - dir_reg[i]); - asic3_write_register(asic, - ASIC3_BANK_TO_BASE(i) + ASIC3_GPIO_OUT, - out_reg[i]); - asic3_write_register(asic, - ASIC3_BANK_TO_BASE(i) + - ASIC3_GPIO_ALT_FUNCTION, - alt_reg[i]); - } - - return gpiochip_add_data(&asic->gpio, asic); -} - -static void asic3_gpio_remove(struct platform_device *pdev) -{ - struct asic3 *asic = platform_get_drvdata(pdev); - - gpiochip_remove(&asic->gpio); -} - -static void asic3_clk_enable(struct asic3 *asic, struct asic3_clk *clk) -{ - unsigned long flags; - u32 cdex; - - raw_spin_lock_irqsave(&asic->lock, flags); - if (clk->enabled++ == 0) { - cdex = asic3_read_register(asic, ASIC3_OFFSET(CLOCK, CDEX)); - cdex |= clk->cdex; - asic3_write_register(asic, ASIC3_OFFSET(CLOCK, CDEX), cdex); - } - raw_spin_unlock_irqrestore(&asic->lock, flags); -} - -static void asic3_clk_disable(struct asic3 *asic, struct asic3_clk *clk) -{ - unsigned long flags; - u32 cdex; - - WARN_ON(clk->enabled == 0); - - raw_spin_lock_irqsave(&asic->lock, flags); - if (--clk->enabled == 0) { - cdex = asic3_read_register(asic, ASIC3_OFFSET(CLOCK, CDEX)); - cdex &= ~clk->cdex; - asic3_write_register(asic, ASIC3_OFFSET(CLOCK, CDEX), cdex); - } - raw_spin_unlock_irqrestore(&asic->lock, flags); -} - -/* MFD cells (SPI, PWM, LED, DS1WM, MMC) */ -static struct ds1wm_driver_data ds1wm_pdata = { - .active_high = 1, - .reset_recover_delay = 1, -}; - -static struct resource ds1wm_resources[] = { - { - .start = ASIC3_OWM_BASE, - .end = ASIC3_OWM_BASE + 0x13, - .flags = IORESOURCE_MEM, - }, - { - .start = ASIC3_IRQ_OWM, - .end = ASIC3_IRQ_OWM, - .flags = IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHEDGE, - }, -}; - -static int ds1wm_enable(struct platform_device *pdev) -{ - struct asic3 *asic = dev_get_drvdata(pdev->dev.parent); - - /* Turn on external clocks and the OWM clock */ - asic3_clk_enable(asic, &asic->clocks[ASIC3_CLOCK_EX0]); - asic3_clk_enable(asic, &asic->clocks[ASIC3_CLOCK_EX1]); - asic3_clk_enable(asic, &asic->clocks[ASIC3_CLOCK_OWM]); - usleep_range(1000, 5000); - - /* Reset and enable DS1WM */ - asic3_set_register(asic, ASIC3_OFFSET(EXTCF, RESET), - ASIC3_EXTCF_OWM_RESET, 1); - usleep_range(1000, 5000); - asic3_set_register(asic, ASIC3_OFFSET(EXTCF, RESET), - ASIC3_EXTCF_OWM_RESET, 0); - usleep_range(1000, 5000); - asic3_set_register(asic, ASIC3_OFFSET(EXTCF, SELECT), - ASIC3_EXTCF_OWM_EN, 1); - usleep_range(1000, 5000); - - return 0; -} - -static int ds1wm_disable(struct platform_device *pdev) -{ - struct asic3 *asic = dev_get_drvdata(pdev->dev.parent); - - asic3_set_register(asic, ASIC3_OFFSET(EXTCF, SELECT), - ASIC3_EXTCF_OWM_EN, 0); - - asic3_clk_disable(asic, &asic->clocks[ASIC3_CLOCK_OWM]); - asic3_clk_disable(asic, &asic->clocks[ASIC3_CLOCK_EX0]); - asic3_clk_disable(asic, &asic->clocks[ASIC3_CLOCK_EX1]); - - return 0; -} - -static const struct mfd_cell asic3_cell_ds1wm = { - .name = "ds1wm", - .enable = ds1wm_enable, - .disable = ds1wm_disable, - .platform_data = &ds1wm_pdata, - .pdata_size = sizeof(ds1wm_pdata), - .num_resources = ARRAY_SIZE(ds1wm_resources), - .resources = ds1wm_resources, -}; - -static void asic3_mmc_pwr(struct platform_device *pdev, int state) -{ - struct asic3 *asic = dev_get_drvdata(pdev->dev.parent); - - tmio_core_mmc_pwr(asic->tmio_cnf, 1 - asic->bus_shift, state); -} - -static void asic3_mmc_clk_div(struct platform_device *pdev, int state) -{ - struct asic3 *asic = dev_get_drvdata(pdev->dev.parent); - - tmio_core_mmc_clk_div(asic->tmio_cnf, 1 - asic->bus_shift, state); -} - -static struct tmio_mmc_data asic3_mmc_data = { - .hclk = 24576000, - .ocr_mask = MMC_VDD_32_33 | MMC_VDD_33_34, - .set_pwr = asic3_mmc_pwr, - .set_clk_div = asic3_mmc_clk_div, -}; - -static struct resource asic3_mmc_resources[] = { - DEFINE_RES_MEM(ASIC3_SD_CTRL_BASE, 0x400), - DEFINE_RES_IRQ(0) -}; - -static int asic3_mmc_enable(struct platform_device *pdev) -{ - struct asic3 *asic = dev_get_drvdata(pdev->dev.parent); - - /* Not sure if it must be done bit by bit, but leaving as-is */ - asic3_set_register(asic, ASIC3_OFFSET(SDHWCTRL, SDCONF), - ASIC3_SDHWCTRL_LEVCD, 1); - asic3_set_register(asic, ASIC3_OFFSET(SDHWCTRL, SDCONF), - ASIC3_SDHWCTRL_LEVWP, 1); - asic3_set_register(asic, ASIC3_OFFSET(SDHWCTRL, SDCONF), - ASIC3_SDHWCTRL_SUSPEND, 0); - asic3_set_register(asic, ASIC3_OFFSET(SDHWCTRL, SDCONF), - ASIC3_SDHWCTRL_PCLR, 0); - - asic3_clk_enable(asic, &asic->clocks[ASIC3_CLOCK_EX0]); - /* CLK32 used for card detection and for interruption detection - * when HCLK is stopped. - */ - asic3_clk_enable(asic, &asic->clocks[ASIC3_CLOCK_EX1]); - usleep_range(1000, 5000); - - /* HCLK 24.576 MHz, BCLK 12.288 MHz: */ - asic3_write_register(asic, ASIC3_OFFSET(CLOCK, SEL), - CLOCK_SEL_CX | CLOCK_SEL_SD_HCLK_SEL); - - asic3_clk_enable(asic, &asic->clocks[ASIC3_CLOCK_SD_HOST]); - asic3_clk_enable(asic, &asic->clocks[ASIC3_CLOCK_SD_BUS]); - usleep_range(1000, 5000); - - asic3_set_register(asic, ASIC3_OFFSET(EXTCF, SELECT), - ASIC3_EXTCF_SD_MEM_ENABLE, 1); - - /* Enable SD card slot 3.3V power supply */ - asic3_set_register(asic, ASIC3_OFFSET(SDHWCTRL, SDCONF), - ASIC3_SDHWCTRL_SDPWR, 1); - - /* ASIC3_SD_CTRL_BASE assumes 32-bit addressing, TMIO is 16-bit */ - tmio_core_mmc_enable(asic->tmio_cnf, 1 - asic->bus_shift, - ASIC3_SD_CTRL_BASE >> 1); - - return 0; -} - -static int asic3_mmc_disable(struct platform_device *pdev) -{ - struct asic3 *asic = dev_get_drvdata(pdev->dev.parent); - - /* Put in suspend mode */ - asic3_set_register(asic, ASIC3_OFFSET(SDHWCTRL, SDCONF), - ASIC3_SDHWCTRL_SUSPEND, 1); - - /* Disable clocks */ - asic3_clk_disable(asic, &asic->clocks[ASIC3_CLOCK_SD_HOST]); - asic3_clk_disable(asic, &asic->clocks[ASIC3_CLOCK_SD_BUS]); - asic3_clk_disable(asic, &asic->clocks[ASIC3_CLOCK_EX0]); - asic3_clk_disable(asic, &asic->clocks[ASIC3_CLOCK_EX1]); - return 0; -} - -static const struct mfd_cell asic3_cell_mmc = { - .name = "tmio-mmc", - .enable = asic3_mmc_enable, - .disable = asic3_mmc_disable, - .suspend = asic3_mmc_disable, - .resume = asic3_mmc_enable, - .platform_data = &asic3_mmc_data, - .pdata_size = sizeof(asic3_mmc_data), - .num_resources = ARRAY_SIZE(asic3_mmc_resources), - .resources = asic3_mmc_resources, -}; - -static const int clock_ledn[ASIC3_NUM_LEDS] = { - [0] = ASIC3_CLOCK_LED0, - [1] = ASIC3_CLOCK_LED1, - [2] = ASIC3_CLOCK_LED2, -}; - -static int asic3_leds_enable(struct platform_device *pdev) -{ - const struct mfd_cell *cell = mfd_get_cell(pdev); - struct asic3 *asic = dev_get_drvdata(pdev->dev.parent); - - asic3_clk_enable(asic, &asic->clocks[clock_ledn[cell->id]]); - - return 0; -} - -static int asic3_leds_disable(struct platform_device *pdev) -{ - const struct mfd_cell *cell = mfd_get_cell(pdev); - struct asic3 *asic = dev_get_drvdata(pdev->dev.parent); - - asic3_clk_disable(asic, &asic->clocks[clock_ledn[cell->id]]); - - return 0; -} - -static int asic3_leds_suspend(struct platform_device *pdev) -{ - const struct mfd_cell *cell = mfd_get_cell(pdev); - struct asic3 *asic = dev_get_drvdata(pdev->dev.parent); - - while (asic3_gpio_get(&asic->gpio, ASIC3_GPIO(C, cell->id)) != 0) - usleep_range(1000, 5000); - - asic3_clk_disable(asic, &asic->clocks[clock_ledn[cell->id]]); - - return 0; -} - -static struct mfd_cell asic3_cell_leds[ASIC3_NUM_LEDS] = { - [0] = { - .name = "leds-asic3", - .id = 0, - .enable = asic3_leds_enable, - .disable = asic3_leds_disable, - .suspend = asic3_leds_suspend, - .resume = asic3_leds_enable, - }, - [1] = { - .name = "leds-asic3", - .id = 1, - .enable = asic3_leds_enable, - .disable = asic3_leds_disable, - .suspend = asic3_leds_suspend, - .resume = asic3_leds_enable, - }, - [2] = { - .name = "leds-asic3", - .id = 2, - .enable = asic3_leds_enable, - .disable = asic3_leds_disable, - .suspend = asic3_leds_suspend, - .resume = asic3_leds_enable, - }, -}; - -static int __init asic3_mfd_probe(struct platform_device *pdev, - struct asic3_platform_data *pdata, - struct resource *mem) -{ - struct asic3 *asic = platform_get_drvdata(pdev); - struct resource *mem_sdio; - int irq, ret; - - mem_sdio = platform_get_resource(pdev, IORESOURCE_MEM, 1); - if (!mem_sdio) - dev_dbg(asic->dev, "no SDIO MEM resource\n"); - - irq = platform_get_irq(pdev, 1); - if (irq < 0) - dev_dbg(asic->dev, "no SDIO IRQ resource\n"); - - /* DS1WM */ - asic3_set_register(asic, ASIC3_OFFSET(EXTCF, SELECT), - ASIC3_EXTCF_OWM_SMB, 0); - - ds1wm_resources[0].start >>= asic->bus_shift; - ds1wm_resources[0].end >>= asic->bus_shift; - - /* MMC */ - if (mem_sdio) { - asic->tmio_cnf = ioremap((ASIC3_SD_CONFIG_BASE >> - asic->bus_shift) + mem_sdio->start, - ASIC3_SD_CONFIG_SIZE >> asic->bus_shift); - if (!asic->tmio_cnf) { - ret = -ENOMEM; - dev_dbg(asic->dev, "Couldn't ioremap SD_CONFIG\n"); - goto out; - } - } - asic3_mmc_resources[0].start >>= asic->bus_shift; - asic3_mmc_resources[0].end >>= asic->bus_shift; - - if (pdata->clock_rate) { - ds1wm_pdata.clock_rate = pdata->clock_rate; - ret = mfd_add_devices(&pdev->dev, pdev->id, - &asic3_cell_ds1wm, 1, mem, asic->irq_base, NULL); - if (ret < 0) - goto out_unmap; - } - - if (mem_sdio && (irq >= 0)) { - ret = mfd_add_devices(&pdev->dev, pdev->id, - &asic3_cell_mmc, 1, mem_sdio, irq, NULL); - if (ret < 0) - goto out_unmap; - } - - ret = 0; - if (pdata->leds) { - int i; - - for (i = 0; i < ASIC3_NUM_LEDS; ++i) { - asic3_cell_leds[i].platform_data = &pdata->leds[i]; - asic3_cell_leds[i].pdata_size = sizeof(pdata->leds[i]); - } - ret = mfd_add_devices(&pdev->dev, 0, - asic3_cell_leds, ASIC3_NUM_LEDS, NULL, 0, NULL); - } - return ret; - -out_unmap: - if (asic->tmio_cnf) - iounmap(asic->tmio_cnf); -out: - return ret; -} - -static void asic3_mfd_remove(struct platform_device *pdev) -{ - struct asic3 *asic = platform_get_drvdata(pdev); - - mfd_remove_devices(&pdev->dev); - iounmap(asic->tmio_cnf); -} - -/* Core */ -static int __init asic3_probe(struct platform_device *pdev) -{ - struct asic3_platform_data *pdata = dev_get_platdata(&pdev->dev); - struct asic3 *asic; - struct resource *mem; - unsigned long clksel; - int ret = 0; - - asic = devm_kzalloc(&pdev->dev, - sizeof(struct asic3), GFP_KERNEL); - if (!asic) - return -ENOMEM; - - raw_spin_lock_init(&asic->lock); - platform_set_drvdata(pdev, asic); - asic->dev = &pdev->dev; - - mem = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (!mem) { - dev_err(asic->dev, "no MEM resource\n"); - return -ENOMEM; - } - - asic->mapping = ioremap(mem->start, resource_size(mem)); - if (!asic->mapping) { - dev_err(asic->dev, "Couldn't ioremap\n"); - return -ENOMEM; - } - - asic->irq_base = pdata->irq_base; - - /* calculate bus shift from mem resource */ - asic->bus_shift = 2 - (resource_size(mem) >> 12); - - clksel = 0; - asic3_write_register(asic, ASIC3_OFFSET(CLOCK, SEL), clksel); - - ret = asic3_irq_probe(pdev); - if (ret < 0) { - dev_err(asic->dev, "Couldn't probe IRQs\n"); - goto out_unmap; - } - - asic->gpio.label = "asic3"; - asic->gpio.base = pdata->gpio_base; - asic->gpio.ngpio = ASIC3_NUM_GPIOS; - asic->gpio.get = asic3_gpio_get; - asic->gpio.set = asic3_gpio_set; - asic->gpio.direction_input = asic3_gpio_direction_input; - asic->gpio.direction_output = asic3_gpio_direction_output; - asic->gpio.to_irq = asic3_gpio_to_irq; - - ret = asic3_gpio_probe(pdev, - pdata->gpio_config, - pdata->gpio_config_num); - if (ret < 0) { - dev_err(asic->dev, "GPIO probe failed\n"); - goto out_irq; - } - - /* Making a per-device copy is only needed for the - * theoretical case of multiple ASIC3s on one board: - */ - memcpy(asic->clocks, asic3_clk_init, sizeof(asic3_clk_init)); - - asic3_mfd_probe(pdev, pdata, mem); - - asic3_set_register(asic, ASIC3_OFFSET(EXTCF, SELECT), - (ASIC3_EXTCF_CF0_BUF_EN|ASIC3_EXTCF_CF0_PWAIT_EN), 1); - - dev_info(asic->dev, "ASIC3 Core driver\n"); - - return 0; - - out_irq: - asic3_irq_remove(pdev); - - out_unmap: - iounmap(asic->mapping); - - return ret; -} - -static int asic3_remove(struct platform_device *pdev) -{ - struct asic3 *asic = platform_get_drvdata(pdev); - - asic3_set_register(asic, ASIC3_OFFSET(EXTCF, SELECT), - (ASIC3_EXTCF_CF0_BUF_EN|ASIC3_EXTCF_CF0_PWAIT_EN), 0); - - asic3_mfd_remove(pdev); - - asic3_gpio_remove(pdev); - - asic3_irq_remove(pdev); - - asic3_write_register(asic, ASIC3_OFFSET(CLOCK, SEL), 0); - - iounmap(asic->mapping); - - return 0; -} - -static void asic3_shutdown(struct platform_device *pdev) -{ -} - -static struct platform_driver asic3_device_driver = { - .driver = { - .name = "asic3", - }, - .remove = asic3_remove, - .shutdown = asic3_shutdown, -}; - -static int __init asic3_init(void) -{ - int retval = 0; - - retval = platform_driver_probe(&asic3_device_driver, asic3_probe); - - return retval; -} - -subsys_initcall(asic3_init); diff --git a/drivers/mfd/t7l66xb.c b/drivers/mfd/t7l66xb.c deleted file mode 100644 index 1d9d1d38d068..000000000000 --- a/drivers/mfd/t7l66xb.c +++ /dev/null @@ -1,427 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * - * Toshiba T7L66XB core mfd support - * - * Copyright (c) 2005, 2007, 2008 Ian Molton - * Copyright (c) 2008 Dmitry Baryshkov - * - * T7L66 features: - * - * Supported in this driver: - * SD/MMC - * SM/NAND flash controller - * - * As yet not supported - * GPIO interface (on NAND pins) - * Serial interface - * TFT 'interface converter' - * PCMCIA interface logic - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -enum { - T7L66XB_CELL_NAND, - T7L66XB_CELL_MMC, -}; - -static const struct resource t7l66xb_mmc_resources[] = { - DEFINE_RES_MEM(0x800, 0x200), - DEFINE_RES_IRQ(IRQ_T7L66XB_MMC) -}; - -#define SCR_REVID 0x08 /* b Revision ID */ -#define SCR_IMR 0x42 /* b Interrupt Mask */ -#define SCR_DEV_CTL 0xe0 /* b Device control */ -#define SCR_ISR 0xe1 /* b Interrupt Status */ -#define SCR_GPO_OC 0xf0 /* b GPO output control */ -#define SCR_GPO_OS 0xf1 /* b GPO output enable */ -#define SCR_GPI_S 0xf2 /* w GPI status */ -#define SCR_APDC 0xf8 /* b Active pullup down ctrl */ - -#define SCR_DEV_CTL_USB BIT(0) /* USB enable */ -#define SCR_DEV_CTL_MMC BIT(1) /* MMC enable */ - -/*--------------------------------------------------------------------------*/ - -struct t7l66xb { - void __iomem *scr; - /* Lock to protect registers requiring read/modify/write ops. */ - raw_spinlock_t lock; - - struct resource rscr; - struct clk *clk48m; - struct clk *clk32k; - int irq; - int irq_base; -}; - -/*--------------------------------------------------------------------------*/ - -static int t7l66xb_mmc_enable(struct platform_device *mmc) -{ - struct t7l66xb *t7l66xb = dev_get_drvdata(mmc->dev.parent); - unsigned long flags; - u8 dev_ctl; - int ret; - - ret = clk_prepare_enable(t7l66xb->clk32k); - if (ret) - return ret; - - raw_spin_lock_irqsave(&t7l66xb->lock, flags); - - dev_ctl = tmio_ioread8(t7l66xb->scr + SCR_DEV_CTL); - dev_ctl |= SCR_DEV_CTL_MMC; - tmio_iowrite8(dev_ctl, t7l66xb->scr + SCR_DEV_CTL); - - raw_spin_unlock_irqrestore(&t7l66xb->lock, flags); - - tmio_core_mmc_enable(t7l66xb->scr + 0x200, 0, - t7l66xb_mmc_resources[0].start & 0xfffe); - - return 0; -} - -static int t7l66xb_mmc_disable(struct platform_device *mmc) -{ - struct t7l66xb *t7l66xb = dev_get_drvdata(mmc->dev.parent); - unsigned long flags; - u8 dev_ctl; - - raw_spin_lock_irqsave(&t7l66xb->lock, flags); - - dev_ctl = tmio_ioread8(t7l66xb->scr + SCR_DEV_CTL); - dev_ctl &= ~SCR_DEV_CTL_MMC; - tmio_iowrite8(dev_ctl, t7l66xb->scr + SCR_DEV_CTL); - - raw_spin_unlock_irqrestore(&t7l66xb->lock, flags); - - clk_disable_unprepare(t7l66xb->clk32k); - - return 0; -} - -static void t7l66xb_mmc_pwr(struct platform_device *mmc, int state) -{ - struct t7l66xb *t7l66xb = dev_get_drvdata(mmc->dev.parent); - - tmio_core_mmc_pwr(t7l66xb->scr + 0x200, 0, state); -} - -static void t7l66xb_mmc_clk_div(struct platform_device *mmc, int state) -{ - struct t7l66xb *t7l66xb = dev_get_drvdata(mmc->dev.parent); - - tmio_core_mmc_clk_div(t7l66xb->scr + 0x200, 0, state); -} - -/*--------------------------------------------------------------------------*/ - -static struct tmio_mmc_data t7166xb_mmc_data = { - .hclk = 24000000, - .set_pwr = t7l66xb_mmc_pwr, - .set_clk_div = t7l66xb_mmc_clk_div, -}; - -static const struct resource t7l66xb_nand_resources[] = { - { - .start = 0xc00, - .end = 0xc07, - .flags = IORESOURCE_MEM, - }, - { - .start = 0x0100, - .end = 0x01ff, - .flags = IORESOURCE_MEM, - }, - { - .start = IRQ_T7L66XB_NAND, - .end = IRQ_T7L66XB_NAND, - .flags = IORESOURCE_IRQ, - }, -}; - -static struct mfd_cell t7l66xb_cells[] = { - [T7L66XB_CELL_MMC] = { - .name = "tmio-mmc", - .enable = t7l66xb_mmc_enable, - .disable = t7l66xb_mmc_disable, - .platform_data = &t7166xb_mmc_data, - .pdata_size = sizeof(t7166xb_mmc_data), - .num_resources = ARRAY_SIZE(t7l66xb_mmc_resources), - .resources = t7l66xb_mmc_resources, - }, - [T7L66XB_CELL_NAND] = { - .name = "tmio-nand", - .num_resources = ARRAY_SIZE(t7l66xb_nand_resources), - .resources = t7l66xb_nand_resources, - }, -}; - -/*--------------------------------------------------------------------------*/ - -/* Handle the T7L66XB interrupt mux */ -static void t7l66xb_irq(struct irq_desc *desc) -{ - struct t7l66xb *t7l66xb = irq_desc_get_handler_data(desc); - unsigned int isr; - unsigned int i, irq_base; - - irq_base = t7l66xb->irq_base; - - while ((isr = tmio_ioread8(t7l66xb->scr + SCR_ISR) & - ~tmio_ioread8(t7l66xb->scr + SCR_IMR))) - for (i = 0; i < T7L66XB_NR_IRQS; i++) - if (isr & (1 << i)) - generic_handle_irq(irq_base + i); -} - -static void t7l66xb_irq_mask(struct irq_data *data) -{ - struct t7l66xb *t7l66xb = irq_data_get_irq_chip_data(data); - unsigned long flags; - u8 imr; - - raw_spin_lock_irqsave(&t7l66xb->lock, flags); - imr = tmio_ioread8(t7l66xb->scr + SCR_IMR); - imr |= 1 << (data->irq - t7l66xb->irq_base); - tmio_iowrite8(imr, t7l66xb->scr + SCR_IMR); - raw_spin_unlock_irqrestore(&t7l66xb->lock, flags); -} - -static void t7l66xb_irq_unmask(struct irq_data *data) -{ - struct t7l66xb *t7l66xb = irq_data_get_irq_chip_data(data); - unsigned long flags; - u8 imr; - - raw_spin_lock_irqsave(&t7l66xb->lock, flags); - imr = tmio_ioread8(t7l66xb->scr + SCR_IMR); - imr &= ~(1 << (data->irq - t7l66xb->irq_base)); - tmio_iowrite8(imr, t7l66xb->scr + SCR_IMR); - raw_spin_unlock_irqrestore(&t7l66xb->lock, flags); -} - -static struct irq_chip t7l66xb_chip = { - .name = "t7l66xb", - .irq_ack = t7l66xb_irq_mask, - .irq_mask = t7l66xb_irq_mask, - .irq_unmask = t7l66xb_irq_unmask, -}; - -/*--------------------------------------------------------------------------*/ - -/* Install the IRQ handler */ -static void t7l66xb_attach_irq(struct platform_device *dev) -{ - struct t7l66xb *t7l66xb = platform_get_drvdata(dev); - unsigned int irq, irq_base; - - irq_base = t7l66xb->irq_base; - - for (irq = irq_base; irq < irq_base + T7L66XB_NR_IRQS; irq++) { - irq_set_chip_and_handler(irq, &t7l66xb_chip, handle_level_irq); - irq_set_chip_data(irq, t7l66xb); - } - - irq_set_irq_type(t7l66xb->irq, IRQ_TYPE_EDGE_FALLING); - irq_set_chained_handler_and_data(t7l66xb->irq, t7l66xb_irq, t7l66xb); -} - -static void t7l66xb_detach_irq(struct platform_device *dev) -{ - struct t7l66xb *t7l66xb = platform_get_drvdata(dev); - unsigned int irq, irq_base; - - irq_base = t7l66xb->irq_base; - - irq_set_chained_handler_and_data(t7l66xb->irq, NULL, NULL); - - for (irq = irq_base; irq < irq_base + T7L66XB_NR_IRQS; irq++) { - irq_set_chip(irq, NULL); - irq_set_chip_data(irq, NULL); - } -} - -/*--------------------------------------------------------------------------*/ - -static int t7l66xb_suspend(struct platform_device *dev, pm_message_t state) -{ - struct t7l66xb *t7l66xb = platform_get_drvdata(dev); - struct t7l66xb_platform_data *pdata = dev_get_platdata(&dev->dev); - - if (pdata && pdata->suspend) - pdata->suspend(dev); - clk_disable_unprepare(t7l66xb->clk48m); - - return 0; -} - -static int t7l66xb_resume(struct platform_device *dev) -{ - struct t7l66xb *t7l66xb = platform_get_drvdata(dev); - struct t7l66xb_platform_data *pdata = dev_get_platdata(&dev->dev); - int ret; - - ret = clk_prepare_enable(t7l66xb->clk48m); - if (ret) - return ret; - - if (pdata && pdata->resume) - pdata->resume(dev); - - tmio_core_mmc_enable(t7l66xb->scr + 0x200, 0, - t7l66xb_mmc_resources[0].start & 0xfffe); - - return 0; -} - -/*--------------------------------------------------------------------------*/ - -static int t7l66xb_probe(struct platform_device *dev) -{ - struct t7l66xb_platform_data *pdata = dev_get_platdata(&dev->dev); - struct t7l66xb *t7l66xb; - struct resource *iomem, *rscr; - int ret; - - if (!pdata) - return -EINVAL; - - iomem = platform_get_resource(dev, IORESOURCE_MEM, 0); - if (!iomem) - return -EINVAL; - - t7l66xb = kzalloc(sizeof *t7l66xb, GFP_KERNEL); - if (!t7l66xb) - return -ENOMEM; - - raw_spin_lock_init(&t7l66xb->lock); - - platform_set_drvdata(dev, t7l66xb); - - ret = platform_get_irq(dev, 0); - if (ret >= 0) - t7l66xb->irq = ret; - else - goto err_noirq; - - t7l66xb->irq_base = pdata->irq_base; - - t7l66xb->clk32k = clk_get(&dev->dev, "CLK_CK32K"); - if (IS_ERR(t7l66xb->clk32k)) { - ret = PTR_ERR(t7l66xb->clk32k); - goto err_clk32k_get; - } - - t7l66xb->clk48m = clk_get(&dev->dev, "CLK_CK48M"); - if (IS_ERR(t7l66xb->clk48m)) { - ret = PTR_ERR(t7l66xb->clk48m); - goto err_clk48m_get; - } - - rscr = &t7l66xb->rscr; - rscr->name = "t7l66xb-core"; - rscr->start = iomem->start; - rscr->end = iomem->start + 0xff; - rscr->flags = IORESOURCE_MEM; - - ret = request_resource(iomem, rscr); - if (ret) - goto err_request_scr; - - t7l66xb->scr = ioremap(rscr->start, resource_size(rscr)); - if (!t7l66xb->scr) { - ret = -ENOMEM; - goto err_ioremap; - } - - ret = clk_prepare_enable(t7l66xb->clk48m); - if (ret) - goto err_clk_enable; - - if (pdata->enable) - pdata->enable(dev); - - /* Mask all interrupts */ - tmio_iowrite8(0xbf, t7l66xb->scr + SCR_IMR); - - printk(KERN_INFO "%s rev %d @ 0x%08lx, irq %d\n", - dev->name, tmio_ioread8(t7l66xb->scr + SCR_REVID), - (unsigned long)iomem->start, t7l66xb->irq); - - t7l66xb_attach_irq(dev); - - t7l66xb_cells[T7L66XB_CELL_NAND].platform_data = pdata->nand_data; - t7l66xb_cells[T7L66XB_CELL_NAND].pdata_size = sizeof(*pdata->nand_data); - - ret = mfd_add_devices(&dev->dev, dev->id, - t7l66xb_cells, ARRAY_SIZE(t7l66xb_cells), - iomem, t7l66xb->irq_base, NULL); - - if (!ret) - return 0; - - t7l66xb_detach_irq(dev); - clk_disable_unprepare(t7l66xb->clk48m); -err_clk_enable: - iounmap(t7l66xb->scr); -err_ioremap: - release_resource(&t7l66xb->rscr); -err_request_scr: - clk_put(t7l66xb->clk48m); -err_clk48m_get: - clk_put(t7l66xb->clk32k); -err_clk32k_get: -err_noirq: - kfree(t7l66xb); - return ret; -} - -static int t7l66xb_remove(struct platform_device *dev) -{ - struct t7l66xb *t7l66xb = platform_get_drvdata(dev); - - clk_disable_unprepare(t7l66xb->clk48m); - clk_put(t7l66xb->clk48m); - clk_disable_unprepare(t7l66xb->clk32k); - clk_put(t7l66xb->clk32k); - t7l66xb_detach_irq(dev); - iounmap(t7l66xb->scr); - release_resource(&t7l66xb->rscr); - mfd_remove_devices(&dev->dev); - kfree(t7l66xb); - - return 0; -} - -static struct platform_driver t7l66xb_platform_driver = { - .driver = { - .name = "t7l66xb", - }, - .suspend = pm_sleep_ptr(t7l66xb_suspend), - .resume = pm_sleep_ptr(t7l66xb_resume), - .probe = t7l66xb_probe, - .remove = t7l66xb_remove, -}; - -/*--------------------------------------------------------------------------*/ - -module_platform_driver(t7l66xb_platform_driver); - -MODULE_DESCRIPTION("Toshiba T7L66XB core driver"); -MODULE_LICENSE("GPL v2"); -MODULE_AUTHOR("Ian Molton"); -MODULE_ALIAS("platform:t7l66xb"); diff --git a/drivers/mfd/tc6387xb.c b/drivers/mfd/tc6387xb.c deleted file mode 100644 index 5392da6ba7b0..000000000000 --- a/drivers/mfd/tc6387xb.c +++ /dev/null @@ -1,228 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Toshiba TC6387XB support - * Copyright (c) 2005 Ian Molton - * - * This file contains TC6387XB base support. - */ - -#include -#include -#include -#include -#include -#include -#include -#include - -enum { - TC6387XB_CELL_MMC, -}; - -struct tc6387xb { - void __iomem *scr; - struct clk *clk32k; - struct resource rscr; -}; - -static const struct resource tc6387xb_mmc_resources[] = { - { - .start = 0x800, - .end = 0x9ff, - .flags = IORESOURCE_MEM, - }, - { - .start = 0, - .end = 0, - .flags = IORESOURCE_IRQ, - }, -}; - -/*--------------------------------------------------------------------------*/ - -static int tc6387xb_suspend(struct platform_device *dev, pm_message_t state) -{ - struct tc6387xb *tc6387xb = platform_get_drvdata(dev); - struct tc6387xb_platform_data *pdata = dev_get_platdata(&dev->dev); - - if (pdata && pdata->suspend) - pdata->suspend(dev); - clk_disable_unprepare(tc6387xb->clk32k); - - return 0; -} - -static int tc6387xb_resume(struct platform_device *dev) -{ - struct tc6387xb *tc6387xb = platform_get_drvdata(dev); - struct tc6387xb_platform_data *pdata = dev_get_platdata(&dev->dev); - - clk_prepare_enable(tc6387xb->clk32k); - if (pdata && pdata->resume) - pdata->resume(dev); - - tmio_core_mmc_resume(tc6387xb->scr + 0x200, 0, - tc6387xb_mmc_resources[0].start & 0xfffe); - - return 0; -} - -/*--------------------------------------------------------------------------*/ - -static void tc6387xb_mmc_pwr(struct platform_device *mmc, int state) -{ - struct tc6387xb *tc6387xb = dev_get_drvdata(mmc->dev.parent); - - tmio_core_mmc_pwr(tc6387xb->scr + 0x200, 0, state); -} - -static void tc6387xb_mmc_clk_div(struct platform_device *mmc, int state) -{ - struct tc6387xb *tc6387xb = dev_get_drvdata(mmc->dev.parent); - - tmio_core_mmc_clk_div(tc6387xb->scr + 0x200, 0, state); -} - - -static int tc6387xb_mmc_enable(struct platform_device *mmc) -{ - struct tc6387xb *tc6387xb = dev_get_drvdata(mmc->dev.parent); - - clk_prepare_enable(tc6387xb->clk32k); - - tmio_core_mmc_enable(tc6387xb->scr + 0x200, 0, - tc6387xb_mmc_resources[0].start & 0xfffe); - - return 0; -} - -static int tc6387xb_mmc_disable(struct platform_device *mmc) -{ - struct tc6387xb *tc6387xb = dev_get_drvdata(mmc->dev.parent); - - clk_disable_unprepare(tc6387xb->clk32k); - - return 0; -} - -static struct tmio_mmc_data tc6387xb_mmc_data = { - .hclk = 24000000, - .set_pwr = tc6387xb_mmc_pwr, - .set_clk_div = tc6387xb_mmc_clk_div, -}; - -/*--------------------------------------------------------------------------*/ - -static const struct mfd_cell tc6387xb_cells[] = { - [TC6387XB_CELL_MMC] = { - .name = "tmio-mmc", - .enable = tc6387xb_mmc_enable, - .disable = tc6387xb_mmc_disable, - .platform_data = &tc6387xb_mmc_data, - .pdata_size = sizeof(tc6387xb_mmc_data), - .num_resources = ARRAY_SIZE(tc6387xb_mmc_resources), - .resources = tc6387xb_mmc_resources, - }, -}; - -static int tc6387xb_probe(struct platform_device *dev) -{ - struct tc6387xb_platform_data *pdata = dev_get_platdata(&dev->dev); - struct resource *iomem, *rscr; - struct clk *clk32k; - struct tc6387xb *tc6387xb; - int irq, ret; - - iomem = platform_get_resource(dev, IORESOURCE_MEM, 0); - if (!iomem) - return -EINVAL; - - tc6387xb = kzalloc(sizeof(*tc6387xb), GFP_KERNEL); - if (!tc6387xb) - return -ENOMEM; - - ret = platform_get_irq(dev, 0); - if (ret >= 0) - irq = ret; - else - goto err_no_irq; - - clk32k = clk_get(&dev->dev, "CLK_CK32K"); - if (IS_ERR(clk32k)) { - ret = PTR_ERR(clk32k); - goto err_no_clk; - } - - rscr = &tc6387xb->rscr; - rscr->name = "tc6387xb-core"; - rscr->start = iomem->start; - rscr->end = iomem->start + 0xff; - rscr->flags = IORESOURCE_MEM; - - ret = request_resource(iomem, rscr); - if (ret) - goto err_resource; - - tc6387xb->scr = ioremap(rscr->start, resource_size(rscr)); - if (!tc6387xb->scr) { - ret = -ENOMEM; - goto err_ioremap; - } - - tc6387xb->clk32k = clk32k; - platform_set_drvdata(dev, tc6387xb); - - if (pdata && pdata->enable) - pdata->enable(dev); - - dev_info(&dev->dev, "Toshiba tc6387xb initialised\n"); - - ret = mfd_add_devices(&dev->dev, dev->id, tc6387xb_cells, - ARRAY_SIZE(tc6387xb_cells), iomem, irq, NULL); - - if (!ret) - return 0; - - iounmap(tc6387xb->scr); -err_ioremap: - release_resource(&tc6387xb->rscr); -err_resource: - clk_put(clk32k); -err_no_clk: -err_no_irq: - kfree(tc6387xb); - return ret; -} - -static int tc6387xb_remove(struct platform_device *dev) -{ - struct tc6387xb *tc6387xb = platform_get_drvdata(dev); - - mfd_remove_devices(&dev->dev); - iounmap(tc6387xb->scr); - release_resource(&tc6387xb->rscr); - clk_disable_unprepare(tc6387xb->clk32k); - clk_put(tc6387xb->clk32k); - kfree(tc6387xb); - - return 0; -} - - -static struct platform_driver tc6387xb_platform_driver = { - .driver = { - .name = "tc6387xb", - }, - .probe = tc6387xb_probe, - .remove = tc6387xb_remove, - .suspend = pm_sleep_ptr(tc6387xb_suspend), - .resume = pm_sleep_ptr(tc6387xb_resume), -}; - -module_platform_driver(tc6387xb_platform_driver); - -MODULE_DESCRIPTION("Toshiba TC6387XB core driver"); -MODULE_LICENSE("GPL v2"); -MODULE_AUTHOR("Ian Molton"); -MODULE_ALIAS("platform:tc6387xb"); - diff --git a/drivers/mfd/tc6393xb.c b/drivers/mfd/tc6393xb.c deleted file mode 100644 index 997bb8b5881d..000000000000 --- a/drivers/mfd/tc6393xb.c +++ /dev/null @@ -1,907 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Toshiba TC6393XB SoC support - * - * Copyright(c) 2005-2006 Chris Humbert - * Copyright(c) 2005 Dirk Opfer - * Copyright(c) 2005 Ian Molton - * Copyright(c) 2007 Dmitry Baryshkov - * - * Based on code written by Sharp/Lineo for 2.4 kernels - * Based on locomo.c - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#define SCR_REVID 0x08 /* b Revision ID */ -#define SCR_ISR 0x50 /* b Interrupt Status */ -#define SCR_IMR 0x52 /* b Interrupt Mask */ -#define SCR_IRR 0x54 /* b Interrupt Routing */ -#define SCR_GPER 0x60 /* w GP Enable */ -#define SCR_GPI_SR(i) (0x64 + (i)) /* b3 GPI Status */ -#define SCR_GPI_IMR(i) (0x68 + (i)) /* b3 GPI INT Mask */ -#define SCR_GPI_EDER(i) (0x6c + (i)) /* b3 GPI Edge Detect Enable */ -#define SCR_GPI_LIR(i) (0x70 + (i)) /* b3 GPI Level Invert */ -#define SCR_GPO_DSR(i) (0x78 + (i)) /* b3 GPO Data Set */ -#define SCR_GPO_DOECR(i) (0x7c + (i)) /* b3 GPO Data OE Control */ -#define SCR_GP_IARCR(i) (0x80 + (i)) /* b3 GP Internal Active Register Control */ -#define SCR_GP_IARLCR(i) (0x84 + (i)) /* b3 GP INTERNAL Active Register Level Control */ -#define SCR_GPI_BCR(i) (0x88 + (i)) /* b3 GPI Buffer Control */ -#define SCR_GPA_IARCR 0x8c /* w GPa Internal Active Register Control */ -#define SCR_GPA_IARLCR 0x90 /* w GPa Internal Active Register Level Control */ -#define SCR_GPA_BCR 0x94 /* w GPa Buffer Control */ -#define SCR_CCR 0x98 /* w Clock Control */ -#define SCR_PLL2CR 0x9a /* w PLL2 Control */ -#define SCR_PLL1CR 0x9c /* l PLL1 Control */ -#define SCR_DIARCR 0xa0 /* b Device Internal Active Register Control */ -#define SCR_DBOCR 0xa1 /* b Device Buffer Off Control */ -#define SCR_FER 0xe0 /* b Function Enable */ -#define SCR_MCR 0xe4 /* w Mode Control */ -#define SCR_CONFIG 0xfc /* b Configuration Control */ -#define SCR_DEBUG 0xff /* b Debug */ - -#define SCR_CCR_CK32K BIT(0) -#define SCR_CCR_USBCK BIT(1) -#define SCR_CCR_UNK1 BIT(4) -#define SCR_CCR_MCLK_MASK (7 << 8) -#define SCR_CCR_MCLK_OFF (0 << 8) -#define SCR_CCR_MCLK_12 (1 << 8) -#define SCR_CCR_MCLK_24 (2 << 8) -#define SCR_CCR_MCLK_48 (3 << 8) -#define SCR_CCR_HCLK_MASK (3 << 12) -#define SCR_CCR_HCLK_24 (0 << 12) -#define SCR_CCR_HCLK_48 (1 << 12) - -#define SCR_FER_USBEN BIT(0) /* USB host enable */ -#define SCR_FER_LCDCVEN BIT(1) /* polysilicon TFT enable */ -#define SCR_FER_SLCDEN BIT(2) /* SLCD enable */ - -#define SCR_MCR_RDY_MASK (3 << 0) -#define SCR_MCR_RDY_OPENDRAIN (0 << 0) -#define SCR_MCR_RDY_TRISTATE (1 << 0) -#define SCR_MCR_RDY_PUSHPULL (2 << 0) -#define SCR_MCR_RDY_UNK BIT(2) -#define SCR_MCR_RDY_EN BIT(3) -#define SCR_MCR_INT_MASK (3 << 4) -#define SCR_MCR_INT_OPENDRAIN (0 << 4) -#define SCR_MCR_INT_TRISTATE (1 << 4) -#define SCR_MCR_INT_PUSHPULL (2 << 4) -#define SCR_MCR_INT_UNK BIT(6) -#define SCR_MCR_INT_EN BIT(7) -/* bits 8 - 16 are unknown */ - -#define TC_GPIO_BIT(i) (1 << (i & 0x7)) - -/*--------------------------------------------------------------------------*/ - -struct tc6393xb { - void __iomem *scr; - struct device *dev; - - struct gpio_chip gpio; - struct gpio_desc *vcc_on; - - struct clk *clk; /* 3,6 Mhz */ - - raw_spinlock_t lock; /* protects RMW cycles */ - - struct { - u8 fer; - u16 ccr; - u8 gpi_bcr[3]; - u8 gpo_dsr[3]; - u8 gpo_doecr[3]; - } suspend_state; - - struct resource rscr; - struct resource *iomem; - int irq; - int irq_base; -}; - -enum { - TC6393XB_CELL_NAND, - TC6393XB_CELL_MMC, - TC6393XB_CELL_OHCI, - TC6393XB_CELL_FB, -}; - -/*--------------------------------------------------------------------------*/ - -static int tc6393xb_nand_enable(struct platform_device *nand) -{ - struct tc6393xb *tc6393xb = dev_get_drvdata(nand->dev.parent); - unsigned long flags; - - raw_spin_lock_irqsave(&tc6393xb->lock, flags); - - /* SMD buffer on */ - dev_dbg(nand->dev.parent, "SMD buffer on\n"); - tmio_iowrite8(0xff, tc6393xb->scr + SCR_GPI_BCR(1)); - - raw_spin_unlock_irqrestore(&tc6393xb->lock, flags); - - return 0; -} - -static const struct resource tc6393xb_nand_resources[] = { - { - .start = 0x1000, - .end = 0x1007, - .flags = IORESOURCE_MEM, - }, - { - .start = 0x0100, - .end = 0x01ff, - .flags = IORESOURCE_MEM, - }, - { - .start = IRQ_TC6393_NAND, - .end = IRQ_TC6393_NAND, - .flags = IORESOURCE_IRQ, - }, -}; - -static const struct resource tc6393xb_mmc_resources[] = { - { - .start = 0x800, - .end = 0x9ff, - .flags = IORESOURCE_MEM, - }, - { - .start = IRQ_TC6393_MMC, - .end = IRQ_TC6393_MMC, - .flags = IORESOURCE_IRQ, - }, -}; - -static const struct resource tc6393xb_ohci_resources[] = { - { - .start = 0x3000, - .end = 0x31ff, - .flags = IORESOURCE_MEM, - }, - { - .start = 0x0300, - .end = 0x03ff, - .flags = IORESOURCE_MEM, - }, - { - .start = 0x010000, - .end = 0x017fff, - .flags = IORESOURCE_MEM, - }, - { - .start = 0x018000, - .end = 0x01ffff, - .flags = IORESOURCE_MEM, - }, - { - .start = IRQ_TC6393_OHCI, - .end = IRQ_TC6393_OHCI, - .flags = IORESOURCE_IRQ, - }, -}; - -static const struct resource tc6393xb_fb_resources[] = { - { - .start = 0x5000, - .end = 0x51ff, - .flags = IORESOURCE_MEM, - }, - { - .start = 0x0500, - .end = 0x05ff, - .flags = IORESOURCE_MEM, - }, - { - .start = 0x100000, - .end = 0x1fffff, - .flags = IORESOURCE_MEM, - }, - { - .start = IRQ_TC6393_FB, - .end = IRQ_TC6393_FB, - .flags = IORESOURCE_IRQ, - }, -}; - -static int tc6393xb_ohci_enable(struct platform_device *dev) -{ - struct tc6393xb *tc6393xb = dev_get_drvdata(dev->dev.parent); - unsigned long flags; - u16 ccr; - u8 fer; - - raw_spin_lock_irqsave(&tc6393xb->lock, flags); - - ccr = tmio_ioread16(tc6393xb->scr + SCR_CCR); - ccr |= SCR_CCR_USBCK; - tmio_iowrite16(ccr, tc6393xb->scr + SCR_CCR); - - fer = tmio_ioread8(tc6393xb->scr + SCR_FER); - fer |= SCR_FER_USBEN; - tmio_iowrite8(fer, tc6393xb->scr + SCR_FER); - - raw_spin_unlock_irqrestore(&tc6393xb->lock, flags); - - return 0; -} - -static int tc6393xb_ohci_disable(struct platform_device *dev) -{ - struct tc6393xb *tc6393xb = dev_get_drvdata(dev->dev.parent); - unsigned long flags; - u16 ccr; - u8 fer; - - raw_spin_lock_irqsave(&tc6393xb->lock, flags); - - fer = tmio_ioread8(tc6393xb->scr + SCR_FER); - fer &= ~SCR_FER_USBEN; - tmio_iowrite8(fer, tc6393xb->scr + SCR_FER); - - ccr = tmio_ioread16(tc6393xb->scr + SCR_CCR); - ccr &= ~SCR_CCR_USBCK; - tmio_iowrite16(ccr, tc6393xb->scr + SCR_CCR); - - raw_spin_unlock_irqrestore(&tc6393xb->lock, flags); - - return 0; -} - -static int tc6393xb_ohci_suspend(struct platform_device *dev) -{ - struct tc6393xb_platform_data *tcpd = dev_get_platdata(dev->dev.parent); - - /* We can't properly store/restore OHCI state, so fail here */ - if (tcpd->resume_restore) - return -EBUSY; - - return tc6393xb_ohci_disable(dev); -} - -static int tc6393xb_fb_enable(struct platform_device *dev) -{ - struct tc6393xb *tc6393xb = dev_get_drvdata(dev->dev.parent); - unsigned long flags; - u16 ccr; - - raw_spin_lock_irqsave(&tc6393xb->lock, flags); - - ccr = tmio_ioread16(tc6393xb->scr + SCR_CCR); - ccr &= ~SCR_CCR_MCLK_MASK; - ccr |= SCR_CCR_MCLK_48; - tmio_iowrite16(ccr, tc6393xb->scr + SCR_CCR); - - raw_spin_unlock_irqrestore(&tc6393xb->lock, flags); - - return 0; -} - -static int tc6393xb_fb_disable(struct platform_device *dev) -{ - struct tc6393xb *tc6393xb = dev_get_drvdata(dev->dev.parent); - unsigned long flags; - u16 ccr; - - raw_spin_lock_irqsave(&tc6393xb->lock, flags); - - ccr = tmio_ioread16(tc6393xb->scr + SCR_CCR); - ccr &= ~SCR_CCR_MCLK_MASK; - ccr |= SCR_CCR_MCLK_OFF; - tmio_iowrite16(ccr, tc6393xb->scr + SCR_CCR); - - raw_spin_unlock_irqrestore(&tc6393xb->lock, flags); - - return 0; -} - -int tc6393xb_lcd_set_power(struct platform_device *fb, bool on) -{ - struct tc6393xb *tc6393xb = dev_get_drvdata(fb->dev.parent); - u8 fer; - unsigned long flags; - - raw_spin_lock_irqsave(&tc6393xb->lock, flags); - - fer = ioread8(tc6393xb->scr + SCR_FER); - if (on) - fer |= SCR_FER_SLCDEN; - else - fer &= ~SCR_FER_SLCDEN; - iowrite8(fer, tc6393xb->scr + SCR_FER); - - raw_spin_unlock_irqrestore(&tc6393xb->lock, flags); - - return 0; -} -EXPORT_SYMBOL(tc6393xb_lcd_set_power); - -int tc6393xb_lcd_mode(struct platform_device *fb, - const struct fb_videomode *mode) { - struct tc6393xb *tc6393xb = dev_get_drvdata(fb->dev.parent); - unsigned long flags; - - raw_spin_lock_irqsave(&tc6393xb->lock, flags); - - iowrite16(mode->pixclock, tc6393xb->scr + SCR_PLL1CR + 0); - iowrite16(mode->pixclock >> 16, tc6393xb->scr + SCR_PLL1CR + 2); - - raw_spin_unlock_irqrestore(&tc6393xb->lock, flags); - - return 0; -} -EXPORT_SYMBOL(tc6393xb_lcd_mode); - -static int tc6393xb_mmc_enable(struct platform_device *mmc) -{ - struct tc6393xb *tc6393xb = dev_get_drvdata(mmc->dev.parent); - - tmio_core_mmc_enable(tc6393xb->scr + 0x200, 0, - tc6393xb_mmc_resources[0].start & 0xfffe); - - return 0; -} - -static int tc6393xb_mmc_resume(struct platform_device *mmc) -{ - struct tc6393xb *tc6393xb = dev_get_drvdata(mmc->dev.parent); - - tmio_core_mmc_resume(tc6393xb->scr + 0x200, 0, - tc6393xb_mmc_resources[0].start & 0xfffe); - - return 0; -} - -static void tc6393xb_mmc_pwr(struct platform_device *mmc, int state) -{ - struct tc6393xb *tc6393xb = dev_get_drvdata(mmc->dev.parent); - - tmio_core_mmc_pwr(tc6393xb->scr + 0x200, 0, state); -} - -static void tc6393xb_mmc_clk_div(struct platform_device *mmc, int state) -{ - struct tc6393xb *tc6393xb = dev_get_drvdata(mmc->dev.parent); - - tmio_core_mmc_clk_div(tc6393xb->scr + 0x200, 0, state); -} - -static struct tmio_mmc_data tc6393xb_mmc_data = { - .hclk = 24000000, - .set_pwr = tc6393xb_mmc_pwr, - .set_clk_div = tc6393xb_mmc_clk_div, -}; - -static struct mfd_cell tc6393xb_cells[] = { - [TC6393XB_CELL_NAND] = { - .name = "tmio-nand", - .enable = tc6393xb_nand_enable, - .num_resources = ARRAY_SIZE(tc6393xb_nand_resources), - .resources = tc6393xb_nand_resources, - }, - [TC6393XB_CELL_MMC] = { - .name = "tmio-mmc", - .enable = tc6393xb_mmc_enable, - .resume = tc6393xb_mmc_resume, - .platform_data = &tc6393xb_mmc_data, - .pdata_size = sizeof(tc6393xb_mmc_data), - .num_resources = ARRAY_SIZE(tc6393xb_mmc_resources), - .resources = tc6393xb_mmc_resources, - }, - [TC6393XB_CELL_OHCI] = { - .name = "tmio-ohci", - .num_resources = ARRAY_SIZE(tc6393xb_ohci_resources), - .resources = tc6393xb_ohci_resources, - .enable = tc6393xb_ohci_enable, - .suspend = tc6393xb_ohci_suspend, - .resume = tc6393xb_ohci_enable, - .disable = tc6393xb_ohci_disable, - }, - [TC6393XB_CELL_FB] = { - .name = "tmio-fb", - .num_resources = ARRAY_SIZE(tc6393xb_fb_resources), - .resources = tc6393xb_fb_resources, - .enable = tc6393xb_fb_enable, - .suspend = tc6393xb_fb_disable, - .resume = tc6393xb_fb_enable, - .disable = tc6393xb_fb_disable, - }, -}; - -/*--------------------------------------------------------------------------*/ - -static int tc6393xb_gpio_get(struct gpio_chip *chip, - unsigned offset) -{ - struct tc6393xb *tc6393xb = gpiochip_get_data(chip); - - /* XXX: does dsr also represent inputs? */ - return !!(tmio_ioread8(tc6393xb->scr + SCR_GPO_DSR(offset / 8)) - & TC_GPIO_BIT(offset)); -} - -static void __tc6393xb_gpio_set(struct gpio_chip *chip, - unsigned offset, int value) -{ - struct tc6393xb *tc6393xb = gpiochip_get_data(chip); - u8 dsr; - - dsr = tmio_ioread8(tc6393xb->scr + SCR_GPO_DSR(offset / 8)); - if (value) - dsr |= TC_GPIO_BIT(offset); - else - dsr &= ~TC_GPIO_BIT(offset); - - tmio_iowrite8(dsr, tc6393xb->scr + SCR_GPO_DSR(offset / 8)); -} - -static void tc6393xb_gpio_set(struct gpio_chip *chip, - unsigned offset, int value) -{ - struct tc6393xb *tc6393xb = gpiochip_get_data(chip); - unsigned long flags; - - raw_spin_lock_irqsave(&tc6393xb->lock, flags); - - __tc6393xb_gpio_set(chip, offset, value); - - raw_spin_unlock_irqrestore(&tc6393xb->lock, flags); -} - -static int tc6393xb_gpio_direction_input(struct gpio_chip *chip, - unsigned offset) -{ - struct tc6393xb *tc6393xb = gpiochip_get_data(chip); - unsigned long flags; - u8 doecr; - - raw_spin_lock_irqsave(&tc6393xb->lock, flags); - - doecr = tmio_ioread8(tc6393xb->scr + SCR_GPO_DOECR(offset / 8)); - doecr &= ~TC_GPIO_BIT(offset); - tmio_iowrite8(doecr, tc6393xb->scr + SCR_GPO_DOECR(offset / 8)); - - raw_spin_unlock_irqrestore(&tc6393xb->lock, flags); - - return 0; -} - -static int tc6393xb_gpio_direction_output(struct gpio_chip *chip, - unsigned offset, int value) -{ - struct tc6393xb *tc6393xb = gpiochip_get_data(chip); - unsigned long flags; - u8 doecr; - - raw_spin_lock_irqsave(&tc6393xb->lock, flags); - - __tc6393xb_gpio_set(chip, offset, value); - - doecr = tmio_ioread8(tc6393xb->scr + SCR_GPO_DOECR(offset / 8)); - doecr |= TC_GPIO_BIT(offset); - tmio_iowrite8(doecr, tc6393xb->scr + SCR_GPO_DOECR(offset / 8)); - - raw_spin_unlock_irqrestore(&tc6393xb->lock, flags); - - return 0; -} - -/* - * TC6393XB GPIOs as used on TOSA, are the only user of this chip. - * GPIOs 2, 5, 8 and 13 are not connected. - */ -#define TOSA_GPIO_TG_ON 0 -#define TOSA_GPIO_L_MUTE 1 -#define TOSA_GPIO_BL_C20MA 3 -#define TOSA_GPIO_CARD_VCC_ON 4 -#define TOSA_GPIO_CHARGE_OFF 6 -#define TOSA_GPIO_CHARGE_OFF_JC 7 -#define TOSA_GPIO_BAT0_V_ON 9 -#define TOSA_GPIO_BAT1_V_ON 10 -#define TOSA_GPIO_BU_CHRG_ON 11 -#define TOSA_GPIO_BAT_SW_ON 12 -#define TOSA_GPIO_BAT0_TH_ON 14 -#define TOSA_GPIO_BAT1_TH_ON 15 - - -GPIO_LOOKUP_SINGLE(tosa_lcd_gpio_lookup, "spi2.0", "tc6393xb", - TOSA_GPIO_TG_ON, "tg #pwr", GPIO_ACTIVE_HIGH); - -GPIO_LOOKUP_SINGLE(tosa_lcd_bl_gpio_lookup, "i2c-tos-bl", "tc6393xb", - TOSA_GPIO_BL_C20MA, "backlight", GPIO_ACTIVE_HIGH); - -GPIO_LOOKUP_SINGLE(tosa_audio_gpio_lookup, "tosa-audio", "tc6393xb", - TOSA_GPIO_L_MUTE, NULL, GPIO_ACTIVE_HIGH); - -static struct gpiod_lookup_table tosa_battery_gpio_lookup = { - .dev_id = "wm97xx-battery", - .table = { - GPIO_LOOKUP("tc6393xb", TOSA_GPIO_CHARGE_OFF, - "main charge off", GPIO_ACTIVE_HIGH), - GPIO_LOOKUP("tc6393xb", TOSA_GPIO_CHARGE_OFF_JC, - "jacket charge off", GPIO_ACTIVE_HIGH), - GPIO_LOOKUP("tc6393xb", TOSA_GPIO_BAT0_V_ON, - "main battery", GPIO_ACTIVE_HIGH), - GPIO_LOOKUP("tc6393xb", TOSA_GPIO_BAT1_V_ON, - "jacket battery", GPIO_ACTIVE_HIGH), - GPIO_LOOKUP("tc6393xb", TOSA_GPIO_BU_CHRG_ON, - "backup battery", GPIO_ACTIVE_HIGH), - /* BAT1 and BAT0 thermistors appear to be swapped */ - GPIO_LOOKUP("tc6393xb", TOSA_GPIO_BAT1_TH_ON, - "main battery temp", GPIO_ACTIVE_HIGH), - GPIO_LOOKUP("tc6393xb", TOSA_GPIO_BAT0_TH_ON, - "jacket battery temp", GPIO_ACTIVE_HIGH), - GPIO_LOOKUP("tc6393xb", TOSA_GPIO_BAT_SW_ON, - "battery switch", GPIO_ACTIVE_HIGH), - { }, - }, -}; - -static struct gpiod_lookup_table *tc6393xb_gpio_lookups[] = { - &tosa_lcd_gpio_lookup, - &tosa_lcd_bl_gpio_lookup, - &tosa_audio_gpio_lookup, - &tosa_battery_gpio_lookup, -}; - -static int tc6393xb_register_gpio(struct tc6393xb *tc6393xb) -{ - struct gpio_chip *gc = &tc6393xb->gpio; - struct device *dev = tc6393xb->dev; - int ret; - - gc->label = "tc6393xb"; - gc->base = -1; /* Dynamic allocation */ - gc->ngpio = 16; - gc->set = tc6393xb_gpio_set; - gc->get = tc6393xb_gpio_get; - gc->direction_input = tc6393xb_gpio_direction_input; - gc->direction_output = tc6393xb_gpio_direction_output; - - ret = devm_gpiochip_add_data(dev, gc, tc6393xb); - if (ret) - return dev_err_probe(dev, ret, "failed to add GPIO chip\n"); - - /* Register descriptor look-ups for consumers */ - gpiod_add_lookup_tables(tc6393xb_gpio_lookups, ARRAY_SIZE(tc6393xb_gpio_lookups)); - - /* Request some of our own GPIOs */ - tc6393xb->vcc_on = gpiochip_request_own_desc(gc, TOSA_GPIO_CARD_VCC_ON, "VCC ON", - GPIO_ACTIVE_HIGH, GPIOD_OUT_HIGH); - if (IS_ERR(tc6393xb->vcc_on)) - return dev_err_probe(dev, PTR_ERR(tc6393xb->vcc_on), - "failed to request VCC ON GPIO\n"); - - return 0; -} - -/*--------------------------------------------------------------------------*/ - -static void tc6393xb_irq(struct irq_desc *desc) -{ - struct tc6393xb *tc6393xb = irq_desc_get_handler_data(desc); - unsigned int isr; - unsigned int i, irq_base; - - irq_base = tc6393xb->irq_base; - - while ((isr = tmio_ioread8(tc6393xb->scr + SCR_ISR) & - ~tmio_ioread8(tc6393xb->scr + SCR_IMR))) - for (i = 0; i < TC6393XB_NR_IRQS; i++) { - if (isr & (1 << i)) - generic_handle_irq(irq_base + i); - } -} - -static void tc6393xb_irq_ack(struct irq_data *data) -{ -} - -static void tc6393xb_irq_mask(struct irq_data *data) -{ - struct tc6393xb *tc6393xb = irq_data_get_irq_chip_data(data); - unsigned long flags; - u8 imr; - - raw_spin_lock_irqsave(&tc6393xb->lock, flags); - imr = tmio_ioread8(tc6393xb->scr + SCR_IMR); - imr |= 1 << (data->irq - tc6393xb->irq_base); - tmio_iowrite8(imr, tc6393xb->scr + SCR_IMR); - raw_spin_unlock_irqrestore(&tc6393xb->lock, flags); -} - -static void tc6393xb_irq_unmask(struct irq_data *data) -{ - struct tc6393xb *tc6393xb = irq_data_get_irq_chip_data(data); - unsigned long flags; - u8 imr; - - raw_spin_lock_irqsave(&tc6393xb->lock, flags); - imr = tmio_ioread8(tc6393xb->scr + SCR_IMR); - imr &= ~(1 << (data->irq - tc6393xb->irq_base)); - tmio_iowrite8(imr, tc6393xb->scr + SCR_IMR); - raw_spin_unlock_irqrestore(&tc6393xb->lock, flags); -} - -static struct irq_chip tc6393xb_chip = { - .name = "tc6393xb", - .irq_ack = tc6393xb_irq_ack, - .irq_mask = tc6393xb_irq_mask, - .irq_unmask = tc6393xb_irq_unmask, -}; - -static void tc6393xb_attach_irq(struct platform_device *dev) -{ - struct tc6393xb *tc6393xb = platform_get_drvdata(dev); - unsigned int irq, irq_base; - - irq_base = tc6393xb->irq_base; - - for (irq = irq_base; irq < irq_base + TC6393XB_NR_IRQS; irq++) { - irq_set_chip_and_handler(irq, &tc6393xb_chip, handle_edge_irq); - irq_set_chip_data(irq, tc6393xb); - irq_clear_status_flags(irq, IRQ_NOREQUEST | IRQ_NOPROBE); - } - - irq_set_irq_type(tc6393xb->irq, IRQ_TYPE_EDGE_FALLING); - irq_set_chained_handler_and_data(tc6393xb->irq, tc6393xb_irq, - tc6393xb); -} - -static void tc6393xb_detach_irq(struct platform_device *dev) -{ - struct tc6393xb *tc6393xb = platform_get_drvdata(dev); - unsigned int irq, irq_base; - - irq_set_chained_handler_and_data(tc6393xb->irq, NULL, NULL); - - irq_base = tc6393xb->irq_base; - - for (irq = irq_base; irq < irq_base + TC6393XB_NR_IRQS; irq++) { - irq_set_status_flags(irq, IRQ_NOREQUEST | IRQ_NOPROBE); - irq_set_chip(irq, NULL); - irq_set_chip_data(irq, NULL); - } -} - -/*--------------------------------------------------------------------------*/ - -static int tc6393xb_probe(struct platform_device *dev) -{ - struct tc6393xb_platform_data *tcpd = dev_get_platdata(&dev->dev); - struct tc6393xb *tc6393xb; - struct resource *iomem, *rscr; - int ret; - - iomem = platform_get_resource(dev, IORESOURCE_MEM, 0); - if (!iomem) - return -EINVAL; - - tc6393xb = kzalloc(sizeof *tc6393xb, GFP_KERNEL); - if (!tc6393xb) { - ret = -ENOMEM; - goto err_kzalloc; - } - tc6393xb->dev = &dev->dev; - - raw_spin_lock_init(&tc6393xb->lock); - - platform_set_drvdata(dev, tc6393xb); - - ret = platform_get_irq(dev, 0); - if (ret >= 0) - tc6393xb->irq = ret; - else - goto err_noirq; - - tc6393xb->iomem = iomem; - tc6393xb->irq_base = tcpd->irq_base; - - tc6393xb->clk = clk_get(&dev->dev, "CLK_CK3P6MI"); - if (IS_ERR(tc6393xb->clk)) { - ret = PTR_ERR(tc6393xb->clk); - goto err_clk_get; - } - - rscr = &tc6393xb->rscr; - rscr->name = "tc6393xb-core"; - rscr->start = iomem->start; - rscr->end = iomem->start + 0xff; - rscr->flags = IORESOURCE_MEM; - - ret = request_resource(iomem, rscr); - if (ret) - goto err_request_scr; - - tc6393xb->scr = ioremap(rscr->start, resource_size(rscr)); - if (!tc6393xb->scr) { - ret = -ENOMEM; - goto err_ioremap; - } - - ret = clk_prepare_enable(tc6393xb->clk); - if (ret) - goto err_clk_enable; - - ret = tcpd->enable(dev); - if (ret) - goto err_enable; - - iowrite8(0, tc6393xb->scr + SCR_FER); - iowrite16(tcpd->scr_pll2cr, tc6393xb->scr + SCR_PLL2CR); - iowrite16(SCR_CCR_UNK1 | SCR_CCR_HCLK_48, - tc6393xb->scr + SCR_CCR); - iowrite16(SCR_MCR_RDY_OPENDRAIN | SCR_MCR_RDY_UNK | SCR_MCR_RDY_EN | - SCR_MCR_INT_OPENDRAIN | SCR_MCR_INT_UNK | SCR_MCR_INT_EN | - BIT(15), tc6393xb->scr + SCR_MCR); - iowrite16(tcpd->scr_gper, tc6393xb->scr + SCR_GPER); - iowrite8(0, tc6393xb->scr + SCR_IRR); - iowrite8(0xbf, tc6393xb->scr + SCR_IMR); - - printk(KERN_INFO "Toshiba tc6393xb revision %d at 0x%08lx, irq %d\n", - tmio_ioread8(tc6393xb->scr + SCR_REVID), - (unsigned long) iomem->start, tc6393xb->irq); - - ret = tc6393xb_register_gpio(tc6393xb); - if (ret) - goto err_gpio_add; - - tc6393xb_attach_irq(dev); - - tc6393xb_cells[TC6393XB_CELL_NAND].platform_data = tcpd->nand_data; - tc6393xb_cells[TC6393XB_CELL_NAND].pdata_size = - sizeof(*tcpd->nand_data); - tc6393xb_cells[TC6393XB_CELL_FB].platform_data = tcpd->fb_data; - tc6393xb_cells[TC6393XB_CELL_FB].pdata_size = sizeof(*tcpd->fb_data); - - ret = mfd_add_devices(&dev->dev, dev->id, - tc6393xb_cells, ARRAY_SIZE(tc6393xb_cells), - iomem, tcpd->irq_base, NULL); - - if (!ret) - return 0; - - tc6393xb_detach_irq(dev); -err_gpio_add: - tcpd->disable(dev); -err_enable: - clk_disable_unprepare(tc6393xb->clk); -err_clk_enable: - iounmap(tc6393xb->scr); -err_ioremap: - release_resource(&tc6393xb->rscr); -err_request_scr: - clk_put(tc6393xb->clk); -err_noirq: -err_clk_get: - kfree(tc6393xb); -err_kzalloc: - return ret; -} - -static int tc6393xb_remove(struct platform_device *dev) -{ - struct tc6393xb_platform_data *tcpd = dev_get_platdata(&dev->dev); - struct tc6393xb *tc6393xb = platform_get_drvdata(dev); - - mfd_remove_devices(&dev->dev); - - tc6393xb_detach_irq(dev); - - tcpd->disable(dev); - clk_disable_unprepare(tc6393xb->clk); - iounmap(tc6393xb->scr); - release_resource(&tc6393xb->rscr); - clk_put(tc6393xb->clk); - kfree(tc6393xb); - - return 0; -} - -static int tc6393xb_suspend(struct platform_device *dev, pm_message_t state) -{ - struct tc6393xb_platform_data *tcpd = dev_get_platdata(&dev->dev); - struct tc6393xb *tc6393xb = platform_get_drvdata(dev); - int i, ret; - - tc6393xb->suspend_state.ccr = ioread16(tc6393xb->scr + SCR_CCR); - tc6393xb->suspend_state.fer = ioread8(tc6393xb->scr + SCR_FER); - - for (i = 0; i < 3; i++) { - tc6393xb->suspend_state.gpo_dsr[i] = - ioread8(tc6393xb->scr + SCR_GPO_DSR(i)); - tc6393xb->suspend_state.gpo_doecr[i] = - ioread8(tc6393xb->scr + SCR_GPO_DOECR(i)); - tc6393xb->suspend_state.gpi_bcr[i] = - ioread8(tc6393xb->scr + SCR_GPI_BCR(i)); - } - ret = tcpd->suspend(dev); - clk_disable_unprepare(tc6393xb->clk); - - return ret; -} - -static int tc6393xb_resume(struct platform_device *dev) -{ - struct tc6393xb_platform_data *tcpd = dev_get_platdata(&dev->dev); - struct tc6393xb *tc6393xb = platform_get_drvdata(dev); - int ret; - int i; - - ret = clk_prepare_enable(tc6393xb->clk); - if (ret) - return ret; - - ret = tcpd->resume(dev); - if (ret) - return ret; - - if (!tcpd->resume_restore) - return 0; - - iowrite8(tc6393xb->suspend_state.fer, tc6393xb->scr + SCR_FER); - iowrite16(tcpd->scr_pll2cr, tc6393xb->scr + SCR_PLL2CR); - iowrite16(tc6393xb->suspend_state.ccr, tc6393xb->scr + SCR_CCR); - iowrite16(SCR_MCR_RDY_OPENDRAIN | SCR_MCR_RDY_UNK | SCR_MCR_RDY_EN | - SCR_MCR_INT_OPENDRAIN | SCR_MCR_INT_UNK | SCR_MCR_INT_EN | - BIT(15), tc6393xb->scr + SCR_MCR); - iowrite16(tcpd->scr_gper, tc6393xb->scr + SCR_GPER); - iowrite8(0, tc6393xb->scr + SCR_IRR); - iowrite8(0xbf, tc6393xb->scr + SCR_IMR); - - for (i = 0; i < 3; i++) { - iowrite8(tc6393xb->suspend_state.gpo_dsr[i], - tc6393xb->scr + SCR_GPO_DSR(i)); - iowrite8(tc6393xb->suspend_state.gpo_doecr[i], - tc6393xb->scr + SCR_GPO_DOECR(i)); - iowrite8(tc6393xb->suspend_state.gpi_bcr[i], - tc6393xb->scr + SCR_GPI_BCR(i)); - } - - return 0; -} - -static struct platform_driver tc6393xb_driver = { - .probe = tc6393xb_probe, - .remove = tc6393xb_remove, - .suspend = pm_sleep_ptr(tc6393xb_suspend), - .resume = pm_sleep_ptr(tc6393xb_resume), - - .driver = { - .name = "tc6393xb", - }, -}; - -static int __init tc6393xb_init(void) -{ - return platform_driver_register(&tc6393xb_driver); -} - -static void __exit tc6393xb_exit(void) -{ - platform_driver_unregister(&tc6393xb_driver); -} - -subsys_initcall(tc6393xb_init); -module_exit(tc6393xb_exit); - -MODULE_LICENSE("GPL v2"); -MODULE_AUTHOR("Ian Molton, Dmitry Baryshkov and Dirk Opfer"); -MODULE_DESCRIPTION("tc6393xb Toshiba Mobile IO Controller"); -MODULE_ALIAS("platform:tc6393xb"); - diff --git a/drivers/mfd/tmio_core.c b/drivers/mfd/tmio_core.c deleted file mode 100644 index 7ee873551482..000000000000 --- a/drivers/mfd/tmio_core.c +++ /dev/null @@ -1,70 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright(c) 2009 Ian Molton - */ - -#include -#include - -#define CNF_CMD 0x04 -#define CNF_CTL_BASE 0x10 -#define CNF_INT_PIN 0x3d -#define CNF_STOP_CLK_CTL 0x40 -#define CNF_GCLK_CTL 0x41 -#define CNF_SD_CLK_MODE 0x42 -#define CNF_PIN_STATUS 0x44 -#define CNF_PWR_CTL_1 0x48 -#define CNF_PWR_CTL_2 0x49 -#define CNF_PWR_CTL_3 0x4a -#define CNF_CARD_DETECT_MODE 0x4c -#define CNF_SD_SLOT 0x50 -#define CNF_EXT_GCLK_CTL_1 0xf0 -#define CNF_EXT_GCLK_CTL_2 0xf1 -#define CNF_EXT_GCLK_CTL_3 0xf9 -#define CNF_SD_LED_EN_1 0xfa -#define CNF_SD_LED_EN_2 0xfe - -#define SDCREN 0x2 /* Enable access to MMC CTL regs. (flag in COMMAND_REG)*/ - -int tmio_core_mmc_enable(void __iomem *cnf, int shift, unsigned long base) -{ - /* Enable the MMC/SD Control registers */ - sd_config_write16(cnf, shift, CNF_CMD, SDCREN); - sd_config_write32(cnf, shift, CNF_CTL_BASE, base & 0xfffe); - - /* Disable SD power during suspend */ - sd_config_write8(cnf, shift, CNF_PWR_CTL_3, 0x01); - - /* The below is required but why? FIXME */ - sd_config_write8(cnf, shift, CNF_STOP_CLK_CTL, 0x1f); - - /* Power down SD bus */ - sd_config_write8(cnf, shift, CNF_PWR_CTL_2, 0x00); - - return 0; -} -EXPORT_SYMBOL(tmio_core_mmc_enable); - -int tmio_core_mmc_resume(void __iomem *cnf, int shift, unsigned long base) -{ - - /* Enable the MMC/SD Control registers */ - sd_config_write16(cnf, shift, CNF_CMD, SDCREN); - sd_config_write32(cnf, shift, CNF_CTL_BASE, base & 0xfffe); - - return 0; -} -EXPORT_SYMBOL(tmio_core_mmc_resume); - -void tmio_core_mmc_pwr(void __iomem *cnf, int shift, int state) -{ - sd_config_write8(cnf, shift, CNF_PWR_CTL_2, state ? 0x02 : 0x00); -} -EXPORT_SYMBOL(tmio_core_mmc_pwr); - -void tmio_core_mmc_clk_div(void __iomem *cnf, int shift, int state) -{ - sd_config_write8(cnf, shift, CNF_SD_CLK_MODE, state ? 1 : 0); -} -EXPORT_SYMBOL(tmio_core_mmc_clk_div); - diff --git a/include/linux/mfd/asic3.h b/include/linux/mfd/asic3.h deleted file mode 100644 index 61e686dbaa74..000000000000 --- a/include/linux/mfd/asic3.h +++ /dev/null @@ -1,313 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * include/linux/mfd/asic3.h - * - * Compaq ASIC3 headers. - * - * Copyright 2001 Compaq Computer Corporation. - * Copyright 2007-2008 OpenedHand Ltd. - */ - -#ifndef __ASIC3_H__ -#define __ASIC3_H__ - -#include - -struct led_classdev; -struct asic3_led { - const char *name; - const char *default_trigger; - struct led_classdev *cdev; -}; - -struct asic3_platform_data { - u16 *gpio_config; - unsigned int gpio_config_num; - - unsigned int irq_base; - - unsigned int gpio_base; - - unsigned int clock_rate; - - struct asic3_led *leds; -}; - -#define ASIC3_NUM_GPIO_BANKS 4 -#define ASIC3_GPIOS_PER_BANK 16 -#define ASIC3_NUM_GPIOS 64 -#define ASIC3_NR_IRQS ASIC3_NUM_GPIOS + 6 - -#define ASIC3_IRQ_LED0 64 -#define ASIC3_IRQ_LED1 65 -#define ASIC3_IRQ_LED2 66 -#define ASIC3_IRQ_SPI 67 -#define ASIC3_IRQ_SMBUS 68 -#define ASIC3_IRQ_OWM 69 - -#define ASIC3_TO_GPIO(gpio) (NR_BUILTIN_GPIO + (gpio)) - -#define ASIC3_GPIO_BANK_A 0 -#define ASIC3_GPIO_BANK_B 1 -#define ASIC3_GPIO_BANK_C 2 -#define ASIC3_GPIO_BANK_D 3 - -#define ASIC3_GPIO(bank, gpio) \ - ((ASIC3_GPIOS_PER_BANK * ASIC3_GPIO_BANK_##bank) + (gpio)) -#define ASIC3_GPIO_bit(gpio) (1 << (gpio & 0xf)) -/* All offsets below are specified with this address bus shift */ -#define ASIC3_DEFAULT_ADDR_SHIFT 2 - -#define ASIC3_OFFSET(base, reg) (ASIC3_##base##_BASE + ASIC3_##base##_##reg) -#define ASIC3_GPIO_OFFSET(base, reg) \ - (ASIC3_GPIO_##base##_BASE + ASIC3_GPIO_##reg) - -#define ASIC3_GPIO_A_BASE 0x0000 -#define ASIC3_GPIO_B_BASE 0x0100 -#define ASIC3_GPIO_C_BASE 0x0200 -#define ASIC3_GPIO_D_BASE 0x0300 - -#define ASIC3_GPIO_TO_BANK(gpio) ((gpio) >> 4) -#define ASIC3_GPIO_TO_BIT(gpio) ((gpio) - \ - (ASIC3_GPIOS_PER_BANK * ((gpio) >> 4))) -#define ASIC3_GPIO_TO_MASK(gpio) (1 << ASIC3_GPIO_TO_BIT(gpio)) -#define ASIC3_GPIO_TO_BASE(gpio) (ASIC3_GPIO_A_BASE + (((gpio) >> 4) * 0x0100)) -#define ASIC3_BANK_TO_BASE(bank) (ASIC3_GPIO_A_BASE + ((bank) * 0x100)) - -#define ASIC3_GPIO_MASK 0x00 /* R/W 0:don't mask */ -#define ASIC3_GPIO_DIRECTION 0x04 /* R/W 0:input */ -#define ASIC3_GPIO_OUT 0x08 /* R/W 0:output low */ -#define ASIC3_GPIO_TRIGGER_TYPE 0x0c /* R/W 0:level */ -#define ASIC3_GPIO_EDGE_TRIGGER 0x10 /* R/W 0:falling */ -#define ASIC3_GPIO_LEVEL_TRIGGER 0x14 /* R/W 0:low level detect */ -#define ASIC3_GPIO_SLEEP_MASK 0x18 /* R/W 0:don't mask in sleep mode */ -#define ASIC3_GPIO_SLEEP_OUT 0x1c /* R/W level 0:low in sleep mode */ -#define ASIC3_GPIO_BAT_FAULT_OUT 0x20 /* R/W level 0:low in batt_fault */ -#define ASIC3_GPIO_INT_STATUS 0x24 /* R/W 0:none, 1:detect */ -#define ASIC3_GPIO_ALT_FUNCTION 0x28 /* R/W 1:LED register control */ -#define ASIC3_GPIO_SLEEP_CONF 0x2c /* - * R/W bit 1: autosleep - * 0: disable gposlpout in normal mode, - * enable gposlpout in sleep mode. - */ -#define ASIC3_GPIO_STATUS 0x30 /* R Pin status */ - -/* - * ASIC3 GPIO config - * - * Bits 0..6 gpio number - * Bits 7..13 Alternate function - * Bit 14 Direction - * Bit 15 Initial value - * - */ -#define ASIC3_CONFIG_GPIO_PIN(config) ((config) & 0x7f) -#define ASIC3_CONFIG_GPIO_ALT(config) (((config) & (0x7f << 7)) >> 7) -#define ASIC3_CONFIG_GPIO_DIR(config) ((config & (1 << 14)) >> 14) -#define ASIC3_CONFIG_GPIO_INIT(config) ((config & (1 << 15)) >> 15) -#define ASIC3_CONFIG_GPIO(gpio, alt, dir, init) (((gpio) & 0x7f) \ - | (((alt) & 0x7f) << 7) | (((dir) & 0x1) << 14) \ - | (((init) & 0x1) << 15)) -#define ASIC3_CONFIG_GPIO_DEFAULT(gpio, dir, init) \ - ASIC3_CONFIG_GPIO((gpio), 0, (dir), (init)) -#define ASIC3_CONFIG_GPIO_DEFAULT_OUT(gpio, init) \ - ASIC3_CONFIG_GPIO((gpio), 0, 1, (init)) - -/* - * Alternate functions - */ -#define ASIC3_GPIOA11_PWM0 ASIC3_CONFIG_GPIO(11, 1, 1, 0) -#define ASIC3_GPIOA12_PWM1 ASIC3_CONFIG_GPIO(12, 1, 1, 0) -#define ASIC3_GPIOA15_CONTROL_CX ASIC3_CONFIG_GPIO(15, 1, 1, 0) -#define ASIC3_GPIOC0_LED0 ASIC3_CONFIG_GPIO(32, 1, 0, 0) -#define ASIC3_GPIOC1_LED1 ASIC3_CONFIG_GPIO(33, 1, 0, 0) -#define ASIC3_GPIOC2_LED2 ASIC3_CONFIG_GPIO(34, 1, 0, 0) -#define ASIC3_GPIOC3_SPI_RXD ASIC3_CONFIG_GPIO(35, 1, 0, 0) -#define ASIC3_GPIOC4_CF_nCD ASIC3_CONFIG_GPIO(36, 1, 0, 0) -#define ASIC3_GPIOC4_SPI_TXD ASIC3_CONFIG_GPIO(36, 1, 1, 0) -#define ASIC3_GPIOC5_SPI_CLK ASIC3_CONFIG_GPIO(37, 1, 1, 0) -#define ASIC3_GPIOC5_nCIOW ASIC3_CONFIG_GPIO(37, 1, 1, 0) -#define ASIC3_GPIOC6_nCIOR ASIC3_CONFIG_GPIO(38, 1, 1, 0) -#define ASIC3_GPIOC7_nPCE_1 ASIC3_CONFIG_GPIO(39, 1, 0, 0) -#define ASIC3_GPIOC8_nPCE_2 ASIC3_CONFIG_GPIO(40, 1, 0, 0) -#define ASIC3_GPIOC9_nPOE ASIC3_CONFIG_GPIO(41, 1, 0, 0) -#define ASIC3_GPIOC10_nPWE ASIC3_CONFIG_GPIO(42, 1, 0, 0) -#define ASIC3_GPIOC11_PSKTSEL ASIC3_CONFIG_GPIO(43, 1, 0, 0) -#define ASIC3_GPIOC12_nPREG ASIC3_CONFIG_GPIO(44, 1, 0, 0) -#define ASIC3_GPIOC13_nPWAIT ASIC3_CONFIG_GPIO(45, 1, 1, 0) -#define ASIC3_GPIOC14_nPIOIS16 ASIC3_CONFIG_GPIO(46, 1, 1, 0) -#define ASIC3_GPIOC15_nPIOR ASIC3_CONFIG_GPIO(47, 1, 0, 0) -#define ASIC3_GPIOD4_CF_nCD ASIC3_CONFIG_GPIO(52, 1, 0, 0) -#define ASIC3_GPIOD11_nCIOIS16 ASIC3_CONFIG_GPIO(59, 1, 0, 0) -#define ASIC3_GPIOD12_nCWAIT ASIC3_CONFIG_GPIO(60, 1, 0, 0) -#define ASIC3_GPIOD15_nPIOW ASIC3_CONFIG_GPIO(63, 1, 0, 0) - - -#define ASIC3_SPI_Base 0x0400 -#define ASIC3_SPI_Control 0x0000 -#define ASIC3_SPI_TxData 0x0004 -#define ASIC3_SPI_RxData 0x0008 -#define ASIC3_SPI_Int 0x000c -#define ASIC3_SPI_Status 0x0010 - -#define SPI_CONTROL_SPR(clk) ((clk) & 0x0f) /* Clock rate */ - -#define ASIC3_PWM_0_Base 0x0500 -#define ASIC3_PWM_1_Base 0x0600 -#define ASIC3_PWM_TimeBase 0x0000 -#define ASIC3_PWM_PeriodTime 0x0004 -#define ASIC3_PWM_DutyTime 0x0008 - -#define PWM_TIMEBASE_VALUE(x) ((x)&0xf) /* Low 4 bits sets time base */ -#define PWM_TIMEBASE_ENABLE (1 << 4) /* Enable clock */ - -#define ASIC3_NUM_LEDS 3 -#define ASIC3_LED_0_Base 0x0700 -#define ASIC3_LED_1_Base 0x0800 -#define ASIC3_LED_2_Base 0x0900 -#define ASIC3_LED_TimeBase 0x0000 /* R/W 7 bits */ -#define ASIC3_LED_PeriodTime 0x0004 /* R/W 12 bits */ -#define ASIC3_LED_DutyTime 0x0008 /* R/W 12 bits */ -#define ASIC3_LED_AutoStopCount 0x000c /* R/W 16 bits */ - -/* LED TimeBase bits - match ASIC2 */ -#define LED_TBS 0x0f /* Low 4 bits sets time base, max = 13 */ - /* Note: max = 5 on hx4700 */ - /* 0: maximum time base */ - /* 1: maximum time base / 2 */ - /* n: maximum time base / 2^n */ - -#define LED_EN (1 << 4) /* LED ON/OFF 0:off, 1:on */ -#define LED_AUTOSTOP (1 << 5) /* LED ON/OFF auto stop 0:disable, 1:enable */ -#define LED_ALWAYS (1 << 6) /* LED Interrupt Mask 0:No mask, 1:mask */ - -#define ASIC3_CLOCK_BASE 0x0A00 -#define ASIC3_CLOCK_CDEX 0x00 -#define ASIC3_CLOCK_SEL 0x04 - -#define CLOCK_CDEX_SOURCE (1 << 0) /* 2 bits */ -#define CLOCK_CDEX_SOURCE0 (1 << 0) -#define CLOCK_CDEX_SOURCE1 (1 << 1) -#define CLOCK_CDEX_SPI (1 << 2) -#define CLOCK_CDEX_OWM (1 << 3) -#define CLOCK_CDEX_PWM0 (1 << 4) -#define CLOCK_CDEX_PWM1 (1 << 5) -#define CLOCK_CDEX_LED0 (1 << 6) -#define CLOCK_CDEX_LED1 (1 << 7) -#define CLOCK_CDEX_LED2 (1 << 8) - -/* Clocks settings: 1 for 24.576 MHz, 0 for 12.288Mhz */ -#define CLOCK_CDEX_SD_HOST (1 << 9) /* R/W: SD host clock source */ -#define CLOCK_CDEX_SD_BUS (1 << 10) /* R/W: SD bus clock source ctrl */ -#define CLOCK_CDEX_SMBUS (1 << 11) -#define CLOCK_CDEX_CONTROL_CX (1 << 12) - -#define CLOCK_CDEX_EX0 (1 << 13) /* R/W: 32.768 kHz crystal */ -#define CLOCK_CDEX_EX1 (1 << 14) /* R/W: 24.576 MHz crystal */ - -#define CLOCK_SEL_SD_HCLK_SEL (1 << 0) /* R/W: SDIO host clock select */ -#define CLOCK_SEL_SD_BCLK_SEL (1 << 1) /* R/W: SDIO bus clock select */ - -/* R/W: INT clock source control (32.768 kHz) */ -#define CLOCK_SEL_CX (1 << 2) - - -#define ASIC3_INTR_BASE 0x0B00 - -#define ASIC3_INTR_INT_MASK 0x00 /* Interrupt mask control */ -#define ASIC3_INTR_P_INT_STAT 0x04 /* Peripheral interrupt status */ -#define ASIC3_INTR_INT_CPS 0x08 /* Interrupt timer clock pre-scale */ -#define ASIC3_INTR_INT_TBS 0x0c /* Interrupt timer set */ - -#define ASIC3_INTMASK_GINTMASK (1 << 0) /* Global INTs mask 1:enable */ -#define ASIC3_INTMASK_GINTEL (1 << 1) /* 1: rising edge, 0: hi level */ -#define ASIC3_INTMASK_MASK0 (1 << 2) -#define ASIC3_INTMASK_MASK1 (1 << 3) -#define ASIC3_INTMASK_MASK2 (1 << 4) -#define ASIC3_INTMASK_MASK3 (1 << 5) -#define ASIC3_INTMASK_MASK4 (1 << 6) -#define ASIC3_INTMASK_MASK5 (1 << 7) - -#define ASIC3_INTR_PERIPHERAL_A (1 << 0) -#define ASIC3_INTR_PERIPHERAL_B (1 << 1) -#define ASIC3_INTR_PERIPHERAL_C (1 << 2) -#define ASIC3_INTR_PERIPHERAL_D (1 << 3) -#define ASIC3_INTR_LED0 (1 << 4) -#define ASIC3_INTR_LED1 (1 << 5) -#define ASIC3_INTR_LED2 (1 << 6) -#define ASIC3_INTR_SPI (1 << 7) -#define ASIC3_INTR_SMBUS (1 << 8) -#define ASIC3_INTR_OWM (1 << 9) - -#define ASIC3_INTR_CPS(x) ((x)&0x0f) /* 4 bits, max 14 */ -#define ASIC3_INTR_CPS_SET (1 << 4) /* Time base enable */ - - -/* Basic control of the SD ASIC */ -#define ASIC3_SDHWCTRL_BASE 0x0E00 -#define ASIC3_SDHWCTRL_SDCONF 0x00 - -#define ASIC3_SDHWCTRL_SUSPEND (1 << 0) /* 1=suspend all SD operations */ -#define ASIC3_SDHWCTRL_CLKSEL (1 << 1) /* 1=SDICK, 0=HCLK */ -#define ASIC3_SDHWCTRL_PCLR (1 << 2) /* All registers of SDIO cleared */ -#define ASIC3_SDHWCTRL_LEVCD (1 << 3) /* SD card detection: 0:low */ - -/* SD card write protection: 0=high */ -#define ASIC3_SDHWCTRL_LEVWP (1 << 4) -#define ASIC3_SDHWCTRL_SDLED (1 << 5) /* SD card LED signal 0=disable */ - -/* SD card power supply ctrl 1=enable */ -#define ASIC3_SDHWCTRL_SDPWR (1 << 6) - -#define ASIC3_EXTCF_BASE 0x1100 - -#define ASIC3_EXTCF_SELECT 0x00 -#define ASIC3_EXTCF_RESET 0x04 - -#define ASIC3_EXTCF_SMOD0 (1 << 0) /* slot number of mode 0 */ -#define ASIC3_EXTCF_SMOD1 (1 << 1) /* slot number of mode 1 */ -#define ASIC3_EXTCF_SMOD2 (1 << 2) /* slot number of mode 2 */ -#define ASIC3_EXTCF_OWM_EN (1 << 4) /* enable onewire module */ -#define ASIC3_EXTCF_OWM_SMB (1 << 5) /* OWM bus selection */ -#define ASIC3_EXTCF_OWM_RESET (1 << 6) /* ?? used by OWM and CF */ -#define ASIC3_EXTCF_CF0_SLEEP_MODE (1 << 7) /* CF0 sleep state */ -#define ASIC3_EXTCF_CF1_SLEEP_MODE (1 << 8) /* CF1 sleep state */ -#define ASIC3_EXTCF_CF0_PWAIT_EN (1 << 10) /* CF0 PWAIT_n control */ -#define ASIC3_EXTCF_CF1_PWAIT_EN (1 << 11) /* CF1 PWAIT_n control */ -#define ASIC3_EXTCF_CF0_BUF_EN (1 << 12) /* CF0 buffer control */ -#define ASIC3_EXTCF_CF1_BUF_EN (1 << 13) /* CF1 buffer control */ -#define ASIC3_EXTCF_SD_MEM_ENABLE (1 << 14) -#define ASIC3_EXTCF_CF_SLEEP (1 << 15) /* CF sleep mode control */ - -/********************************************* - * The Onewire interface (DS1WM) is handled - * by the ds1wm driver. - * - *********************************************/ - -#define ASIC3_OWM_BASE 0xC00 - -/***************************************************************************** - * The SD configuration registers are at a completely different location - * in memory. They are divided into three sets of registers: - * - * SD_CONFIG Core configuration register - * SD_CTRL Control registers for SD operations - * SDIO_CTRL Control registers for SDIO operations - * - *****************************************************************************/ -#define ASIC3_SD_CONFIG_BASE 0x0400 /* Assumes 32 bit addressing */ -#define ASIC3_SD_CONFIG_SIZE 0x0200 /* Assumes 32 bit addressing */ -#define ASIC3_SD_CTRL_BASE 0x1000 -#define ASIC3_SDIO_CTRL_BASE 0x1200 - -#define ASIC3_MAP_SIZE_32BIT 0x2000 -#define ASIC3_MAP_SIZE_16BIT 0x1000 - -/* Functions needed by leds-asic3 */ - -struct asic3; -extern void asic3_write_register(struct asic3 *asic, unsigned int reg, u32 val); -extern u32 asic3_read_register(struct asic3 *asic, unsigned int reg); - -#endif /* __ASIC3_H__ */ diff --git a/include/linux/mfd/t7l66xb.h b/include/linux/mfd/t7l66xb.h deleted file mode 100644 index ae3e7a5c5219..000000000000 --- a/include/linux/mfd/t7l66xb.h +++ /dev/null @@ -1,29 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * This file contains the definitions for the T7L66XB - * - * (C) Copyright 2005 Ian Molton - */ -#ifndef MFD_T7L66XB_H -#define MFD_T7L66XB_H - -#include -#include - -struct t7l66xb_platform_data { - int (*enable)(struct platform_device *dev); - int (*suspend)(struct platform_device *dev); - int (*resume)(struct platform_device *dev); - - int irq_base; /* The base for subdevice irqs */ - - struct tmio_nand_data *nand_data; -}; - - -#define IRQ_T7L66XB_MMC (1) -#define IRQ_T7L66XB_NAND (3) - -#define T7L66XB_NR_IRQS 8 - -#endif diff --git a/include/linux/mfd/tc6387xb.h b/include/linux/mfd/tc6387xb.h deleted file mode 100644 index aacf1dcc86b9..000000000000 --- a/include/linux/mfd/tc6387xb.h +++ /dev/null @@ -1,19 +0,0 @@ -/* - * This file contains the definitions for the TC6387XB - * - * (C) Copyright 2005 Ian Molton - * - * May be copied or modified under the terms of the GNU General Public - * License. See linux/COPYING for more information. - * - */ -#ifndef MFD_TC6387XB_H -#define MFD_TC6387XB_H - -struct tc6387xb_platform_data { - int (*enable)(struct platform_device *dev); - int (*suspend)(struct platform_device *dev); - int (*resume)(struct platform_device *dev); -}; - -#endif diff --git a/include/linux/mfd/tc6393xb.h b/include/linux/mfd/tc6393xb.h deleted file mode 100644 index d17807f2d0c9..000000000000 --- a/include/linux/mfd/tc6393xb.h +++ /dev/null @@ -1,53 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Toshiba TC6393XB SoC support - * - * Copyright(c) 2005-2006 Chris Humbert - * Copyright(c) 2005 Dirk Opfer - * Copyright(c) 2005 Ian Molton - * Copyright(c) 2007 Dmitry Baryshkov - * - * Based on code written by Sharp/Lineo for 2.4 kernels - * Based on locomo.c - */ - -#ifndef MFD_TC6393XB_H -#define MFD_TC6393XB_H - -#include - -/* Also one should provide the CK3P6MI clock */ -struct tc6393xb_platform_data { - u16 scr_pll2cr; /* PLL2 Control */ - u16 scr_gper; /* GP Enable */ - - int (*enable)(struct platform_device *dev); - void (*disable)(struct platform_device *dev); - int (*suspend)(struct platform_device *dev); - int (*resume)(struct platform_device *dev); - - int irq_base; /* base for subdevice irqs */ - - struct tmio_nand_data *nand_data; - struct tmio_fb_data *fb_data; - - unsigned resume_restore : 1; /* make special actions - to preserve the state - on suspend/resume */ -}; - -extern int tc6393xb_lcd_mode(struct platform_device *fb, - const struct fb_videomode *mode); -extern int tc6393xb_lcd_set_power(struct platform_device *fb, bool on); - -/* - * Relative to irq_base - */ -#define IRQ_TC6393_NAND 0 -#define IRQ_TC6393_MMC 1 -#define IRQ_TC6393_OHCI 2 -#define IRQ_TC6393_FB 4 - -#define TC6393XB_NR_IRQS 8 - -#endif diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h index e8bf90281ba0..eace8ea6cda0 100644 --- a/include/linux/mfd/tmio.h +++ b/include/linux/mfd/tmio.h @@ -84,11 +84,6 @@ /* Some controllers have a CBSY bit */ #define TMIO_MMC_HAVE_CBSY BIT(11) -int tmio_core_mmc_enable(void __iomem *cnf, int shift, unsigned long base); -int tmio_core_mmc_resume(void __iomem *cnf, int shift, unsigned long base); -void tmio_core_mmc_pwr(void __iomem *cnf, int shift, int state); -void tmio_core_mmc_clk_div(void __iomem *cnf, int shift, int state); - struct dma_chan; /* -- cgit v1.2.3 From 8a15b4daed3d45c9162f23d393a06df2a7be4778 Mon Sep 17 00:00:00 2001 From: Andreas Kemnade Date: Fri, 27 Jan 2023 17:58:28 +0100 Subject: mfd: ntxec: Add version number for EC in Tolino Vision The EC firmware has a different version number than anything defined until now. Signed-off-by: Andreas Kemnade Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230127165828.3256170-1-andreas@kemnade.info --- drivers/mfd/ntxec.c | 1 + include/linux/mfd/ntxec.h | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/mfd/ntxec.c b/drivers/mfd/ntxec.c index e16a7a82a929..b02785b10d48 100644 --- a/drivers/mfd/ntxec.c +++ b/drivers/mfd/ntxec.c @@ -175,6 +175,7 @@ static int ntxec_probe(struct i2c_client *client) /* Bail out if we encounter an unknown firmware version */ switch (version) { case NTXEC_VERSION_KOBO_AURA: + case NTXEC_VERSION_TOLINO_VISION: subdevs = ntxec_subdev; n_subdevs = ARRAY_SIZE(ntxec_subdev); break; diff --git a/include/linux/mfd/ntxec.h b/include/linux/mfd/ntxec.h index cc6f07bfa2b3..e5880c346da9 100644 --- a/include/linux/mfd/ntxec.h +++ b/include/linux/mfd/ntxec.h @@ -34,5 +34,5 @@ static inline u16 ntxec_reg8(u8 value) /* Known firmware versions */ #define NTXEC_VERSION_KOBO_AURA 0xd726 /* found in Kobo Aura */ #define NTXEC_VERSION_TOLINO_SHINE2 0xf110 /* found in Tolino Shine 2 HD */ - +#define NTXEC_VERSION_TOLINO_VISION 0xe135 /* found in Tolino Vision, contains RTC, ADC, PWM, home pad */ #endif -- cgit v1.2.3 From c1855dd0a62b7ead360eb9231fb65c2108efaf47 Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Wed, 22 Feb 2023 06:31:10 -0800 Subject: clk: qcom: Revert sync_state based clk_disable_unused Revert the postponement of clk_disable_unused() for clock providers that implement sync_state, and the change to drivers implementing this, until agreement on the implementation has been reached. This reverts: 29e31415e14e ("clk: qcom: Remove need for clk_ignore_unused on sc8280xp") 99c0f7d35c4b ("clk: qcom: sdm845: Use generic clk_sync_state_disable_unused callback") 26b36df75166 ("clk: Add generic sync_state callback for disabling unused clocks") Requested-by: Stephen Boyd Signed-off-by: Bjorn Andersson --- drivers/clk/clk.c | 57 ++++++++------------------------------ drivers/clk/qcom/camcc-sdm845.c | 1 - drivers/clk/qcom/dispcc-sc8280xp.c | 1 - drivers/clk/qcom/dispcc-sdm845.c | 1 - drivers/clk/qcom/gcc-sc8280xp.c | 1 - drivers/clk/qcom/gcc-sdm845.c | 1 - drivers/clk/qcom/gpucc-sdm845.c | 1 - include/linux/clk-provider.h | 1 - 8 files changed, 11 insertions(+), 53 deletions(-) (limited to 'include/linux') diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index ac7182903d88..e62552a75f08 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -1302,26 +1302,14 @@ static void clk_core_disable_unprepare(struct clk_core *core) clk_core_unprepare_lock(core); } -static void clk_unprepare_unused_subtree(struct clk_core *core, - struct device *dev) +static void __init clk_unprepare_unused_subtree(struct clk_core *core) { - bool from_sync_state = !!dev; struct clk_core *child; lockdep_assert_held(&prepare_lock); hlist_for_each_entry(child, &core->children, child_node) - clk_unprepare_unused_subtree(child, dev); - - if (from_sync_state && core->dev != dev) - return; - - /* - * clock will be unprepared on sync_state, - * so leave as is for now - */ - if (!from_sync_state && dev_has_sync_state(core->dev)) - return; + clk_unprepare_unused_subtree(child); if (core->prepare_count) return; @@ -1344,27 +1332,15 @@ static void clk_unprepare_unused_subtree(struct clk_core *core, clk_pm_runtime_put(core); } -static void clk_disable_unused_subtree(struct clk_core *core, - struct device *dev) +static void __init clk_disable_unused_subtree(struct clk_core *core) { - bool from_sync_state = !!dev; struct clk_core *child; unsigned long flags; lockdep_assert_held(&prepare_lock); hlist_for_each_entry(child, &core->children, child_node) - clk_disable_unused_subtree(child, dev); - - if (from_sync_state && core->dev != dev) - return; - - /* - * clock will be disabled on sync_state, - * so leave as is for now - */ - if (!from_sync_state && dev_has_sync_state(core->dev)) - return; + clk_disable_unused_subtree(child); if (core->flags & CLK_OPS_PARENT_ENABLE) clk_core_prepare_enable(core->parent); @@ -1402,7 +1378,7 @@ unprepare_out: clk_core_disable_unprepare(core->parent); } -static bool clk_ignore_unused; +static bool clk_ignore_unused __initdata; static int __init clk_ignore_unused_setup(char *__unused) { clk_ignore_unused = true; @@ -1410,46 +1386,35 @@ static int __init clk_ignore_unused_setup(char *__unused) } __setup("clk_ignore_unused", clk_ignore_unused_setup); -static void __clk_disable_unused(struct device *dev) +static int __init clk_disable_unused(void) { struct clk_core *core; if (clk_ignore_unused) { pr_warn("clk: Not disabling unused clocks\n"); - return; + return 0; } clk_prepare_lock(); hlist_for_each_entry(core, &clk_root_list, child_node) - clk_disable_unused_subtree(core, dev); + clk_disable_unused_subtree(core); hlist_for_each_entry(core, &clk_orphan_list, child_node) - clk_disable_unused_subtree(core, dev); + clk_disable_unused_subtree(core); hlist_for_each_entry(core, &clk_root_list, child_node) - clk_unprepare_unused_subtree(core, dev); + clk_unprepare_unused_subtree(core); hlist_for_each_entry(core, &clk_orphan_list, child_node) - clk_unprepare_unused_subtree(core, dev); + clk_unprepare_unused_subtree(core); clk_prepare_unlock(); -} - -static int __init clk_disable_unused(void) -{ - __clk_disable_unused(NULL); return 0; } late_initcall_sync(clk_disable_unused); -void clk_sync_state_disable_unused(struct device *dev) -{ - __clk_disable_unused(dev); -} -EXPORT_SYMBOL_GPL(clk_sync_state_disable_unused); - static int clk_core_determine_round_nolock(struct clk_core *core, struct clk_rate_request *req) { diff --git a/drivers/clk/qcom/camcc-sdm845.c b/drivers/clk/qcom/camcc-sdm845.c index e5aeb832e47b..27d44188a7ab 100644 --- a/drivers/clk/qcom/camcc-sdm845.c +++ b/drivers/clk/qcom/camcc-sdm845.c @@ -1743,7 +1743,6 @@ static struct platform_driver cam_cc_sdm845_driver = { .driver = { .name = "sdm845-camcc", .of_match_table = cam_cc_sdm845_match_table, - .sync_state = clk_sync_state_disable_unused, }, }; diff --git a/drivers/clk/qcom/dispcc-sc8280xp.c b/drivers/clk/qcom/dispcc-sc8280xp.c index c84a6481b879..167470beb369 100644 --- a/drivers/clk/qcom/dispcc-sc8280xp.c +++ b/drivers/clk/qcom/dispcc-sc8280xp.c @@ -3199,7 +3199,6 @@ static struct platform_driver disp_cc_sc8280xp_driver = { .driver = { .name = "disp_cc-sc8280xp", .of_match_table = disp_cc_sc8280xp_match_table, - .sync_state = clk_sync_state_disable_unused, }, }; diff --git a/drivers/clk/qcom/dispcc-sdm845.c b/drivers/clk/qcom/dispcc-sdm845.c index 1810d58bad09..735adfefc379 100644 --- a/drivers/clk/qcom/dispcc-sdm845.c +++ b/drivers/clk/qcom/dispcc-sdm845.c @@ -869,7 +869,6 @@ static struct platform_driver disp_cc_sdm845_driver = { .driver = { .name = "disp_cc-sdm845", .of_match_table = disp_cc_sdm845_match_table, - .sync_state = clk_sync_state_disable_unused, }, }; diff --git a/drivers/clk/qcom/gcc-sc8280xp.c b/drivers/clk/qcom/gcc-sc8280xp.c index f4fdc5b9663c..b3198784e1c3 100644 --- a/drivers/clk/qcom/gcc-sc8280xp.c +++ b/drivers/clk/qcom/gcc-sc8280xp.c @@ -7441,7 +7441,6 @@ static struct platform_driver gcc_sc8280xp_driver = { .driver = { .name = "gcc-sc8280xp", .of_match_table = gcc_sc8280xp_match_table, - .sync_state = clk_sync_state_disable_unused, }, }; diff --git a/drivers/clk/qcom/gcc-sdm845.c b/drivers/clk/qcom/gcc-sdm845.c index 0ff05af515c4..6af08e0ca847 100644 --- a/drivers/clk/qcom/gcc-sdm845.c +++ b/drivers/clk/qcom/gcc-sdm845.c @@ -4020,7 +4020,6 @@ static struct platform_driver gcc_sdm845_driver = { .driver = { .name = "gcc-sdm845", .of_match_table = gcc_sdm845_match_table, - .sync_state = clk_sync_state_disable_unused, }, }; diff --git a/drivers/clk/qcom/gpucc-sdm845.c b/drivers/clk/qcom/gpucc-sdm845.c index d48ad19e832d..970d7414bdf0 100644 --- a/drivers/clk/qcom/gpucc-sdm845.c +++ b/drivers/clk/qcom/gpucc-sdm845.c @@ -200,7 +200,6 @@ static struct platform_driver gpu_cc_sdm845_driver = { .driver = { .name = "sdm845-gpucc", .of_match_table = gpu_cc_sdm845_match_table, - .sync_state = clk_sync_state_disable_unused, }, }; diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index cf1adfeaf257..842e72a5348f 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -720,7 +720,6 @@ struct clk *clk_register_divider_table(struct device *dev, const char *name, void __iomem *reg, u8 shift, u8 width, u8 clk_divider_flags, const struct clk_div_table *table, spinlock_t *lock); -void clk_sync_state_disable_unused(struct device *dev); /** * clk_register_divider - register a divider clock with the clock framework * @dev: device registering this clock -- cgit v1.2.3 From 8d664282a03fec09682f10252d3c785c2513691d Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 17 Feb 2023 08:27:23 -0700 Subject: io_uring: rename 'in_idle' to 'in_cancel' This better describes what it does - it's incremented when the task is currently undergoing a cancelation operation, due to exiting or exec'ing. Signed-off-by: Jens Axboe --- include/linux/io_uring_types.h | 2 +- io_uring/io_uring.c | 18 +++++++++--------- io_uring/tctx.c | 2 +- 3 files changed, 11 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 0efe4d784358..00689c12f6ab 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -58,7 +58,7 @@ struct io_uring_task { struct xarray xa; struct wait_queue_head wait; - atomic_t in_idle; + atomic_t in_cancel; atomic_t inflight_tracked; struct percpu_counter inflight; diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index cbe06deb84ff..64e07df034d1 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -719,7 +719,7 @@ static void io_put_task_remote(struct task_struct *task, int nr) struct io_uring_task *tctx = task->io_uring; percpu_counter_sub(&tctx->inflight, nr); - if (unlikely(atomic_read(&tctx->in_idle))) + if (unlikely(atomic_read(&tctx->in_cancel))) wake_up(&tctx->wait); put_task_struct_many(task, nr); } @@ -1258,8 +1258,8 @@ void tctx_task_work(struct callback_head *cb) ctx_flush_and_put(ctx, &uring_locked); - /* relaxed read is enough as only the task itself sets ->in_idle */ - if (unlikely(atomic_read(&tctx->in_idle))) + /* relaxed read is enough as only the task itself sets ->in_cancel */ + if (unlikely(atomic_read(&tctx->in_cancel))) io_uring_drop_tctx_refs(current); trace_io_uring_task_work_run(tctx, count, loops); @@ -1291,7 +1291,7 @@ static void io_req_local_work_add(struct io_kiocb *req) /* needed for the following wake up */ smp_mb__after_atomic(); - if (unlikely(atomic_read(&req->task->io_uring->in_idle))) { + if (unlikely(atomic_read(&req->task->io_uring->in_cancel))) { io_move_task_work_from_local(ctx); goto put_ref; } @@ -2937,12 +2937,12 @@ static __cold void io_tctx_exit_cb(struct callback_head *cb) work = container_of(cb, struct io_tctx_exit, task_work); /* - * When @in_idle, we're in cancellation and it's racy to remove the + * When @in_cancel, we're in cancellation and it's racy to remove the * node. It'll be removed by the end of cancellation, just ignore it. * tctx can be NULL if the queueing of this task_work raced with * work cancelation off the exec path. */ - if (tctx && !atomic_read(&tctx->in_idle)) + if (tctx && !atomic_read(&tctx->in_cancel)) io_uring_del_tctx_node((unsigned long)work->ctx); complete(&work->completion); } @@ -3210,7 +3210,7 @@ __cold void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd) if (tctx->io_wq) io_wq_exit_start(tctx->io_wq); - atomic_inc(&tctx->in_idle); + atomic_inc(&tctx->in_cancel); do { bool loop = false; @@ -3261,9 +3261,9 @@ __cold void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd) if (cancel_all) { /* * We shouldn't run task_works after cancel, so just leave - * ->in_idle set for normal exit. + * ->in_cancel set for normal exit. */ - atomic_dec(&tctx->in_idle); + atomic_dec(&tctx->in_cancel); /* for exec all current's requests should be gone, kill tctx */ __io_uring_free(current); } diff --git a/io_uring/tctx.c b/io_uring/tctx.c index 4324b1cf1f6a..3a8d1dd97e1b 100644 --- a/io_uring/tctx.c +++ b/io_uring/tctx.c @@ -83,7 +83,7 @@ __cold int io_uring_alloc_task_context(struct task_struct *task, xa_init(&tctx->xa); init_waitqueue_head(&tctx->wait); - atomic_set(&tctx->in_idle, 0); + atomic_set(&tctx->in_cancel, 0); atomic_set(&tctx->inflight_tracked, 0); task->io_uring = tctx; init_llist_head(&tctx->task_list); -- cgit v1.2.3 From 16f8a08643b6d63d2e8252ddaa9e17e2408a2531 Mon Sep 17 00:00:00 2001 From: Serge Semin Date: Fri, 13 Jan 2023 20:14:05 +0300 Subject: dmaengine: dw-edma: Add mem-mapped LL-entries support Currently the DW eDMA driver only supports the linked lists memory allocated locally with respect to the remote eDMA engine setup. It means the linked lists will be accessible by the CPU via the MMIO space only. If eDMA is embedded into the DW PCIe Root Ports or local Endpoints (which support will be added in subsequent commits) the linked lists are supposed to be allocated in the CPU memory. In that case the LL-entries can be directly accessed, while the former case implies using the MMIO accessors for that. In order to have both cases supported by the driver, the dw_edma_region descriptor should be fixed to contain the MMIO-backed and just memory-based virtual addresses. The linked lists initialization procedure will use one of them depending on the eDMA device nature. If the eDMA engine is embedded into the local DW PCIe Root Port/Endpoint controllers, the list entries will be directly accessed by referencing the corresponding structure fields. Otherwise the MMIO accessors usage will be preserved. Link: https://lore.kernel.org/r/20230113171409.30470-24-Sergey.Semin@baikalelectronics.ru Signed-off-by: Serge Semin Signed-off-by: Lorenzo Pieralisi Signed-off-by: Bjorn Helgaas Acked-by: Vinod Koul --- drivers/dma/dw-edma/dw-edma-pcie.c | 32 ++++++++-------- drivers/dma/dw-edma/dw-edma-v0-core.c | 69 ++++++++++++++++++++++------------- include/linux/dma/edma.h | 5 ++- 3 files changed, 64 insertions(+), 42 deletions(-) (limited to 'include/linux') diff --git a/drivers/dma/dw-edma/dw-edma-pcie.c b/drivers/dma/dw-edma/dw-edma-pcie.c index 3f9dadc73854..2b40f2b44f5e 100644 --- a/drivers/dma/dw-edma/dw-edma-pcie.c +++ b/drivers/dma/dw-edma/dw-edma-pcie.c @@ -240,20 +240,20 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev, struct dw_edma_block *ll_block = &vsec_data.ll_wr[i]; struct dw_edma_block *dt_block = &vsec_data.dt_wr[i]; - ll_region->vaddr = pcim_iomap_table(pdev)[ll_block->bar]; - if (!ll_region->vaddr) + ll_region->vaddr.io = pcim_iomap_table(pdev)[ll_block->bar]; + if (!ll_region->vaddr.io) return -ENOMEM; - ll_region->vaddr += ll_block->off; + ll_region->vaddr.io += ll_block->off; ll_region->paddr = pci_bus_address(pdev, ll_block->bar); ll_region->paddr += ll_block->off; ll_region->sz = ll_block->sz; - dt_region->vaddr = pcim_iomap_table(pdev)[dt_block->bar]; - if (!dt_region->vaddr) + dt_region->vaddr.io = pcim_iomap_table(pdev)[dt_block->bar]; + if (!dt_region->vaddr.io) return -ENOMEM; - dt_region->vaddr += dt_block->off; + dt_region->vaddr.io += dt_block->off; dt_region->paddr = pci_bus_address(pdev, dt_block->bar); dt_region->paddr += dt_block->off; dt_region->sz = dt_block->sz; @@ -265,20 +265,20 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev, struct dw_edma_block *ll_block = &vsec_data.ll_rd[i]; struct dw_edma_block *dt_block = &vsec_data.dt_rd[i]; - ll_region->vaddr = pcim_iomap_table(pdev)[ll_block->bar]; - if (!ll_region->vaddr) + ll_region->vaddr.io = pcim_iomap_table(pdev)[ll_block->bar]; + if (!ll_region->vaddr.io) return -ENOMEM; - ll_region->vaddr += ll_block->off; + ll_region->vaddr.io += ll_block->off; ll_region->paddr = pci_bus_address(pdev, ll_block->bar); ll_region->paddr += ll_block->off; ll_region->sz = ll_block->sz; - dt_region->vaddr = pcim_iomap_table(pdev)[dt_block->bar]; - if (!dt_region->vaddr) + dt_region->vaddr.io = pcim_iomap_table(pdev)[dt_block->bar]; + if (!dt_region->vaddr.io) return -ENOMEM; - dt_region->vaddr += dt_block->off; + dt_region->vaddr.io += dt_block->off; dt_region->paddr = pci_bus_address(pdev, dt_block->bar); dt_region->paddr += dt_block->off; dt_region->sz = dt_block->sz; @@ -303,24 +303,24 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev, pci_dbg(pdev, "L. List:\tWRITE CH%.2u, BAR=%u, off=0x%.8lx, sz=0x%zx bytes, addr(v=%p, p=%pa)\n", i, vsec_data.ll_wr[i].bar, vsec_data.ll_wr[i].off, chip->ll_region_wr[i].sz, - chip->ll_region_wr[i].vaddr, &chip->ll_region_wr[i].paddr); + chip->ll_region_wr[i].vaddr.io, &chip->ll_region_wr[i].paddr); pci_dbg(pdev, "Data:\tWRITE CH%.2u, BAR=%u, off=0x%.8lx, sz=0x%zx bytes, addr(v=%p, p=%pa)\n", i, vsec_data.dt_wr[i].bar, vsec_data.dt_wr[i].off, chip->dt_region_wr[i].sz, - chip->dt_region_wr[i].vaddr, &chip->dt_region_wr[i].paddr); + chip->dt_region_wr[i].vaddr.io, &chip->dt_region_wr[i].paddr); } for (i = 0; i < chip->ll_rd_cnt; i++) { pci_dbg(pdev, "L. List:\tREAD CH%.2u, BAR=%u, off=0x%.8lx, sz=0x%zx bytes, addr(v=%p, p=%pa)\n", i, vsec_data.ll_rd[i].bar, vsec_data.ll_rd[i].off, chip->ll_region_rd[i].sz, - chip->ll_region_rd[i].vaddr, &chip->ll_region_rd[i].paddr); + chip->ll_region_rd[i].vaddr.io, &chip->ll_region_rd[i].paddr); pci_dbg(pdev, "Data:\tREAD CH%.2u, BAR=%u, off=0x%.8lx, sz=0x%zx bytes, addr(v=%p, p=%pa)\n", i, vsec_data.dt_rd[i].bar, vsec_data.dt_rd[i].off, chip->dt_region_rd[i].sz, - chip->dt_region_rd[i].vaddr, &chip->dt_region_rd[i].paddr); + chip->dt_region_rd[i].vaddr.io, &chip->dt_region_rd[i].paddr); } pci_dbg(pdev, "Nr. IRQs:\t%u\n", chip->nr_irqs); diff --git a/drivers/dma/dw-edma/dw-edma-v0-core.c b/drivers/dma/dw-edma/dw-edma-v0-core.c index 6bcc57512258..72e79a0c0a4e 100644 --- a/drivers/dma/dw-edma/dw-edma-v0-core.c +++ b/drivers/dma/dw-edma/dw-edma-v0-core.c @@ -159,9 +159,6 @@ static inline u32 readl_ch(struct dw_edma *dw, enum dw_edma_dir dir, u16 ch, #define GET_CH_32(dw, dir, ch, name) \ readl_ch(dw, dir, ch, &(__dw_ch_regs(dw, dir, ch)->name)) -#define SET_LL_32(ll, value) \ - writel(value, ll) - static inline void writeq_ch(struct dw_edma *dw, enum dw_edma_dir dir, u16 ch, u64 value, void __iomem *addr) { @@ -218,9 +215,6 @@ static inline u64 readq_ch(struct dw_edma *dw, enum dw_edma_dir dir, u16 ch, #define GET_CH_64(dw, dir, ch, name) \ readq_ch(dw, dir, ch, &(__dw_ch_regs(dw, dir, ch)->name)) -#define SET_LL_64(ll, value) \ - writeq(value, ll) - /* eDMA management callbacks */ void dw_edma_v0_core_off(struct dw_edma *dw) { @@ -292,17 +286,53 @@ u32 dw_edma_v0_core_status_abort_int(struct dw_edma *dw, enum dw_edma_dir dir) GET_RW_32(dw, dir, int_status)); } +static void dw_edma_v0_write_ll_data(struct dw_edma_chunk *chunk, int i, + u32 control, u32 size, u64 sar, u64 dar) +{ + ptrdiff_t ofs = i * sizeof(struct dw_edma_v0_lli); + + if (chunk->chan->dw->chip->flags & DW_EDMA_CHIP_LOCAL) { + struct dw_edma_v0_lli *lli = chunk->ll_region.vaddr.mem + ofs; + + lli->control = control; + lli->transfer_size = size; + lli->sar.reg = sar; + lli->dar.reg = dar; + } else { + struct dw_edma_v0_lli __iomem *lli = chunk->ll_region.vaddr.io + ofs; + + writel(control, &lli->control); + writel(size, &lli->transfer_size); + writeq(sar, &lli->sar.reg); + writeq(dar, &lli->dar.reg); + } +} + +static void dw_edma_v0_write_ll_link(struct dw_edma_chunk *chunk, + int i, u32 control, u64 pointer) +{ + ptrdiff_t ofs = i * sizeof(struct dw_edma_v0_lli); + + if (chunk->chan->dw->chip->flags & DW_EDMA_CHIP_LOCAL) { + struct dw_edma_v0_llp *llp = chunk->ll_region.vaddr.mem + ofs; + + llp->control = control; + llp->llp.reg = pointer; + } else { + struct dw_edma_v0_llp __iomem *llp = chunk->ll_region.vaddr.io + ofs; + + writel(control, &llp->control); + writeq(pointer, &llp->llp.reg); + } +} + static void dw_edma_v0_core_write_chunk(struct dw_edma_chunk *chunk) { struct dw_edma_burst *child; struct dw_edma_chan *chan = chunk->chan; - struct dw_edma_v0_lli __iomem *lli; - struct dw_edma_v0_llp __iomem *llp; u32 control = 0, i = 0; int j; - lli = chunk->ll_region.vaddr; - if (chunk->cb) control = DW_EDMA_V0_CB; @@ -314,27 +344,16 @@ static void dw_edma_v0_core_write_chunk(struct dw_edma_chunk *chunk) if (!(chan->dw->chip->flags & DW_EDMA_CHIP_LOCAL)) control |= DW_EDMA_V0_RIE; } - /* Channel control */ - SET_LL_32(&lli[i].control, control); - /* Transfer size */ - SET_LL_32(&lli[i].transfer_size, child->sz); - /* SAR */ - SET_LL_64(&lli[i].sar.reg, child->sar); - /* DAR */ - SET_LL_64(&lli[i].dar.reg, child->dar); - - i++; + + dw_edma_v0_write_ll_data(chunk, i++, control, child->sz, + child->sar, child->dar); } - llp = (void __iomem *)&lli[i]; control = DW_EDMA_V0_LLP | DW_EDMA_V0_TCB; if (!chunk->cb) control |= DW_EDMA_V0_CB; - /* Channel control */ - SET_LL_32(&llp->control, control); - /* Linked list */ - SET_LL_64(&llp->llp.reg, chunk->ll_region.paddr); + dw_edma_v0_write_ll_link(chunk, i, control, chunk->ll_region.paddr); } void dw_edma_v0_core_start(struct dw_edma_chunk *chunk, bool first) diff --git a/include/linux/dma/edma.h b/include/linux/dma/edma.h index 96bfd0173f3a..3b80040b95cc 100644 --- a/include/linux/dma/edma.h +++ b/include/linux/dma/edma.h @@ -19,7 +19,10 @@ struct dw_edma; struct dw_edma_region { u64 paddr; - void __iomem *vaddr; + union { + void *mem; + void __iomem *io; + } vaddr; size_t sz; }; -- cgit v1.2.3 From 3bc0f149405e07c7e59985a24ce96db83973f8d7 Mon Sep 17 00:00:00 2001 From: Serge Semin Date: Fri, 13 Jan 2023 20:14:06 +0300 Subject: dmaengine: dw-edma: Prepare dw_edma_probe() for builtin callers When CONFIG_DW_EDMA=m, dw_edma_probe() is built as a module. Previously edma.h declared it as extern, but the implementation isn't available for builtin callers. A subsequent commit will add calls from dw_pcie_host_init() and dw_pcie_ep_init(), which can only be built-in. Make it safe for such builtin callers to call dw_edma_probe() by using IS_REACHABLE() to define a stub when CONFIG_DW_EDMA=m. When CONFIG_DW_EDMA=m, these builtin callers will fail to detect and register eDMA devices, so eDMA won't be usable even if the dw-edma module is loaded. [bhelgaas: split to separate patch, commit log] Link: https://lore.kernel.org/r/20230113171409.30470-25-Sergey.Semin@baikalelectronics.ru Signed-off-by: Serge Semin Signed-off-by: Lorenzo Pieralisi Signed-off-by: Bjorn Helgaas Acked-by: Vinod Koul --- include/linux/dma/edma.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dma/edma.h b/include/linux/dma/edma.h index 3b80040b95cc..d2638d9259dc 100644 --- a/include/linux/dma/edma.h +++ b/include/linux/dma/edma.h @@ -101,7 +101,7 @@ struct dw_edma_chip { }; /* Export to the platform drivers */ -#if IS_ENABLED(CONFIG_DW_EDMA) +#if IS_REACHABLE(CONFIG_DW_EDMA) int dw_edma_probe(struct dw_edma_chip *chip); int dw_edma_remove(struct dw_edma_chip *chip); #else -- cgit v1.2.3 From b6478b8c93304fa0483e4657779b44634a1711c7 Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Wed, 22 Feb 2023 06:50:41 +0100 Subject: net: phy: c45: add genphy_c45_an_config_eee_aneg() function Add new genphy_c45_an_config_eee_aneg() function and replace some of genphy_c45_write_eee_adv() calls. This will be needed by the next patch. Signed-off-by: Oleksij Rempel Reviewed-by: Russell King (Oracle) Signed-off-by: Paolo Abeni --- drivers/net/phy/phy-c45.c | 11 ++++++++++- drivers/net/phy/phy_device.c | 2 +- include/linux/phy.h | 1 + 3 files changed, 12 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/phy/phy-c45.c b/drivers/net/phy/phy-c45.c index f23cce2c5199..784868e818a7 100644 --- a/drivers/net/phy/phy-c45.c +++ b/drivers/net/phy/phy-c45.c @@ -262,7 +262,7 @@ int genphy_c45_an_config_aneg(struct phy_device *phydev) linkmode_and(phydev->advertising, phydev->advertising, phydev->supported); - ret = genphy_c45_write_eee_adv(phydev, phydev->supported_eee); + ret = genphy_c45_an_config_eee_aneg(phydev); if (ret < 0) return ret; else if (ret) @@ -858,6 +858,15 @@ int genphy_c45_read_eee_abilities(struct phy_device *phydev) } EXPORT_SYMBOL_GPL(genphy_c45_read_eee_abilities); +/** + * genphy_c45_an_config_eee_aneg - configure EEE advertisement + * @phydev: target phy_device struct + */ +int genphy_c45_an_config_eee_aneg(struct phy_device *phydev) +{ + return genphy_c45_write_eee_adv(phydev, phydev->supported_eee); +} + /** * genphy_c45_pma_read_abilities - read supported link modes from PMA * @phydev: target phy_device struct diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 71becceb8764..570a5803f9c2 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -2231,7 +2231,7 @@ int __genphy_config_aneg(struct phy_device *phydev, bool changed) { int err; - err = genphy_c45_write_eee_adv(phydev, phydev->supported_eee); + err = genphy_c45_an_config_eee_aneg(phydev); if (err < 0) return err; else if (err) diff --git a/include/linux/phy.h b/include/linux/phy.h index 727bff531a14..19d83e112beb 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1765,6 +1765,7 @@ int genphy_c45_ethtool_get_eee(struct phy_device *phydev, int genphy_c45_ethtool_set_eee(struct phy_device *phydev, struct ethtool_eee *data); int genphy_c45_write_eee_adv(struct phy_device *phydev, unsigned long *adv); +int genphy_c45_an_config_eee_aneg(struct phy_device *phydev); /* Generic C45 PHY driver */ extern struct phy_driver genphy_c45_driver; -- cgit v1.2.3 From 3eeca4e199cee2066c65b872391cecee5cbbbb81 Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Wed, 22 Feb 2023 06:50:42 +0100 Subject: net: phy: do not force EEE support With following patches: commit 9b01c885be36 ("net: phy: c22: migrate to genphy_c45_write_eee_adv()") commit 5827b168125d ("net: phy: c45: migrate to genphy_c45_write_eee_adv()") we set the advertisement to potentially supported values. This behavior may introduce new regressions on systems where EEE was disabled by default (BIOS or boot loader configuration or by other ways.) At same time, with this patches, we would overwrite EEE advertisement configuration made over ethtool. To avoid this issues, we need to cache initial and ethtool advertisement configuration and store it for later use. Fixes: 9b01c885be36 ("net: phy: c22: migrate to genphy_c45_write_eee_adv()") Fixes: 5827b168125d ("net: phy: c45: migrate to genphy_c45_write_eee_adv()") Fixes: 022c3f87f88e ("net: phy: add genphy_c45_ethtool_get/set_eee() support") Signed-off-by: Oleksij Rempel Reviewed-by: Russell King (Oracle) Signed-off-by: Paolo Abeni --- drivers/net/phy/phy-c45.c | 24 +++++++++++++++++------- drivers/net/phy/phy_device.c | 19 +++++++++++++++++++ include/linux/phy.h | 5 +++++ 3 files changed, 41 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/phy/phy-c45.c b/drivers/net/phy/phy-c45.c index 784868e818a7..8717c122e2f3 100644 --- a/drivers/net/phy/phy-c45.c +++ b/drivers/net/phy/phy-c45.c @@ -721,8 +721,7 @@ int genphy_c45_write_eee_adv(struct phy_device *phydev, unsigned long *adv) * @phydev: target phy_device struct * @adv: the linkmode advertisement status */ -static int genphy_c45_read_eee_adv(struct phy_device *phydev, - unsigned long *adv) +int genphy_c45_read_eee_adv(struct phy_device *phydev, unsigned long *adv) { int val; @@ -864,7 +863,13 @@ EXPORT_SYMBOL_GPL(genphy_c45_read_eee_abilities); */ int genphy_c45_an_config_eee_aneg(struct phy_device *phydev) { - return genphy_c45_write_eee_adv(phydev, phydev->supported_eee); + if (!phydev->eee_enabled) { + __ETHTOOL_DECLARE_LINK_MODE_MASK(adv) = {}; + + return genphy_c45_write_eee_adv(phydev, adv); + } + + return genphy_c45_write_eee_adv(phydev, phydev->advertising_eee); } /** @@ -1430,17 +1435,22 @@ EXPORT_SYMBOL(genphy_c45_ethtool_get_eee); int genphy_c45_ethtool_set_eee(struct phy_device *phydev, struct ethtool_eee *data) { - __ETHTOOL_DECLARE_LINK_MODE_MASK(adv) = {}; int ret; if (data->eee_enabled) { if (data->advertised) - adv[0] = data->advertised; + ethtool_convert_legacy_u32_to_link_mode(phydev->advertising_eee, + data->advertised); else - linkmode_copy(adv, phydev->supported_eee); + linkmode_copy(phydev->advertising_eee, + phydev->supported_eee); + + phydev->eee_enabled = true; + } else { + phydev->eee_enabled = false; } - ret = genphy_c45_write_eee_adv(phydev, adv); + ret = genphy_c45_an_config_eee_aneg(phydev); if (ret < 0) return ret; if (ret > 0) diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 570a5803f9c2..3f8a64fb9d71 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -3141,6 +3141,25 @@ static int phy_probe(struct device *dev) of_set_phy_supported(phydev); phy_advertise_supported(phydev); + /* Get PHY default EEE advertising modes and handle them as potentially + * safe initial configuration. + */ + err = genphy_c45_read_eee_adv(phydev, phydev->advertising_eee); + if (err) + return err; + + /* There is no "enabled" flag. If PHY is advertising, assume it is + * kind of enabled. + */ + phydev->eee_enabled = !linkmode_empty(phydev->advertising_eee); + + /* Some PHYs may advertise, by default, not support EEE modes. So, + * we need to clean them. + */ + if (phydev->eee_enabled) + linkmode_and(phydev->advertising_eee, phydev->supported_eee, + phydev->advertising_eee); + /* Get the EEE modes we want to prohibit. We will ask * the PHY stop advertising these mode later on */ diff --git a/include/linux/phy.h b/include/linux/phy.h index 19d83e112beb..36bf0bbc8efa 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -575,6 +575,8 @@ struct macsec_ops; * @advertising: Currently advertised linkmodes * @adv_old: Saved advertised while power saving for WoL * @supported_eee: supported PHY EEE linkmodes + * @advertising_eee: Currently advertised EEE linkmodes + * @eee_enabled: Flag indicating whether the EEE feature is enabled * @lp_advertising: Current link partner advertised linkmodes * @host_interfaces: PHY interface modes supported by host * @eee_broken_modes: Energy efficient ethernet modes which should be prohibited @@ -681,6 +683,8 @@ struct phy_device { __ETHTOOL_DECLARE_LINK_MODE_MASK(adv_old); /* used for eee validation */ __ETHTOOL_DECLARE_LINK_MODE_MASK(supported_eee); + __ETHTOOL_DECLARE_LINK_MODE_MASK(advertising_eee); + bool eee_enabled; /* Host supported PHY interface types. Should be ignored if empty. */ DECLARE_PHY_INTERFACE_MASK(host_interfaces); @@ -1766,6 +1770,7 @@ int genphy_c45_ethtool_set_eee(struct phy_device *phydev, struct ethtool_eee *data); int genphy_c45_write_eee_adv(struct phy_device *phydev, unsigned long *adv); int genphy_c45_an_config_eee_aneg(struct phy_device *phydev); +int genphy_c45_read_eee_adv(struct phy_device *phydev, unsigned long *adv); /* Generic C45 PHY driver */ extern struct phy_driver genphy_c45_driver; -- cgit v1.2.3 From 0322ef49c1ac6f0e2ef37b146c0bf8440873072c Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 24 Feb 2023 17:52:33 +0200 Subject: net: dsa: seville: ignore mscc-miim read errors from Lynx PCS During the refactoring in the commit below, vsc9953_mdio_read() was replaced with mscc_miim_read(), which has one extra step: it checks for the MSCC_MIIM_DATA_ERROR bits before returning the result. On T1040RDB, there are 8 QSGMII PCSes belonging to the switch, and they are organized in 2 groups. First group responds to MDIO addresses 4-7 because QSGMIIACR1[MDEV_PORT] is 1, and the second group responds to MDIO addresses 8-11 because QSGMIIBCR1[MDEV_PORT] is 2. I have double checked that these values are correctly set in the SERDES, as well as PCCR1[QSGMA_CFG] and PCCR1[QSGMB_CFG] are both 0b01. mscc_miim_read: phyad 8 reg 0x1 MIIM_DATA 0x2d mscc_miim_read: phyad 8 reg 0x5 MIIM_DATA 0x5801 mscc_miim_read: phyad 8 reg 0x1 MIIM_DATA 0x2d mscc_miim_read: phyad 8 reg 0x5 MIIM_DATA 0x5801 mscc_miim_read: phyad 9 reg 0x1 MIIM_DATA 0x2d mscc_miim_read: phyad 9 reg 0x5 MIIM_DATA 0x5801 mscc_miim_read: phyad 9 reg 0x1 MIIM_DATA 0x2d mscc_miim_read: phyad 9 reg 0x5 MIIM_DATA 0x5801 mscc_miim_read: phyad 10 reg 0x1 MIIM_DATA 0x2d mscc_miim_read: phyad 10 reg 0x5 MIIM_DATA 0x5801 mscc_miim_read: phyad 10 reg 0x1 MIIM_DATA 0x2d mscc_miim_read: phyad 10 reg 0x5 MIIM_DATA 0x5801 mscc_miim_read: phyad 11 reg 0x1 MIIM_DATA 0x2d mscc_miim_read: phyad 11 reg 0x5 MIIM_DATA 0x5801 mscc_miim_read: phyad 11 reg 0x1 MIIM_DATA 0x2d mscc_miim_read: phyad 11 reg 0x5 MIIM_DATA 0x5801 mscc_miim_read: phyad 4 reg 0x1 MIIM_DATA 0x3002d, ERROR mscc_miim_read: phyad 4 reg 0x5 MIIM_DATA 0x3da01, ERROR mscc_miim_read: phyad 5 reg 0x1 MIIM_DATA 0x3002d, ERROR mscc_miim_read: phyad 5 reg 0x5 MIIM_DATA 0x35801, ERROR mscc_miim_read: phyad 5 reg 0x1 MIIM_DATA 0x3002d, ERROR mscc_miim_read: phyad 5 reg 0x5 MIIM_DATA 0x35801, ERROR mscc_miim_read: phyad 6 reg 0x1 MIIM_DATA 0x3002d, ERROR mscc_miim_read: phyad 6 reg 0x5 MIIM_DATA 0x35801, ERROR mscc_miim_read: phyad 6 reg 0x1 MIIM_DATA 0x3002d, ERROR mscc_miim_read: phyad 6 reg 0x5 MIIM_DATA 0x35801, ERROR mscc_miim_read: phyad 7 reg 0x1 MIIM_DATA 0x3002d, ERROR mscc_miim_read: phyad 7 reg 0x5 MIIM_DATA 0x35801, ERROR mscc_miim_read: phyad 7 reg 0x1 MIIM_DATA 0x3002d, ERROR mscc_miim_read: phyad 7 reg 0x5 MIIM_DATA 0x35801, ERROR As can be seen, the data in MIIM_DATA is still valid despite having the MSCC_MIIM_DATA_ERROR bits set. The driver as introduced in commit 84705fc16552 ("net: dsa: felix: introduce support for Seville VSC9953 switch") was ignoring these bits, perhaps deliberately (although unbeknownst to me). This is an old IP and the hardware team cannot seem to be able to help me track down a plausible reason for these failures. I'll keep investigating, but in the meantime, this is a direct regression which must be restored to a working state. The only thing I can do is keep ignoring the errors as before. Fixes: b99658452355 ("net: dsa: ocelot: felix: utilize shared mscc-miim driver for indirect MDIO access") Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/dsa/ocelot/seville_vsc9953.c | 4 ++-- drivers/net/mdio/mdio-mscc-miim.c | 9 ++++++--- include/linux/mdio/mdio-mscc-miim.h | 2 +- 3 files changed, 9 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/dsa/ocelot/seville_vsc9953.c b/drivers/net/dsa/ocelot/seville_vsc9953.c index 287b64b788db..563ad338da25 100644 --- a/drivers/net/dsa/ocelot/seville_vsc9953.c +++ b/drivers/net/dsa/ocelot/seville_vsc9953.c @@ -893,8 +893,8 @@ static int vsc9953_mdio_bus_alloc(struct ocelot *ocelot) rc = mscc_miim_setup(dev, &bus, "VSC9953 internal MDIO bus", ocelot->targets[GCB], - ocelot->map[GCB][GCB_MIIM_MII_STATUS & REG_MASK]); - + ocelot->map[GCB][GCB_MIIM_MII_STATUS & REG_MASK], + true); if (rc) { dev_err(dev, "failed to setup MDIO bus\n"); return rc; diff --git a/drivers/net/mdio/mdio-mscc-miim.c b/drivers/net/mdio/mdio-mscc-miim.c index c87e991d1a17..1a1b95ae95fa 100644 --- a/drivers/net/mdio/mdio-mscc-miim.c +++ b/drivers/net/mdio/mdio-mscc-miim.c @@ -52,6 +52,7 @@ struct mscc_miim_info { struct mscc_miim_dev { struct regmap *regs; int mii_status_offset; + bool ignore_read_errors; struct regmap *phy_regs; const struct mscc_miim_info *info; struct clk *clk; @@ -135,7 +136,7 @@ static int mscc_miim_read(struct mii_bus *bus, int mii_id, int regnum) goto out; } - if (val & MSCC_MIIM_DATA_ERROR) { + if (!miim->ignore_read_errors && !!(val & MSCC_MIIM_DATA_ERROR)) { ret = -EIO; goto out; } @@ -212,7 +213,8 @@ static const struct regmap_config mscc_miim_phy_regmap_config = { }; int mscc_miim_setup(struct device *dev, struct mii_bus **pbus, const char *name, - struct regmap *mii_regmap, int status_offset) + struct regmap *mii_regmap, int status_offset, + bool ignore_read_errors) { struct mscc_miim_dev *miim; struct mii_bus *bus; @@ -234,6 +236,7 @@ int mscc_miim_setup(struct device *dev, struct mii_bus **pbus, const char *name, miim->regs = mii_regmap; miim->mii_status_offset = status_offset; + miim->ignore_read_errors = ignore_read_errors; *pbus = bus; @@ -285,7 +288,7 @@ static int mscc_miim_probe(struct platform_device *pdev) return dev_err_probe(dev, PTR_ERR(phy_regmap), "Unable to create phy register regmap\n"); - ret = mscc_miim_setup(dev, &bus, "mscc_miim", mii_regmap, 0); + ret = mscc_miim_setup(dev, &bus, "mscc_miim", mii_regmap, 0, false); if (ret < 0) { dev_err(dev, "Unable to setup the MDIO bus\n"); return ret; diff --git a/include/linux/mdio/mdio-mscc-miim.h b/include/linux/mdio/mdio-mscc-miim.h index 5b4ed2c3cbb9..1ce699740af6 100644 --- a/include/linux/mdio/mdio-mscc-miim.h +++ b/include/linux/mdio/mdio-mscc-miim.h @@ -14,6 +14,6 @@ int mscc_miim_setup(struct device *device, struct mii_bus **bus, const char *name, struct regmap *mii_regmap, - int status_offset); + int status_offset, bool ignore_read_errors); #endif -- cgit v1.2.3 From 250870824c1cf199b032b1ef889c8e8d69d9123a Mon Sep 17 00:00:00 2001 From: Michael Karcher Date: Tue, 24 Jan 2023 22:48:16 +0100 Subject: sh: intc: Avoid spurious sizeof-pointer-div warning GCC warns about the pattern sizeof(void*)/sizeof(void), as it looks like the abuse of a pattern to calculate the array size. This pattern appears in the unevaluated part of the ternary operator in _INTC_ARRAY if the parameter is NULL. The replacement uses an alternate approach to return 0 in case of NULL which does not generate the pattern sizeof(void*)/sizeof(void), but still emits the warning if _INTC_ARRAY is called with a nonarray parameter. This patch is required for successful compilation with -Werror enabled. The idea to use _Generic for type distinction is taken from Comment #7 in https://gcc.gnu.org/bugzilla/show_bug.cgi?id=108483 by Jakub Jelinek Signed-off-by: Michael Karcher Acked-by: Randy Dunlap # build-tested Link: https://lore.kernel.org/r/619fa552-c988-35e5-b1d7-fe256c46a272@mkarcher.dialup.fu-berlin.de Signed-off-by: John Paul Adrian Glaubitz --- include/linux/sh_intc.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sh_intc.h b/include/linux/sh_intc.h index c255273b0281..37ad81058d6a 100644 --- a/include/linux/sh_intc.h +++ b/include/linux/sh_intc.h @@ -97,7 +97,10 @@ struct intc_hw_desc { unsigned int nr_subgroups; }; -#define _INTC_ARRAY(a) a, __same_type(a, NULL) ? 0 : sizeof(a)/sizeof(*a) +#define _INTC_SIZEOF_OR_ZERO(a) (_Generic(a, \ + typeof(NULL): 0, \ + default: sizeof(a))) +#define _INTC_ARRAY(a) a, _INTC_SIZEOF_OR_ZERO(a)/sizeof(*a) #define INTC_HW_DESC(vectors, groups, mask_regs, \ prio_regs, sense_regs, ack_regs) \ -- cgit v1.2.3 From a4eecbae092759537748360299de03e434c9a956 Mon Sep 17 00:00:00 2001 From: Mateusz Guzik Date: Wed, 25 Jan 2023 16:55:56 +0100 Subject: capability: add cap_isidentical Signed-off-by: Mateusz Guzik Reviewed-by: Serge Hallyn Cc: Al Viro Signed-off-by: Linus Torvalds --- include/linux/capability.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/capability.h b/include/linux/capability.h index 03c2a613ad40..d3c6c2d1ff45 100644 --- a/include/linux/capability.h +++ b/include/linux/capability.h @@ -157,6 +157,16 @@ static inline bool cap_isclear(const kernel_cap_t a) return true; } +static inline bool cap_isidentical(const kernel_cap_t a, const kernel_cap_t b) +{ + unsigned __capi; + CAP_FOR_EACH_U32(__capi) { + if (a.cap[__capi] != b.cap[__capi]) + return false; + } + return true; +} + /* * Check if "a" is a subset of "set". * return true if ALL of the capabilities in "a" are also in "set" -- cgit v1.2.3 From 6da6b1d4a7df8c35770186b53ef65d388398e139 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Tue, 21 Feb 2023 17:59:05 +0900 Subject: mm/hwpoison: convert TTU_IGNORE_HWPOISON to TTU_HWPOISON After a memory error happens on a clean folio, a process unexpectedly receives SIGBUS when it accesses the error page. This SIGBUS killing is pointless and simply degrades the level of RAS of the system, because the clean folio can be dropped without any data lost on memory error handling as we do for a clean pagecache. When memory_failure() is called on a clean folio, try_to_unmap() is called twice (one from split_huge_page() and one from hwpoison_user_mappings()). The root cause of the issue is that pte conversion to hwpoisoned entry is now done in the first call of try_to_unmap() because PageHWPoison is already set at this point, while it's actually expected to be done in the second call. This behavior disturbs the error handling operation like removing pagecache, which results in the malfunction described above. So convert TTU_IGNORE_HWPOISON into TTU_HWPOISON and set TTU_HWPOISON only when we really intend to convert pte to hwpoison entry. This can prevent other callers of try_to_unmap() from accidentally converting to hwpoison entries. Link: https://lkml.kernel.org/r/20230221085905.1465385-1-naoya.horiguchi@linux.dev Fixes: a42634a6c07d ("readahead: Use a folio in read_pages()") Signed-off-by: Naoya Horiguchi Cc: David Hildenbrand Cc: Hugh Dickins Cc: Matthew Wilcox Cc: Miaohe Lin Cc: Minchan Kim Cc: Vlastimil Babka Cc: Signed-off-by: Andrew Morton --- include/linux/rmap.h | 2 +- mm/memory-failure.c | 8 ++++---- mm/rmap.c | 2 +- 3 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index a4570da03e58..b87d01660412 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -94,7 +94,7 @@ enum ttu_flags { TTU_SPLIT_HUGE_PMD = 0x4, /* split huge PMD if any */ TTU_IGNORE_MLOCK = 0x8, /* ignore mlock */ TTU_SYNC = 0x10, /* avoid racy checks with PVMW_SYNC */ - TTU_IGNORE_HWPOISON = 0x20, /* corrupted page is recoverable */ + TTU_HWPOISON = 0x20, /* do convert pte to hwpoison entry */ TTU_BATCH_FLUSH = 0x40, /* Batch TLB flushes where possible * and caller guarantees they will * do a final flush if necessary */ diff --git a/mm/memory-failure.c b/mm/memory-failure.c index a1ede7bdce95..fae9baf3be16 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1069,7 +1069,7 @@ static int me_pagecache_dirty(struct page_state *ps, struct page *p) * cache and swap cache(ie. page is freshly swapped in). So it could be * referenced concurrently by 2 types of PTEs: * normal PTEs and swap PTEs. We try to handle them consistently by calling - * try_to_unmap(TTU_IGNORE_HWPOISON) to convert the normal PTEs to swap PTEs, + * try_to_unmap(!TTU_HWPOISON) to convert the normal PTEs to swap PTEs, * and then * - clear dirty bit to prevent IO * - remove from LRU @@ -1486,7 +1486,7 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn, int flags, struct page *hpage) { struct folio *folio = page_folio(hpage); - enum ttu_flags ttu = TTU_IGNORE_MLOCK | TTU_SYNC; + enum ttu_flags ttu = TTU_IGNORE_MLOCK | TTU_SYNC | TTU_HWPOISON; struct address_space *mapping; LIST_HEAD(tokill); bool unmap_success; @@ -1516,7 +1516,7 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn, if (PageSwapCache(p)) { pr_err("%#lx: keeping poisoned page in swap cache\n", pfn); - ttu |= TTU_IGNORE_HWPOISON; + ttu &= ~TTU_HWPOISON; } /* @@ -1531,7 +1531,7 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn, if (page_mkclean(hpage)) { SetPageDirty(hpage); } else { - ttu |= TTU_IGNORE_HWPOISON; + ttu &= ~TTU_HWPOISON; pr_info("%#lx: corrupted page was clean: dropped without side effects\n", pfn); } diff --git a/mm/rmap.c b/mm/rmap.c index 15ae24585fc4..8632e02661ac 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1602,7 +1602,7 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, /* Update high watermark before we lower rss */ update_hiwater_rss(mm); - if (PageHWPoison(subpage) && !(flags & TTU_IGNORE_HWPOISON)) { + if (PageHWPoison(subpage) && (flags & TTU_HWPOISON)) { pteval = swp_entry_to_pte(make_hwpoison_entry(subpage)); if (folio_test_hugetlb(folio)) { hugetlb_count_sub(folio_nr_pages(folio), mm); -- cgit v1.2.3 From f122a08b197d076ccf136c73fae0146875812a88 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 28 Feb 2023 11:39:09 -0800 Subject: capability: just use a 'u64' instead of a 'u32[2]' array Back in 2008 we extended the capability bits from 32 to 64, and we did it by extending the single 32-bit capability word from one word to an array of two words. It was then obfuscated by hiding the "2" behind two macro expansions, with the reasoning being that maybe it gets extended further some day. That reasoning may have been valid at the time, but the last thing we want to do is to extend the capability set any more. And the array of values not only causes source code oddities (with loops to deal with it), but also results in worse code generation. It's a lose-lose situation. So just change the 'u32[2]' into a 'u64' and be done with it. We still have to deal with the fact that the user space interface is designed around an array of these 32-bit values, but that was the case before too, since the array layouts were different (ie user space doesn't use an array of 32-bit values for individual capability masks, but an array of 32-bit slices of multiple masks). So that marshalling of data is actually simplified too, even if it does remain somewhat obscure and odd. This was all triggered by my reaction to the new "cap_isidentical()" introduced recently. By just using a saner data structure, it went from unsigned __capi; CAP_FOR_EACH_U32(__capi) { if (a.cap[__capi] != b.cap[__capi]) return false; } return true; to just being return a.val == b.val; instead. Which is rather more obvious both to humans and to compilers. Cc: Mateusz Guzik Cc: Casey Schaufler Cc: Serge Hallyn Cc: Al Viro Cc: Paul Moore Signed-off-by: Linus Torvalds --- fs/proc/array.c | 7 +- include/linux/capability.h | 131 +++++---------------- io_uring/fdinfo.c | 4 +- kernel/auditsc.c | 6 +- kernel/capability.c | 104 +++++++--------- kernel/umh.c | 41 +++---- security/apparmor/policy_unpack.c | 40 +++++-- security/commoncap.c | 49 ++++---- .../selftests/bpf/progs/test_deny_namespace.c | 7 +- 9 files changed, 150 insertions(+), 239 deletions(-) (limited to 'include/linux') diff --git a/fs/proc/array.c b/fs/proc/array.c index 49283b8103c7..9b0315d34c58 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -300,13 +300,8 @@ static inline void task_sig(struct seq_file *m, struct task_struct *p) static void render_cap_t(struct seq_file *m, const char *header, kernel_cap_t *a) { - unsigned __capi; - seq_puts(m, header); - CAP_FOR_EACH_U32(__capi) { - seq_put_hex_ll(m, NULL, - a->cap[CAP_LAST_U32 - __capi], 8); - } + seq_put_hex_ll(m, NULL, a->val, 16); seq_putc(m, '\n'); } diff --git a/include/linux/capability.h b/include/linux/capability.h index d3c6c2d1ff45..0c356a517991 100644 --- a/include/linux/capability.h +++ b/include/linux/capability.h @@ -15,28 +15,25 @@ #include #include +#include #define _KERNEL_CAPABILITY_VERSION _LINUX_CAPABILITY_VERSION_3 -#define _KERNEL_CAPABILITY_U32S _LINUX_CAPABILITY_U32S_3 extern int file_caps_enabled; -typedef struct kernel_cap_struct { - __u32 cap[_KERNEL_CAPABILITY_U32S]; -} kernel_cap_t; +typedef struct { u64 val; } kernel_cap_t; /* same as vfs_ns_cap_data but in cpu endian and always filled completely */ struct cpu_vfs_cap_data { __u32 magic_etc; + kuid_t rootid; kernel_cap_t permitted; kernel_cap_t inheritable; - kuid_t rootid; }; #define _USER_CAP_HEADER_SIZE (sizeof(struct __user_cap_header_struct)) #define _KERNEL_CAP_T_SIZE (sizeof(kernel_cap_t)) - struct file; struct inode; struct dentry; @@ -44,16 +41,6 @@ struct task_struct; struct user_namespace; struct mnt_idmap; -extern const kernel_cap_t __cap_empty_set; -extern const kernel_cap_t __cap_init_eff_set; - -/* - * Internal kernel functions only - */ - -#define CAP_FOR_EACH_U32(__capi) \ - for (__capi = 0; __capi < _KERNEL_CAPABILITY_U32S; ++__capi) - /* * CAP_FS_MASK and CAP_NFSD_MASKS: * @@ -67,104 +54,52 @@ extern const kernel_cap_t __cap_init_eff_set; * 2. The security.* and trusted.* xattrs are fs-related MAC permissions */ -# define CAP_FS_MASK_B0 (CAP_TO_MASK(CAP_CHOWN) \ - | CAP_TO_MASK(CAP_MKNOD) \ - | CAP_TO_MASK(CAP_DAC_OVERRIDE) \ - | CAP_TO_MASK(CAP_DAC_READ_SEARCH) \ - | CAP_TO_MASK(CAP_FOWNER) \ - | CAP_TO_MASK(CAP_FSETID)) - -# define CAP_FS_MASK_B1 (CAP_TO_MASK(CAP_MAC_OVERRIDE)) - -#if _KERNEL_CAPABILITY_U32S != 2 -# error Fix up hand-coded capability macro initializers -#else /* HAND-CODED capability initializers */ +# define CAP_FS_MASK (BIT_ULL(CAP_CHOWN) \ + | BIT_ULL(CAP_MKNOD) \ + | BIT_ULL(CAP_DAC_OVERRIDE) \ + | BIT_ULL(CAP_DAC_READ_SEARCH) \ + | BIT_ULL(CAP_FOWNER) \ + | BIT_ULL(CAP_FSETID) \ + | BIT_ULL(CAP_MAC_OVERRIDE)) +#define CAP_VALID_MASK (BIT_ULL(CAP_LAST_CAP+1)-1) -#define CAP_LAST_U32 ((_KERNEL_CAPABILITY_U32S) - 1) -#define CAP_LAST_U32_VALID_MASK (CAP_TO_MASK(CAP_LAST_CAP + 1) -1) +# define CAP_EMPTY_SET ((kernel_cap_t) { 0 }) +# define CAP_FULL_SET ((kernel_cap_t) { CAP_VALID_MASK }) +# define CAP_FS_SET ((kernel_cap_t) { CAP_FS_MASK | BIT_ULL(CAP_LINUX_IMMUTABLE) }) +# define CAP_NFSD_SET ((kernel_cap_t) { CAP_FS_MASK | BIT_ULL(CAP_SYS_RESOURCE) }) -# define CAP_EMPTY_SET ((kernel_cap_t){{ 0, 0 }}) -# define CAP_FULL_SET ((kernel_cap_t){{ ~0, CAP_LAST_U32_VALID_MASK }}) -# define CAP_FS_SET ((kernel_cap_t){{ CAP_FS_MASK_B0 \ - | CAP_TO_MASK(CAP_LINUX_IMMUTABLE), \ - CAP_FS_MASK_B1 } }) -# define CAP_NFSD_SET ((kernel_cap_t){{ CAP_FS_MASK_B0 \ - | CAP_TO_MASK(CAP_SYS_RESOURCE), \ - CAP_FS_MASK_B1 } }) +# define cap_clear(c) do { (c).val = 0; } while (0) -#endif /* _KERNEL_CAPABILITY_U32S != 2 */ - -# define cap_clear(c) do { (c) = __cap_empty_set; } while (0) - -#define cap_raise(c, flag) ((c).cap[CAP_TO_INDEX(flag)] |= CAP_TO_MASK(flag)) -#define cap_lower(c, flag) ((c).cap[CAP_TO_INDEX(flag)] &= ~CAP_TO_MASK(flag)) -#define cap_raised(c, flag) ((c).cap[CAP_TO_INDEX(flag)] & CAP_TO_MASK(flag)) - -#define CAP_BOP_ALL(c, a, b, OP) \ -do { \ - unsigned __capi; \ - CAP_FOR_EACH_U32(__capi) { \ - c.cap[__capi] = a.cap[__capi] OP b.cap[__capi]; \ - } \ -} while (0) - -#define CAP_UOP_ALL(c, a, OP) \ -do { \ - unsigned __capi; \ - CAP_FOR_EACH_U32(__capi) { \ - c.cap[__capi] = OP a.cap[__capi]; \ - } \ -} while (0) +#define cap_raise(c, flag) ((c).val |= BIT_ULL(flag)) +#define cap_lower(c, flag) ((c).val &= ~BIT_ULL(flag)) +#define cap_raised(c, flag) (((c).val & BIT_ULL(flag)) != 0) static inline kernel_cap_t cap_combine(const kernel_cap_t a, const kernel_cap_t b) { - kernel_cap_t dest; - CAP_BOP_ALL(dest, a, b, |); - return dest; + return (kernel_cap_t) { a.val | b.val }; } static inline kernel_cap_t cap_intersect(const kernel_cap_t a, const kernel_cap_t b) { - kernel_cap_t dest; - CAP_BOP_ALL(dest, a, b, &); - return dest; + return (kernel_cap_t) { a.val & b.val }; } static inline kernel_cap_t cap_drop(const kernel_cap_t a, const kernel_cap_t drop) { - kernel_cap_t dest; - CAP_BOP_ALL(dest, a, drop, &~); - return dest; -} - -static inline kernel_cap_t cap_invert(const kernel_cap_t c) -{ - kernel_cap_t dest; - CAP_UOP_ALL(dest, c, ~); - return dest; + return (kernel_cap_t) { a.val &~ drop.val }; } static inline bool cap_isclear(const kernel_cap_t a) { - unsigned __capi; - CAP_FOR_EACH_U32(__capi) { - if (a.cap[__capi] != 0) - return false; - } - return true; + return !a.val; } static inline bool cap_isidentical(const kernel_cap_t a, const kernel_cap_t b) { - unsigned __capi; - CAP_FOR_EACH_U32(__capi) { - if (a.cap[__capi] != b.cap[__capi]) - return false; - } - return true; + return a.val == b.val; } /* @@ -176,39 +111,31 @@ static inline bool cap_isidentical(const kernel_cap_t a, const kernel_cap_t b) */ static inline bool cap_issubset(const kernel_cap_t a, const kernel_cap_t set) { - kernel_cap_t dest; - dest = cap_drop(a, set); - return cap_isclear(dest); + return !(a.val & ~set.val); } /* Used to decide between falling back on the old suser() or fsuser(). */ static inline kernel_cap_t cap_drop_fs_set(const kernel_cap_t a) { - const kernel_cap_t __cap_fs_set = CAP_FS_SET; - return cap_drop(a, __cap_fs_set); + return cap_drop(a, CAP_FS_SET); } static inline kernel_cap_t cap_raise_fs_set(const kernel_cap_t a, const kernel_cap_t permitted) { - const kernel_cap_t __cap_fs_set = CAP_FS_SET; - return cap_combine(a, - cap_intersect(permitted, __cap_fs_set)); + return cap_combine(a, cap_intersect(permitted, CAP_FS_SET)); } static inline kernel_cap_t cap_drop_nfsd_set(const kernel_cap_t a) { - const kernel_cap_t __cap_fs_set = CAP_NFSD_SET; - return cap_drop(a, __cap_fs_set); + return cap_drop(a, CAP_NFSD_SET); } static inline kernel_cap_t cap_raise_nfsd_set(const kernel_cap_t a, const kernel_cap_t permitted) { - const kernel_cap_t __cap_nfsd_set = CAP_NFSD_SET; - return cap_combine(a, - cap_intersect(permitted, __cap_nfsd_set)); + return cap_combine(a, cap_intersect(permitted, CAP_NFSD_SET)); } #ifdef CONFIG_MULTIUSER diff --git a/io_uring/fdinfo.c b/io_uring/fdinfo.c index 882bd56b01ed..76c279b13aee 100644 --- a/io_uring/fdinfo.c +++ b/io_uring/fdinfo.c @@ -22,7 +22,6 @@ static __cold int io_uring_show_cred(struct seq_file *m, unsigned int id, struct user_namespace *uns = seq_user_ns(m); struct group_info *gi; kernel_cap_t cap; - unsigned __capi; int g; seq_printf(m, "%5d\n", id); @@ -42,8 +41,7 @@ static __cold int io_uring_show_cred(struct seq_file *m, unsigned int id, } seq_puts(m, "\n\tCapEff:\t"); cap = cred->cap_effective; - CAP_FOR_EACH_U32(__capi) - seq_put_hex_ll(m, NULL, cap.cap[CAP_LAST_U32 - __capi], 8); + seq_put_hex_ll(m, NULL, cap.val, 16); seq_putc(m, '\n'); return 0; } diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 93d0b87f3283..addeed3df15d 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -1295,15 +1295,11 @@ out: static void audit_log_cap(struct audit_buffer *ab, char *prefix, kernel_cap_t *cap) { - int i; - if (cap_isclear(*cap)) { audit_log_format(ab, " %s=0", prefix); return; } - audit_log_format(ab, " %s=", prefix); - CAP_FOR_EACH_U32(i) - audit_log_format(ab, "%08x", cap->cap[CAP_LAST_U32 - i]); + audit_log_format(ab, " %s=%016llx", prefix, cap->val); } static void audit_log_fcaps(struct audit_buffer *ab, struct audit_names *name) diff --git a/kernel/capability.c b/kernel/capability.c index 339a44dfe2f4..3e058f41df32 100644 --- a/kernel/capability.c +++ b/kernel/capability.c @@ -20,13 +20,6 @@ #include #include -/* - * Leveraged for setting/resetting capabilities - */ - -const kernel_cap_t __cap_empty_set = CAP_EMPTY_SET; -EXPORT_SYMBOL(__cap_empty_set); - int file_caps_enabled = 1; static int __init file_caps_disable(char *str) @@ -151,6 +144,7 @@ SYSCALL_DEFINE2(capget, cap_user_header_t, header, cap_user_data_t, dataptr) pid_t pid; unsigned tocopy; kernel_cap_t pE, pI, pP; + struct __user_cap_data_struct kdata[2]; ret = cap_validate_magic(header, &tocopy); if ((dataptr == NULL) || (ret != 0)) @@ -163,42 +157,46 @@ SYSCALL_DEFINE2(capget, cap_user_header_t, header, cap_user_data_t, dataptr) return -EINVAL; ret = cap_get_target_pid(pid, &pE, &pI, &pP); - if (!ret) { - struct __user_cap_data_struct kdata[_KERNEL_CAPABILITY_U32S]; - unsigned i; - - for (i = 0; i < tocopy; i++) { - kdata[i].effective = pE.cap[i]; - kdata[i].permitted = pP.cap[i]; - kdata[i].inheritable = pI.cap[i]; - } - - /* - * Note, in the case, tocopy < _KERNEL_CAPABILITY_U32S, - * we silently drop the upper capabilities here. This - * has the effect of making older libcap - * implementations implicitly drop upper capability - * bits when they perform a: capget/modify/capset - * sequence. - * - * This behavior is considered fail-safe - * behavior. Upgrading the application to a newer - * version of libcap will enable access to the newer - * capabilities. - * - * An alternative would be to return an error here - * (-ERANGE), but that causes legacy applications to - * unexpectedly fail; the capget/modify/capset aborts - * before modification is attempted and the application - * fails. - */ - if (copy_to_user(dataptr, kdata, tocopy - * sizeof(struct __user_cap_data_struct))) { - return -EFAULT; - } - } + if (ret) + return ret; - return ret; + /* + * Annoying legacy format with 64-bit capabilities exposed + * as two sets of 32-bit fields, so we need to split the + * capability values up. + */ + kdata[0].effective = pE.val; kdata[1].effective = pE.val >> 32; + kdata[0].permitted = pP.val; kdata[1].permitted = pP.val >> 32; + kdata[0].inheritable = pI.val; kdata[1].inheritable = pI.val >> 32; + + /* + * Note, in the case, tocopy < _KERNEL_CAPABILITY_U32S, + * we silently drop the upper capabilities here. This + * has the effect of making older libcap + * implementations implicitly drop upper capability + * bits when they perform a: capget/modify/capset + * sequence. + * + * This behavior is considered fail-safe + * behavior. Upgrading the application to a newer + * version of libcap will enable access to the newer + * capabilities. + * + * An alternative would be to return an error here + * (-ERANGE), but that causes legacy applications to + * unexpectedly fail; the capget/modify/capset aborts + * before modification is attempted and the application + * fails. + */ + if (copy_to_user(dataptr, kdata, tocopy * sizeof(kdata[0]))) + return -EFAULT; + + return 0; +} + +static kernel_cap_t mk_kernel_cap(u32 low, u32 high) +{ + return (kernel_cap_t) { (low | ((u64)high << 32)) & CAP_VALID_MASK }; } /** @@ -221,8 +219,8 @@ SYSCALL_DEFINE2(capget, cap_user_header_t, header, cap_user_data_t, dataptr) */ SYSCALL_DEFINE2(capset, cap_user_header_t, header, const cap_user_data_t, data) { - struct __user_cap_data_struct kdata[_KERNEL_CAPABILITY_U32S]; - unsigned i, tocopy, copybytes; + struct __user_cap_data_struct kdata[2] = { { 0, }, }; + unsigned tocopy, copybytes; kernel_cap_t inheritable, permitted, effective; struct cred *new; int ret; @@ -246,21 +244,9 @@ SYSCALL_DEFINE2(capset, cap_user_header_t, header, const cap_user_data_t, data) if (copy_from_user(&kdata, data, copybytes)) return -EFAULT; - for (i = 0; i < tocopy; i++) { - effective.cap[i] = kdata[i].effective; - permitted.cap[i] = kdata[i].permitted; - inheritable.cap[i] = kdata[i].inheritable; - } - while (i < _KERNEL_CAPABILITY_U32S) { - effective.cap[i] = 0; - permitted.cap[i] = 0; - inheritable.cap[i] = 0; - i++; - } - - effective.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK; - permitted.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK; - inheritable.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK; + effective = mk_kernel_cap(kdata[0].effective, kdata[1].effective); + permitted = mk_kernel_cap(kdata[0].permitted, kdata[1].permitted); + inheritable = mk_kernel_cap(kdata[0].inheritable, kdata[1].inheritable); new = prepare_creds(); if (!new) diff --git a/kernel/umh.c b/kernel/umh.c index fbf872c624cb..2a4708277335 100644 --- a/kernel/umh.c +++ b/kernel/umh.c @@ -501,9 +501,9 @@ static int proc_cap_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table t; - unsigned long cap_array[_KERNEL_CAPABILITY_U32S]; - kernel_cap_t new_cap; - int err, i; + unsigned long cap_array[2]; + kernel_cap_t new_cap, *cap; + int err; if (write && (!capable(CAP_SETPCAP) || !capable(CAP_SYS_MODULE))) @@ -514,14 +514,16 @@ static int proc_cap_handler(struct ctl_table *table, int write, * userspace if this is a read. */ spin_lock(&umh_sysctl_lock); - for (i = 0; i < _KERNEL_CAPABILITY_U32S; i++) { - if (table->data == CAP_BSET) - cap_array[i] = usermodehelper_bset.cap[i]; - else if (table->data == CAP_PI) - cap_array[i] = usermodehelper_inheritable.cap[i]; - else - BUG(); - } + if (table->data == CAP_BSET) + cap = &usermodehelper_bset; + else if (table->data == CAP_PI) + cap = &usermodehelper_inheritable; + else + BUG(); + + /* Legacy format: capabilities are exposed as two 32-bit values */ + cap_array[0] = (u32) cap->val; + cap_array[1] = cap->val >> 32; spin_unlock(&umh_sysctl_lock); t = *table; @@ -535,22 +537,15 @@ static int proc_cap_handler(struct ctl_table *table, int write, if (err < 0) return err; - /* - * convert from the sysctl array of ulongs to the kernel_cap_t - * internal representation - */ - for (i = 0; i < _KERNEL_CAPABILITY_U32S; i++) - new_cap.cap[i] = cap_array[i]; + new_cap.val = (u32)cap_array[0]; + new_cap.val += (u64)cap_array[1] << 32; /* * Drop everything not in the new_cap (but don't add things) */ if (write) { spin_lock(&umh_sysctl_lock); - if (table->data == CAP_BSET) - usermodehelper_bset = cap_intersect(usermodehelper_bset, new_cap); - if (table->data == CAP_PI) - usermodehelper_inheritable = cap_intersect(usermodehelper_inheritable, new_cap); + *cap = cap_intersect(*cap, new_cap); spin_unlock(&umh_sysctl_lock); } @@ -561,14 +556,14 @@ struct ctl_table usermodehelper_table[] = { { .procname = "bset", .data = CAP_BSET, - .maxlen = _KERNEL_CAPABILITY_U32S * sizeof(unsigned long), + .maxlen = 2 * sizeof(unsigned long), .mode = 0600, .proc_handler = proc_cap_handler, }, { .procname = "inheritable", .data = CAP_PI, - .maxlen = _KERNEL_CAPABILITY_U32S * sizeof(unsigned long), + .maxlen = 2 * sizeof(unsigned long), .mode = 0600, .proc_handler = proc_cap_handler, }, diff --git a/security/apparmor/policy_unpack.c b/security/apparmor/policy_unpack.c index 5e9949832af6..cf2ceec40b28 100644 --- a/security/apparmor/policy_unpack.c +++ b/security/apparmor/policy_unpack.c @@ -304,6 +304,26 @@ fail: } EXPORT_SYMBOL_IF_KUNIT(aa_unpack_u64); +static bool aa_unpack_cap_low(struct aa_ext *e, kernel_cap_t *data, const char *name) +{ + u32 val; + + if (!aa_unpack_u32(e, &val, name)) + return false; + data->val = val; + return true; +} + +static bool aa_unpack_cap_high(struct aa_ext *e, kernel_cap_t *data, const char *name) +{ + u32 val; + + if (!aa_unpack_u32(e, &val, name)) + return false; + data->val = (u32)data->val | ((u64)val << 32); + return true; +} + VISIBLE_IF_KUNIT bool aa_unpack_array(struct aa_ext *e, const char *name, u16 *size) { void *pos = e->pos; @@ -897,25 +917,25 @@ static struct aa_profile *unpack_profile(struct aa_ext *e, char **ns_name) profile->path_flags = PATH_MEDIATE_DELETED; info = "failed to unpack profile capabilities"; - if (!aa_unpack_u32(e, &(rules->caps.allow.cap[0]), NULL)) + if (!aa_unpack_cap_low(e, &rules->caps.allow, NULL)) goto fail; - if (!aa_unpack_u32(e, &(rules->caps.audit.cap[0]), NULL)) + if (!aa_unpack_cap_low(e, &rules->caps.audit, NULL)) goto fail; - if (!aa_unpack_u32(e, &(rules->caps.quiet.cap[0]), NULL)) + if (!aa_unpack_cap_low(e, &rules->caps.quiet, NULL)) goto fail; - if (!aa_unpack_u32(e, &tmpcap.cap[0], NULL)) + if (!aa_unpack_cap_low(e, &tmpcap, NULL)) goto fail; info = "failed to unpack upper profile capabilities"; if (aa_unpack_nameX(e, AA_STRUCT, "caps64")) { /* optional upper half of 64 bit caps */ - if (!aa_unpack_u32(e, &(rules->caps.allow.cap[1]), NULL)) + if (!aa_unpack_cap_high(e, &rules->caps.allow, NULL)) goto fail; - if (!aa_unpack_u32(e, &(rules->caps.audit.cap[1]), NULL)) + if (!aa_unpack_cap_high(e, &rules->caps.audit, NULL)) goto fail; - if (!aa_unpack_u32(e, &(rules->caps.quiet.cap[1]), NULL)) + if (!aa_unpack_cap_high(e, &rules->caps.quiet, NULL)) goto fail; - if (!aa_unpack_u32(e, &(tmpcap.cap[1]), NULL)) + if (!aa_unpack_cap_high(e, &tmpcap, NULL)) goto fail; if (!aa_unpack_nameX(e, AA_STRUCTEND, NULL)) goto fail; @@ -924,9 +944,9 @@ static struct aa_profile *unpack_profile(struct aa_ext *e, char **ns_name) info = "failed to unpack extended profile capabilities"; if (aa_unpack_nameX(e, AA_STRUCT, "capsx")) { /* optional extended caps mediation mask */ - if (!aa_unpack_u32(e, &(rules->caps.extended.cap[0]), NULL)) + if (!aa_unpack_cap_low(e, &rules->caps.extended, NULL)) goto fail; - if (!aa_unpack_u32(e, &(rules->caps.extended.cap[1]), NULL)) + if (!aa_unpack_cap_high(e, &rules->caps.extended, NULL)) goto fail; if (!aa_unpack_nameX(e, AA_STRUCTEND, NULL)) goto fail; diff --git a/security/commoncap.c b/security/commoncap.c index aec62db55271..5bb7d1e96277 100644 --- a/security/commoncap.c +++ b/security/commoncap.c @@ -589,7 +589,6 @@ static inline int bprm_caps_from_vfs_caps(struct cpu_vfs_cap_data *caps, bool *has_fcap) { struct cred *new = bprm->cred; - unsigned i; int ret = 0; if (caps->magic_etc & VFS_CAP_FLAGS_EFFECTIVE) @@ -598,22 +597,17 @@ static inline int bprm_caps_from_vfs_caps(struct cpu_vfs_cap_data *caps, if (caps->magic_etc & VFS_CAP_REVISION_MASK) *has_fcap = true; - CAP_FOR_EACH_U32(i) { - __u32 permitted = caps->permitted.cap[i]; - __u32 inheritable = caps->inheritable.cap[i]; - - /* - * pP' = (X & fP) | (pI & fI) - * The addition of pA' is handled later. - */ - new->cap_permitted.cap[i] = - (new->cap_bset.cap[i] & permitted) | - (new->cap_inheritable.cap[i] & inheritable); + /* + * pP' = (X & fP) | (pI & fI) + * The addition of pA' is handled later. + */ + new->cap_permitted.val = + (new->cap_bset.val & caps->permitted.val) | + (new->cap_inheritable.val & caps->inheritable.val); - if (permitted & ~new->cap_permitted.cap[i]) - /* insufficient to execute correctly */ - ret = -EPERM; - } + if (caps->permitted.val & ~new->cap_permitted.val) + /* insufficient to execute correctly */ + ret = -EPERM; /* * For legacy apps, with no internal support for recognizing they @@ -644,7 +638,6 @@ int get_vfs_caps_from_disk(struct mnt_idmap *idmap, { struct inode *inode = d_backing_inode(dentry); __u32 magic_etc; - unsigned tocopy, i; int size; struct vfs_ns_cap_data data, *nscaps = &data; struct vfs_cap_data *caps = (struct vfs_cap_data *) &data; @@ -677,17 +670,14 @@ int get_vfs_caps_from_disk(struct mnt_idmap *idmap, case VFS_CAP_REVISION_1: if (size != XATTR_CAPS_SZ_1) return -EINVAL; - tocopy = VFS_CAP_U32_1; break; case VFS_CAP_REVISION_2: if (size != XATTR_CAPS_SZ_2) return -EINVAL; - tocopy = VFS_CAP_U32_2; break; case VFS_CAP_REVISION_3: if (size != XATTR_CAPS_SZ_3) return -EINVAL; - tocopy = VFS_CAP_U32_3; rootkuid = make_kuid(fs_ns, le32_to_cpu(nscaps->rootid)); break; @@ -705,15 +695,20 @@ int get_vfs_caps_from_disk(struct mnt_idmap *idmap, if (!rootid_owns_currentns(rootvfsuid)) return -ENODATA; - CAP_FOR_EACH_U32(i) { - if (i >= tocopy) - break; - cpu_caps->permitted.cap[i] = le32_to_cpu(caps->data[i].permitted); - cpu_caps->inheritable.cap[i] = le32_to_cpu(caps->data[i].inheritable); + cpu_caps->permitted.val = le32_to_cpu(caps->data[0].permitted); + cpu_caps->inheritable.val = le32_to_cpu(caps->data[0].inheritable); + + /* + * Rev1 had just a single 32-bit word, later expanded + * to a second one for the high bits + */ + if ((magic_etc & VFS_CAP_REVISION_MASK) != VFS_CAP_REVISION_1) { + cpu_caps->permitted.val += (u64)le32_to_cpu(caps->data[1].permitted) << 32; + cpu_caps->inheritable.val += (u64)le32_to_cpu(caps->data[1].inheritable) << 32; } - cpu_caps->permitted.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK; - cpu_caps->inheritable.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK; + cpu_caps->permitted.val &= CAP_VALID_MASK; + cpu_caps->inheritable.val &= CAP_VALID_MASK; cpu_caps->rootid = vfsuid_into_kuid(rootvfsuid); diff --git a/tools/testing/selftests/bpf/progs/test_deny_namespace.c b/tools/testing/selftests/bpf/progs/test_deny_namespace.c index 09ad5a4ebd1f..591104e79812 100644 --- a/tools/testing/selftests/bpf/progs/test_deny_namespace.c +++ b/tools/testing/selftests/bpf/progs/test_deny_namespace.c @@ -6,7 +6,7 @@ #include struct kernel_cap_struct { - __u32 cap[_LINUX_CAPABILITY_U32S_3]; + __u64 val; } __attribute__((preserve_access_index)); struct cred { @@ -19,14 +19,13 @@ SEC("lsm.s/userns_create") int BPF_PROG(test_userns_create, const struct cred *cred, int ret) { struct kernel_cap_struct caps = cred->cap_effective; - int cap_index = CAP_TO_INDEX(CAP_SYS_ADMIN); - __u32 cap_mask = CAP_TO_MASK(CAP_SYS_ADMIN); + __u64 cap_mask = BIT_LL(CAP_SYS_ADMIN); if (ret) return 0; ret = -EPERM; - if (caps.cap[cap_index] & cap_mask) + if (caps.val & cap_mask) return 0; return -EPERM; -- cgit v1.2.3 From 0fb7fb713461e44b12e72c292bf90ee300f40710 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 1 Mar 2023 22:07:48 +0100 Subject: genirq/msi, platform-msi: Ensure that MSI descriptors are unreferenced Miquel reported a warning in the MSI core which is triggered when interrupts are freed via platform_msi_device_domain_free(). This code got reworked to use core functions for freeing the MSI descriptors, but nothing took care to clear the msi_desc->irq entry, which then triggers the warning in msi_free_msi_desc() which uses desc->irq to validate that the descriptor has been torn down. The same issue exists in msi_domain_populate_irqs(). Up to the point that msi_free_msi_descs() grew a warning for this case, this went un-noticed. Provide the counterpart of msi_domain_populate_irqs() and invoke it in platform_msi_device_domain_free() before freeing the interrupts and MSI descriptors and also in the error path of msi_domain_populate_irqs(). Fixes: 2f2940d16823 ("genirq/msi: Remove filter from msi_free_descs_free_range()") Reported-by: Miquel Raynal Signed-off-by: Thomas Gleixner Tested-by: Miquel Raynal Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/87mt4wkwnv.ffs@tglx --- drivers/base/platform-msi.c | 1 + include/linux/msi.h | 2 ++ kernel/irq/msi.c | 23 ++++++++++++++++++++++- 3 files changed, 25 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/base/platform-msi.c b/drivers/base/platform-msi.c index 5883e7634a2b..f37ad34c80ec 100644 --- a/drivers/base/platform-msi.c +++ b/drivers/base/platform-msi.c @@ -324,6 +324,7 @@ void platform_msi_device_domain_free(struct irq_domain *domain, unsigned int vir struct platform_msi_priv_data *data = domain->host_data; msi_lock_descs(data->dev); + msi_domain_depopulate_descs(data->dev, virq, nr_irqs); irq_domain_free_irqs_common(domain, virq, nr_irqs); msi_free_msi_descs_range(data->dev, virq, virq + nr_irqs - 1); msi_unlock_descs(data->dev); diff --git a/include/linux/msi.h b/include/linux/msi.h index a112b913fff9..15dd71817996 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -631,6 +631,8 @@ int msi_domain_prepare_irqs(struct irq_domain *domain, struct device *dev, int nvec, msi_alloc_info_t *args); int msi_domain_populate_irqs(struct irq_domain *domain, struct device *dev, int virq, int nvec, msi_alloc_info_t *args); +void msi_domain_depopulate_descs(struct device *dev, int virq, int nvec); + struct irq_domain * __platform_msi_create_device_domain(struct device *dev, unsigned int nvec, diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index efd21b79bf32..d169ee0c1799 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -1109,14 +1109,35 @@ int msi_domain_populate_irqs(struct irq_domain *domain, struct device *dev, return 0; fail: - for (--virq; virq >= virq_base; virq--) + for (--virq; virq >= virq_base; virq--) { + msi_domain_depopulate_descs(dev, virq, 1); irq_domain_free_irqs_common(domain, virq, 1); + } msi_domain_free_descs(dev, &ctrl); unlock: msi_unlock_descs(dev); return ret; } +void msi_domain_depopulate_descs(struct device *dev, int virq_base, int nvec) +{ + struct msi_ctrl ctrl = { + .domid = MSI_DEFAULT_DOMAIN, + .first = virq_base, + .last = virq_base + nvec - 1, + }; + struct msi_desc *desc; + struct xarray *xa; + unsigned long idx; + + if (!msi_ctrl_valid(dev, &ctrl)) + return; + + xa = &dev->msi.data->__domains[ctrl.domid].store; + xa_for_each_range(xa, idx, desc, ctrl.first, ctrl.last) + desc->irq = 0; +} + /* * Carefully check whether the device can use reservation mode. If * reservation mode is enabled then the early activation will assign a -- cgit v1.2.3 From 95207db8166ab95c42a03fdc5e3abd212c9987dc Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 17 Oct 2022 03:23:49 +0900 Subject: Remove Intel compiler support include/linux/compiler-intel.h had no update in the past 3 years. We often forget about the third C compiler to build the kernel. For example, commit a0a12c3ed057 ("asm goto: eradicate CC_HAS_ASM_GOTO") only mentioned GCC and Clang. init/Kconfig defines CC_IS_GCC and CC_IS_CLANG but not CC_IS_ICC, and nobody has reported any issue. I guess the Intel Compiler support is broken, and nobody is caring about it. Harald Arnesen pointed out ICC (classic Intel C/C++ compiler) is deprecated: $ icc -v icc: remark #10441: The Intel(R) C++ Compiler Classic (ICC) is deprecated and will be removed from product release in the second half of 2023. The Intel(R) oneAPI DPC++/C++ Compiler (ICX) is the recommended compiler moving forward. Please transition to use this compiler. Use '-diag-disable=10441' to disable this message. icc version 2021.7.0 (gcc version 12.1.0 compatibility) Arnd Bergmann provided a link to the article, "Intel C/C++ compilers complete adoption of LLVM". lib/zstd/common/compiler.h and lib/zstd/compress/zstd_fast.c were kept untouched for better sync with https://github.com/facebook/zstd Link: https://www.intel.com/content/www/us/en/developer/articles/technical/adoption-of-llvm-complete-icx.html Signed-off-by: Masahiro Yamada Acked-by: Arnd Bergmann Reviewed-by: Nick Desaulniers Reviewed-by: Nathan Chancellor Reviewed-by: Miguel Ojeda Signed-off-by: Linus Torvalds --- arch/ia64/include/uapi/asm/cmpxchg.h | 6 +- arch/ia64/include/uapi/asm/intel_intrin.h | 162 ------------------------------ arch/ia64/include/uapi/asm/intrinsics.h | 6 +- include/acpi/platform/acenv.h | 5 +- include/acpi/platform/acenvex.h | 2 +- include/acpi/platform/acintel.h | 55 ---------- include/linux/compiler-intel.h | 34 ------- include/linux/compiler_attributes.h | 14 +-- include/linux/compiler_types.h | 2 - scripts/cc-version.sh | 2 - scripts/min-tool-version.sh | 4 - 11 files changed, 5 insertions(+), 287 deletions(-) delete mode 100644 arch/ia64/include/uapi/asm/intel_intrin.h delete mode 100644 include/acpi/platform/acintel.h delete mode 100644 include/linux/compiler-intel.h (limited to 'include/linux') diff --git a/arch/ia64/include/uapi/asm/cmpxchg.h b/arch/ia64/include/uapi/asm/cmpxchg.h index ca2e02685343..259ae57570bf 100644 --- a/arch/ia64/include/uapi/asm/cmpxchg.h +++ b/arch/ia64/include/uapi/asm/cmpxchg.h @@ -15,11 +15,7 @@ #include /* include compiler specific intrinsics */ #include -#ifdef __INTEL_COMPILER -# include -#else -# include -#endif +#include /* * This function doesn't exist, so you'll get a linker error if diff --git a/arch/ia64/include/uapi/asm/intel_intrin.h b/arch/ia64/include/uapi/asm/intel_intrin.h deleted file mode 100644 index dc1884dc54b5..000000000000 --- a/arch/ia64/include/uapi/asm/intel_intrin.h +++ /dev/null @@ -1,162 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -#ifndef _ASM_IA64_INTEL_INTRIN_H -#define _ASM_IA64_INTEL_INTRIN_H -/* - * Intel Compiler Intrinsics - * - * Copyright (C) 2002,2003 Jun Nakajima - * Copyright (C) 2002,2003 Suresh Siddha - * Copyright (C) 2005,2006 Hongjiu Lu - * - */ -#include - -#define ia64_barrier() __memory_barrier() - -#define ia64_stop() /* Nothing: As of now stop bit is generated for each - * intrinsic - */ - -#define ia64_getreg __getReg -#define ia64_setreg __setReg - -#define ia64_hint __hint -#define ia64_hint_pause __hint_pause - -#define ia64_mux1_brcst _m64_mux1_brcst -#define ia64_mux1_mix _m64_mux1_mix -#define ia64_mux1_shuf _m64_mux1_shuf -#define ia64_mux1_alt _m64_mux1_alt -#define ia64_mux1_rev _m64_mux1_rev - -#define ia64_mux1(x,v) _m_to_int64(_m64_mux1(_m_from_int64(x), (v))) -#define ia64_popcnt _m64_popcnt -#define ia64_getf_exp __getf_exp -#define ia64_shrp _m64_shrp - -#define ia64_tpa __tpa -#define ia64_invala __invala -#define ia64_invala_gr __invala_gr -#define ia64_invala_fr __invala_fr -#define ia64_nop __nop -#define ia64_sum __sum -#define ia64_ssm __ssm -#define ia64_rum __rum -#define ia64_rsm __rsm -#define ia64_fc __fc - -#define ia64_ldfs __ldfs -#define ia64_ldfd __ldfd -#define ia64_ldfe __ldfe -#define ia64_ldf8 __ldf8 -#define ia64_ldf_fill __ldf_fill - -#define ia64_stfs __stfs -#define ia64_stfd __stfd -#define ia64_stfe __stfe -#define ia64_stf8 __stf8 -#define ia64_stf_spill __stf_spill - -#define ia64_mf __mf -#define ia64_mfa __mfa - -#define ia64_fetchadd4_acq __fetchadd4_acq -#define ia64_fetchadd4_rel __fetchadd4_rel -#define ia64_fetchadd8_acq __fetchadd8_acq -#define ia64_fetchadd8_rel __fetchadd8_rel - -#define ia64_xchg1 _InterlockedExchange8 -#define ia64_xchg2 _InterlockedExchange16 -#define ia64_xchg4 _InterlockedExchange -#define ia64_xchg8 _InterlockedExchange64 - -#define ia64_cmpxchg1_rel _InterlockedCompareExchange8_rel -#define ia64_cmpxchg1_acq _InterlockedCompareExchange8_acq -#define ia64_cmpxchg2_rel _InterlockedCompareExchange16_rel -#define ia64_cmpxchg2_acq _InterlockedCompareExchange16_acq -#define ia64_cmpxchg4_rel _InterlockedCompareExchange_rel -#define ia64_cmpxchg4_acq _InterlockedCompareExchange_acq -#define ia64_cmpxchg8_rel _InterlockedCompareExchange64_rel -#define ia64_cmpxchg8_acq _InterlockedCompareExchange64_acq - -#define __ia64_set_dbr(index, val) \ - __setIndReg(_IA64_REG_INDR_DBR, index, val) -#define ia64_set_ibr(index, val) \ - __setIndReg(_IA64_REG_INDR_IBR, index, val) -#define ia64_set_pkr(index, val) \ - __setIndReg(_IA64_REG_INDR_PKR, index, val) -#define ia64_set_pmc(index, val) \ - __setIndReg(_IA64_REG_INDR_PMC, index, val) -#define ia64_set_pmd(index, val) \ - __setIndReg(_IA64_REG_INDR_PMD, index, val) -#define ia64_set_rr(index, val) \ - __setIndReg(_IA64_REG_INDR_RR, index, val) - -#define ia64_get_cpuid(index) \ - __getIndReg(_IA64_REG_INDR_CPUID, index) -#define __ia64_get_dbr(index) __getIndReg(_IA64_REG_INDR_DBR, index) -#define ia64_get_ibr(index) __getIndReg(_IA64_REG_INDR_IBR, index) -#define ia64_get_pkr(index) __getIndReg(_IA64_REG_INDR_PKR, index) -#define ia64_get_pmc(index) __getIndReg(_IA64_REG_INDR_PMC, index) -#define ia64_get_pmd(index) __getIndReg(_IA64_REG_INDR_PMD, index) -#define ia64_get_rr(index) __getIndReg(_IA64_REG_INDR_RR, index) - -#define ia64_srlz_d __dsrlz -#define ia64_srlz_i __isrlz - -#define ia64_dv_serialize_data() -#define ia64_dv_serialize_instruction() - -#define ia64_st1_rel __st1_rel -#define ia64_st2_rel __st2_rel -#define ia64_st4_rel __st4_rel -#define ia64_st8_rel __st8_rel - -/* FIXME: need st4.rel.nta intrinsic */ -#define ia64_st4_rel_nta __st4_rel - -#define ia64_ld1_acq __ld1_acq -#define ia64_ld2_acq __ld2_acq -#define ia64_ld4_acq __ld4_acq -#define ia64_ld8_acq __ld8_acq - -#define ia64_sync_i __synci -#define ia64_thash __thash -#define ia64_ttag __ttag -#define ia64_itcd __itcd -#define ia64_itci __itci -#define ia64_itrd __itrd -#define ia64_itri __itri -#define ia64_ptce __ptce -#define ia64_ptcl __ptcl -#define ia64_ptcg __ptcg -#define ia64_ptcga __ptcga -#define ia64_ptri __ptri -#define ia64_ptrd __ptrd -#define ia64_dep_mi _m64_dep_mi - -/* Values for lfhint in __lfetch and __lfetch_fault */ - -#define ia64_lfhint_none __lfhint_none -#define ia64_lfhint_nt1 __lfhint_nt1 -#define ia64_lfhint_nt2 __lfhint_nt2 -#define ia64_lfhint_nta __lfhint_nta - -#define ia64_lfetch __lfetch -#define ia64_lfetch_excl __lfetch_excl -#define ia64_lfetch_fault __lfetch_fault -#define ia64_lfetch_fault_excl __lfetch_fault_excl - -#define ia64_intrin_local_irq_restore(x) \ -do { \ - if ((x) != 0) { \ - ia64_ssm(IA64_PSR_I); \ - ia64_srlz_d(); \ - } else { \ - ia64_rsm(IA64_PSR_I); \ - } \ -} while (0) - -#define __builtin_trap() __break(0); - -#endif /* _ASM_IA64_INTEL_INTRIN_H */ diff --git a/arch/ia64/include/uapi/asm/intrinsics.h b/arch/ia64/include/uapi/asm/intrinsics.h index a0e0a064f5b1..63f27c4ec739 100644 --- a/arch/ia64/include/uapi/asm/intrinsics.h +++ b/arch/ia64/include/uapi/asm/intrinsics.h @@ -14,11 +14,7 @@ #include /* include compiler specific intrinsics */ #include -#ifdef __INTEL_COMPILER -# include -#else -# include -#endif +#include #include #define ia64_set_rr0_to_rr4(val0, val1, val2, val3, val4) \ diff --git a/include/acpi/platform/acenv.h b/include/acpi/platform/acenv.h index 03eb3d977075..9e4f7564201a 100644 --- a/include/acpi/platform/acenv.h +++ b/include/acpi/platform/acenv.h @@ -148,15 +148,12 @@ * *****************************************************************************/ -#if defined(__GNUC__) && !defined(__INTEL_COMPILER) +#if defined(__GNUC__) #include #elif defined(_MSC_VER) #include "acmsvc.h" -#elif defined(__INTEL_COMPILER) -#include - #endif #if defined(_LINUX) || defined(__linux__) diff --git a/include/acpi/platform/acenvex.h b/include/acpi/platform/acenvex.h index 3a6b1db9a984..72cc7bab469e 100644 --- a/include/acpi/platform/acenvex.h +++ b/include/acpi/platform/acenvex.h @@ -35,7 +35,7 @@ #endif -#if defined(__GNUC__) && !defined(__INTEL_COMPILER) +#if defined(__GNUC__) #include "acgccex.h" #elif defined(_MSC_VER) diff --git a/include/acpi/platform/acintel.h b/include/acpi/platform/acintel.h deleted file mode 100644 index 85b1ae86ee63..000000000000 --- a/include/acpi/platform/acintel.h +++ /dev/null @@ -1,55 +0,0 @@ -/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */ -/****************************************************************************** - * - * Name: acintel.h - VC specific defines, etc. - * - * Copyright (C) 2000 - 2022, Intel Corp. - * - *****************************************************************************/ - -#ifndef __ACINTEL_H__ -#define __ACINTEL_H__ - -/* - * Use compiler specific is a good practice for even when - * -nostdinc is specified (i.e., ACPI_USE_STANDARD_HEADERS undefined. - */ -#ifndef va_arg -#include -#endif - -/* Configuration specific to Intel 64-bit C compiler */ - -#define COMPILER_DEPENDENT_INT64 __int64 -#define COMPILER_DEPENDENT_UINT64 unsigned __int64 -#define ACPI_INLINE __inline - -/* - * Calling conventions: - * - * ACPI_SYSTEM_XFACE - Interfaces to host OS (handlers, threads) - * ACPI_EXTERNAL_XFACE - External ACPI interfaces - * ACPI_INTERNAL_XFACE - Internal ACPI interfaces - * ACPI_INTERNAL_VAR_XFACE - Internal variable-parameter list interfaces - */ -#define ACPI_SYSTEM_XFACE -#define ACPI_EXTERNAL_XFACE -#define ACPI_INTERNAL_XFACE -#define ACPI_INTERNAL_VAR_XFACE - -/* remark 981 - operands evaluated in no particular order */ -#pragma warning(disable:981) - -/* warn C4100: unreferenced formal parameter */ -#pragma warning(disable:4100) - -/* warn C4127: conditional expression is constant */ -#pragma warning(disable:4127) - -/* warn C4706: assignment within conditional expression */ -#pragma warning(disable:4706) - -/* warn C4214: bit field types other than int */ -#pragma warning(disable:4214) - -#endif /* __ACINTEL_H__ */ diff --git a/include/linux/compiler-intel.h b/include/linux/compiler-intel.h deleted file mode 100644 index b17f3cd18334..000000000000 --- a/include/linux/compiler-intel.h +++ /dev/null @@ -1,34 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __LINUX_COMPILER_TYPES_H -#error "Please don't include directly, include instead." -#endif - -#ifdef __ECC - -/* Compiler specific definitions for Intel ECC compiler */ - -#include - -/* Intel ECC compiler doesn't support gcc specific asm stmts. - * It uses intrinsics to do the equivalent things. - */ - -#define barrier() __memory_barrier() -#define barrier_data(ptr) barrier() - -#define RELOC_HIDE(ptr, off) \ - ({ unsigned long __ptr; \ - __ptr = (unsigned long) (ptr); \ - (typeof(ptr)) (__ptr + (off)); }) - -/* This should act as an optimization barrier on var. - * Given that this compiler does not have inline assembly, a compiler barrier - * is the best we can do. - */ -#define OPTIMIZER_HIDE_VAR(var) barrier() - -#endif - -/* icc has this, but it's called _bswap16 */ -#define __HAVE_BUILTIN_BSWAP16__ -#define __builtin_bswap16 _bswap16 diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index 4a3bd114a24f..e659cb6fded3 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -64,16 +64,10 @@ * compiler should see some alignment anyway, when the return value is * massaged by 'flags = ptr & 3; ptr &= ~3;'). * - * Optional: not supported by icc - * * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-assume_005faligned-function-attribute * clang: https://clang.llvm.org/docs/AttributeReference.html#assume-aligned */ -#if __has_attribute(__assume_aligned__) -# define __assume_aligned(a, ...) __attribute__((__assume_aligned__(a, ## __VA_ARGS__))) -#else -# define __assume_aligned(a, ...) -#endif +#define __assume_aligned(a, ...) __attribute__((__assume_aligned__(a, ## __VA_ARGS__))) /* * Note the long name. @@ -85,7 +79,6 @@ /* * Optional: only supported since gcc >= 9 * Optional: not supported by clang - * Optional: not supported by icc * * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-copy-function-attribute */ @@ -98,7 +91,6 @@ /* * Optional: not supported by gcc * Optional: only supported since clang >= 14.0 - * Optional: not supported by icc * * clang: https://clang.llvm.org/docs/AttributeReference.html#diagnose_as_builtin */ @@ -122,7 +114,6 @@ /* * Optional: not supported by clang - * Optional: not supported by icc * * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Type-Attributes.html#index-designated_005finit-type-attribute */ @@ -236,7 +227,6 @@ /* * Optional: only supported since gcc >= 8 * Optional: not supported by clang - * Optional: not supported by icc * * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-nonstring-variable-attribute */ @@ -267,7 +257,6 @@ /* * Optional: not supported by gcc. - * Optional: not supported by icc. * * clang: https://clang.llvm.org/docs/AttributeReference.html#overloadable */ @@ -287,7 +276,6 @@ * Note: the "type" argument should match any __builtin_object_size(p, type) usage. * * Optional: not supported by gcc. - * Optional: not supported by icc. * * clang: https://clang.llvm.org/docs/AttributeReference.html#pass-object-size-pass-dynamic-object-size */ diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 690c7c826fbf..547ea1ff806e 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -120,8 +120,6 @@ static inline void __chk_io_ptr(const volatile void __iomem *ptr) { } /* Compiler specific macros. */ #ifdef __clang__ #include -#elif defined(__INTEL_COMPILER) -#include #elif defined(__GNUC__) /* The above compilers also define __GNUC__, so order is important here. */ #include diff --git a/scripts/cc-version.sh b/scripts/cc-version.sh index 2401c86fcf53..0573c92e841d 100755 --- a/scripts/cc-version.sh +++ b/scripts/cc-version.sh @@ -12,8 +12,6 @@ get_c_compiler_info() cat <<- EOF | "$@" -E -P -x c - 2>/dev/null #if defined(__clang__) Clang __clang_major__ __clang_minor__ __clang_patchlevel__ - #elif defined(__INTEL_COMPILER) - ICC __INTEL_COMPILER __INTEL_COMPILER_UPDATE #elif defined(__GNUC__) GCC __GNUC__ __GNUC_MINOR__ __GNUC_PATCHLEVEL__ #else diff --git a/scripts/min-tool-version.sh b/scripts/min-tool-version.sh index a814f1efb39d..20d483ec6f5f 100755 --- a/scripts/min-tool-version.sh +++ b/scripts/min-tool-version.sh @@ -19,10 +19,6 @@ binutils) gcc) echo 5.1.0 ;; -icc) - # temporary - echo 16.0.3 - ;; llvm) if [ "$SRCARCH" = s390 ]; then echo 15.0.0 -- cgit v1.2.3 From 596ff4a09b8981790e15572e8e7bc904df5835e7 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 4 Mar 2023 13:35:43 -0800 Subject: cpumask: re-introduce constant-sized cpumask optimizations Commit aa47a7c215e7 ("lib/cpumask: deprecate nr_cpumask_bits") resulted in the cpumask operations potentially becoming hugely less efficient, because suddenly the cpumask was always considered to be variable-sized. The optimization was then later added back in a limited form by commit 6f9c07be9d02 ("lib/cpumask: add FORCE_NR_CPUS config option"), but that FORCE_NR_CPUS option is not useful in a generic kernel and more of a special case for embedded situations with fixed hardware. Instead, just re-introduce the optimization, with some changes. Instead of depending on CPUMASK_OFFSTACK being false, and then always using the full constant cpumask width, this introduces three different cpumask "sizes": - the exact size (nr_cpumask_bits) remains identical to nr_cpu_ids. This is used for situations where we should use the exact size. - the "small" size (small_cpumask_bits) is the NR_CPUS constant if it fits in a single word and the bitmap operations thus end up able to trigger the "small_const_nbits()" optimizations. This is used for the operations that have optimized single-word cases that get inlined, notably the bit find and scanning functions. - the "large" size (large_cpumask_bits) is the NR_CPUS constant if it is an sufficiently small constant that makes simple "copy" and "clear" operations more efficient. This is arbitrarily set at four words or less. As a an example of this situation, without this fixed size optimization, cpumask_clear() will generate code like movl nr_cpu_ids(%rip), %edx addq $63, %rdx shrq $3, %rdx andl $-8, %edx callq memset@PLT on x86-64, because it would calculate the "exact" number of longwords that need to be cleared. In contrast, with this patch, using a MAX_CPU of 64 (which is quite a reasonable value to use), the above becomes a single movq $0,cpumask instruction instead, because instead of caring to figure out exactly how many CPU's the system has, it just knows that the cpumask will be a single word and can just clear it all. Note that this does end up tightening the rules a bit from the original version in another way: operations that set bits in the cpumask are now limited to the actual nr_cpu_ids limit, whereas we used to do the nr_cpumask_bits thing almost everywhere in the cpumask code. But if you just clear bits, or scan for bits, we can use the simpler compile-time constants. In the process, remove 'cpumask_complement()' and 'for_each_cpu_not()' which were not useful, and which fundamentally have to be limited to 'nr_cpu_ids'. Better remove them now than have somebody introduce use of them later. Of course, on x86-64 with MAXSMP there is no sane small compile-time constant for the cpumask sizes, and we end up using the actual CPU bits, and will generate the above kind of horrors regardless. Please don't use MAXSMP unless you really expect to have machines with thousands of cores. Signed-off-by: Linus Torvalds --- .clang-format | 1 - arch/ia64/kernel/acpi.c | 4 +- include/linux/cpumask.h | 125 +++++++++++++++++++++++++++--------------------- lib/cpumask_kunit.c | 14 +----- 4 files changed, 72 insertions(+), 72 deletions(-) (limited to 'include/linux') diff --git a/.clang-format b/.clang-format index 2c61b4553374..d988e9fa9b26 100644 --- a/.clang-format +++ b/.clang-format @@ -226,7 +226,6 @@ ForEachMacros: - 'for_each_console_srcu' - 'for_each_cpu' - 'for_each_cpu_and' - - 'for_each_cpu_not' - 'for_each_cpu_wrap' - 'for_each_dapm_widgets' - 'for_each_dedup_cand' diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c index 96d13cb7c19f..15f6cfddcc08 100644 --- a/arch/ia64/kernel/acpi.c +++ b/arch/ia64/kernel/acpi.c @@ -783,11 +783,9 @@ __init void prefill_possible_map(void) static int _acpi_map_lsapic(acpi_handle handle, int physid, int *pcpu) { - cpumask_t tmp_map; int cpu; - cpumask_complement(&tmp_map, cpu_present_mask); - cpu = cpumask_first(&tmp_map); + cpu = cpumask_first_zero(cpu_present_mask); if (cpu >= nr_cpu_ids) return -EINVAL; diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 10c92bd9b807..8fbe76607965 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -50,8 +50,41 @@ static inline void set_nr_cpu_ids(unsigned int nr) #endif } -/* Deprecated. Always use nr_cpu_ids. */ -#define nr_cpumask_bits nr_cpu_ids +/* + * We have several different "preferred sizes" for the cpumask + * operations, depending on operation. + * + * For example, the bitmap scanning and operating operations have + * optimized routines that work for the single-word case, but only when + * the size is constant. So if NR_CPUS fits in one single word, we are + * better off using that small constant, in order to trigger the + * optimized bit finding. That is 'small_cpumask_size'. + * + * The clearing and copying operations will similarly perform better + * with a constant size, but we limit that size arbitrarily to four + * words. We call this 'large_cpumask_size'. + * + * Finally, some operations just want the exact limit, either because + * they set bits or just don't have any faster fixed-sized versions. We + * call this just 'nr_cpumask_size'. + * + * Note that these optional constants are always guaranteed to be at + * least as big as 'nr_cpu_ids' itself is, and all our cpumask + * allocations are at least that size (see cpumask_size()). The + * optimization comes from being able to potentially use a compile-time + * constant instead of a run-time generated exact number of CPUs. + */ +#if NR_CPUS <= BITS_PER_LONG + #define small_cpumask_bits ((unsigned int)NR_CPUS) + #define large_cpumask_bits ((unsigned int)NR_CPUS) +#elif NR_CPUS <= 4*BITS_PER_LONG + #define small_cpumask_bits nr_cpu_ids + #define large_cpumask_bits ((unsigned int)NR_CPUS) +#else + #define small_cpumask_bits nr_cpu_ids + #define large_cpumask_bits nr_cpu_ids +#endif +#define nr_cpumask_bits nr_cpu_ids /* * The following particular system cpumasks and operations manage @@ -126,7 +159,7 @@ static __always_inline unsigned int cpumask_check(unsigned int cpu) */ static inline unsigned int cpumask_first(const struct cpumask *srcp) { - return find_first_bit(cpumask_bits(srcp), nr_cpumask_bits); + return find_first_bit(cpumask_bits(srcp), small_cpumask_bits); } /** @@ -137,7 +170,7 @@ static inline unsigned int cpumask_first(const struct cpumask *srcp) */ static inline unsigned int cpumask_first_zero(const struct cpumask *srcp) { - return find_first_zero_bit(cpumask_bits(srcp), nr_cpumask_bits); + return find_first_zero_bit(cpumask_bits(srcp), small_cpumask_bits); } /** @@ -150,7 +183,7 @@ static inline unsigned int cpumask_first_zero(const struct cpumask *srcp) static inline unsigned int cpumask_first_and(const struct cpumask *srcp1, const struct cpumask *srcp2) { - return find_first_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), nr_cpumask_bits); + return find_first_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits); } /** @@ -161,7 +194,7 @@ unsigned int cpumask_first_and(const struct cpumask *srcp1, const struct cpumask */ static inline unsigned int cpumask_last(const struct cpumask *srcp) { - return find_last_bit(cpumask_bits(srcp), nr_cpumask_bits); + return find_last_bit(cpumask_bits(srcp), small_cpumask_bits); } /** @@ -177,7 +210,7 @@ unsigned int cpumask_next(int n, const struct cpumask *srcp) /* -1 is a legal arg here. */ if (n != -1) cpumask_check(n); - return find_next_bit(cpumask_bits(srcp), nr_cpumask_bits, n + 1); + return find_next_bit(cpumask_bits(srcp), small_cpumask_bits, n + 1); } /** @@ -192,7 +225,7 @@ static inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp) /* -1 is a legal arg here. */ if (n != -1) cpumask_check(n); - return find_next_zero_bit(cpumask_bits(srcp), nr_cpumask_bits, n+1); + return find_next_zero_bit(cpumask_bits(srcp), small_cpumask_bits, n+1); } #if NR_CPUS == 1 @@ -235,7 +268,7 @@ unsigned int cpumask_next_and(int n, const struct cpumask *src1p, if (n != -1) cpumask_check(n); return find_next_and_bit(cpumask_bits(src1p), cpumask_bits(src2p), - nr_cpumask_bits, n + 1); + small_cpumask_bits, n + 1); } /** @@ -246,17 +279,7 @@ unsigned int cpumask_next_and(int n, const struct cpumask *src1p, * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu(cpu, mask) \ - for_each_set_bit(cpu, cpumask_bits(mask), nr_cpumask_bits) - -/** - * for_each_cpu_not - iterate over every cpu in a complemented mask - * @cpu: the (optionally unsigned) integer iterator - * @mask: the cpumask pointer - * - * After the loop, cpu is >= nr_cpu_ids. - */ -#define for_each_cpu_not(cpu, mask) \ - for_each_clear_bit(cpu, cpumask_bits(mask), nr_cpumask_bits) + for_each_set_bit(cpu, cpumask_bits(mask), small_cpumask_bits) #if NR_CPUS == 1 static inline @@ -290,7 +313,7 @@ unsigned int __pure cpumask_next_wrap(int n, const struct cpumask *mask, int sta * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu_wrap(cpu, mask, start) \ - for_each_set_bit_wrap(cpu, cpumask_bits(mask), nr_cpumask_bits, start) + for_each_set_bit_wrap(cpu, cpumask_bits(mask), small_cpumask_bits, start) /** * for_each_cpu_and - iterate over every cpu in both masks @@ -307,7 +330,7 @@ unsigned int __pure cpumask_next_wrap(int n, const struct cpumask *mask, int sta * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu_and(cpu, mask1, mask2) \ - for_each_and_bit(cpu, cpumask_bits(mask1), cpumask_bits(mask2), nr_cpumask_bits) + for_each_and_bit(cpu, cpumask_bits(mask1), cpumask_bits(mask2), small_cpumask_bits) /** * for_each_cpu_andnot - iterate over every cpu present in one mask, excluding @@ -325,7 +348,7 @@ unsigned int __pure cpumask_next_wrap(int n, const struct cpumask *mask, int sta * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu_andnot(cpu, mask1, mask2) \ - for_each_andnot_bit(cpu, cpumask_bits(mask1), cpumask_bits(mask2), nr_cpumask_bits) + for_each_andnot_bit(cpu, cpumask_bits(mask1), cpumask_bits(mask2), small_cpumask_bits) /** * cpumask_any_but - return a "random" in a cpumask, but not this one. @@ -356,7 +379,7 @@ unsigned int cpumask_any_but(const struct cpumask *mask, unsigned int cpu) */ static inline unsigned int cpumask_nth(unsigned int cpu, const struct cpumask *srcp) { - return find_nth_bit(cpumask_bits(srcp), nr_cpumask_bits, cpumask_check(cpu)); + return find_nth_bit(cpumask_bits(srcp), small_cpumask_bits, cpumask_check(cpu)); } /** @@ -372,7 +395,7 @@ unsigned int cpumask_nth_and(unsigned int cpu, const struct cpumask *srcp1, const struct cpumask *srcp2) { return find_nth_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), - nr_cpumask_bits, cpumask_check(cpu)); + small_cpumask_bits, cpumask_check(cpu)); } /** @@ -388,7 +411,7 @@ unsigned int cpumask_nth_andnot(unsigned int cpu, const struct cpumask *srcp1, const struct cpumask *srcp2) { return find_nth_andnot_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), - nr_cpumask_bits, cpumask_check(cpu)); + small_cpumask_bits, cpumask_check(cpu)); } /** @@ -408,7 +431,7 @@ unsigned int cpumask_nth_and_andnot(unsigned int cpu, const struct cpumask *srcp return find_nth_and_andnot_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), cpumask_bits(srcp3), - nr_cpumask_bits, cpumask_check(cpu)); + small_cpumask_bits, cpumask_check(cpu)); } #define CPU_BITS_NONE \ @@ -495,10 +518,14 @@ static __always_inline bool cpumask_test_and_clear_cpu(int cpu, struct cpumask * /** * cpumask_setall - set all cpus (< nr_cpu_ids) in a cpumask * @dstp: the cpumask pointer + * + * Note: since we set bits, we should use the tighter 'bitmap_set()' with + * the eact number of bits, not 'bitmap_fill()' that will fill past the + * end. */ static inline void cpumask_setall(struct cpumask *dstp) { - bitmap_fill(cpumask_bits(dstp), nr_cpumask_bits); + bitmap_set(cpumask_bits(dstp), 0, nr_cpumask_bits); } /** @@ -507,7 +534,7 @@ static inline void cpumask_setall(struct cpumask *dstp) */ static inline void cpumask_clear(struct cpumask *dstp) { - bitmap_zero(cpumask_bits(dstp), nr_cpumask_bits); + bitmap_zero(cpumask_bits(dstp), large_cpumask_bits); } /** @@ -523,7 +550,7 @@ static inline bool cpumask_and(struct cpumask *dstp, const struct cpumask *src2p) { return bitmap_and(cpumask_bits(dstp), cpumask_bits(src1p), - cpumask_bits(src2p), nr_cpumask_bits); + cpumask_bits(src2p), small_cpumask_bits); } /** @@ -536,7 +563,7 @@ static inline void cpumask_or(struct cpumask *dstp, const struct cpumask *src1p, const struct cpumask *src2p) { bitmap_or(cpumask_bits(dstp), cpumask_bits(src1p), - cpumask_bits(src2p), nr_cpumask_bits); + cpumask_bits(src2p), small_cpumask_bits); } /** @@ -550,7 +577,7 @@ static inline void cpumask_xor(struct cpumask *dstp, const struct cpumask *src2p) { bitmap_xor(cpumask_bits(dstp), cpumask_bits(src1p), - cpumask_bits(src2p), nr_cpumask_bits); + cpumask_bits(src2p), small_cpumask_bits); } /** @@ -566,19 +593,7 @@ static inline bool cpumask_andnot(struct cpumask *dstp, const struct cpumask *src2p) { return bitmap_andnot(cpumask_bits(dstp), cpumask_bits(src1p), - cpumask_bits(src2p), nr_cpumask_bits); -} - -/** - * cpumask_complement - *dstp = ~*srcp - * @dstp: the cpumask result - * @srcp: the input to invert - */ -static inline void cpumask_complement(struct cpumask *dstp, - const struct cpumask *srcp) -{ - bitmap_complement(cpumask_bits(dstp), cpumask_bits(srcp), - nr_cpumask_bits); + cpumask_bits(src2p), small_cpumask_bits); } /** @@ -590,7 +605,7 @@ static inline bool cpumask_equal(const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_equal(cpumask_bits(src1p), cpumask_bits(src2p), - nr_cpumask_bits); + small_cpumask_bits); } /** @@ -604,7 +619,7 @@ static inline bool cpumask_or_equal(const struct cpumask *src1p, const struct cpumask *src3p) { return bitmap_or_equal(cpumask_bits(src1p), cpumask_bits(src2p), - cpumask_bits(src3p), nr_cpumask_bits); + cpumask_bits(src3p), small_cpumask_bits); } /** @@ -616,7 +631,7 @@ static inline bool cpumask_intersects(const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_intersects(cpumask_bits(src1p), cpumask_bits(src2p), - nr_cpumask_bits); + small_cpumask_bits); } /** @@ -630,7 +645,7 @@ static inline bool cpumask_subset(const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_subset(cpumask_bits(src1p), cpumask_bits(src2p), - nr_cpumask_bits); + small_cpumask_bits); } /** @@ -639,7 +654,7 @@ static inline bool cpumask_subset(const struct cpumask *src1p, */ static inline bool cpumask_empty(const struct cpumask *srcp) { - return bitmap_empty(cpumask_bits(srcp), nr_cpumask_bits); + return bitmap_empty(cpumask_bits(srcp), small_cpumask_bits); } /** @@ -657,7 +672,7 @@ static inline bool cpumask_full(const struct cpumask *srcp) */ static inline unsigned int cpumask_weight(const struct cpumask *srcp) { - return bitmap_weight(cpumask_bits(srcp), nr_cpumask_bits); + return bitmap_weight(cpumask_bits(srcp), small_cpumask_bits); } /** @@ -668,7 +683,7 @@ static inline unsigned int cpumask_weight(const struct cpumask *srcp) static inline unsigned int cpumask_weight_and(const struct cpumask *srcp1, const struct cpumask *srcp2) { - return bitmap_weight_and(cpumask_bits(srcp1), cpumask_bits(srcp2), nr_cpumask_bits); + return bitmap_weight_and(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits); } /** @@ -681,7 +696,7 @@ static inline void cpumask_shift_right(struct cpumask *dstp, const struct cpumask *srcp, int n) { bitmap_shift_right(cpumask_bits(dstp), cpumask_bits(srcp), n, - nr_cpumask_bits); + small_cpumask_bits); } /** @@ -705,7 +720,7 @@ static inline void cpumask_shift_left(struct cpumask *dstp, static inline void cpumask_copy(struct cpumask *dstp, const struct cpumask *srcp) { - bitmap_copy(cpumask_bits(dstp), cpumask_bits(srcp), nr_cpumask_bits); + bitmap_copy(cpumask_bits(dstp), cpumask_bits(srcp), large_cpumask_bits); } /** @@ -789,7 +804,7 @@ static inline int cpulist_parse(const char *buf, struct cpumask *dstp) */ static inline unsigned int cpumask_size(void) { - return BITS_TO_LONGS(nr_cpumask_bits) * sizeof(long); + return BITS_TO_LONGS(large_cpumask_bits) * sizeof(long); } /* diff --git a/lib/cpumask_kunit.c b/lib/cpumask_kunit.c index d1fc6ece21f3..a105e6369efc 100644 --- a/lib/cpumask_kunit.c +++ b/lib/cpumask_kunit.c @@ -23,16 +23,6 @@ KUNIT_EXPECT_EQ_MSG((test), mask_weight, iter, MASK_MSG(mask)); \ } while (0) -#define EXPECT_FOR_EACH_CPU_NOT_EQ(test, mask) \ - do { \ - const cpumask_t *m = (mask); \ - int mask_weight = cpumask_weight(m); \ - int cpu, iter = 0; \ - for_each_cpu_not(cpu, m) \ - iter++; \ - KUNIT_EXPECT_EQ_MSG((test), nr_cpu_ids - mask_weight, iter, MASK_MSG(mask)); \ - } while (0) - #define EXPECT_FOR_EACH_CPU_OP_EQ(test, op, mask1, mask2) \ do { \ const cpumask_t *m1 = (mask1); \ @@ -77,7 +67,7 @@ static void test_cpumask_weight(struct kunit *test) KUNIT_EXPECT_EQ_MSG(test, 0, cpumask_weight(&mask_empty), MASK_MSG(&mask_empty)); KUNIT_EXPECT_EQ_MSG(test, nr_cpu_ids, cpumask_weight(cpu_possible_mask), MASK_MSG(cpu_possible_mask)); - KUNIT_EXPECT_EQ_MSG(test, nr_cpumask_bits, cpumask_weight(&mask_all), MASK_MSG(&mask_all)); + KUNIT_EXPECT_EQ_MSG(test, nr_cpu_ids, cpumask_weight(&mask_all), MASK_MSG(&mask_all)); } static void test_cpumask_first(struct kunit *test) @@ -113,14 +103,12 @@ static void test_cpumask_next(struct kunit *test) static void test_cpumask_iterators(struct kunit *test) { EXPECT_FOR_EACH_CPU_EQ(test, &mask_empty); - EXPECT_FOR_EACH_CPU_NOT_EQ(test, &mask_empty); EXPECT_FOR_EACH_CPU_WRAP_EQ(test, &mask_empty); EXPECT_FOR_EACH_CPU_OP_EQ(test, and, &mask_empty, &mask_empty); EXPECT_FOR_EACH_CPU_OP_EQ(test, and, cpu_possible_mask, &mask_empty); EXPECT_FOR_EACH_CPU_OP_EQ(test, andnot, &mask_empty, &mask_empty); EXPECT_FOR_EACH_CPU_EQ(test, cpu_possible_mask); - EXPECT_FOR_EACH_CPU_NOT_EQ(test, cpu_possible_mask); EXPECT_FOR_EACH_CPU_WRAP_EQ(test, cpu_possible_mask); EXPECT_FOR_EACH_CPU_OP_EQ(test, and, cpu_possible_mask, cpu_possible_mask); EXPECT_FOR_EACH_CPU_OP_EQ(test, andnot, cpu_possible_mask, &mask_empty); -- cgit v1.2.3 From 80c16b2b121fbc3380dbffa9bab7559acbaaa2ed Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 6 Mar 2023 17:22:04 +0200 Subject: cpumask: Fix typo nr_cpumask_size --> nr_cpumask_bits The never used nr_cpumask_size is just a typo, hence use existing redefinition that's called nr_cpumask_bits. Signed-off-by: Andy Shevchenko Signed-off-by: Linus Torvalds --- include/linux/cpumask.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 8fbe76607965..ce8eb7ef2107 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -66,7 +66,7 @@ static inline void set_nr_cpu_ids(unsigned int nr) * * Finally, some operations just want the exact limit, either because * they set bits or just don't have any faster fixed-sized versions. We - * call this just 'nr_cpumask_size'. + * call this just 'nr_cpumask_bits'. * * Note that these optional constants are always guaranteed to be at * least as big as 'nr_cpu_ids' itself is, and all our cpumask -- cgit v1.2.3 From c28cd1f3433c7e339315d1ddacaeacf0fdfbe252 Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Wed, 1 Mar 2023 17:46:38 -0800 Subject: clk: Mark a fwnode as initialized when using CLK_OF_DECLARE() macro We already mark fwnodes as initialized when they are registered as clock providers. We do this so that fw_devlink can tell when a clock driver doesn't use the driver core framework to probe/initialize its device. This ensures fw_devlink doesn't block the consumers of such a clock provider indefinitely. However, some users of CLK_OF_DECLARE() macros don't use the same node that matches the macro as the node for the clock provider, but they initialize the entire node. To cover these cases, also mark the nodes that match the macros as initialized when the init callback function is called. An example of this is "stericsson,u8500-clks" that's handled using CLK_OF_DECLARE() and looks something like this: clocks { compatible = "stericsson,u8500-clks"; prcmu_clk: prcmu-clock { #clock-cells = <1>; }; prcc_pclk: prcc-periph-clock { #clock-cells = <2>; }; prcc_kclk: prcc-kernel-clock { #clock-cells = <2>; }; prcc_reset: prcc-reset-controller { #reset-cells = <2>; }; ... }; This patch makes sure that "clocks" is marked as initialized so that fw_devlink knows that all nodes under it have been initialized. If the driver creates struct devices for some of the subnodes, fw_devlink is smart enough to know to wait for those devices to probe, so no special handling is required for those cases. Cc: Greg Kroah-Hartman Reported-by: Linus Walleij Link: https://lore.kernel.org/lkml/CACRpkdamxDX6EBVjKX5=D3rkHp17f5pwGdBVhzFU90-0MHY6dQ@mail.gmail.com/ Fixes: 4a032827daa8 ("of: property: Simplify of_link_to_phandle()") Signed-off-by: Saravana Kannan Link: https://lore.kernel.org/r/20230302014639.297514-1-saravanak@google.com Reviewed-by: Linus Walleij Tested-by: Linus Walleij Signed-off-by: Stephen Boyd --- include/linux/clk-provider.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 842e72a5348f..c9f5276006a0 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -1363,7 +1363,13 @@ struct clk_hw_onecell_data { struct clk_hw *hws[]; }; -#define CLK_OF_DECLARE(name, compat, fn) OF_DECLARE_1(clk, name, compat, fn) +#define CLK_OF_DECLARE(name, compat, fn) \ + static void __init name##_of_clk_init_declare(struct device_node *np) \ + { \ + fn(np); \ + fwnode_dev_initialized(of_fwnode_handle(np), true); \ + } \ + OF_DECLARE_1(clk, name, compat, name##_of_clk_init_declare) /* * Use this macro when you have a driver that requires two initialization -- cgit v1.2.3 From 849ad04cf562ac63b0371a825eed473d84de9c6d Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 7 Mar 2023 01:50:53 -0500 Subject: new helper: put_and_unmap_page() kunmap_local() + put_page(), as done by e.g. ext2 directory handling. Signed-off-by: Al Viro --- include/linux/highmem.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/highmem.h b/include/linux/highmem.h index b06254e76d99..8fc10089e19e 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -481,4 +481,10 @@ static inline void folio_zero_range(struct folio *folio, zero_user_segments(&folio->page, start, start + length, 0, 0); } +static inline void put_and_unmap_page(struct page *page, void *addr) +{ + kunmap_local(addr); + put_page(page); +} + #endif /* _LINUX_HIGHMEM_H */ -- cgit v1.2.3 From 63355b9884b3d1677de6bd1517cd2b8a9bf53978 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 7 Mar 2023 12:16:18 -0800 Subject: cpumask: be more careful with 'cpumask_setall()' Commit 596ff4a09b89 ("cpumask: re-introduce constant-sized cpumask optimizations") changed cpumask_setall() to use "bitmap_set()" instead of "bitmap_fill()", because bitmap_fill() would explicitly set all the bits of a constant sized small bitmap, and that's exactly what we don't want: we want to only set bits up to 'nr_cpu_ids', which is what "bitmap_set()" does. However, Yury correctly points out that while "bitmap_set()" does indeed only set bits up to the required bitmap size, it doesn't _clear_ bits above that size, so the upper bits would still not have well-defined values. Now, none of this should really matter, since any bits set past 'nr_cpu_ids' should always be ignored in the first place. Yes, the bit scanning functions might return them as a result, but since users should always consider the ">= nr_cpu_ids" condition to mean "no more bits", that shouldn't have any actual effect (see previous commit 8ca09d5fa354 "cpumask: fix incorrect cpumask scanning result checks"). But let's just do it right, the way the code was _intended_ to work. We have had enough lazy code that works but bites us in the *rse later (again, see previous commit) that there's no reason to not just do this properly. It turns out that "bitmap_fill()" gets this all right for the complex case, and really only fails for the inlined optimized case that just fills the whole word. And while we could just fix bitmap_fill() to use the proper last word mask, there's two issues with that: - the cpumask case wants to do the _optimization_ based on "NR_CPUS is a small constant", but then wants to do the actual bit _fill_ based on "nr_cpu_ids" that isn't necessarily that same constant - we have lots of non-cpumask users of bitmap_fill(), and while they hopefully don't care, and probably would want the proper semantics anyway ("only set bits up to the limit"), I do not want the cpumask changes to impact other parts So this ends up just doing the single-word optimization by hand in the cpumask code. If our cpumask is fundamentally limited to a single word, just do the proper "fill in that word" exactly. And if it's the more complex multi-word case, then the generic bitmap_fill() will DTRT. This is all an example of how our bitmap function optimizations really are somewhat broken. They conflate the "this is size of the bitmap" optimizations with the actual bit(s) we want to set. In many cases we really want to have the two be separate things: sometimes we base our optimizations on the size of the whole bitmap ("I know this whole bitmap fits in a single word, so I'll just use single-word accesses"), and sometimes we base them on the bit we are looking at ("this is just acting on bits that are in the first word, so I'll use single-word accesses"). Notice how the end result of the two optimizations are the same, but the way we get to them are quite different. And all our cpumask optimization games are really about that fundamental distinction, and we'd often really want to pass in both the "this is the bit I'm working on" (which _can_ be a small constant but might be variable), and "I know it's in this range even if it's variable" (based on CONFIG_NR_CPUS). So this cpumask_setall() implementation just makes that explicit. It checks the "I statically know the size is small" using the known static size of the cpumask (which is what that 'small_cpumask_bits' is all about), but then sets the actual bits using the exact number of cpus we have (ie 'nr_cpumask_bits') Of course, in a perfect world, the compiler would have done all the range analysis (possibly with help from us just telling it that "this value is always in this range"), and would do all of this for us. But that is not the world we live in. While we dream of that perfect world, this does that manual logic to make it all work out. And this was a very long explanation for a small code change that shouldn't even matter. Reported-by: Yury Norov Link: https://lore.kernel.org/lkml/ZAV9nGG9e1%2FrV+L%2F@yury-laptop/ Signed-off-by: Linus Torvalds --- include/linux/cpumask.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index ce8eb7ef2107..63d637d18e79 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -518,14 +518,14 @@ static __always_inline bool cpumask_test_and_clear_cpu(int cpu, struct cpumask * /** * cpumask_setall - set all cpus (< nr_cpu_ids) in a cpumask * @dstp: the cpumask pointer - * - * Note: since we set bits, we should use the tighter 'bitmap_set()' with - * the eact number of bits, not 'bitmap_fill()' that will fill past the - * end. */ static inline void cpumask_setall(struct cpumask *dstp) { - bitmap_set(cpumask_bits(dstp), 0, nr_cpumask_bits); + if (small_const_nbits(small_cpumask_bits)) { + cpumask_bits(dstp)[0] = BITMAP_LAST_WORD_MASK(nr_cpumask_bits); + return; + } + bitmap_fill(cpumask_bits(dstp), nr_cpumask_bits); } /** -- cgit v1.2.3 From eb59eca0d8ac15f8c1b7f1cd35999455a90292c0 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 6 Mar 2023 08:56:31 +0100 Subject: interconnect: fix provider registration API The current interconnect provider interface is inherently racy as providers are expected to be added before being fully initialised. Specifically, nodes are currently not added and the provider data is not initialised until after registering the provider which can cause racing DT lookups to fail. Add a new provider API which will be used to fix up the interconnect drivers. The old API is reimplemented using the new interface and will be removed once all drivers have been fixed. Fixes: 11f1ceca7031 ("interconnect: Add generic on-chip interconnect API") Fixes: 87e3031b6fbd ("interconnect: Allow endpoints translation via DT") Cc: stable@vger.kernel.org # 5.1 Reviewed-by: Konrad Dybcio Signed-off-by: Johan Hovold Tested-by: Luca Ceresoli # i.MX8MP MSC SM2-MB-EP1 Board Link: https://lore.kernel.org/r/20230306075651.2449-4-johan+linaro@kernel.org Signed-off-by: Georgi Djakov --- drivers/interconnect/core.c | 52 +++++++++++++++++++++++++---------- include/linux/interconnect-provider.h | 12 ++++++++ 2 files changed, 50 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c index cabb6f5df83e..7a24c1444ace 100644 --- a/drivers/interconnect/core.c +++ b/drivers/interconnect/core.c @@ -1033,44 +1033,68 @@ int icc_nodes_remove(struct icc_provider *provider) EXPORT_SYMBOL_GPL(icc_nodes_remove); /** - * icc_provider_add() - add a new interconnect provider - * @provider: the interconnect provider that will be added into topology + * icc_provider_init() - initialize a new interconnect provider + * @provider: the interconnect provider to initialize + * + * Must be called before adding nodes to the provider. + */ +void icc_provider_init(struct icc_provider *provider) +{ + WARN_ON(!provider->set); + + INIT_LIST_HEAD(&provider->nodes); +} +EXPORT_SYMBOL_GPL(icc_provider_init); + +/** + * icc_provider_register() - register a new interconnect provider + * @provider: the interconnect provider to register * * Return: 0 on success, or an error code otherwise */ -int icc_provider_add(struct icc_provider *provider) +int icc_provider_register(struct icc_provider *provider) { - if (WARN_ON(!provider->set)) - return -EINVAL; if (WARN_ON(!provider->xlate && !provider->xlate_extended)) return -EINVAL; mutex_lock(&icc_lock); - - INIT_LIST_HEAD(&provider->nodes); list_add_tail(&provider->provider_list, &icc_providers); - mutex_unlock(&icc_lock); - dev_dbg(provider->dev, "interconnect provider added to topology\n"); + dev_dbg(provider->dev, "interconnect provider registered\n"); return 0; } -EXPORT_SYMBOL_GPL(icc_provider_add); +EXPORT_SYMBOL_GPL(icc_provider_register); /** - * icc_provider_del() - delete previously added interconnect provider - * @provider: the interconnect provider that will be removed from topology + * icc_provider_deregister() - deregister an interconnect provider + * @provider: the interconnect provider to deregister */ -void icc_provider_del(struct icc_provider *provider) +void icc_provider_deregister(struct icc_provider *provider) { mutex_lock(&icc_lock); WARN_ON(provider->users); - WARN_ON(!list_empty(&provider->nodes)); list_del(&provider->provider_list); mutex_unlock(&icc_lock); } +EXPORT_SYMBOL_GPL(icc_provider_deregister); + +int icc_provider_add(struct icc_provider *provider) +{ + icc_provider_init(provider); + + return icc_provider_register(provider); +} +EXPORT_SYMBOL_GPL(icc_provider_add); + +void icc_provider_del(struct icc_provider *provider) +{ + WARN_ON(!list_empty(&provider->nodes)); + + icc_provider_deregister(provider); +} EXPORT_SYMBOL_GPL(icc_provider_del); static const struct of_device_id __maybe_unused ignore_list[] = { diff --git a/include/linux/interconnect-provider.h b/include/linux/interconnect-provider.h index cd5c5a27557f..d12cd18aab3f 100644 --- a/include/linux/interconnect-provider.h +++ b/include/linux/interconnect-provider.h @@ -122,6 +122,9 @@ int icc_link_destroy(struct icc_node *src, struct icc_node *dst); void icc_node_add(struct icc_node *node, struct icc_provider *provider); void icc_node_del(struct icc_node *node); int icc_nodes_remove(struct icc_provider *provider); +void icc_provider_init(struct icc_provider *provider); +int icc_provider_register(struct icc_provider *provider); +void icc_provider_deregister(struct icc_provider *provider); int icc_provider_add(struct icc_provider *provider); void icc_provider_del(struct icc_provider *provider); struct icc_node_data *of_icc_get_from_provider(struct of_phandle_args *spec); @@ -167,6 +170,15 @@ static inline int icc_nodes_remove(struct icc_provider *provider) return -ENOTSUPP; } +static inline void icc_provider_init(struct icc_provider *provider) { } + +static inline int icc_provider_register(struct icc_provider *provider) +{ + return -ENOTSUPP; +} + +static inline void icc_provider_deregister(struct icc_provider *provider) { } + static inline int icc_provider_add(struct icc_provider *provider) { return -ENOTSUPP; -- cgit v1.2.3 From 03c835f498b540087244a6757e87dfe7ef10999b Mon Sep 17 00:00:00 2001 From: Uwe Kleine-König Date: Sun, 26 Feb 2023 23:26:52 +0100 Subject: i2c: Switch .probe() to not take an id parameter Commit b8a1a4cd5a98 ("i2c: Provide a temporary .probe_new() call-back type") introduced a new probe callback to convert i2c init routines to not take an i2c_device_id parameter. Now that all in-tree drivers are converted to the temporary .probe_new() callback, .probe() can be modified to match the desired prototype. Now that .probe() and .probe_new() have the same semantic, they can be defined as members of an anonymous union to save some memory and simplify the core code a bit. Signed-off-by: Uwe Kleine-König Signed-off-by: Wolfram Sang --- drivers/i2c/i2c-core-base.c | 11 ++--------- include/linux/i2c.h | 18 +++++++++++------- 2 files changed, 13 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c index cb5fa971d67e..63253e2b2c1f 100644 --- a/drivers/i2c/i2c-core-base.c +++ b/drivers/i2c/i2c-core-base.c @@ -561,15 +561,8 @@ static int i2c_device_probe(struct device *dev) goto err_detach_pm_domain; } - /* - * When there are no more users of probe(), - * rename probe_new to probe. - */ - if (driver->probe_new) - status = driver->probe_new(client); - else if (driver->probe) - status = driver->probe(client, - i2c_match_id(driver->id_table, client)); + if (driver->probe) + status = driver->probe(client); else status = -EINVAL; diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 500404d85141..5ba89663ea86 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -236,8 +236,8 @@ enum i2c_driver_flags { /** * struct i2c_driver - represent an I2C device driver * @class: What kind of i2c device we instantiate (for detect) - * @probe: Callback for device binding - soon to be deprecated - * @probe_new: New callback for device binding + * @probe: Callback for device binding + * @probe_new: Transitional callback for device binding - do not use * @remove: Callback for device unbinding * @shutdown: Callback for device shutdown * @alert: Alert callback, for example for the SMBus alert protocol @@ -272,14 +272,18 @@ enum i2c_driver_flags { struct i2c_driver { unsigned int class; + union { /* Standard driver model interfaces */ - int (*probe)(struct i2c_client *client, const struct i2c_device_id *id); + int (*probe)(struct i2c_client *client); + /* + * Legacy callback that was part of a conversion of .probe(). + * Today it has the same semantic as .probe(). Don't use for new + * code. + */ + int (*probe_new)(struct i2c_client *client); + }; void (*remove)(struct i2c_client *client); - /* New driver model interface to aid the seamless removal of the - * current probe()'s, more commonly unused than used second parameter. - */ - int (*probe_new)(struct i2c_client *client); /* driver model interfaces that don't relate to enumeration */ void (*shutdown)(struct i2c_client *client); -- cgit v1.2.3 From 5cf9d015be160e2d90d29ae74ef1364390e8fce8 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Wed, 8 Mar 2023 13:47:11 -0700 Subject: clk: Avoid invalid function names in CLK_OF_DECLARE() After commit c28cd1f3433c ("clk: Mark a fwnode as initialized when using CLK_OF_DECLARE() macro"), drivers/clk/mvebu/kirkwood.c fails to build: drivers/clk/mvebu/kirkwood.c:358:1: error: expected identifier or '(' CLK_OF_DECLARE(98dx1135_clk, "marvell,mv98dx1135-core-clock", ^ include/linux/clk-provider.h:1367:21: note: expanded from macro 'CLK_OF_DECLARE' static void __init name##_of_clk_init_declare(struct device_node *np) \ ^ :124:1: note: expanded from here 98dx1135_clk_of_clk_init_declare ^ drivers/clk/mvebu/kirkwood.c:358:1: error: invalid digit 'd' in decimal constant include/linux/clk-provider.h:1372:34: note: expanded from macro 'CLK_OF_DECLARE' OF_DECLARE_1(clk, name, compat, name##_of_clk_init_declare) ^ :125:3: note: expanded from here 98dx1135_clk_of_clk_init_declare ^ drivers/clk/mvebu/kirkwood.c:358:1: error: invalid digit 'd' in decimal constant include/linux/clk-provider.h:1372:34: note: expanded from macro 'CLK_OF_DECLARE' OF_DECLARE_1(clk, name, compat, name##_of_clk_init_declare) ^ :125:3: note: expanded from here 98dx1135_clk_of_clk_init_declare ^ drivers/clk/mvebu/kirkwood.c:358:1: error: invalid digit 'd' in decimal constant include/linux/clk-provider.h:1372:34: note: expanded from macro 'CLK_OF_DECLARE' OF_DECLARE_1(clk, name, compat, name##_of_clk_init_declare) ^ :125:3: note: expanded from here 98dx1135_clk_of_clk_init_declare ^ C function names must start with either an alphabetic letter or an underscore. To avoid generating invalid function names from clock names, add two underscores to the beginning of the identifier. Fixes: c28cd1f3433c ("clk: Mark a fwnode as initialized when using CLK_OF_DECLARE() macro") Suggested-by: Saravana Kannan Signed-off-by: Nathan Chancellor Link: https://lore.kernel.org/r/20230308-clk_of_declare-fix-v1-1-317b741e2532@kernel.org Reviewed-by: Saravana Kannan Reported-by: Naresh Kamboju Signed-off-by: Stephen Boyd --- include/linux/clk-provider.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index c9f5276006a0..6f3175f0678a 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -1364,12 +1364,12 @@ struct clk_hw_onecell_data { }; #define CLK_OF_DECLARE(name, compat, fn) \ - static void __init name##_of_clk_init_declare(struct device_node *np) \ + static void __init __##name##_of_clk_init_declare(struct device_node *np) \ { \ fn(np); \ fwnode_dev_initialized(of_fwnode_handle(np), true); \ } \ - OF_DECLARE_1(clk, name, compat, name##_of_clk_init_declare) + OF_DECLARE_1(clk, name, compat, __##name##_of_clk_init_declare) /* * Use this macro when you have a driver that requires two initialization -- cgit v1.2.3 From fe9ae05cfbe587dda724fcf537c00bc2f287da62 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Wed, 8 Mar 2023 11:50:12 +0100 Subject: fbdev: Fix incorrect page mapping clearance at fb_deferred_io_release() The recent fix for the deferred I/O by the commit 3efc61d95259 ("fbdev: Fix invalid page access after closing deferred I/O devices") caused a regression when the same fb device is opened/closed while it's being used. It resulted in a frozen screen even if something is redrawn there after the close. The breakage is because the patch was made under a wrong assumption of a single open; in the current code, fb_deferred_io_release() cleans up the page mapping of the pageref list and it calls cancel_delayed_work_sync() unconditionally, where both are no correct behavior for multiple opens. This patch adds a refcount for the opens of the device, and applies the cleanup only when all files get closed. As both fb_deferred_io_open() and _close() are called always in the fb_info lock (mutex), it's safe to use the normal int for the refcounting. Also, a useless BUG_ON() is dropped. Fixes: 3efc61d95259 ("fbdev: Fix invalid page access after closing deferred I/O devices") Cc: Signed-off-by: Takashi Iwai Reviewed-by: Patrik Jakobsson Signed-off-by: Thomas Zimmermann Link: https://patchwork.freedesktop.org/patch/msgid/20230308105012.1845-1-tiwai@suse.de --- drivers/video/fbdev/core/fb_defio.c | 17 +++++++++++++---- include/linux/fb.h | 1 + 2 files changed, 14 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/video/fbdev/core/fb_defio.c b/drivers/video/fbdev/core/fb_defio.c index 583cbcf09446..a3cf1f764f29 100644 --- a/drivers/video/fbdev/core/fb_defio.c +++ b/drivers/video/fbdev/core/fb_defio.c @@ -309,17 +309,18 @@ void fb_deferred_io_open(struct fb_info *info, struct inode *inode, struct file *file) { + struct fb_deferred_io *fbdefio = info->fbdefio; + file->f_mapping->a_ops = &fb_deferred_io_aops; + fbdefio->open_count++; } EXPORT_SYMBOL_GPL(fb_deferred_io_open); -void fb_deferred_io_release(struct fb_info *info) +static void fb_deferred_io_lastclose(struct fb_info *info) { - struct fb_deferred_io *fbdefio = info->fbdefio; struct page *page; int i; - BUG_ON(!fbdefio); cancel_delayed_work_sync(&info->deferred_work); /* clear out the mapping that we setup */ @@ -328,13 +329,21 @@ void fb_deferred_io_release(struct fb_info *info) page->mapping = NULL; } } + +void fb_deferred_io_release(struct fb_info *info) +{ + struct fb_deferred_io *fbdefio = info->fbdefio; + + if (!--fbdefio->open_count) + fb_deferred_io_lastclose(info); +} EXPORT_SYMBOL_GPL(fb_deferred_io_release); void fb_deferred_io_cleanup(struct fb_info *info) { struct fb_deferred_io *fbdefio = info->fbdefio; - fb_deferred_io_release(info); + fb_deferred_io_lastclose(info); kvfree(info->pagerefs); mutex_destroy(&fbdefio->lock); diff --git a/include/linux/fb.h b/include/linux/fb.h index 73eb1f85ea8e..05e40fcc7696 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -212,6 +212,7 @@ struct fb_deferred_io { /* delay between mkwrite and deferred handler */ unsigned long delay; bool sort_pagereflist; /* sort pagelist by offset */ + int open_count; /* number of opened files; protected by fb_info lock */ struct mutex lock; /* mutex that protects the pageref list */ struct list_head pagereflist; /* list of pagerefs for touched pages */ /* callback */ -- cgit v1.2.3 From 62913ae96de747091c4dacd06d158e7729c1a76d Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Tue, 7 Mar 2023 23:15:49 -0500 Subject: ext4, jbd2: add an optimized bmap for the journal inode The generic bmap() function exported by the VFS takes locks and does checks that are not necessary for the journal inode. So allow the file system to set a journal-optimized bmap function in journal->j_bmap. Reported-by: syzbot+9543479984ae9e576000@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?id=e4aaa78795e490421c79f76ec3679006c8ff4cf0 Signed-off-by: Theodore Ts'o --- fs/ext4/super.c | 23 +++++++++++++++++++++++ fs/jbd2/journal.c | 9 ++++++--- include/linux/jbd2.h | 8 ++++++++ 3 files changed, 37 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 2192b4111442..46b7345d2b6a 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -5742,6 +5742,28 @@ static struct inode *ext4_get_journal_inode(struct super_block *sb, return journal_inode; } +static int ext4_journal_bmap(journal_t *journal, sector_t *block) +{ + struct ext4_map_blocks map; + int ret; + + if (journal->j_inode == NULL) + return 0; + + map.m_lblk = *block; + map.m_len = 1; + ret = ext4_map_blocks(NULL, journal->j_inode, &map, 0); + if (ret <= 0) { + ext4_msg(journal->j_inode->i_sb, KERN_CRIT, + "journal bmap failed: block %llu ret %d\n", + *block, ret); + jbd2_journal_abort(journal, ret ? ret : -EIO); + return ret; + } + *block = map.m_pblk; + return 0; +} + static journal_t *ext4_get_journal(struct super_block *sb, unsigned int journal_inum) { @@ -5762,6 +5784,7 @@ static journal_t *ext4_get_journal(struct super_block *sb, return NULL; } journal->j_private = sb; + journal->j_bmap = ext4_journal_bmap; ext4_init_journal_params(sb, journal); return journal; } diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 2696f43e7239..c84f588fdcd0 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -970,10 +970,13 @@ int jbd2_journal_bmap(journal_t *journal, unsigned long blocknr, { int err = 0; unsigned long long ret; - sector_t block = 0; + sector_t block = blocknr; - if (journal->j_inode) { - block = blocknr; + if (journal->j_bmap) { + err = journal->j_bmap(journal, &block); + if (err == 0) + *retp = block; + } else if (journal->j_inode) { ret = bmap(journal->j_inode, &block); if (ret || !block) { diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 2170e0cc279d..6ffa34c51a11 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1308,6 +1308,14 @@ struct journal_s struct buffer_head *bh, enum passtype pass, int off, tid_t expected_commit_id); + + /** + * @j_bmap: + * + * Bmap function that should be used instead of the generic + * VFS bmap function. + */ + int (*j_bmap)(struct journal_s *journal, sector_t *block); }; #define jbd2_might_wait_for_commit(j) \ -- cgit v1.2.3 From e7304080e0e50d979ce9eaf694ad8283e2e539ea Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 12 Mar 2023 08:52:03 -0700 Subject: cpumask: relax sanity checking constraints The cpumask_check() was unnecessarily tight, and causes problems for the users of cpumask_next(). We have a number of users that take the previous return value of one of the bit scanning functions and subtract one to keep it in "range". But since the scanning functions end up returning up to 'small_cpumask_bits' instead of the tighter 'nr_cpumask_bits', the range really needs to be using that widened form. [ This "previous-1" behavior is also the reason we have all those comments about /* -1 is a legal arg here. */ and separate checks for that being ok. So we could have just made "small_cpumask_bits-1" be a similar special "don't check this" value. Tetsuo Handa even suggested a patch that only does that for cpumask_next(), since that seems to be the only actual case that triggers, but that all makes it even _more_ magical and special. So just relax the check ] One example of this kind of pattern being the 'c_start()' function in arch/x86/kernel/cpu/proc.c, but also duplicated in various forms on other architectures. Reported-by: syzbot+96cae094d90877641f32@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?extid=96cae094d90877641f32 Reported-by: Tetsuo Handa Link: https://lore.kernel.org/lkml/c1f4cc16-feea-b83c-82cf-1a1f007b7eb9@I-love.SAKURA.ne.jp/ Fixes: 596ff4a09b89 ("cpumask: re-introduce constant-sized cpumask optimizations") Signed-off-by: Linus Torvalds --- include/linux/cpumask.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 63d637d18e79..d4901ca8883c 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -147,7 +147,7 @@ static __always_inline void cpu_max_bits_warn(unsigned int cpu, unsigned int bit /* verify cpu argument to cpumask_* operators */ static __always_inline unsigned int cpumask_check(unsigned int cpu) { - cpu_max_bits_warn(cpu, nr_cpumask_bits); + cpu_max_bits_warn(cpu, small_cpumask_bits); return cpu; } -- cgit v1.2.3 From ab909509850b27fd39b8ba99e44cda39dbc3858c Mon Sep 17 00:00:00 2001 From: Niklas Schnelle Date: Mon, 6 Mar 2023 16:10:11 +0100 Subject: PCI: s390: Fix use-after-free of PCI resources with per-function hotplug On s390 PCI functions may be hotplugged individually even when they belong to a multi-function device. In particular on an SR-IOV device VFs may be removed and later re-added. In commit a50297cf8235 ("s390/pci: separate zbus creation from scanning") it was missed however that struct pci_bus and struct zpci_bus's resource list retained a reference to the PCI functions MMIO resources even though those resources are released and freed on hot-unplug. These stale resources may subsequently be claimed when the PCI function re-appears resulting in use-after-free. One idea of fixing this use-after-free in s390 specific code that was investigated was to simply keep resources around from the moment a PCI function first appeared until the whole virtual PCI bus created for a multi-function device disappears. The problem with this however is that due to the requirement of artificial MMIO addreesses (address cookies) extra logic is then needed to keep the address cookies compatible on re-plug. At the same time the MMIO resources semantically belong to the PCI function so tying their lifecycle to the function seems more logical. Instead a simpler approach is to remove the resources of an individually hot-unplugged PCI function from the PCI bus's resource list while keeping the resources of other PCI functions on the PCI bus untouched. This is done by introducing pci_bus_remove_resource() to remove an individual resource. Similarly the resource also needs to be removed from the struct zpci_bus's resource list. It turns out however, that there is really no need to add the MMIO resources to the struct zpci_bus's resource list at all and instead we can simply use the zpci_bar_struct's resource pointer directly. Fixes: a50297cf8235 ("s390/pci: separate zbus creation from scanning") Signed-off-by: Niklas Schnelle Reviewed-by: Matthew Rosato Acked-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20230306151014.60913-2-schnelle@linux.ibm.com Signed-off-by: Vasily Gorbik --- arch/s390/pci/pci.c | 16 ++++++++++------ arch/s390/pci/pci_bus.c | 12 +++++------- arch/s390/pci/pci_bus.h | 3 +-- drivers/pci/bus.c | 21 +++++++++++++++++++++ include/linux/pci.h | 1 + 5 files changed, 38 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index ef38b1514c77..e16afacc8fd1 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -544,8 +544,7 @@ static struct resource *__alloc_res(struct zpci_dev *zdev, unsigned long start, return r; } -int zpci_setup_bus_resources(struct zpci_dev *zdev, - struct list_head *resources) +int zpci_setup_bus_resources(struct zpci_dev *zdev) { unsigned long addr, size, flags; struct resource *res; @@ -581,7 +580,6 @@ int zpci_setup_bus_resources(struct zpci_dev *zdev, return -ENOMEM; } zdev->bars[i].res = res; - pci_add_resource(resources, res); } zdev->has_resources = 1; @@ -590,17 +588,23 @@ int zpci_setup_bus_resources(struct zpci_dev *zdev, static void zpci_cleanup_bus_resources(struct zpci_dev *zdev) { + struct resource *res; int i; + pci_lock_rescan_remove(); for (i = 0; i < PCI_STD_NUM_BARS; i++) { - if (!zdev->bars[i].size || !zdev->bars[i].res) + res = zdev->bars[i].res; + if (!res) continue; + release_resource(res); + pci_bus_remove_resource(zdev->zbus->bus, res); zpci_free_iomap(zdev, zdev->bars[i].map_idx); - release_resource(zdev->bars[i].res); - kfree(zdev->bars[i].res); + zdev->bars[i].res = NULL; + kfree(res); } zdev->has_resources = 0; + pci_unlock_rescan_remove(); } int pcibios_device_add(struct pci_dev *pdev) diff --git a/arch/s390/pci/pci_bus.c b/arch/s390/pci/pci_bus.c index 6a8da1b742ae..a99926af2b69 100644 --- a/arch/s390/pci/pci_bus.c +++ b/arch/s390/pci/pci_bus.c @@ -41,9 +41,7 @@ static int zpci_nb_devices; */ static int zpci_bus_prepare_device(struct zpci_dev *zdev) { - struct resource_entry *window, *n; - struct resource *res; - int rc; + int rc, i; if (!zdev_enabled(zdev)) { rc = zpci_enable_device(zdev); @@ -57,10 +55,10 @@ static int zpci_bus_prepare_device(struct zpci_dev *zdev) } if (!zdev->has_resources) { - zpci_setup_bus_resources(zdev, &zdev->zbus->resources); - resource_list_for_each_entry_safe(window, n, &zdev->zbus->resources) { - res = window->res; - pci_bus_add_resource(zdev->zbus->bus, res, 0); + zpci_setup_bus_resources(zdev); + for (i = 0; i < PCI_STD_NUM_BARS; i++) { + if (zdev->bars[i].res) + pci_bus_add_resource(zdev->zbus->bus, zdev->bars[i].res, 0); } } diff --git a/arch/s390/pci/pci_bus.h b/arch/s390/pci/pci_bus.h index e96c9860e064..af9f0ac79a1b 100644 --- a/arch/s390/pci/pci_bus.h +++ b/arch/s390/pci/pci_bus.h @@ -30,8 +30,7 @@ static inline void zpci_zdev_get(struct zpci_dev *zdev) int zpci_alloc_domain(int domain); void zpci_free_domain(int domain); -int zpci_setup_bus_resources(struct zpci_dev *zdev, - struct list_head *resources); +int zpci_setup_bus_resources(struct zpci_dev *zdev); static inline struct zpci_dev *zdev_from_bus(struct pci_bus *bus, unsigned int devfn) diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c index 83ae838ceb5f..549c4bd5caec 100644 --- a/drivers/pci/bus.c +++ b/drivers/pci/bus.c @@ -76,6 +76,27 @@ struct resource *pci_bus_resource_n(const struct pci_bus *bus, int n) } EXPORT_SYMBOL_GPL(pci_bus_resource_n); +void pci_bus_remove_resource(struct pci_bus *bus, struct resource *res) +{ + struct pci_bus_resource *bus_res, *tmp; + int i; + + for (i = 0; i < PCI_BRIDGE_RESOURCE_NUM; i++) { + if (bus->resource[i] == res) { + bus->resource[i] = NULL; + return; + } + } + + list_for_each_entry_safe(bus_res, tmp, &bus->resources, list) { + if (bus_res->res == res) { + list_del(&bus_res->list); + kfree(bus_res); + return; + } + } +} + void pci_bus_remove_resources(struct pci_bus *bus) { int i; diff --git a/include/linux/pci.h b/include/linux/pci.h index fafd8020c6d7..b50e5c79f7e3 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1438,6 +1438,7 @@ void pci_bus_add_resource(struct pci_bus *bus, struct resource *res, unsigned int flags); struct resource *pci_bus_resource_n(const struct pci_bus *bus, int n); void pci_bus_remove_resources(struct pci_bus *bus); +void pci_bus_remove_resource(struct pci_bus *bus, struct resource *res); int devm_request_pci_bus_resources(struct device *dev, struct list_head *resources); -- cgit v1.2.3 From 8b3a149db461d3286d1e211112de3b44ccaeaf71 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Sun, 12 Mar 2023 23:00:03 +0100 Subject: efi: earlycon: Reprobe after parsing config tables Commit 732ea9db9d8a ("efi: libstub: Move screen_info handling to common code") reorganized the earlycon handling so that all architectures pass the screen_info data via a EFI config table instead of populating struct screen_info directly, as the latter is only possible when the EFI stub is baked into the kernel (and not into the decompressor). However, this means that struct screen_info may not have been populated yet by the time the earlycon probe takes place, and this results in a non-functional early console. So let's probe again right after parsing the config tables and populating struct screen_info. Note that this means that earlycon output starts a bit later than before, and so it may fail to capture issues that occur while doing the early EFI initialization. Fixes: 732ea9db9d8a ("efi: libstub: Move screen_info handling to common code") Reported-by: Shawn Guo Tested-by: Shawn Guo Signed-off-by: Ard Biesheuvel --- drivers/firmware/efi/earlycon.c | 16 +++++++++++++--- drivers/firmware/efi/efi-init.c | 3 +++ include/linux/efi.h | 1 + 3 files changed, 17 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/firmware/efi/earlycon.c b/drivers/firmware/efi/earlycon.c index f54e6fdf08e2..f80a9af3d16e 100644 --- a/drivers/firmware/efi/earlycon.c +++ b/drivers/firmware/efi/earlycon.c @@ -215,6 +215,14 @@ efi_earlycon_write(struct console *con, const char *str, unsigned int num) } } +static bool __initdata fb_probed; + +void __init efi_earlycon_reprobe(void) +{ + if (fb_probed) + setup_earlycon("efifb"); +} + static int __init efi_earlycon_setup(struct earlycon_device *device, const char *opt) { @@ -222,15 +230,17 @@ static int __init efi_earlycon_setup(struct earlycon_device *device, u16 xres, yres; u32 i; - if (screen_info.orig_video_isVGA != VIDEO_TYPE_EFI) + fb_wb = opt && !strcmp(opt, "ram"); + + if (screen_info.orig_video_isVGA != VIDEO_TYPE_EFI) { + fb_probed = true; return -ENODEV; + } fb_base = screen_info.lfb_base; if (screen_info.capabilities & VIDEO_CAPABILITY_64BIT_BASE) fb_base |= (u64)screen_info.ext_lfb_base << 32; - fb_wb = opt && !strcmp(opt, "ram"); - si = &screen_info; xres = si->lfb_width; yres = si->lfb_height; diff --git a/drivers/firmware/efi/efi-init.c b/drivers/firmware/efi/efi-init.c index 2c16080e1f71..ef0820f1a924 100644 --- a/drivers/firmware/efi/efi-init.c +++ b/drivers/firmware/efi/efi-init.c @@ -72,6 +72,9 @@ static void __init init_screen_info(void) if (memblock_is_map_memory(screen_info.lfb_base)) memblock_mark_nomap(screen_info.lfb_base, screen_info.lfb_size); + + if (IS_ENABLED(CONFIG_EFI_EARLYCON)) + efi_earlycon_reprobe(); } } diff --git a/include/linux/efi.h b/include/linux/efi.h index 04a733f0ba95..7aa62c92185f 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -693,6 +693,7 @@ efi_guid_to_str(efi_guid_t *guid, char *out) } extern void efi_init (void); +extern void efi_earlycon_reprobe(void); #ifdef CONFIG_EFI extern void efi_enter_virtual_mode (void); /* switch EFI to virtual mode, if possible */ #else -- cgit v1.2.3 From 34e0a279a993debaff03158fc2fbf6a00c093643 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 13 Mar 2023 10:30:02 +0100 Subject: block: do not reverse request order when flushing plug list Commit 26fed4ac4eab ("block: flush plug based on hardware and software queue order") changed flushing of plug list to submit requests one device at a time. However while doing that it also started using list_add_tail() instead of list_add() used previously thus effectively submitting requests in reverse order. Also when forming a rq_list with remaining requests (in case two or more devices are used), we effectively reverse the ordering of the plug list for each device we process. Submitting requests in reverse order has negative impact on performance for rotational disks (when BFQ is not in use). We observe 10-25% regression in random 4k write throughput, as well as ~20% regression in MariaDB OLTP benchmark on rotational storage on btrfs filesystem. Fix the problem by preserving ordering of the plug list when inserting requests into the queuelist as well as by appending to requeue_list instead of prepending to it. Fixes: 26fed4ac4eab ("block: flush plug based on hardware and software queue order") Signed-off-by: Jan Kara Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20230313093002.11756-1-jack@suse.cz Signed-off-by: Jens Axboe --- block/blk-mq.c | 5 +++-- include/linux/blk-mq.h | 6 ++++++ 2 files changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/block/blk-mq.c b/block/blk-mq.c index d0cb2ef18fe2..cf1a39adf9a5 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2725,6 +2725,7 @@ static void blk_mq_dispatch_plug_list(struct blk_plug *plug, bool from_sched) struct blk_mq_hw_ctx *this_hctx = NULL; struct blk_mq_ctx *this_ctx = NULL; struct request *requeue_list = NULL; + struct request **requeue_lastp = &requeue_list; unsigned int depth = 0; LIST_HEAD(list); @@ -2735,10 +2736,10 @@ static void blk_mq_dispatch_plug_list(struct blk_plug *plug, bool from_sched) this_hctx = rq->mq_hctx; this_ctx = rq->mq_ctx; } else if (this_hctx != rq->mq_hctx || this_ctx != rq->mq_ctx) { - rq_list_add(&requeue_list, rq); + rq_list_add_tail(&requeue_lastp, rq); continue; } - list_add_tail(&rq->queuelist, &list); + list_add(&rq->queuelist, &list); depth++; } while (!rq_list_empty(plug->mq_list)); diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index dd5ce1137f04..de0b0c3e7395 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -228,6 +228,12 @@ static inline unsigned short req_get_ioprio(struct request *req) *(listptr) = rq; \ } while (0) +#define rq_list_add_tail(lastpptr, rq) do { \ + (rq)->rq_next = NULL; \ + **(lastpptr) = rq; \ + *(lastpptr) = &rq->rq_next; \ +} while (0) + #define rq_list_pop(listptr) \ ({ \ struct request *__req = NULL; \ -- cgit v1.2.3 From 7ff84910c66c9144cc0de9d9deed9fb84c03aff0 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Tue, 14 Mar 2023 06:20:58 -0400 Subject: lockd: set file_lock start and end when decoding nlm4 testargs Commit 6930bcbfb6ce dropped the setting of the file_lock range when decoding a nlm_lock off the wire. This causes the client side grant callback to miss matching blocks and reject the lock, only to rerequest it 30s later. Add a helper function to set the file_lock range from the start and end values that the protocol uses, and have the nlm_lock decoder call that to set up the file_lock args properly. Fixes: 6930bcbfb6ce ("lockd: detect and reject lock arguments that overflow") Reported-by: Amir Goldstein Signed-off-by: Jeff Layton Tested-by: Amir Goldstein Cc: stable@vger.kernel.org #6.0 Signed-off-by: Anna Schumaker --- fs/lockd/clnt4xdr.c | 9 +-------- fs/lockd/xdr4.c | 13 ++++++++++++- include/linux/lockd/xdr4.h | 1 + 3 files changed, 14 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/fs/lockd/clnt4xdr.c b/fs/lockd/clnt4xdr.c index 7df6324ccb8a..8161667c976f 100644 --- a/fs/lockd/clnt4xdr.c +++ b/fs/lockd/clnt4xdr.c @@ -261,7 +261,6 @@ static int decode_nlm4_holder(struct xdr_stream *xdr, struct nlm_res *result) u32 exclusive; int error; __be32 *p; - s32 end; memset(lock, 0, sizeof(*lock)); locks_init_lock(fl); @@ -285,13 +284,7 @@ static int decode_nlm4_holder(struct xdr_stream *xdr, struct nlm_res *result) fl->fl_type = exclusive != 0 ? F_WRLCK : F_RDLCK; p = xdr_decode_hyper(p, &l_offset); xdr_decode_hyper(p, &l_len); - end = l_offset + l_len - 1; - - fl->fl_start = (loff_t)l_offset; - if (l_len == 0 || end < 0) - fl->fl_end = OFFSET_MAX; - else - fl->fl_end = (loff_t)end; + nlm4svc_set_file_lock_range(fl, l_offset, l_len); error = 0; out: return error; diff --git a/fs/lockd/xdr4.c b/fs/lockd/xdr4.c index 712fdfeb8ef0..5fcbf30cd275 100644 --- a/fs/lockd/xdr4.c +++ b/fs/lockd/xdr4.c @@ -33,6 +33,17 @@ loff_t_to_s64(loff_t offset) return res; } +void nlm4svc_set_file_lock_range(struct file_lock *fl, u64 off, u64 len) +{ + s64 end = off + len - 1; + + fl->fl_start = off; + if (len == 0 || end < 0) + fl->fl_end = OFFSET_MAX; + else + fl->fl_end = end; +} + /* * NLM file handles are defined by specification to be a variable-length * XDR opaque no longer than 1024 bytes. However, this implementation @@ -80,7 +91,7 @@ svcxdr_decode_lock(struct xdr_stream *xdr, struct nlm_lock *lock) locks_init_lock(fl); fl->fl_flags = FL_POSIX; fl->fl_type = F_RDLCK; - + nlm4svc_set_file_lock_range(fl, lock->lock_start, lock->lock_len); return true; } diff --git a/include/linux/lockd/xdr4.h b/include/linux/lockd/xdr4.h index 9a6b55da8fd6..72831e35dca3 100644 --- a/include/linux/lockd/xdr4.h +++ b/include/linux/lockd/xdr4.h @@ -22,6 +22,7 @@ #define nlm4_fbig cpu_to_be32(NLM_FBIG) #define nlm4_failed cpu_to_be32(NLM_FAILED) +void nlm4svc_set_file_lock_range(struct file_lock *fl, u64 off, u64 len); bool nlm4svc_decode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr); bool nlm4svc_decode_testargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); bool nlm4svc_decode_lockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); -- cgit v1.2.3 From c2679254b9c9980d9045f0f722cf093a2b1f7590 Mon Sep 17 00:00:00 2001 From: Steven Rostedt (Google) Date: Fri, 10 Mar 2023 17:28:56 -0500 Subject: tracing: Make tracepoint lockdep check actually test something A while ago where the trace events had the following: rcu_read_lock_sched_notrace(); rcu_dereference_sched(...); rcu_read_unlock_sched_notrace(); If the tracepoint is enabled, it could trigger RCU issues if called in the wrong place. And this warning was only triggered if lockdep was enabled. If the tracepoint was never enabled with lockdep, the bug would not be caught. To handle this, the above sequence was done when lockdep was enabled regardless if the tracepoint was enabled or not (although the always enabled code really didn't do anything, it would still trigger a warning). But a lot has changed since that lockdep code was added. One is, that sequence no longer triggers any warning. Another is, the tracepoint when enabled doesn't even do that sequence anymore. The main check we care about today is whether RCU is "watching" or not. So if lockdep is enabled, always check if rcu_is_watching() which will trigger a warning if it is not (tracepoints require RCU to be watching). Note, that old sequence did add a bit of overhead when lockdep was enabled, and with the latest kernel updates, would cause the system to slow down enough to trigger kernel "stalled" warnings. Link: http://lore.kernel.org/lkml/20140806181801.GA4605@redhat.com Link: http://lore.kernel.org/lkml/20140807175204.C257CAC5@viggo.jf.intel.com Link: https://lore.kernel.org/lkml/20230307184645.521db5c9@gandalf.local.home/ Link: https://lore.kernel.org/linux-trace-kernel/20230310172856.77406446@gandalf.local.home Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Dave Hansen Cc: "Paul E. McKenney" Cc: Mathieu Desnoyers Cc: Joel Fernandes Acked-by: Peter Zijlstra (Intel) Acked-by: Paul E. McKenney Fixes: e6753f23d961 ("tracepoint: Make rcuidle tracepoint callers use SRCU") Signed-off-by: Steven Rostedt (Google) --- include/linux/tracepoint.h | 15 ++++++--------- 1 file changed, 6 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index fa1004fcf810..2083f2d2f05b 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -231,12 +231,11 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) * not add unwanted padding between the beginning of the section and the * structure. Force alignment to the same alignment as the section start. * - * When lockdep is enabled, we make sure to always do the RCU portions of - * the tracepoint code, regardless of whether tracing is on. However, - * don't check if the condition is false, due to interaction with idle - * instrumentation. This lets us find RCU issues triggered with tracepoints - * even when this tracepoint is off. This code has no purpose other than - * poking RCU a bit. + * When lockdep is enabled, we make sure to always test if RCU is + * "watching" regardless if the tracepoint is enabled or not. Tracepoints + * require RCU to be active, and it should always warn at the tracepoint + * site if it is not watching, as it will need to be active when the + * tracepoint is enabled. */ #define __DECLARE_TRACE(name, proto, args, cond, data_proto) \ extern int __traceiter_##name(data_proto); \ @@ -249,9 +248,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) TP_ARGS(args), \ TP_CONDITION(cond), 0); \ if (IS_ENABLED(CONFIG_LOCKDEP) && (cond)) { \ - rcu_read_lock_sched_notrace(); \ - rcu_dereference_sched(__tracepoint_##name.funcs);\ - rcu_read_unlock_sched_notrace(); \ + WARN_ON_ONCE(!rcu_is_watching()); \ } \ } \ __DECLARE_TRACE_RCU(name, PARAMS(proto), PARAMS(args), \ -- cgit v1.2.3 From 4b397c06cb987935b1b097336532aa6b4210e091 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 10 Mar 2023 19:11:09 +0000 Subject: net: tunnels: annotate lockless accesses to dev->needed_headroom IP tunnels can apparently update dev->needed_headroom in their xmit path. This patch takes care of three tunnels xmit, and also the core LL_RESERVED_SPACE() and LL_RESERVED_SPACE_EXTRA() helpers. More changes might be needed for completeness. BUG: KCSAN: data-race in ip_tunnel_xmit / ip_tunnel_xmit read to 0xffff88815b9da0ec of 2 bytes by task 888 on cpu 1: ip_tunnel_xmit+0x1270/0x1730 net/ipv4/ip_tunnel.c:803 __gre_xmit net/ipv4/ip_gre.c:469 [inline] ipgre_xmit+0x516/0x570 net/ipv4/ip_gre.c:661 __netdev_start_xmit include/linux/netdevice.h:4881 [inline] netdev_start_xmit include/linux/netdevice.h:4895 [inline] xmit_one net/core/dev.c:3580 [inline] dev_hard_start_xmit+0x127/0x400 net/core/dev.c:3596 __dev_queue_xmit+0x1007/0x1eb0 net/core/dev.c:4246 dev_queue_xmit include/linux/netdevice.h:3051 [inline] neigh_direct_output+0x17/0x20 net/core/neighbour.c:1623 neigh_output include/net/neighbour.h:546 [inline] ip_finish_output2+0x740/0x840 net/ipv4/ip_output.c:228 ip_finish_output+0xf4/0x240 net/ipv4/ip_output.c:316 NF_HOOK_COND include/linux/netfilter.h:291 [inline] ip_output+0xe5/0x1b0 net/ipv4/ip_output.c:430 dst_output include/net/dst.h:444 [inline] ip_local_out+0x64/0x80 net/ipv4/ip_output.c:126 iptunnel_xmit+0x34a/0x4b0 net/ipv4/ip_tunnel_core.c:82 ip_tunnel_xmit+0x1451/0x1730 net/ipv4/ip_tunnel.c:813 __gre_xmit net/ipv4/ip_gre.c:469 [inline] ipgre_xmit+0x516/0x570 net/ipv4/ip_gre.c:661 __netdev_start_xmit include/linux/netdevice.h:4881 [inline] netdev_start_xmit include/linux/netdevice.h:4895 [inline] xmit_one net/core/dev.c:3580 [inline] dev_hard_start_xmit+0x127/0x400 net/core/dev.c:3596 __dev_queue_xmit+0x1007/0x1eb0 net/core/dev.c:4246 dev_queue_xmit include/linux/netdevice.h:3051 [inline] neigh_direct_output+0x17/0x20 net/core/neighbour.c:1623 neigh_output include/net/neighbour.h:546 [inline] ip_finish_output2+0x740/0x840 net/ipv4/ip_output.c:228 ip_finish_output+0xf4/0x240 net/ipv4/ip_output.c:316 NF_HOOK_COND include/linux/netfilter.h:291 [inline] ip_output+0xe5/0x1b0 net/ipv4/ip_output.c:430 dst_output include/net/dst.h:444 [inline] ip_local_out+0x64/0x80 net/ipv4/ip_output.c:126 iptunnel_xmit+0x34a/0x4b0 net/ipv4/ip_tunnel_core.c:82 ip_tunnel_xmit+0x1451/0x1730 net/ipv4/ip_tunnel.c:813 __gre_xmit net/ipv4/ip_gre.c:469 [inline] ipgre_xmit+0x516/0x570 net/ipv4/ip_gre.c:661 __netdev_start_xmit include/linux/netdevice.h:4881 [inline] netdev_start_xmit include/linux/netdevice.h:4895 [inline] xmit_one net/core/dev.c:3580 [inline] dev_hard_start_xmit+0x127/0x400 net/core/dev.c:3596 __dev_queue_xmit+0x1007/0x1eb0 net/core/dev.c:4246 dev_queue_xmit include/linux/netdevice.h:3051 [inline] neigh_direct_output+0x17/0x20 net/core/neighbour.c:1623 neigh_output include/net/neighbour.h:546 [inline] ip_finish_output2+0x740/0x840 net/ipv4/ip_output.c:228 ip_finish_output+0xf4/0x240 net/ipv4/ip_output.c:316 NF_HOOK_COND include/linux/netfilter.h:291 [inline] ip_output+0xe5/0x1b0 net/ipv4/ip_output.c:430 dst_output include/net/dst.h:444 [inline] ip_local_out+0x64/0x80 net/ipv4/ip_output.c:126 iptunnel_xmit+0x34a/0x4b0 net/ipv4/ip_tunnel_core.c:82 ip_tunnel_xmit+0x1451/0x1730 net/ipv4/ip_tunnel.c:813 __gre_xmit net/ipv4/ip_gre.c:469 [inline] ipgre_xmit+0x516/0x570 net/ipv4/ip_gre.c:661 __netdev_start_xmit include/linux/netdevice.h:4881 [inline] netdev_start_xmit include/linux/netdevice.h:4895 [inline] xmit_one net/core/dev.c:3580 [inline] dev_hard_start_xmit+0x127/0x400 net/core/dev.c:3596 __dev_queue_xmit+0x1007/0x1eb0 net/core/dev.c:4246 dev_queue_xmit include/linux/netdevice.h:3051 [inline] neigh_direct_output+0x17/0x20 net/core/neighbour.c:1623 neigh_output include/net/neighbour.h:546 [inline] ip_finish_output2+0x740/0x840 net/ipv4/ip_output.c:228 ip_finish_output+0xf4/0x240 net/ipv4/ip_output.c:316 NF_HOOK_COND include/linux/netfilter.h:291 [inline] ip_output+0xe5/0x1b0 net/ipv4/ip_output.c:430 dst_output include/net/dst.h:444 [inline] ip_local_out+0x64/0x80 net/ipv4/ip_output.c:126 iptunnel_xmit+0x34a/0x4b0 net/ipv4/ip_tunnel_core.c:82 ip_tunnel_xmit+0x1451/0x1730 net/ipv4/ip_tunnel.c:813 __gre_xmit net/ipv4/ip_gre.c:469 [inline] ipgre_xmit+0x516/0x570 net/ipv4/ip_gre.c:661 __netdev_start_xmit include/linux/netdevice.h:4881 [inline] netdev_start_xmit include/linux/netdevice.h:4895 [inline] xmit_one net/core/dev.c:3580 [inline] dev_hard_start_xmit+0x127/0x400 net/core/dev.c:3596 __dev_queue_xmit+0x1007/0x1eb0 net/core/dev.c:4246 dev_queue_xmit include/linux/netdevice.h:3051 [inline] neigh_direct_output+0x17/0x20 net/core/neighbour.c:1623 neigh_output include/net/neighbour.h:546 [inline] ip_finish_output2+0x740/0x840 net/ipv4/ip_output.c:228 ip_finish_output+0xf4/0x240 net/ipv4/ip_output.c:316 NF_HOOK_COND include/linux/netfilter.h:291 [inline] ip_output+0xe5/0x1b0 net/ipv4/ip_output.c:430 dst_output include/net/dst.h:444 [inline] ip_local_out+0x64/0x80 net/ipv4/ip_output.c:126 iptunnel_xmit+0x34a/0x4b0 net/ipv4/ip_tunnel_core.c:82 ip_tunnel_xmit+0x1451/0x1730 net/ipv4/ip_tunnel.c:813 __gre_xmit net/ipv4/ip_gre.c:469 [inline] ipgre_xmit+0x516/0x570 net/ipv4/ip_gre.c:661 __netdev_start_xmit include/linux/netdevice.h:4881 [inline] netdev_start_xmit include/linux/netdevice.h:4895 [inline] xmit_one net/core/dev.c:3580 [inline] dev_hard_start_xmit+0x127/0x400 net/core/dev.c:3596 __dev_queue_xmit+0x1007/0x1eb0 net/core/dev.c:4246 dev_queue_xmit include/linux/netdevice.h:3051 [inline] neigh_direct_output+0x17/0x20 net/core/neighbour.c:1623 neigh_output include/net/neighbour.h:546 [inline] ip_finish_output2+0x740/0x840 net/ipv4/ip_output.c:228 ip_finish_output+0xf4/0x240 net/ipv4/ip_output.c:316 NF_HOOK_COND include/linux/netfilter.h:291 [inline] ip_output+0xe5/0x1b0 net/ipv4/ip_output.c:430 dst_output include/net/dst.h:444 [inline] ip_local_out+0x64/0x80 net/ipv4/ip_output.c:126 iptunnel_xmit+0x34a/0x4b0 net/ipv4/ip_tunnel_core.c:82 ip_tunnel_xmit+0x1451/0x1730 net/ipv4/ip_tunnel.c:813 __gre_xmit net/ipv4/ip_gre.c:469 [inline] ipgre_xmit+0x516/0x570 net/ipv4/ip_gre.c:661 __netdev_start_xmit include/linux/netdevice.h:4881 [inline] netdev_start_xmit include/linux/netdevice.h:4895 [inline] xmit_one net/core/dev.c:3580 [inline] dev_hard_start_xmit+0x127/0x400 net/core/dev.c:3596 __dev_queue_xmit+0x1007/0x1eb0 net/core/dev.c:4246 write to 0xffff88815b9da0ec of 2 bytes by task 2379 on cpu 0: ip_tunnel_xmit+0x1294/0x1730 net/ipv4/ip_tunnel.c:804 __gre_xmit net/ipv4/ip_gre.c:469 [inline] ipgre_xmit+0x516/0x570 net/ipv4/ip_gre.c:661 __netdev_start_xmit include/linux/netdevice.h:4881 [inline] netdev_start_xmit include/linux/netdevice.h:4895 [inline] xmit_one net/core/dev.c:3580 [inline] dev_hard_start_xmit+0x127/0x400 net/core/dev.c:3596 __dev_queue_xmit+0x1007/0x1eb0 net/core/dev.c:4246 dev_queue_xmit include/linux/netdevice.h:3051 [inline] neigh_direct_output+0x17/0x20 net/core/neighbour.c:1623 neigh_output include/net/neighbour.h:546 [inline] ip6_finish_output2+0x9bc/0xc50 net/ipv6/ip6_output.c:134 __ip6_finish_output net/ipv6/ip6_output.c:195 [inline] ip6_finish_output+0x39a/0x4e0 net/ipv6/ip6_output.c:206 NF_HOOK_COND include/linux/netfilter.h:291 [inline] ip6_output+0xeb/0x220 net/ipv6/ip6_output.c:227 dst_output include/net/dst.h:444 [inline] NF_HOOK include/linux/netfilter.h:302 [inline] mld_sendpack+0x438/0x6a0 net/ipv6/mcast.c:1820 mld_send_cr net/ipv6/mcast.c:2121 [inline] mld_ifc_work+0x519/0x7b0 net/ipv6/mcast.c:2653 process_one_work+0x3e6/0x750 kernel/workqueue.c:2390 worker_thread+0x5f2/0xa10 kernel/workqueue.c:2537 kthread+0x1ac/0x1e0 kernel/kthread.c:376 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:308 value changed: 0x0dd4 -> 0x0e14 Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 2379 Comm: kworker/0:0 Not tainted 6.3.0-rc1-syzkaller-00002-g8ca09d5fa354-dirty #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 03/02/2023 Workqueue: mld mld_ifc_work Fixes: 8eb30be0352d ("ipv6: Create ip6_tnl_xmit") Reported-by: syzbot Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20230310191109.2384387-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 6 ++++-- net/ipv4/ip_tunnel.c | 12 ++++++------ net/ipv6/ip6_tunnel.c | 4 ++-- 3 files changed, 12 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 6a14b7b11766..470085b121d3 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -297,9 +297,11 @@ struct hh_cache { * relationship HH alignment <= LL alignment. */ #define LL_RESERVED_SPACE(dev) \ - ((((dev)->hard_header_len+(dev)->needed_headroom)&~(HH_DATA_MOD - 1)) + HH_DATA_MOD) + ((((dev)->hard_header_len + READ_ONCE((dev)->needed_headroom)) \ + & ~(HH_DATA_MOD - 1)) + HH_DATA_MOD) #define LL_RESERVED_SPACE_EXTRA(dev,extra) \ - ((((dev)->hard_header_len+(dev)->needed_headroom+(extra))&~(HH_DATA_MOD - 1)) + HH_DATA_MOD) + ((((dev)->hard_header_len + READ_ONCE((dev)->needed_headroom) + (extra)) \ + & ~(HH_DATA_MOD - 1)) + HH_DATA_MOD) struct header_ops { int (*create) (struct sk_buff *skb, struct net_device *dev, diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index de90b09dfe78..2541083d49ad 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -614,10 +614,10 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, } headroom += LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len; - if (headroom > dev->needed_headroom) - dev->needed_headroom = headroom; + if (headroom > READ_ONCE(dev->needed_headroom)) + WRITE_ONCE(dev->needed_headroom, headroom); - if (skb_cow_head(skb, dev->needed_headroom)) { + if (skb_cow_head(skb, READ_ONCE(dev->needed_headroom))) { ip_rt_put(rt); goto tx_dropped; } @@ -800,10 +800,10 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, max_headroom = LL_RESERVED_SPACE(rt->dst.dev) + sizeof(struct iphdr) + rt->dst.header_len + ip_encap_hlen(&tunnel->encap); - if (max_headroom > dev->needed_headroom) - dev->needed_headroom = max_headroom; + if (max_headroom > READ_ONCE(dev->needed_headroom)) + WRITE_ONCE(dev->needed_headroom, max_headroom); - if (skb_cow_head(skb, dev->needed_headroom)) { + if (skb_cow_head(skb, READ_ONCE(dev->needed_headroom))) { ip_rt_put(rt); DEV_STATS_INC(dev, tx_dropped); kfree_skb(skb); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 47b6607a1370..5e80e517f071 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1240,8 +1240,8 @@ route_lookup: */ max_headroom = LL_RESERVED_SPACE(dst->dev) + sizeof(struct ipv6hdr) + dst->header_len + t->hlen; - if (max_headroom > dev->needed_headroom) - dev->needed_headroom = max_headroom; + if (max_headroom > READ_ONCE(dev->needed_headroom)) + WRITE_ONCE(dev->needed_headroom, max_headroom); err = ip6_tnl_encap(skb, t, &proto, fl6); if (err) -- cgit v1.2.3 From 8e19b87cfce2de2125f11363d7dea3d08f16ccae Mon Sep 17 00:00:00 2001 From: Minwoo Im Date: Thu, 9 Mar 2023 23:31:18 +0900 Subject: nvme-trace: show more opcode names We have more commands to show in the trace. Sync up. Signed-off-by: Minwoo Im Reviewed-by: Chaitanya Kulkarni Signed-off-by: Christoph Hellwig --- include/linux/nvme.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 4fad4aa245fb..779507ac750b 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -812,6 +812,7 @@ enum nvme_opcode { nvme_opcode_name(nvme_cmd_compare), \ nvme_opcode_name(nvme_cmd_write_zeroes), \ nvme_opcode_name(nvme_cmd_dsm), \ + nvme_opcode_name(nvme_cmd_verify), \ nvme_opcode_name(nvme_cmd_resv_register), \ nvme_opcode_name(nvme_cmd_resv_report), \ nvme_opcode_name(nvme_cmd_resv_acquire), \ @@ -1144,10 +1145,14 @@ enum nvme_admin_opcode { nvme_admin_opcode_name(nvme_admin_ns_mgmt), \ nvme_admin_opcode_name(nvme_admin_activate_fw), \ nvme_admin_opcode_name(nvme_admin_download_fw), \ + nvme_admin_opcode_name(nvme_admin_dev_self_test), \ nvme_admin_opcode_name(nvme_admin_ns_attach), \ nvme_admin_opcode_name(nvme_admin_keep_alive), \ nvme_admin_opcode_name(nvme_admin_directive_send), \ nvme_admin_opcode_name(nvme_admin_directive_recv), \ + nvme_admin_opcode_name(nvme_admin_virtual_mgmt), \ + nvme_admin_opcode_name(nvme_admin_nvme_mi_send), \ + nvme_admin_opcode_name(nvme_admin_nvme_mi_recv), \ nvme_admin_opcode_name(nvme_admin_dbbuf), \ nvme_admin_opcode_name(nvme_admin_format_nvm), \ nvme_admin_opcode_name(nvme_admin_security_send), \ -- cgit v1.2.3 From 5f27571382ca42daa3e3d40d1b252bf18c2b61d2 Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Thu, 23 Feb 2023 17:12:26 +0800 Subject: block: count 'ios' and 'sectors' when io is done for bio-based device While using iostat for raid, I observed very strange 'await' occasionally, and turns out it's due to that 'ios' and 'sectors' is counted in bdev_start_io_acct(), while 'nsecs' is counted in bdev_end_io_acct(). I'm not sure why they are ccounted like that but I think this behaviour is obviously wrong because user will get wrong disk stats. Fix the problem by counting 'ios' and 'sectors' when io is done, like what rq-based device does. Fixes: 394ffa503bc4 ("blk: introduce generic io stat accounting help function") Signed-off-by: Yu Kuai Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20230223091226.1135678-1-yukuai1@huaweicloud.com Signed-off-by: Jens Axboe --- block/blk-core.c | 16 ++++++---------- drivers/md/dm.c | 6 +++--- drivers/nvme/host/multipath.c | 8 ++++---- include/linux/blkdev.h | 5 ++--- 4 files changed, 15 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/block/blk-core.c b/block/blk-core.c index 9e5e0277a4d9..42926e6cb83c 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -959,16 +959,11 @@ again: } } -unsigned long bdev_start_io_acct(struct block_device *bdev, - unsigned int sectors, enum req_op op, +unsigned long bdev_start_io_acct(struct block_device *bdev, enum req_op op, unsigned long start_time) { - const int sgrp = op_stat_group(op); - part_stat_lock(); update_io_ticks(bdev, start_time, false); - part_stat_inc(bdev, ios[sgrp]); - part_stat_add(bdev, sectors[sgrp], sectors); part_stat_local_inc(bdev, in_flight[op_is_write(op)]); part_stat_unlock(); @@ -984,13 +979,12 @@ EXPORT_SYMBOL(bdev_start_io_acct); */ unsigned long bio_start_io_acct(struct bio *bio) { - return bdev_start_io_acct(bio->bi_bdev, bio_sectors(bio), - bio_op(bio), jiffies); + return bdev_start_io_acct(bio->bi_bdev, bio_op(bio), jiffies); } EXPORT_SYMBOL_GPL(bio_start_io_acct); void bdev_end_io_acct(struct block_device *bdev, enum req_op op, - unsigned long start_time) + unsigned int sectors, unsigned long start_time) { const int sgrp = op_stat_group(op); unsigned long now = READ_ONCE(jiffies); @@ -998,6 +992,8 @@ void bdev_end_io_acct(struct block_device *bdev, enum req_op op, part_stat_lock(); update_io_ticks(bdev, now, true); + part_stat_inc(bdev, ios[sgrp]); + part_stat_add(bdev, sectors[sgrp], sectors); part_stat_add(bdev, nsecs[sgrp], jiffies_to_nsecs(duration)); part_stat_local_dec(bdev, in_flight[op_is_write(op)]); part_stat_unlock(); @@ -1007,7 +1003,7 @@ EXPORT_SYMBOL(bdev_end_io_acct); void bio_end_io_acct_remapped(struct bio *bio, unsigned long start_time, struct block_device *orig_bdev) { - bdev_end_io_acct(orig_bdev, bio_op(bio), start_time); + bdev_end_io_acct(orig_bdev, bio_op(bio), bio_sectors(bio), start_time); } EXPORT_SYMBOL_GPL(bio_end_io_acct_remapped); diff --git a/drivers/md/dm.c b/drivers/md/dm.c index eace45a18d45..f5cc330bb549 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -512,10 +512,10 @@ static void dm_io_acct(struct dm_io *io, bool end) sectors = io->sectors; if (!end) - bdev_start_io_acct(bio->bi_bdev, sectors, bio_op(bio), - start_time); + bdev_start_io_acct(bio->bi_bdev, bio_op(bio), start_time); else - bdev_end_io_acct(bio->bi_bdev, bio_op(bio), start_time); + bdev_end_io_acct(bio->bi_bdev, bio_op(bio), sectors, + start_time); if (static_branch_unlikely(&stats_enabled) && unlikely(dm_stats_used(&md->stats))) { diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index fc39d01e7b63..9171452e2f6d 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -123,9 +123,8 @@ void nvme_mpath_start_request(struct request *rq) return; nvme_req(rq)->flags |= NVME_MPATH_IO_STATS; - nvme_req(rq)->start_time = bdev_start_io_acct(disk->part0, - blk_rq_bytes(rq) >> SECTOR_SHIFT, - req_op(rq), jiffies); + nvme_req(rq)->start_time = bdev_start_io_acct(disk->part0, req_op(rq), + jiffies); } EXPORT_SYMBOL_GPL(nvme_mpath_start_request); @@ -136,7 +135,8 @@ void nvme_mpath_end_request(struct request *rq) if (!(nvme_req(rq)->flags & NVME_MPATH_IO_STATS)) return; bdev_end_io_acct(ns->head->disk->part0, req_op(rq), - nvme_req(rq)->start_time); + blk_rq_bytes(rq) >> SECTOR_SHIFT, + nvme_req(rq)->start_time); } void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d1aee08f8c18..941304f17492 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1446,11 +1446,10 @@ static inline void blk_wake_io_task(struct task_struct *waiter) wake_up_process(waiter); } -unsigned long bdev_start_io_acct(struct block_device *bdev, - unsigned int sectors, enum req_op op, +unsigned long bdev_start_io_acct(struct block_device *bdev, enum req_op op, unsigned long start_time); void bdev_end_io_acct(struct block_device *bdev, enum req_op op, - unsigned long start_time); + unsigned int sectors, unsigned long start_time); unsigned long bio_start_io_acct(struct bio *bio); void bio_end_io_acct_remapped(struct bio *bio, unsigned long start_time, -- cgit v1.2.3 From 3615c78673c332b69aaacefbcde5937c5c706686 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Tue, 14 Mar 2023 13:31:02 +0100 Subject: efi: sysfb_efi: Fix DMI quirks not working for simpledrm Commit 8633ef82f101 ("drivers/firmware: consolidate EFI framebuffer setup for all arches") moved the sysfb_apply_efi_quirks() call in sysfb_init() from before the [sysfb_]parse_mode() call to after it. But sysfb_apply_efi_quirks() modifies the global screen_info struct which [sysfb_]parse_mode() parses, so doing it later is too late. This has broken all DMI based quirks for correcting wrong firmware efifb settings when simpledrm is used. To fix this move the sysfb_apply_efi_quirks() call back to its old place and split the new setup of the efifb_fwnode (which requires the platform_device) into its own function and call that at the place of the moved sysfb_apply_efi_quirks(pd) calls. Fixes: 8633ef82f101 ("drivers/firmware: consolidate EFI framebuffer setup for all arches") Cc: stable@vger.kernel.org Cc: Javier Martinez Canillas Cc: Thomas Zimmermann Signed-off-by: Hans de Goede Reviewed-by: Javier Martinez Canillas Signed-off-by: Ard Biesheuvel --- drivers/firmware/efi/sysfb_efi.c | 5 ++++- drivers/firmware/sysfb.c | 4 +++- drivers/firmware/sysfb_simplefb.c | 2 +- include/linux/sysfb.h | 9 +++++++-- 4 files changed, 15 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/firmware/efi/sysfb_efi.c b/drivers/firmware/efi/sysfb_efi.c index f06fdacc9bc8..e76d6803bdd0 100644 --- a/drivers/firmware/efi/sysfb_efi.c +++ b/drivers/firmware/efi/sysfb_efi.c @@ -341,7 +341,7 @@ static const struct fwnode_operations efifb_fwnode_ops = { #ifdef CONFIG_EFI static struct fwnode_handle efifb_fwnode; -__init void sysfb_apply_efi_quirks(struct platform_device *pd) +__init void sysfb_apply_efi_quirks(void) { if (screen_info.orig_video_isVGA != VIDEO_TYPE_EFI || !(screen_info.capabilities & VIDEO_CAPABILITY_SKIP_QUIRKS)) @@ -355,7 +355,10 @@ __init void sysfb_apply_efi_quirks(struct platform_device *pd) screen_info.lfb_height = temp; screen_info.lfb_linelength = 4 * screen_info.lfb_width; } +} +__init void sysfb_set_efifb_fwnode(struct platform_device *pd) +{ if (screen_info.orig_video_isVGA == VIDEO_TYPE_EFI && IS_ENABLED(CONFIG_PCI)) { fwnode_init(&efifb_fwnode, &efifb_fwnode_ops); pd->dev.fwnode = &efifb_fwnode; diff --git a/drivers/firmware/sysfb.c b/drivers/firmware/sysfb.c index 3fd3563d962b..3c197db42c9d 100644 --- a/drivers/firmware/sysfb.c +++ b/drivers/firmware/sysfb.c @@ -81,6 +81,8 @@ static __init int sysfb_init(void) if (disabled) goto unlock_mutex; + sysfb_apply_efi_quirks(); + /* try to create a simple-framebuffer device */ compatible = sysfb_parse_mode(si, &mode); if (compatible) { @@ -107,7 +109,7 @@ static __init int sysfb_init(void) goto unlock_mutex; } - sysfb_apply_efi_quirks(pd); + sysfb_set_efifb_fwnode(pd); ret = platform_device_add_data(pd, si, sizeof(*si)); if (ret) diff --git a/drivers/firmware/sysfb_simplefb.c b/drivers/firmware/sysfb_simplefb.c index ce9c007ed66f..82c64cb9f531 100644 --- a/drivers/firmware/sysfb_simplefb.c +++ b/drivers/firmware/sysfb_simplefb.c @@ -141,7 +141,7 @@ __init struct platform_device *sysfb_create_simplefb(const struct screen_info *s if (!pd) return ERR_PTR(-ENOMEM); - sysfb_apply_efi_quirks(pd); + sysfb_set_efifb_fwnode(pd); ret = platform_device_add_resources(pd, &res, 1); if (ret) diff --git a/include/linux/sysfb.h b/include/linux/sysfb.h index 8ba8b5be5567..c1ef5fc60a3c 100644 --- a/include/linux/sysfb.h +++ b/include/linux/sysfb.h @@ -70,11 +70,16 @@ static inline void sysfb_disable(void) #ifdef CONFIG_EFI extern struct efifb_dmi_info efifb_dmi_list[]; -void sysfb_apply_efi_quirks(struct platform_device *pd); +void sysfb_apply_efi_quirks(void); +void sysfb_set_efifb_fwnode(struct platform_device *pd); #else /* CONFIG_EFI */ -static inline void sysfb_apply_efi_quirks(struct platform_device *pd) +static inline void sysfb_apply_efi_quirks(void) +{ +} + +static inline void sysfb_set_efifb_fwnode(struct platform_device *pd) { } -- cgit v1.2.3 From 99669259f3361d759219811e670b7e0742668556 Mon Sep 17 00:00:00 2001 From: Maxime Bizon Date: Thu, 16 Mar 2023 16:33:16 -0700 Subject: net: mdio: fix owner field for mdio buses registered using device-tree Bus ownership is wrong when using of_mdiobus_register() to register an mdio bus. That function is not inline, so when it calls mdiobus_register() the wrong THIS_MODULE value is captured. Signed-off-by: Maxime Bizon Fixes: 90eff9096c01 ("net: phy: Allow splitting MDIO bus/device support from PHYs") [florian: fix kdoc, added Fixes tag] Signed-off-by: Florian Fainelli Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/mdio/of_mdio.c | 12 +++++++----- drivers/net/phy/mdio_devres.c | 11 ++++++----- include/linux/of_mdio.h | 22 +++++++++++++++++++--- 3 files changed, 32 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/mdio/of_mdio.c b/drivers/net/mdio/of_mdio.c index 510822d6d0d9..1e46e39f5f46 100644 --- a/drivers/net/mdio/of_mdio.c +++ b/drivers/net/mdio/of_mdio.c @@ -139,21 +139,23 @@ bool of_mdiobus_child_is_phy(struct device_node *child) EXPORT_SYMBOL(of_mdiobus_child_is_phy); /** - * of_mdiobus_register - Register mii_bus and create PHYs from the device tree + * __of_mdiobus_register - Register mii_bus and create PHYs from the device tree * @mdio: pointer to mii_bus structure * @np: pointer to device_node of MDIO bus. + * @owner: module owning the @mdio object. * * This function registers the mii_bus structure and registers a phy_device * for each child node of @np. */ -int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np) +int __of_mdiobus_register(struct mii_bus *mdio, struct device_node *np, + struct module *owner) { struct device_node *child; bool scanphys = false; int addr, rc; if (!np) - return mdiobus_register(mdio); + return __mdiobus_register(mdio, owner); /* Do not continue if the node is disabled */ if (!of_device_is_available(np)) @@ -172,7 +174,7 @@ int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np) of_property_read_u32(np, "reset-post-delay-us", &mdio->reset_post_delay_us); /* Register the MDIO bus */ - rc = mdiobus_register(mdio); + rc = __mdiobus_register(mdio, owner); if (rc) return rc; @@ -236,7 +238,7 @@ unregister: mdiobus_unregister(mdio); return rc; } -EXPORT_SYMBOL(of_mdiobus_register); +EXPORT_SYMBOL(__of_mdiobus_register); /** * of_mdio_find_device - Given a device tree node, find the mdio_device diff --git a/drivers/net/phy/mdio_devres.c b/drivers/net/phy/mdio_devres.c index b560e99695df..69b829e6ab35 100644 --- a/drivers/net/phy/mdio_devres.c +++ b/drivers/net/phy/mdio_devres.c @@ -98,13 +98,14 @@ EXPORT_SYMBOL(__devm_mdiobus_register); #if IS_ENABLED(CONFIG_OF_MDIO) /** - * devm_of_mdiobus_register - Resource managed variant of of_mdiobus_register() + * __devm_of_mdiobus_register - Resource managed variant of of_mdiobus_register() * @dev: Device to register mii_bus for * @mdio: MII bus structure to register * @np: Device node to parse + * @owner: Owning module */ -int devm_of_mdiobus_register(struct device *dev, struct mii_bus *mdio, - struct device_node *np) +int __devm_of_mdiobus_register(struct device *dev, struct mii_bus *mdio, + struct device_node *np, struct module *owner) { struct mdiobus_devres *dr; int ret; @@ -117,7 +118,7 @@ int devm_of_mdiobus_register(struct device *dev, struct mii_bus *mdio, if (!dr) return -ENOMEM; - ret = of_mdiobus_register(mdio, np); + ret = __of_mdiobus_register(mdio, np, owner); if (ret) { devres_free(dr); return ret; @@ -127,7 +128,7 @@ int devm_of_mdiobus_register(struct device *dev, struct mii_bus *mdio, devres_add(dev, dr); return 0; } -EXPORT_SYMBOL(devm_of_mdiobus_register); +EXPORT_SYMBOL(__devm_of_mdiobus_register); #endif /* CONFIG_OF_MDIO */ MODULE_LICENSE("GPL"); diff --git a/include/linux/of_mdio.h b/include/linux/of_mdio.h index da633d34ab86..8a52ef2e6fa6 100644 --- a/include/linux/of_mdio.h +++ b/include/linux/of_mdio.h @@ -14,9 +14,25 @@ #if IS_ENABLED(CONFIG_OF_MDIO) bool of_mdiobus_child_is_phy(struct device_node *child); -int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np); -int devm_of_mdiobus_register(struct device *dev, struct mii_bus *mdio, - struct device_node *np); +int __of_mdiobus_register(struct mii_bus *mdio, struct device_node *np, + struct module *owner); + +static inline int of_mdiobus_register(struct mii_bus *mdio, + struct device_node *np) +{ + return __of_mdiobus_register(mdio, np, THIS_MODULE); +} + +int __devm_of_mdiobus_register(struct device *dev, struct mii_bus *mdio, + struct device_node *np, struct module *owner); + +static inline int devm_of_mdiobus_register(struct device *dev, + struct mii_bus *mdio, + struct device_node *np) +{ + return __devm_of_mdiobus_register(dev, mdio, np, THIS_MODULE); +} + struct mdio_device *of_mdio_find_device(struct device_node *np); struct phy_device *of_phy_find_device(struct device_node *phy_np); struct phy_device * -- cgit v1.2.3 From 30b605b8501e321f79e19c3238aa6ca31da6087c Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Thu, 16 Mar 2023 16:33:17 -0700 Subject: net: mdio: fix owner field for mdio buses registered using ACPI Bus ownership is wrong when using acpi_mdiobus_register() to register an mdio bus. That function is not inline, so when it calls mdiobus_register() the wrong THIS_MODULE value is captured. CC: Maxime Bizon Fixes: 803ca24d2f92 ("net: mdio: Add ACPI support code for mdio") Signed-off-by: Florian Fainelli Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/mdio/acpi_mdio.c | 10 ++++++---- include/linux/acpi_mdio.h | 9 ++++++++- 2 files changed, 14 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/mdio/acpi_mdio.c b/drivers/net/mdio/acpi_mdio.c index d77c987fda9c..4630dde01974 100644 --- a/drivers/net/mdio/acpi_mdio.c +++ b/drivers/net/mdio/acpi_mdio.c @@ -18,16 +18,18 @@ MODULE_AUTHOR("Calvin Johnson "); MODULE_LICENSE("GPL"); /** - * acpi_mdiobus_register - Register mii_bus and create PHYs from the ACPI ASL. + * __acpi_mdiobus_register - Register mii_bus and create PHYs from the ACPI ASL. * @mdio: pointer to mii_bus structure * @fwnode: pointer to fwnode of MDIO bus. This fwnode is expected to represent + * @owner: module owning this @mdio object. * an ACPI device object corresponding to the MDIO bus and its children are * expected to correspond to the PHY devices on that bus. * * This function registers the mii_bus structure and registers a phy_device * for each child node of @fwnode. */ -int acpi_mdiobus_register(struct mii_bus *mdio, struct fwnode_handle *fwnode) +int __acpi_mdiobus_register(struct mii_bus *mdio, struct fwnode_handle *fwnode, + struct module *owner) { struct fwnode_handle *child; u32 addr; @@ -35,7 +37,7 @@ int acpi_mdiobus_register(struct mii_bus *mdio, struct fwnode_handle *fwnode) /* Mask out all PHYs from auto probing. */ mdio->phy_mask = GENMASK(31, 0); - ret = mdiobus_register(mdio); + ret = __mdiobus_register(mdio, owner); if (ret) return ret; @@ -55,4 +57,4 @@ int acpi_mdiobus_register(struct mii_bus *mdio, struct fwnode_handle *fwnode) } return 0; } -EXPORT_SYMBOL(acpi_mdiobus_register); +EXPORT_SYMBOL(__acpi_mdiobus_register); diff --git a/include/linux/acpi_mdio.h b/include/linux/acpi_mdio.h index 0a24ab7cb66f..8e2eefa9fbc0 100644 --- a/include/linux/acpi_mdio.h +++ b/include/linux/acpi_mdio.h @@ -9,7 +9,14 @@ #include #if IS_ENABLED(CONFIG_ACPI_MDIO) -int acpi_mdiobus_register(struct mii_bus *mdio, struct fwnode_handle *fwnode); +int __acpi_mdiobus_register(struct mii_bus *mdio, struct fwnode_handle *fwnode, + struct module *owner); + +static inline int +acpi_mdiobus_register(struct mii_bus *mdio, struct fwnode_handle *handle) +{ + return __acpi_mdiobus_register(mdio, handle, THIS_MODULE); +} #else /* CONFIG_ACPI_MDIO */ static inline int acpi_mdiobus_register(struct mii_bus *mdio, struct fwnode_handle *fwnode) -- cgit v1.2.3 From 070246e4674b125860d311c18ce2623e73e2bd51 Mon Sep 17 00:00:00 2001 From: Jochen Henneberg Date: Fri, 17 Mar 2023 09:08:17 +0100 Subject: net: stmmac: Fix for mismatched host/device DMA address width Currently DMA address width is either read from a RO device register or force set from the platform data. This breaks DMA when the host DMA address width is <=32it but the device is >32bit. Right now the driver may decide to use a 2nd DMA descriptor for another buffer (happens in case of TSO xmit) assuming that 32bit addressing is used due to platform configuration but the device will still use both descriptor addresses as one address. This can be observed with the Intel EHL platform driver that sets 32bit for addr64 but the MAC reports 40bit. The TX queue gets stuck in case of TCP with iptables NAT configuration on TSO packets. The logic should be like this: Whatever we do on the host side (memory allocation GFP flags) should happen with the host DMA width, whenever we decide how to set addresses on the device registers we must use the device DMA address width. This patch renames the platform address width field from addr64 (term used in device datasheet) to host_addr and uses this value exclusively for host side operations while all chip operations consider the device DMA width as read from the device register. Fixes: 7cfc4486e7ea ("stmmac: intel: Configure EHL PSE0 GbE and PSE1 GbE to 32 bits DMA addressing") Signed-off-by: Jochen Henneberg Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/common.h | 1 + drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c | 2 +- drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c | 4 +-- .../net/ethernet/stmicro/stmmac/dwmac-mediatek.c | 2 +- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 30 ++++++++++++---------- include/linux/stmmac.h | 2 +- 6 files changed, 22 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index 6b5d96bced47..ec9c130276d8 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -418,6 +418,7 @@ struct dma_features { unsigned int frpbs; unsigned int frpes; unsigned int addr64; + unsigned int host_dma_width; unsigned int rssen; unsigned int vlhash; unsigned int sphen; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c index ac550d1ac015..2a2be65d65a0 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c @@ -288,7 +288,7 @@ static int imx_dwmac_probe(struct platform_device *pdev) goto err_parse_dt; } - plat_dat->addr64 = dwmac->ops->addr_width; + plat_dat->host_dma_width = dwmac->ops->addr_width; plat_dat->init = imx_dwmac_init; plat_dat->exit = imx_dwmac_exit; plat_dat->clks_config = imx_dwmac_clks_config; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c index 7deb1f817dac..13aa919633b4 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c @@ -684,7 +684,7 @@ static int ehl_pse0_common_data(struct pci_dev *pdev, intel_priv->is_pse = true; plat->bus_id = 2; - plat->addr64 = 32; + plat->host_dma_width = 32; plat->clk_ptp_rate = 200000000; @@ -725,7 +725,7 @@ static int ehl_pse1_common_data(struct pci_dev *pdev, intel_priv->is_pse = true; plat->bus_id = 3; - plat->addr64 = 32; + plat->host_dma_width = 32; plat->clk_ptp_rate = 200000000; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c index 2f7d8e4561d9..9ae31e3dc821 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c @@ -591,7 +591,7 @@ static int mediatek_dwmac_common_data(struct platform_device *pdev, plat->use_phy_wol = priv_plat->mac_wol ? 0 : 1; plat->riwt_off = 1; plat->maxmtu = ETH_DATA_LEN; - plat->addr64 = priv_plat->variant->dma_bit_mask; + plat->host_dma_width = priv_plat->variant->dma_bit_mask; plat->bsp_priv = priv_plat; plat->init = mediatek_dwmac_init; plat->clks_config = mediatek_dwmac_clks_config; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 8f543c3ab5c5..17310ade88dd 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1431,7 +1431,7 @@ static int stmmac_init_rx_buffers(struct stmmac_priv *priv, struct stmmac_rx_buffer *buf = &rx_q->buf_pool[i]; gfp_t gfp = (GFP_ATOMIC | __GFP_NOWARN); - if (priv->dma_cap.addr64 <= 32) + if (priv->dma_cap.host_dma_width <= 32) gfp |= GFP_DMA32; if (!buf->page) { @@ -4587,7 +4587,7 @@ static inline void stmmac_rx_refill(struct stmmac_priv *priv, u32 queue) unsigned int entry = rx_q->dirty_rx; gfp_t gfp = (GFP_ATOMIC | __GFP_NOWARN); - if (priv->dma_cap.addr64 <= 32) + if (priv->dma_cap.host_dma_width <= 32) gfp |= GFP_DMA32; while (dirty-- > 0) { @@ -6205,7 +6205,7 @@ static int stmmac_dma_cap_show(struct seq_file *seq, void *v) seq_printf(seq, "\tFlexible RX Parser: %s\n", priv->dma_cap.frpsel ? "Y" : "N"); seq_printf(seq, "\tEnhanced Addressing: %d\n", - priv->dma_cap.addr64); + priv->dma_cap.host_dma_width); seq_printf(seq, "\tReceive Side Scaling: %s\n", priv->dma_cap.rssen ? "Y" : "N"); seq_printf(seq, "\tVLAN Hash Filtering: %s\n", @@ -7178,20 +7178,22 @@ int stmmac_dvr_probe(struct device *device, dev_info(priv->device, "SPH feature enabled\n"); } - /* The current IP register MAC_HW_Feature1[ADDR64] only define - * 32/40/64 bit width, but some SOC support others like i.MX8MP - * support 34 bits but it map to 40 bits width in MAC_HW_Feature1[ADDR64]. - * So overwrite dma_cap.addr64 according to HW real design. + /* Ideally our host DMA address width is the same as for the + * device. However, it may differ and then we have to use our + * host DMA width for allocation and the device DMA width for + * register handling. */ - if (priv->plat->addr64) - priv->dma_cap.addr64 = priv->plat->addr64; + if (priv->plat->host_dma_width) + priv->dma_cap.host_dma_width = priv->plat->host_dma_width; + else + priv->dma_cap.host_dma_width = priv->dma_cap.addr64; - if (priv->dma_cap.addr64) { + if (priv->dma_cap.host_dma_width) { ret = dma_set_mask_and_coherent(device, - DMA_BIT_MASK(priv->dma_cap.addr64)); + DMA_BIT_MASK(priv->dma_cap.host_dma_width)); if (!ret) { - dev_info(priv->device, "Using %d bits DMA width\n", - priv->dma_cap.addr64); + dev_info(priv->device, "Using %d/%d bits DMA host/device width\n", + priv->dma_cap.host_dma_width, priv->dma_cap.addr64); /* * If more than 32 bits can be addressed, make sure to @@ -7206,7 +7208,7 @@ int stmmac_dvr_probe(struct device *device, goto error_hw_init; } - priv->dma_cap.addr64 = 32; + priv->dma_cap.host_dma_width = 32; } } diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index a152678b82b7..a2414c187483 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -215,7 +215,7 @@ struct plat_stmmacenet_data { int unicast_filter_entries; int tx_fifo_size; int rx_fifo_size; - u32 addr64; + u32 host_dma_width; u32 rx_queues_to_use; u32 tx_queues_to_use; u8 rx_sched_algorithm; -- cgit v1.2.3 From 1470afefc3c42df5d1662f87d079b46651bdc95b Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Wed, 15 Mar 2023 17:31:02 -0700 Subject: cpumask: introduce for_each_cpu_or Equivalent of for_each_cpu_and, except it ORs the two masks together so it iterates all the CPUs present in either mask. Signed-off-by: Dave Chinner Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- include/linux/cpumask.h | 17 +++++++++++++++++ include/linux/find.h | 37 +++++++++++++++++++++++++++++++++++++ lib/find_bit.c | 9 +++++++++ 3 files changed, 63 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 8fbe76607965..220974ef1bf5 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -350,6 +350,23 @@ unsigned int __pure cpumask_next_wrap(int n, const struct cpumask *mask, int sta #define for_each_cpu_andnot(cpu, mask1, mask2) \ for_each_andnot_bit(cpu, cpumask_bits(mask1), cpumask_bits(mask2), small_cpumask_bits) +/** + * for_each_cpu_or - iterate over every cpu present in either mask + * @cpu: the (optionally unsigned) integer iterator + * @mask1: the first cpumask pointer + * @mask2: the second cpumask pointer + * + * This saves a temporary CPU mask in many places. It is equivalent to: + * struct cpumask tmp; + * cpumask_or(&tmp, &mask1, &mask2); + * for_each_cpu(cpu, &tmp) + * ... + * + * After the loop, cpu is >= nr_cpu_ids. + */ +#define for_each_cpu_or(cpu, mask1, mask2) \ + for_each_or_bit(cpu, cpumask_bits(mask1), cpumask_bits(mask2), small_cpumask_bits) + /** * cpumask_any_but - return a "random" in a cpumask, but not this one. * @mask: the cpumask to search diff --git a/include/linux/find.h b/include/linux/find.h index 4647864a5ffd..5e4f39ef2e72 100644 --- a/include/linux/find.h +++ b/include/linux/find.h @@ -14,6 +14,8 @@ unsigned long _find_next_and_bit(const unsigned long *addr1, const unsigned long unsigned long nbits, unsigned long start); unsigned long _find_next_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long nbits, unsigned long start); +unsigned long _find_next_or_bit(const unsigned long *addr1, const unsigned long *addr2, + unsigned long nbits, unsigned long start); unsigned long _find_next_zero_bit(const unsigned long *addr, unsigned long nbits, unsigned long start); extern unsigned long _find_first_bit(const unsigned long *addr, unsigned long size); @@ -127,6 +129,36 @@ unsigned long find_next_andnot_bit(const unsigned long *addr1, } #endif +#ifndef find_next_or_bit +/** + * find_next_or_bit - find the next set bit in either memory regions + * @addr1: The first address to base the search on + * @addr2: The second address to base the search on + * @size: The bitmap size in bits + * @offset: The bitnumber to start searching at + * + * Returns the bit number for the next set bit + * If no bits are set, returns @size. + */ +static inline +unsigned long find_next_or_bit(const unsigned long *addr1, + const unsigned long *addr2, unsigned long size, + unsigned long offset) +{ + if (small_const_nbits(size)) { + unsigned long val; + + if (unlikely(offset >= size)) + return size; + + val = (*addr1 | *addr2) & GENMASK(size - 1, offset); + return val ? __ffs(val) : size; + } + + return _find_next_or_bit(addr1, addr2, size, offset); +} +#endif + #ifndef find_next_zero_bit /** * find_next_zero_bit - find the next cleared bit in a memory region @@ -536,6 +568,11 @@ unsigned long find_next_bit_le(const void *addr, unsigned (bit) = find_next_andnot_bit((addr1), (addr2), (size), (bit)), (bit) < (size);\ (bit)++) +#define for_each_or_bit(bit, addr1, addr2, size) \ + for ((bit) = 0; \ + (bit) = find_next_or_bit((addr1), (addr2), (size), (bit)), (bit) < (size);\ + (bit)++) + /* same as for_each_set_bit() but use bit as value to start with */ #define for_each_set_bit_from(bit, addr, size) \ for (; (bit) = find_next_bit((addr), (size), (bit)), (bit) < (size); (bit)++) diff --git a/lib/find_bit.c b/lib/find_bit.c index c10920e66788..32f99e9a670e 100644 --- a/lib/find_bit.c +++ b/lib/find_bit.c @@ -182,6 +182,15 @@ unsigned long _find_next_andnot_bit(const unsigned long *addr1, const unsigned l EXPORT_SYMBOL(_find_next_andnot_bit); #endif +#ifndef find_next_or_bit +unsigned long _find_next_or_bit(const unsigned long *addr1, const unsigned long *addr2, + unsigned long nbits, unsigned long start) +{ + return FIND_NEXT_BIT(addr1[idx] | addr2[idx], /* nop */, nbits, start); +} +EXPORT_SYMBOL(_find_next_or_bit); +#endif + #ifndef find_next_zero_bit unsigned long _find_next_zero_bit(const unsigned long *addr, unsigned long nbits, unsigned long start) -- cgit v1.2.3 From e9b60c7f97130795c7aa81a649ae4b93a172a277 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Wed, 15 Mar 2023 17:31:03 -0700 Subject: pcpcntr: remove percpu_counter_sum_all() percpu_counter_sum_all() is now redundant as the race condition it was invented to handle is now dealt with by percpu_counter_sum() directly and all users of percpu_counter_sum_all() have been removed. Remove it. This effectively reverts the changes made in f689054aace2 ("percpu_counter: add percpu_counter_sum_all interface") except for the cpumask iteration that fixes percpu_counter_sum() made earlier in this series. Signed-off-by: Dave Chinner Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- include/linux/percpu_counter.h | 6 ------ lib/percpu_counter.c | 40 +++++++++++----------------------------- 2 files changed, 11 insertions(+), 35 deletions(-) (limited to 'include/linux') diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h index 521a733e21a9..75b73c83bc9d 100644 --- a/include/linux/percpu_counter.h +++ b/include/linux/percpu_counter.h @@ -45,7 +45,6 @@ void percpu_counter_set(struct percpu_counter *fbc, s64 amount); void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch); s64 __percpu_counter_sum(struct percpu_counter *fbc); -s64 percpu_counter_sum_all(struct percpu_counter *fbc); int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch); void percpu_counter_sync(struct percpu_counter *fbc); @@ -196,11 +195,6 @@ static inline s64 percpu_counter_sum(struct percpu_counter *fbc) return percpu_counter_read(fbc); } -static inline s64 percpu_counter_sum_all(struct percpu_counter *fbc) -{ - return percpu_counter_read(fbc); -} - static inline bool percpu_counter_initialized(struct percpu_counter *fbc) { return true; diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c index 0e096311e0c0..5004463c4f9f 100644 --- a/lib/percpu_counter.c +++ b/lib/percpu_counter.c @@ -122,23 +122,6 @@ void percpu_counter_sync(struct percpu_counter *fbc) } EXPORT_SYMBOL(percpu_counter_sync); -static s64 __percpu_counter_sum_mask(struct percpu_counter *fbc, - const struct cpumask *cpu_mask) -{ - s64 ret; - int cpu; - unsigned long flags; - - raw_spin_lock_irqsave(&fbc->lock, flags); - ret = fbc->count; - for_each_cpu_or(cpu, cpu_online_mask, cpu_mask) { - s32 *pcount = per_cpu_ptr(fbc->counters, cpu); - ret += *pcount; - } - raw_spin_unlock_irqrestore(&fbc->lock, flags); - return ret; -} - /* * Add up all the per-cpu counts, return the result. This is a more accurate * but much slower version of percpu_counter_read_positive(). @@ -153,22 +136,21 @@ static s64 __percpu_counter_sum_mask(struct percpu_counter *fbc, */ s64 __percpu_counter_sum(struct percpu_counter *fbc) { + s64 ret; + int cpu; + unsigned long flags; - return __percpu_counter_sum_mask(fbc, cpu_dying_mask); + raw_spin_lock_irqsave(&fbc->lock, flags); + ret = fbc->count; + for_each_cpu_or(cpu, cpu_online_mask, cpu_dying_mask) { + s32 *pcount = per_cpu_ptr(fbc->counters, cpu); + ret += *pcount; + } + raw_spin_unlock_irqrestore(&fbc->lock, flags); + return ret; } EXPORT_SYMBOL(__percpu_counter_sum); -/* - * This is slower version of percpu_counter_sum as it traverses all possible - * cpus. Use this only in the cases where accurate data is needed in the - * presense of CPUs getting offlined. - */ -s64 percpu_counter_sum_all(struct percpu_counter *fbc) -{ - return __percpu_counter_sum_mask(fbc, cpu_possible_mask); -} -EXPORT_SYMBOL(percpu_counter_sum_all); - int __percpu_counter_init(struct percpu_counter *fbc, s64 amount, gfp_t gfp, struct lock_class_key *key) { -- cgit v1.2.3 From 9d2789ac9d60c049d26ef6d3005d9c94c5a559e9 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 20 Mar 2023 20:01:25 -0600 Subject: block/io_uring: pass in issue_flags for uring_cmd task_work handling io_uring_cmd_done() currently assumes that the uring_lock is held when invoked, and while it generally is, this is not guaranteed. Pass in the issue_flags associated with it, so that we have IO_URING_F_UNLOCKED available to be able to lock the CQ ring appropriately when completing events. Cc: stable@vger.kernel.org Fixes: ee692a21e9bf ("fs,io_uring: add infrastructure for uring-cmd") Signed-off-by: Jens Axboe --- drivers/block/ublk_drv.c | 31 ++++++++++++++++++------------- drivers/nvme/host/ioctl.c | 14 ++++++++------ include/linux/io_uring.h | 11 ++++++----- io_uring/uring_cmd.c | 10 ++++++---- 4 files changed, 38 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index fb5a557afde8..c73cc57ec547 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -715,7 +715,8 @@ static void __ublk_fail_req(struct ublk_queue *ubq, struct ublk_io *io, } } -static void ubq_complete_io_cmd(struct ublk_io *io, int res) +static void ubq_complete_io_cmd(struct ublk_io *io, int res, + unsigned issue_flags) { /* mark this cmd owned by ublksrv */ io->flags |= UBLK_IO_FLAG_OWNED_BY_SRV; @@ -727,7 +728,7 @@ static void ubq_complete_io_cmd(struct ublk_io *io, int res) io->flags &= ~UBLK_IO_FLAG_ACTIVE; /* tell ublksrv one io request is coming */ - io_uring_cmd_done(io->cmd, res, 0); + io_uring_cmd_done(io->cmd, res, 0, issue_flags); } #define UBLK_REQUEUE_DELAY_MS 3 @@ -744,7 +745,8 @@ static inline void __ublk_abort_rq(struct ublk_queue *ubq, mod_delayed_work(system_wq, &ubq->dev->monitor_work, 0); } -static inline void __ublk_rq_task_work(struct request *req) +static inline void __ublk_rq_task_work(struct request *req, + unsigned issue_flags) { struct ublk_queue *ubq = req->mq_hctx->driver_data; int tag = req->tag; @@ -782,7 +784,7 @@ static inline void __ublk_rq_task_work(struct request *req) pr_devel("%s: need get data. op %d, qid %d tag %d io_flags %x\n", __func__, io->cmd->cmd_op, ubq->q_id, req->tag, io->flags); - ubq_complete_io_cmd(io, UBLK_IO_RES_NEED_GET_DATA); + ubq_complete_io_cmd(io, UBLK_IO_RES_NEED_GET_DATA, issue_flags); return; } /* @@ -820,17 +822,18 @@ static inline void __ublk_rq_task_work(struct request *req) mapped_bytes >> 9; } - ubq_complete_io_cmd(io, UBLK_IO_RES_OK); + ubq_complete_io_cmd(io, UBLK_IO_RES_OK, issue_flags); } -static inline void ublk_forward_io_cmds(struct ublk_queue *ubq) +static inline void ublk_forward_io_cmds(struct ublk_queue *ubq, + unsigned issue_flags) { struct llist_node *io_cmds = llist_del_all(&ubq->io_cmds); struct ublk_rq_data *data, *tmp; io_cmds = llist_reverse_order(io_cmds); llist_for_each_entry_safe(data, tmp, io_cmds, node) - __ublk_rq_task_work(blk_mq_rq_from_pdu(data)); + __ublk_rq_task_work(blk_mq_rq_from_pdu(data), issue_flags); } static inline void ublk_abort_io_cmds(struct ublk_queue *ubq) @@ -842,12 +845,12 @@ static inline void ublk_abort_io_cmds(struct ublk_queue *ubq) __ublk_abort_rq(ubq, blk_mq_rq_from_pdu(data)); } -static void ublk_rq_task_work_cb(struct io_uring_cmd *cmd) +static void ublk_rq_task_work_cb(struct io_uring_cmd *cmd, unsigned issue_flags) { struct ublk_uring_cmd_pdu *pdu = ublk_get_uring_cmd_pdu(cmd); struct ublk_queue *ubq = pdu->ubq; - ublk_forward_io_cmds(ubq); + ublk_forward_io_cmds(ubq, issue_flags); } static void ublk_rq_task_work_fn(struct callback_head *work) @@ -856,8 +859,9 @@ static void ublk_rq_task_work_fn(struct callback_head *work) struct ublk_rq_data, work); struct request *req = blk_mq_rq_from_pdu(data); struct ublk_queue *ubq = req->mq_hctx->driver_data; + unsigned issue_flags = IO_URING_F_UNLOCKED; - ublk_forward_io_cmds(ubq); + ublk_forward_io_cmds(ubq, issue_flags); } static void ublk_queue_cmd(struct ublk_queue *ubq, struct request *rq) @@ -1111,7 +1115,8 @@ static void ublk_cancel_queue(struct ublk_queue *ubq) struct ublk_io *io = &ubq->ios[i]; if (io->flags & UBLK_IO_FLAG_ACTIVE) - io_uring_cmd_done(io->cmd, UBLK_IO_RES_ABORT, 0); + io_uring_cmd_done(io->cmd, UBLK_IO_RES_ABORT, 0, + IO_URING_F_UNLOCKED); } /* all io commands are canceled */ @@ -1351,7 +1356,7 @@ static int ublk_ch_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags) return -EIOCBQUEUED; out: - io_uring_cmd_done(cmd, ret, 0); + io_uring_cmd_done(cmd, ret, 0, issue_flags); pr_devel("%s: complete: cmd op %d, tag %d ret %x io_flags %x\n", __func__, cmd_op, tag, ret, io->flags); return -EIOCBQUEUED; @@ -2234,7 +2239,7 @@ static int ublk_ctrl_uring_cmd(struct io_uring_cmd *cmd, if (ub) ublk_put_device(ub); out: - io_uring_cmd_done(cmd, ret, 0); + io_uring_cmd_done(cmd, ret, 0, issue_flags); pr_devel("%s: cmd done ret %d cmd_op %x, dev id %d qid %d\n", __func__, ret, cmd->cmd_op, header->dev_id, header->queue_id); return -EIOCBQUEUED; diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c index 723e7d5b778f..d24ea2e05156 100644 --- a/drivers/nvme/host/ioctl.c +++ b/drivers/nvme/host/ioctl.c @@ -464,7 +464,8 @@ static inline struct nvme_uring_cmd_pdu *nvme_uring_cmd_pdu( return (struct nvme_uring_cmd_pdu *)&ioucmd->pdu; } -static void nvme_uring_task_meta_cb(struct io_uring_cmd *ioucmd) +static void nvme_uring_task_meta_cb(struct io_uring_cmd *ioucmd, + unsigned issue_flags) { struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd); struct request *req = pdu->req; @@ -485,17 +486,18 @@ static void nvme_uring_task_meta_cb(struct io_uring_cmd *ioucmd) blk_rq_unmap_user(req->bio); blk_mq_free_request(req); - io_uring_cmd_done(ioucmd, status, result); + io_uring_cmd_done(ioucmd, status, result, issue_flags); } -static void nvme_uring_task_cb(struct io_uring_cmd *ioucmd) +static void nvme_uring_task_cb(struct io_uring_cmd *ioucmd, + unsigned issue_flags) { struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd); if (pdu->bio) blk_rq_unmap_user(pdu->bio); - io_uring_cmd_done(ioucmd, pdu->nvme_status, pdu->u.result); + io_uring_cmd_done(ioucmd, pdu->nvme_status, pdu->u.result, issue_flags); } static enum rq_end_io_ret nvme_uring_cmd_end_io(struct request *req, @@ -517,7 +519,7 @@ static enum rq_end_io_ret nvme_uring_cmd_end_io(struct request *req, * Otherwise, move the completion to task work. */ if (cookie != NULL && blk_rq_is_poll(req)) - nvme_uring_task_cb(ioucmd); + nvme_uring_task_cb(ioucmd, IO_URING_F_UNLOCKED); else io_uring_cmd_complete_in_task(ioucmd, nvme_uring_task_cb); @@ -539,7 +541,7 @@ static enum rq_end_io_ret nvme_uring_cmd_end_io_meta(struct request *req, * Otherwise, move the completion to task work. */ if (cookie != NULL && blk_rq_is_poll(req)) - nvme_uring_task_meta_cb(ioucmd); + nvme_uring_task_meta_cb(ioucmd, IO_URING_F_UNLOCKED); else io_uring_cmd_complete_in_task(ioucmd, nvme_uring_task_meta_cb); diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index 934e5dd4ccc0..35b9328ca335 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -27,7 +27,7 @@ struct io_uring_cmd { const void *cmd; union { /* callback to defer completions to task context */ - void (*task_work_cb)(struct io_uring_cmd *cmd); + void (*task_work_cb)(struct io_uring_cmd *cmd, unsigned); /* used for polled completion */ void *cookie; }; @@ -39,9 +39,10 @@ struct io_uring_cmd { #if defined(CONFIG_IO_URING) int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw, struct iov_iter *iter, void *ioucmd); -void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret, ssize_t res2); +void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret, ssize_t res2, + unsigned issue_flags); void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd, - void (*task_work_cb)(struct io_uring_cmd *)); + void (*task_work_cb)(struct io_uring_cmd *, unsigned)); struct sock *io_uring_get_socket(struct file *file); void __io_uring_cancel(bool cancel_all); void __io_uring_free(struct task_struct *tsk); @@ -72,11 +73,11 @@ static inline int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw, return -EOPNOTSUPP; } static inline void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret, - ssize_t ret2) + ssize_t ret2, unsigned issue_flags) { } static inline void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd, - void (*task_work_cb)(struct io_uring_cmd *)) + void (*task_work_cb)(struct io_uring_cmd *, unsigned)) { } static inline struct sock *io_uring_get_socket(struct file *file) diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c index 446a189b78b0..e535e8db01e3 100644 --- a/io_uring/uring_cmd.c +++ b/io_uring/uring_cmd.c @@ -15,12 +15,13 @@ static void io_uring_cmd_work(struct io_kiocb *req, bool *locked) { struct io_uring_cmd *ioucmd = io_kiocb_to_cmd(req, struct io_uring_cmd); + unsigned issue_flags = *locked ? 0 : IO_URING_F_UNLOCKED; - ioucmd->task_work_cb(ioucmd); + ioucmd->task_work_cb(ioucmd, issue_flags); } void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd, - void (*task_work_cb)(struct io_uring_cmd *)) + void (*task_work_cb)(struct io_uring_cmd *, unsigned)) { struct io_kiocb *req = cmd_to_io_kiocb(ioucmd); @@ -42,7 +43,8 @@ static inline void io_req_set_cqe32_extra(struct io_kiocb *req, * Called by consumers of io_uring_cmd, if they originally returned * -EIOCBQUEUED upon receiving the command. */ -void io_uring_cmd_done(struct io_uring_cmd *ioucmd, ssize_t ret, ssize_t res2) +void io_uring_cmd_done(struct io_uring_cmd *ioucmd, ssize_t ret, ssize_t res2, + unsigned issue_flags) { struct io_kiocb *req = cmd_to_io_kiocb(ioucmd); @@ -56,7 +58,7 @@ void io_uring_cmd_done(struct io_uring_cmd *ioucmd, ssize_t ret, ssize_t res2) /* order with io_iopoll_req_issued() checking ->iopoll_complete */ smp_store_release(&req->iopoll_completed, 1); else - io_req_complete_post(req, 0); + io_req_complete_post(req, issue_flags); } EXPORT_SYMBOL_GPL(io_uring_cmd_done); -- cgit v1.2.3 From f87d28673b71b35b248231a2086f9404afbb7f28 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Sat, 25 Feb 2023 16:01:36 -0800 Subject: entry: Fix noinstr warning in __enter_from_user_mode() __enter_from_user_mode() is triggering noinstr warnings with CONFIG_DEBUG_PREEMPT due to its call of preempt_count_add() via ct_state(). The preemption disable isn't needed as interrupts are already disabled. And the context_tracking_enabled() check in ct_state() also isn't needed as that's already being done by the CT_WARN_ON(). Just use __ct_state() instead. Fixes the following warnings: vmlinux.o: warning: objtool: enter_from_user_mode+0xba: call to preempt_count_add() leaves .noinstr.text section vmlinux.o: warning: objtool: syscall_enter_from_user_mode+0xf9: call to preempt_count_add() leaves .noinstr.text section vmlinux.o: warning: objtool: syscall_enter_from_user_mode_prepare+0xc7: call to preempt_count_add() leaves .noinstr.text section vmlinux.o: warning: objtool: irqentry_enter_from_user_mode+0xba: call to preempt_count_add() leaves .noinstr.text section Fixes: 171476775d32 ("context_tracking: Convert state to atomic_t") Signed-off-by: Josh Poimboeuf Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/d8955fa6d68dc955dda19baf13ae014ae27926f5.1677369694.git.jpoimboe@kernel.org --- include/linux/context_tracking.h | 1 + include/linux/context_tracking_state.h | 2 ++ kernel/entry/common.c | 2 +- 3 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index d4afa8508a80..3a7909ed5498 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -96,6 +96,7 @@ static inline void user_exit_irqoff(void) { } static inline int exception_enter(void) { return 0; } static inline void exception_exit(enum ctx_state prev_ctx) { } static inline int ct_state(void) { return -1; } +static inline int __ct_state(void) { return -1; } static __always_inline bool context_tracking_guest_enter(void) { return false; } static inline void context_tracking_guest_exit(void) { } #define CT_WARN_ON(cond) do { } while (0) diff --git a/include/linux/context_tracking_state.h b/include/linux/context_tracking_state.h index 4a4d56f77180..fdd537ea513f 100644 --- a/include/linux/context_tracking_state.h +++ b/include/linux/context_tracking_state.h @@ -46,7 +46,9 @@ struct context_tracking { #ifdef CONFIG_CONTEXT_TRACKING DECLARE_PER_CPU(struct context_tracking, context_tracking); +#endif +#ifdef CONFIG_CONTEXT_TRACKING_USER static __always_inline int __ct_state(void) { return arch_atomic_read(this_cpu_ptr(&context_tracking.state)) & CT_STATE_MASK; diff --git a/kernel/entry/common.c b/kernel/entry/common.c index 846add8394c4..1314894d2efa 100644 --- a/kernel/entry/common.c +++ b/kernel/entry/common.c @@ -21,7 +21,7 @@ static __always_inline void __enter_from_user_mode(struct pt_regs *regs) arch_enter_from_user_mode(regs); lockdep_hardirqs_off(CALLER_ADDR0); - CT_WARN_ON(ct_state() != CONTEXT_USER); + CT_WARN_ON(__ct_state() != CONTEXT_USER); user_exit_irqoff(); instrumentation_begin(); -- cgit v1.2.3 From fbaa38214cd9e150764ccaa82e04ecf42cc1140c Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Sat, 11 Mar 2023 15:40:01 +0100 Subject: cxl/pci: Fix CDAT retrieval on big endian The CDAT exposed in sysfs differs between little endian and big endian arches: On big endian, every 4 bytes are byte-swapped. PCI Configuration Space is little endian (PCI r3.0 sec 6.1). Accessors such as pci_read_config_dword() implicitly swap bytes on big endian. That way, the macros in include/uapi/linux/pci_regs.h work regardless of the arch's endianness. For an example of implicit byte-swapping, see ppc4xx_pciex_read_config(), which calls in_le32(), which uses lwbrx (Load Word Byte-Reverse Indexed). DOE Read/Write Data Mailbox Registers are unlike other registers in Configuration Space in that they contain or receive a 4 byte portion of an opaque byte stream (a "Data Object" per PCIe r6.0 sec 7.9.24.5f). They need to be copied to or from the request/response buffer verbatim. So amend pci_doe_send_req() and pci_doe_recv_resp() to undo the implicit byte-swapping. The CXL_DOE_TABLE_ACCESS_* and PCI_DOE_DATA_OBJECT_DISC_* macros assume implicit byte-swapping. Byte-swap requests after constructing them with those macros and byte-swap responses before parsing them. Change the request and response type to __le32 to avoid sparse warnings. Per a request from Jonathan, replace sizeof(u32) with sizeof(__le32) for consistency. Fixes: c97006046c79 ("cxl/port: Read CDAT table") Tested-by: Ira Weiny Signed-off-by: Lukas Wunner Reviewed-by: Dan Williams Cc: stable@vger.kernel.org # v6.0+ Reviewed-by: Jonathan Cameron Link: https://lore.kernel.org/r/3051114102f41d19df3debbee123129118fc5e6d.1678543498.git.lukas@wunner.de Signed-off-by: Dan Williams --- drivers/cxl/core/pci.c | 26 +++++++++++++------------- drivers/pci/doe.c | 25 ++++++++++++++----------- include/linux/pci-doe.h | 8 ++++++-- 3 files changed, 33 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c index 7328a2552411..49a99a84b6aa 100644 --- a/drivers/cxl/core/pci.c +++ b/drivers/cxl/core/pci.c @@ -462,7 +462,7 @@ static struct pci_doe_mb *find_cdat_doe(struct device *uport) return NULL; } -#define CDAT_DOE_REQ(entry_handle) \ +#define CDAT_DOE_REQ(entry_handle) cpu_to_le32 \ (FIELD_PREP(CXL_DOE_TABLE_ACCESS_REQ_CODE, \ CXL_DOE_TABLE_ACCESS_REQ_CODE_READ) | \ FIELD_PREP(CXL_DOE_TABLE_ACCESS_TABLE_TYPE, \ @@ -475,8 +475,8 @@ static void cxl_doe_task_complete(struct pci_doe_task *task) } struct cdat_doe_task { - u32 request_pl; - u32 response_pl[32]; + __le32 request_pl; + __le32 response_pl[32]; struct completion c; struct pci_doe_task task; }; @@ -510,10 +510,10 @@ static int cxl_cdat_get_length(struct device *dev, return rc; } wait_for_completion(&t.c); - if (t.task.rv < sizeof(u32)) + if (t.task.rv < sizeof(__le32)) return -EIO; - *length = t.response_pl[1]; + *length = le32_to_cpu(t.response_pl[1]); dev_dbg(dev, "CDAT length %zu\n", *length); return 0; @@ -524,13 +524,13 @@ static int cxl_cdat_read_table(struct device *dev, struct cxl_cdat *cdat) { size_t length = cdat->length; - u32 *data = cdat->table; + __le32 *data = cdat->table; int entry_handle = 0; do { DECLARE_CDAT_DOE_TASK(CDAT_DOE_REQ(entry_handle), t); size_t entry_dw; - u32 *entry; + __le32 *entry; int rc; rc = pci_doe_submit_task(cdat_doe, &t.task); @@ -540,21 +540,21 @@ static int cxl_cdat_read_table(struct device *dev, } wait_for_completion(&t.c); /* 1 DW header + 1 DW data min */ - if (t.task.rv < (2 * sizeof(u32))) + if (t.task.rv < (2 * sizeof(__le32))) return -EIO; /* Get the CXL table access header entry handle */ entry_handle = FIELD_GET(CXL_DOE_TABLE_ACCESS_ENTRY_HANDLE, - t.response_pl[0]); + le32_to_cpu(t.response_pl[0])); entry = t.response_pl + 1; - entry_dw = t.task.rv / sizeof(u32); + entry_dw = t.task.rv / sizeof(__le32); /* Skip Header */ entry_dw -= 1; - entry_dw = min(length / sizeof(u32), entry_dw); + entry_dw = min(length / sizeof(__le32), entry_dw); /* Prevent length < 1 DW from causing a buffer overflow */ if (entry_dw) { - memcpy(data, entry, entry_dw * sizeof(u32)); - length -= entry_dw * sizeof(u32); + memcpy(data, entry, entry_dw * sizeof(__le32)); + length -= entry_dw * sizeof(__le32); data += entry_dw; } } while (entry_handle != CXL_DOE_TABLE_ACCESS_LAST_ENTRY); diff --git a/drivers/pci/doe.c b/drivers/pci/doe.c index 66d9ab288646..6f097932ccbf 100644 --- a/drivers/pci/doe.c +++ b/drivers/pci/doe.c @@ -128,7 +128,7 @@ static int pci_doe_send_req(struct pci_doe_mb *doe_mb, return -EIO; /* Length is 2 DW of header + length of payload in DW */ - length = 2 + task->request_pl_sz / sizeof(u32); + length = 2 + task->request_pl_sz / sizeof(__le32); if (length > PCI_DOE_MAX_LENGTH) return -EIO; if (length == PCI_DOE_MAX_LENGTH) @@ -141,9 +141,9 @@ static int pci_doe_send_req(struct pci_doe_mb *doe_mb, pci_write_config_dword(pdev, offset + PCI_DOE_WRITE, FIELD_PREP(PCI_DOE_DATA_OBJECT_HEADER_2_LENGTH, length)); - for (i = 0; i < task->request_pl_sz / sizeof(u32); i++) + for (i = 0; i < task->request_pl_sz / sizeof(__le32); i++) pci_write_config_dword(pdev, offset + PCI_DOE_WRITE, - task->request_pl[i]); + le32_to_cpu(task->request_pl[i])); pci_doe_write_ctrl(doe_mb, PCI_DOE_CTRL_GO); @@ -195,11 +195,11 @@ static int pci_doe_recv_resp(struct pci_doe_mb *doe_mb, struct pci_doe_task *tas /* First 2 dwords have already been read */ length -= 2; - payload_length = min(length, task->response_pl_sz / sizeof(u32)); + payload_length = min(length, task->response_pl_sz / sizeof(__le32)); /* Read the rest of the response payload */ for (i = 0; i < payload_length; i++) { - pci_read_config_dword(pdev, offset + PCI_DOE_READ, - &task->response_pl[i]); + pci_read_config_dword(pdev, offset + PCI_DOE_READ, &val); + task->response_pl[i] = cpu_to_le32(val); /* Prior to the last ack, ensure Data Object Ready */ if (i == (payload_length - 1) && !pci_doe_data_obj_ready(doe_mb)) return -EIO; @@ -217,7 +217,7 @@ static int pci_doe_recv_resp(struct pci_doe_mb *doe_mb, struct pci_doe_task *tas if (FIELD_GET(PCI_DOE_STATUS_ERROR, val)) return -EIO; - return min(length, task->response_pl_sz / sizeof(u32)) * sizeof(u32); + return min(length, task->response_pl_sz / sizeof(__le32)) * sizeof(__le32); } static void signal_task_complete(struct pci_doe_task *task, int rv) @@ -317,14 +317,16 @@ static int pci_doe_discovery(struct pci_doe_mb *doe_mb, u8 *index, u16 *vid, { u32 request_pl = FIELD_PREP(PCI_DOE_DATA_OBJECT_DISC_REQ_3_INDEX, *index); + __le32 request_pl_le = cpu_to_le32(request_pl); + __le32 response_pl_le; u32 response_pl; DECLARE_COMPLETION_ONSTACK(c); struct pci_doe_task task = { .prot.vid = PCI_VENDOR_ID_PCI_SIG, .prot.type = PCI_DOE_PROTOCOL_DISCOVERY, - .request_pl = &request_pl, + .request_pl = &request_pl_le, .request_pl_sz = sizeof(request_pl), - .response_pl = &response_pl, + .response_pl = &response_pl_le, .response_pl_sz = sizeof(response_pl), .complete = pci_doe_task_complete, .private = &c, @@ -340,6 +342,7 @@ static int pci_doe_discovery(struct pci_doe_mb *doe_mb, u8 *index, u16 *vid, if (task.rv != sizeof(response_pl)) return -EIO; + response_pl = le32_to_cpu(response_pl_le); *vid = FIELD_GET(PCI_DOE_DATA_OBJECT_DISC_RSP_3_VID, response_pl); *protocol = FIELD_GET(PCI_DOE_DATA_OBJECT_DISC_RSP_3_PROTOCOL, response_pl); @@ -533,8 +536,8 @@ int pci_doe_submit_task(struct pci_doe_mb *doe_mb, struct pci_doe_task *task) * DOE requests must be a whole number of DW and the response needs to * be big enough for at least 1 DW */ - if (task->request_pl_sz % sizeof(u32) || - task->response_pl_sz < sizeof(u32)) + if (task->request_pl_sz % sizeof(__le32) || + task->response_pl_sz < sizeof(__le32)) return -EINVAL; if (test_bit(PCI_DOE_FLAG_DEAD, &doe_mb->flags)) diff --git a/include/linux/pci-doe.h b/include/linux/pci-doe.h index ed9b4df792b8..43765eaf2342 100644 --- a/include/linux/pci-doe.h +++ b/include/linux/pci-doe.h @@ -34,6 +34,10 @@ struct pci_doe_mb; * @work: Used internally by the mailbox * @doe_mb: Used internally by the mailbox * + * Payloads are treated as opaque byte streams which are transmitted verbatim, + * without byte-swapping. If payloads contain little-endian register values, + * the caller is responsible for conversion with cpu_to_le32() / le32_to_cpu(). + * * The payload sizes and rv are specified in bytes with the following * restrictions concerning the protocol. * @@ -45,9 +49,9 @@ struct pci_doe_mb; */ struct pci_doe_task { struct pci_doe_protocol prot; - u32 *request_pl; + __le32 *request_pl; size_t request_pl_sz; - u32 *response_pl; + __le32 *response_pl; size_t response_pl_sz; int rv; void (*complete)(struct pci_doe_task *task); -- cgit v1.2.3 From aa01c67de5926fdb276793180564f172c55fb0d7 Mon Sep 17 00:00:00 2001 From: Caleb Sander Date: Mon, 20 Mar 2023 09:57:36 -0600 Subject: nvme-tcp: fix nvme_tcp_term_pdu to match spec The FEI field of C2HTermReq/H2CTermReq is 4 bytes but not 4-byte-aligned in the NVMe/TCP specification (it is located at offset 10 in the PDU). Split it into two 16-bit integers in struct nvme_tcp_term_pdu so no padding is inserted. There should also be 10 reserved bytes after. There are currently no users of this type. Fixes: fc221d05447aa6db ("nvme-tcp: Add protocol header") Reported-by: Geert Uytterhoeven Signed-off-by: Caleb Sander Reviewed-by: Sagi Grimberg Signed-off-by: Christoph Hellwig --- include/linux/nvme-tcp.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nvme-tcp.h b/include/linux/nvme-tcp.h index 75470159a194..57ebe1267f7f 100644 --- a/include/linux/nvme-tcp.h +++ b/include/linux/nvme-tcp.h @@ -115,8 +115,9 @@ struct nvme_tcp_icresp_pdu { struct nvme_tcp_term_pdu { struct nvme_tcp_hdr hdr; __le16 fes; - __le32 fei; - __u8 rsvd[8]; + __le16 feil; + __le16 feiu; + __u8 rsvd[10]; }; /** -- cgit v1.2.3 From 790930f44289c8209c57461b2db499fcc702e0b3 Mon Sep 17 00:00:00 2001 From: Rafael J. Wysocki Date: Fri, 17 Mar 2023 18:01:26 +0100 Subject: thermal: core: Introduce thermal_cooling_device_update() Introduce a core thermal API function, thermal_cooling_device_update(), for updating the max_state value for a cooling device and rearranging its statistics in sysfs after a possible change of its ->get_max_state() callback return value. That callback is now invoked only once, during cooling device registration, to populate the max_state field in the cooling device object, so if its return value changes, it needs to be invoked again and the new return value needs to be stored as max_state. Moreover, the statistics presented in sysfs need to be rearranged in general, because there may not be enough room in them to store data for all of the possible states (in the case when max_state grows). The new function takes care of that (and some other minor things related to it), but some extra locking and lockdep annotations are added in several places too to protect against crashes in the cases when the statistics are not present or when a stale max_state value might be used by sysfs attributes. Note that the actual user of the new function will be added separately. Link: https://lore.kernel.org/linux-pm/53ec1f06f61c984100868926f282647e57ecfb2d.camel@intel.com/ Signed-off-by: Rafael J. Wysocki Tested-by: Zhang Rui Reviewed-by: Zhang Rui --- drivers/thermal/thermal_core.c | 83 ++++++++++++++++++++++++++++++++++++++++- drivers/thermal/thermal_core.h | 2 + drivers/thermal/thermal_sysfs.c | 74 +++++++++++++++++++++++++++++++----- include/linux/thermal.h | 1 + 4 files changed, 150 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c index 8894342540f1..cfd4c1afeae7 100644 --- a/drivers/thermal/thermal_core.c +++ b/drivers/thermal/thermal_core.c @@ -613,6 +613,7 @@ int thermal_zone_bind_cooling_device(struct thermal_zone_device *tz, struct thermal_instance *pos; struct thermal_zone_device *pos1; struct thermal_cooling_device *pos2; + bool upper_no_limit; int result; if (trip >= tz->num_trips || trip < 0) @@ -632,7 +633,13 @@ int thermal_zone_bind_cooling_device(struct thermal_zone_device *tz, /* lower default 0, upper default max_state */ lower = lower == THERMAL_NO_LIMIT ? 0 : lower; - upper = upper == THERMAL_NO_LIMIT ? cdev->max_state : upper; + + if (upper == THERMAL_NO_LIMIT) { + upper = cdev->max_state; + upper_no_limit = true; + } else { + upper_no_limit = false; + } if (lower > upper || upper > cdev->max_state) return -EINVAL; @@ -644,6 +651,7 @@ int thermal_zone_bind_cooling_device(struct thermal_zone_device *tz, dev->cdev = cdev; dev->trip = trip; dev->upper = upper; + dev->upper_no_limit = upper_no_limit; dev->lower = lower; dev->target = THERMAL_NO_TARGET; dev->weight = weight; @@ -1057,6 +1065,79 @@ static bool thermal_cooling_device_present(struct thermal_cooling_device *cdev) return false; } +/** + * thermal_cooling_device_update - Update a cooling device object + * @cdev: Target cooling device. + * + * Update @cdev to reflect a change of the underlying hardware or platform. + * + * Must be called when the maximum cooling state of @cdev becomes invalid and so + * its .get_max_state() callback needs to be run to produce the new maximum + * cooling state value. + */ +void thermal_cooling_device_update(struct thermal_cooling_device *cdev) +{ + struct thermal_instance *ti; + unsigned long state; + + if (IS_ERR_OR_NULL(cdev)) + return; + + /* + * Hold thermal_list_lock throughout the update to prevent the device + * from going away while being updated. + */ + mutex_lock(&thermal_list_lock); + + if (!thermal_cooling_device_present(cdev)) + goto unlock_list; + + /* + * Update under the cdev lock to prevent the state from being set beyond + * the new limit concurrently. + */ + mutex_lock(&cdev->lock); + + if (cdev->ops->get_max_state(cdev, &cdev->max_state)) + goto unlock; + + thermal_cooling_device_stats_reinit(cdev); + + list_for_each_entry(ti, &cdev->thermal_instances, cdev_node) { + if (ti->upper == cdev->max_state) + continue; + + if (ti->upper < cdev->max_state) { + if (ti->upper_no_limit) + ti->upper = cdev->max_state; + + continue; + } + + ti->upper = cdev->max_state; + if (ti->lower > ti->upper) + ti->lower = ti->upper; + + if (ti->target == THERMAL_NO_TARGET) + continue; + + if (ti->target > ti->upper) + ti->target = ti->upper; + } + + if (cdev->ops->get_cur_state(cdev, &state) || state > cdev->max_state) + goto unlock; + + thermal_cooling_device_stats_update(cdev, state); + +unlock: + mutex_unlock(&cdev->lock); + +unlock_list: + mutex_unlock(&thermal_list_lock); +} +EXPORT_SYMBOL_GPL(thermal_cooling_device_update); + static void __unbind(struct thermal_zone_device *tz, int mask, struct thermal_cooling_device *cdev) { diff --git a/drivers/thermal/thermal_core.h b/drivers/thermal/thermal_core.h index 7af54382e915..3d4a787c6b28 100644 --- a/drivers/thermal/thermal_core.h +++ b/drivers/thermal/thermal_core.h @@ -101,6 +101,7 @@ struct thermal_instance { struct list_head tz_node; /* node in tz->thermal_instances */ struct list_head cdev_node; /* node in cdev->thermal_instances */ unsigned int weight; /* The weight of the cooling device */ + bool upper_no_limit; }; #define to_thermal_zone(_dev) \ @@ -127,6 +128,7 @@ int thermal_zone_create_device_groups(struct thermal_zone_device *, int); void thermal_zone_destroy_device_groups(struct thermal_zone_device *); void thermal_cooling_device_setup_sysfs(struct thermal_cooling_device *); void thermal_cooling_device_destroy_sysfs(struct thermal_cooling_device *cdev); +void thermal_cooling_device_stats_reinit(struct thermal_cooling_device *cdev); /* used only at binding time */ ssize_t trip_point_show(struct device *, struct device_attribute *, char *); ssize_t weight_show(struct device *, struct device_attribute *, char *); diff --git a/drivers/thermal/thermal_sysfs.c b/drivers/thermal/thermal_sysfs.c index cef860deaf91..a4aba7b8bb8b 100644 --- a/drivers/thermal/thermal_sysfs.c +++ b/drivers/thermal/thermal_sysfs.c @@ -685,6 +685,8 @@ void thermal_cooling_device_stats_update(struct thermal_cooling_device *cdev, { struct cooling_dev_stats *stats = cdev->stats; + lockdep_assert_held(&cdev->lock); + if (!stats) return; @@ -706,13 +708,22 @@ static ssize_t total_trans_show(struct device *dev, struct device_attribute *attr, char *buf) { struct thermal_cooling_device *cdev = to_cooling_device(dev); - struct cooling_dev_stats *stats = cdev->stats; - int ret; + struct cooling_dev_stats *stats; + int ret = 0; + + mutex_lock(&cdev->lock); + + stats = cdev->stats; + if (!stats) + goto unlock; spin_lock(&stats->lock); ret = sprintf(buf, "%u\n", stats->total_trans); spin_unlock(&stats->lock); +unlock: + mutex_unlock(&cdev->lock); + return ret; } @@ -721,11 +732,18 @@ time_in_state_ms_show(struct device *dev, struct device_attribute *attr, char *buf) { struct thermal_cooling_device *cdev = to_cooling_device(dev); - struct cooling_dev_stats *stats = cdev->stats; + struct cooling_dev_stats *stats; ssize_t len = 0; int i; + mutex_lock(&cdev->lock); + + stats = cdev->stats; + if (!stats) + goto unlock; + spin_lock(&stats->lock); + update_time_in_state(stats); for (i = 0; i <= cdev->max_state; i++) { @@ -734,6 +752,9 @@ time_in_state_ms_show(struct device *dev, struct device_attribute *attr, } spin_unlock(&stats->lock); +unlock: + mutex_unlock(&cdev->lock); + return len; } @@ -742,8 +763,16 @@ reset_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct thermal_cooling_device *cdev = to_cooling_device(dev); - struct cooling_dev_stats *stats = cdev->stats; - int i, states = cdev->max_state + 1; + struct cooling_dev_stats *stats; + int i, states; + + mutex_lock(&cdev->lock); + + stats = cdev->stats; + if (!stats) + goto unlock; + + states = cdev->max_state + 1; spin_lock(&stats->lock); @@ -757,6 +786,9 @@ reset_store(struct device *dev, struct device_attribute *attr, const char *buf, spin_unlock(&stats->lock); +unlock: + mutex_unlock(&cdev->lock); + return count; } @@ -764,10 +796,18 @@ static ssize_t trans_table_show(struct device *dev, struct device_attribute *attr, char *buf) { struct thermal_cooling_device *cdev = to_cooling_device(dev); - struct cooling_dev_stats *stats = cdev->stats; + struct cooling_dev_stats *stats; ssize_t len = 0; int i, j; + mutex_lock(&cdev->lock); + + stats = cdev->stats; + if (!stats) { + len = -ENODATA; + goto unlock; + } + len += snprintf(buf + len, PAGE_SIZE - len, " From : To\n"); len += snprintf(buf + len, PAGE_SIZE - len, " : "); for (i = 0; i <= cdev->max_state; i++) { @@ -775,8 +815,10 @@ static ssize_t trans_table_show(struct device *dev, break; len += snprintf(buf + len, PAGE_SIZE - len, "state%2u ", i); } - if (len >= PAGE_SIZE) - return PAGE_SIZE; + if (len >= PAGE_SIZE) { + len = PAGE_SIZE; + goto unlock; + } len += snprintf(buf + len, PAGE_SIZE - len, "\n"); @@ -799,8 +841,12 @@ static ssize_t trans_table_show(struct device *dev, if (len >= PAGE_SIZE) { pr_warn_once("Thermal transition table exceeds PAGE_SIZE. Disabling\n"); - return -EFBIG; + len = -EFBIG; } + +unlock: + mutex_unlock(&cdev->lock); + return len; } @@ -830,6 +876,8 @@ static void cooling_device_stats_setup(struct thermal_cooling_device *cdev) unsigned long states = cdev->max_state + 1; int var; + lockdep_assert_held(&cdev->lock); + var = sizeof(*stats); var += sizeof(*stats->time_in_state) * states; var += sizeof(*stats->trans_table) * states * states; @@ -855,6 +903,8 @@ out: static void cooling_device_stats_destroy(struct thermal_cooling_device *cdev) { + lockdep_assert_held(&cdev->lock); + kfree(cdev->stats); cdev->stats = NULL; } @@ -879,6 +929,12 @@ void thermal_cooling_device_destroy_sysfs(struct thermal_cooling_device *cdev) cooling_device_stats_destroy(cdev); } +void thermal_cooling_device_stats_reinit(struct thermal_cooling_device *cdev) +{ + cooling_device_stats_destroy(cdev); + cooling_device_stats_setup(cdev); +} + /* these helper will be used only at the time of bindig */ ssize_t trip_point_show(struct device *dev, struct device_attribute *attr, char *buf) diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 2bb4bf33f4f3..13c6aaed18df 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -384,6 +384,7 @@ devm_thermal_of_cooling_device_register(struct device *dev, struct device_node *np, char *type, void *devdata, const struct thermal_cooling_device_ops *ops); +void thermal_cooling_device_update(struct thermal_cooling_device *); void thermal_cooling_device_unregister(struct thermal_cooling_device *); struct thermal_zone_device *thermal_zone_get_zone_by_name(const char *name); int thermal_zone_get_temp(struct thermal_zone_device *tz, int *temp); -- cgit v1.2.3 From a90ac762d345890b40d88a1385a34a2449c2d75e Mon Sep 17 00:00:00 2001 From: Russell King (Oracle) Date: Fri, 24 Mar 2023 09:23:42 +0000 Subject: net: sfp: make sfp_bus_find_fwnode() take a const fwnode sfp_bus_find_fwnode() does not write to the fwnode, so let's make it const. Signed-off-by: Russell King (Oracle) Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/phy/sfp-bus.c | 2 +- include/linux/sfp.h | 5 +++-- 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c index daac293e8ede..8284f29b3644 100644 --- a/drivers/net/phy/sfp-bus.c +++ b/drivers/net/phy/sfp-bus.c @@ -593,7 +593,7 @@ static void sfp_upstream_clear(struct sfp_bus *bus) * - %-ENOMEM if we failed to allocate the bus. * - an error from the upstream's connect_phy() method. */ -struct sfp_bus *sfp_bus_find_fwnode(struct fwnode_handle *fwnode) +struct sfp_bus *sfp_bus_find_fwnode(const struct fwnode_handle *fwnode) { struct fwnode_reference_args ref; struct sfp_bus *bus; diff --git a/include/linux/sfp.h b/include/linux/sfp.h index 52b98f9666a2..ef06a195b3c2 100644 --- a/include/linux/sfp.h +++ b/include/linux/sfp.h @@ -557,7 +557,7 @@ int sfp_get_module_eeprom_by_page(struct sfp_bus *bus, void sfp_upstream_start(struct sfp_bus *bus); void sfp_upstream_stop(struct sfp_bus *bus); void sfp_bus_put(struct sfp_bus *bus); -struct sfp_bus *sfp_bus_find_fwnode(struct fwnode_handle *fwnode); +struct sfp_bus *sfp_bus_find_fwnode(const struct fwnode_handle *fwnode); int sfp_bus_add_upstream(struct sfp_bus *bus, void *upstream, const struct sfp_upstream_ops *ops); void sfp_bus_del_upstream(struct sfp_bus *bus); @@ -619,7 +619,8 @@ static inline void sfp_bus_put(struct sfp_bus *bus) { } -static inline struct sfp_bus *sfp_bus_find_fwnode(struct fwnode_handle *fwnode) +static inline struct sfp_bus * +sfp_bus_find_fwnode(const struct fwnode_handle *fwnode) { return NULL; } -- cgit v1.2.3 From 4a0faa02d419a6728abef0f1d8a32d8c35ef95e6 Mon Sep 17 00:00:00 2001 From: Russell King (Oracle) Date: Fri, 24 Mar 2023 09:23:53 +0000 Subject: net: phy: constify fwnode_get_phy_node() fwnode argument fwnode_get_phy_node() does not motify the fwnode structure, so make the argument const, Signed-off-by: Russell King (Oracle) Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/phy/phy_device.c | 2 +- include/linux/phy.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 1785f1cead97..1de3e339b31a 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -3057,7 +3057,7 @@ EXPORT_SYMBOL_GPL(device_phy_find_device); * and "phy-device" are not supported in ACPI. DT supports all the three * named references to the phy node. */ -struct fwnode_handle *fwnode_get_phy_node(struct fwnode_handle *fwnode) +struct fwnode_handle *fwnode_get_phy_node(const struct fwnode_handle *fwnode) { struct fwnode_handle *phy_node; diff --git a/include/linux/phy.h b/include/linux/phy.h index 36bf0bbc8efa..db7c0bd67559 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1547,7 +1547,7 @@ int fwnode_get_phy_id(struct fwnode_handle *fwnode, u32 *phy_id); struct mdio_device *fwnode_mdio_find_device(struct fwnode_handle *fwnode); struct phy_device *fwnode_phy_find_device(struct fwnode_handle *phy_fwnode); struct phy_device *device_phy_find_device(struct device *dev); -struct fwnode_handle *fwnode_get_phy_node(struct fwnode_handle *fwnode); +struct fwnode_handle *fwnode_get_phy_node(const struct fwnode_handle *fwnode); struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45); int phy_device_register(struct phy_device *phy); void phy_device_free(struct phy_device *phydev); -- cgit v1.2.3 From d583fbd7066a2dea43050521a95d9770f7d7593e Mon Sep 17 00:00:00 2001 From: Dmytro Maluka Date: Wed, 22 Mar 2023 21:43:43 +0100 Subject: KVM: irqfd: Make resampler_list an RCU list It is useful to be able to do read-only traversal of the list of all the registered irqfd resamplers without locking the resampler_lock mutex. In particular, we are going to traverse it to search for a resampler registered for the given irq of an irqchip, and that will be done with an irqchip spinlock (ioapic->lock) held, so it is undesirable to lock a mutex in this context. So turn this list into an RCU list. For protecting the read side, reuse kvm->irq_srcu which is already used for protecting a number of irq related things (kvm->irq_routing, irqfd->resampler->list, kvm->irq_ack_notifier_list, kvm->arch.mask_notifier_list). Signed-off-by: Dmytro Maluka Message-Id: <20230322204344.50138-2-dmy@semihalf.com> Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 1 + include/linux/kvm_irqfd.h | 2 +- virt/kvm/eventfd.c | 8 ++++++-- 3 files changed, 8 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 8ada23756b0e..9f508c8e66e1 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -755,6 +755,7 @@ struct kvm { struct { spinlock_t lock; struct list_head items; + /* resampler_list update side is protected by resampler_lock. */ struct list_head resampler_list; struct mutex resampler_lock; } irqfds; diff --git a/include/linux/kvm_irqfd.h b/include/linux/kvm_irqfd.h index dac047abdba7..8ad43692e3bb 100644 --- a/include/linux/kvm_irqfd.h +++ b/include/linux/kvm_irqfd.h @@ -31,7 +31,7 @@ struct kvm_kernel_irqfd_resampler { /* * Entry in list of kvm->irqfd.resampler_list. Use for sharing * resamplers among irqfds on the same gsi. - * Accessed and modified under kvm->irqfds.resampler_lock + * RCU list modified under kvm->irqfds.resampler_lock */ struct list_head link; }; diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c index 2a3ed401ce46..61aea70dd888 100644 --- a/virt/kvm/eventfd.c +++ b/virt/kvm/eventfd.c @@ -96,8 +96,12 @@ irqfd_resampler_shutdown(struct kvm_kernel_irqfd *irqfd) synchronize_srcu(&kvm->irq_srcu); if (list_empty(&resampler->list)) { - list_del(&resampler->link); + list_del_rcu(&resampler->link); kvm_unregister_irq_ack_notifier(kvm, &resampler->notifier); + /* + * synchronize_srcu(&kvm->irq_srcu) already called + * in kvm_unregister_irq_ack_notifier(). + */ kvm_set_irq(kvm, KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID, resampler->notifier.gsi, 0, false); kfree(resampler); @@ -369,7 +373,7 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args) resampler->notifier.irq_acked = irqfd_resampler_ack; INIT_LIST_HEAD(&resampler->link); - list_add(&resampler->link, &kvm->irqfds.resampler_list); + list_add_rcu(&resampler->link, &kvm->irqfds.resampler_list); kvm_register_irq_ack_notifier(kvm, &resampler->notifier); irqfd->resampler = resampler; -- cgit v1.2.3 From fef8f2b90edbd7089a4278021314f11f056b0cbb Mon Sep 17 00:00:00 2001 From: Dmytro Maluka Date: Wed, 22 Mar 2023 21:43:44 +0100 Subject: KVM: x86/ioapic: Resample the pending state of an IRQ when unmasking KVM irqfd based emulation of level-triggered interrupts doesn't work quite correctly in some cases, particularly in the case of interrupts that are handled in a Linux guest as oneshot interrupts (IRQF_ONESHOT). Such an interrupt is acked to the device in its threaded irq handler, i.e. later than it is acked to the interrupt controller (EOI at the end of hardirq), not earlier. Linux keeps such interrupt masked until its threaded handler finishes, to prevent the EOI from re-asserting an unacknowledged interrupt. However, with KVM + vfio (or whatever is listening on the resamplefd) we always notify resamplefd at the EOI, so vfio prematurely unmasks the host physical IRQ, thus a new physical interrupt is fired in the host. This extra interrupt in the host is not a problem per se. The problem is that it is unconditionally queued for injection into the guest, so the guest sees an extra bogus interrupt. [*] There are observed at least 2 user-visible issues caused by those extra erroneous interrupts for a oneshot irq in the guest: 1. System suspend aborted due to a pending wakeup interrupt from ChromeOS EC (drivers/platform/chrome/cros_ec.c). 2. Annoying "invalid report id data" errors from ELAN0000 touchpad (drivers/input/mouse/elan_i2c_core.c), flooding the guest dmesg every time the touchpad is touched. The core issue here is that by the time when the guest unmasks the IRQ, the physical IRQ line is no longer asserted (since the guest has acked the interrupt to the device in the meantime), yet we unconditionally inject the interrupt queued into the guest by the previous resampling. So to fix the issue, we need a way to detect that the IRQ is no longer pending, and cancel the queued interrupt in this case. With IOAPIC we are not able to probe the physical IRQ line state directly (at least not if the underlying physical interrupt controller is an IOAPIC too), so in this patch we use irqfd resampler for that. Namely, instead of injecting the queued interrupt, we just notify the resampler that this interrupt is done. If the IRQ line is actually already deasserted, we are done. If it is still asserted, a new interrupt will be shortly triggered through irqfd and injected into the guest. In the case if there is no irqfd resampler registered for this IRQ, we cannot fix the issue, so we keep the existing behavior: immediately unconditionally inject the queued interrupt. This patch fixes the issue for x86 IOAPIC only. In the long run, we can fix it for other irqchips and other architectures too, possibly taking advantage of reading the physical state of the IRQ line, which is possible with some other irqchips (e.g. with arm64 GIC, maybe even with the legacy x86 PIC). [*] In this description we assume that the interrupt is a physical host interrupt forwarded to the guest e.g. by vfio. Potentially the same issue may occur also with a purely virtual interrupt from an emulated device, e.g. if the guest handles this interrupt, again, as a oneshot interrupt. Signed-off-by: Dmytro Maluka Link: https://lore.kernel.org/kvm/31420943-8c5f-125c-a5ee-d2fde2700083@semihalf.com/ Link: https://lore.kernel.org/lkml/87o7wrug0w.wl-maz@kernel.org/ Message-Id: <20230322204344.50138-3-dmy@semihalf.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/ioapic.c | 36 +++++++++++++++++++++++++++++++++--- include/linux/kvm_host.h | 10 ++++++++++ virt/kvm/eventfd.c | 41 +++++++++++++++++++++++++++++++++++------ 3 files changed, 78 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index 042dee556125..995eb5054360 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -368,9 +368,39 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val) mask_after = e->fields.mask; if (mask_before != mask_after) kvm_fire_mask_notifiers(ioapic->kvm, KVM_IRQCHIP_IOAPIC, index, mask_after); - if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG - && ioapic->irr & (1 << index)) - ioapic_service(ioapic, index, false); + if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG && + ioapic->irr & (1 << index) && !e->fields.mask && !e->fields.remote_irr) { + /* + * Pending status in irr may be outdated: the IRQ line may have + * already been deasserted by a device while the IRQ was masked. + * This occurs, for instance, if the interrupt is handled in a + * Linux guest as a oneshot interrupt (IRQF_ONESHOT). In this + * case the guest acknowledges the interrupt to the device in + * its threaded irq handler, i.e. after the EOI but before + * unmasking, so at the time of unmasking the IRQ line is + * already down but our pending irr bit is still set. In such + * cases, injecting this pending interrupt to the guest is + * buggy: the guest will receive an extra unwanted interrupt. + * + * So we need to check here if the IRQ is actually still pending. + * As we are generally not able to probe the IRQ line status + * directly, we do it through irqfd resampler. Namely, we clear + * the pending status and notify the resampler that this interrupt + * is done, without actually injecting it into the guest. If the + * IRQ line is actually already deasserted, we are done. If it is + * still asserted, a new interrupt will be shortly triggered + * through irqfd and injected into the guest. + * + * If, however, it's not possible to resample (no irqfd resampler + * registered for this irq), then unconditionally inject this + * pending interrupt into the guest, so the guest will not miss + * an interrupt, although may get an extra unwanted interrupt. + */ + if (kvm_notify_irqfd_resampler(ioapic->kvm, KVM_IRQCHIP_IOAPIC, index)) + ioapic->irr &= ~(1 << index); + else + ioapic_service(ioapic, index, false); + } if (e->fields.delivery_mode == APIC_DM_FIXED) { struct kvm_lapic_irq irq; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 9f508c8e66e1..a9adf75344be 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1987,6 +1987,9 @@ int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args); #ifdef CONFIG_HAVE_KVM_IRQFD int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args); void kvm_irqfd_release(struct kvm *kvm); +bool kvm_notify_irqfd_resampler(struct kvm *kvm, + unsigned int irqchip, + unsigned int pin); void kvm_irq_routing_update(struct kvm *); #else static inline int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args) @@ -1995,6 +1998,13 @@ static inline int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args) } static inline void kvm_irqfd_release(struct kvm *kvm) {} + +static inline bool kvm_notify_irqfd_resampler(struct kvm *kvm, + unsigned int irqchip, + unsigned int pin) +{ + return false; +} #endif #else diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c index 61aea70dd888..b0af834ffa95 100644 --- a/virt/kvm/eventfd.c +++ b/virt/kvm/eventfd.c @@ -55,6 +55,15 @@ irqfd_inject(struct work_struct *work) irqfd->gsi, 1, false); } +static void irqfd_resampler_notify(struct kvm_kernel_irqfd_resampler *resampler) +{ + struct kvm_kernel_irqfd *irqfd; + + list_for_each_entry_srcu(irqfd, &resampler->list, resampler_link, + srcu_read_lock_held(&resampler->kvm->irq_srcu)) + eventfd_signal(irqfd->resamplefd, 1); +} + /* * Since resampler irqfds share an IRQ source ID, we de-assert once * then notify all of the resampler irqfds using this GSI. We can't @@ -65,7 +74,6 @@ irqfd_resampler_ack(struct kvm_irq_ack_notifier *kian) { struct kvm_kernel_irqfd_resampler *resampler; struct kvm *kvm; - struct kvm_kernel_irqfd *irqfd; int idx; resampler = container_of(kian, @@ -76,11 +84,7 @@ irqfd_resampler_ack(struct kvm_irq_ack_notifier *kian) resampler->notifier.gsi, 0, false); idx = srcu_read_lock(&kvm->irq_srcu); - - list_for_each_entry_srcu(irqfd, &resampler->list, resampler_link, - srcu_read_lock_held(&kvm->irq_srcu)) - eventfd_signal(irqfd->resamplefd, 1); - + irqfd_resampler_notify(resampler); srcu_read_unlock(&kvm->irq_srcu, idx); } @@ -648,6 +652,31 @@ void kvm_irq_routing_update(struct kvm *kvm) spin_unlock_irq(&kvm->irqfds.lock); } +bool kvm_notify_irqfd_resampler(struct kvm *kvm, + unsigned int irqchip, + unsigned int pin) +{ + struct kvm_kernel_irqfd_resampler *resampler; + int gsi, idx; + + idx = srcu_read_lock(&kvm->irq_srcu); + gsi = kvm_irq_map_chip_pin(kvm, irqchip, pin); + if (gsi != -1) { + list_for_each_entry_srcu(resampler, + &kvm->irqfds.resampler_list, link, + srcu_read_lock_held(&kvm->irq_srcu)) { + if (resampler->notifier.gsi == gsi) { + irqfd_resampler_notify(resampler); + srcu_read_unlock(&kvm->irq_srcu, idx); + return true; + } + } + } + srcu_read_unlock(&kvm->irq_srcu, idx); + + return false; +} + /* * create a host-wide workqueue for issuing deferred shutdown requests * aggregated from all vm* instances. We need our own isolated -- cgit v1.2.3 From 16812c96550c30a8d5743167ef4e462d6fbe7472 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Wed, 29 Mar 2023 21:47:21 +0800 Subject: iommu/vt-d: Fix an IOMMU perfmon warning when CPU hotplug A warning can be triggered when hotplug CPU 0. $ echo 0 > /sys/devices/system/cpu/cpu0/online ------------[ cut here ]------------ Voluntary context switch within RCU read-side critical section! WARNING: CPU: 0 PID: 19 at kernel/rcu/tree_plugin.h:318 rcu_note_context_switch+0x4f4/0x580 RIP: 0010:rcu_note_context_switch+0x4f4/0x580 Call Trace: ? perf_event_update_userpage+0x104/0x150 __schedule+0x8d/0x960 ? perf_event_set_state.part.82+0x11/0x50 schedule+0x44/0xb0 schedule_timeout+0x226/0x310 ? __perf_event_disable+0x64/0x1a0 ? _raw_spin_unlock+0x14/0x30 wait_for_completion+0x94/0x130 __wait_rcu_gp+0x108/0x130 synchronize_rcu+0x67/0x70 ? invoke_rcu_core+0xb0/0xb0 ? __bpf_trace_rcu_stall_warning+0x10/0x10 perf_pmu_migrate_context+0x121/0x370 iommu_pmu_cpu_offline+0x6a/0xa0 ? iommu_pmu_del+0x1e0/0x1e0 cpuhp_invoke_callback+0x129/0x510 cpuhp_thread_fun+0x94/0x150 smpboot_thread_fn+0x183/0x220 ? sort_range+0x20/0x20 kthread+0xe6/0x110 ? kthread_complete_and_exit+0x20/0x20 ret_from_fork+0x1f/0x30 ---[ end trace 0000000000000000 ]--- The synchronize_rcu() will be invoked in the perf_pmu_migrate_context(), when migrating a PMU to a new CPU. However, the current for_each_iommu() is within RCU read-side critical section. Two methods were considered to fix the issue. - Use the dmar_global_lock to replace the RCU read lock when going through the drhd list. But it triggers a lockdep warning. - Use the cpuhp_setup_state_multi() to set up a dedicated state for each IOMMU PMU. The lock can be avoided. The latter method is implemented in this patch. Since each IOMMU PMU has a dedicated state, add cpuhp_node and cpu in struct iommu_pmu to track the state. The state can be dynamically allocated now. Remove the CPUHP_AP_PERF_X86_IOMMU_PERF_ONLINE. Fixes: 46284c6ceb5e ("iommu/vt-d: Support cpumask for IOMMU perfmon") Reported-by: Ammy Yi Signed-off-by: Kan Liang Link: https://lore.kernel.org/r/20230328182028.1366416-1-kan.liang@linux.intel.com Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20230329134721.469447-4-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/iommu.h | 2 ++ drivers/iommu/intel/perfmon.c | 68 ++++++++++++++++++++++++++++--------------- include/linux/cpuhotplug.h | 1 - 3 files changed, 46 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h index d6df3b865812..694ab9b7d3e9 100644 --- a/drivers/iommu/intel/iommu.h +++ b/drivers/iommu/intel/iommu.h @@ -641,6 +641,8 @@ struct iommu_pmu { DECLARE_BITMAP(used_mask, IOMMU_PMU_IDX_MAX); struct perf_event *event_list[IOMMU_PMU_IDX_MAX]; unsigned char irq_name[16]; + struct hlist_node cpuhp_node; + int cpu; }; #define IOMMU_IRQ_ID_OFFSET_PRQ (DMAR_UNITS_SUPPORTED) diff --git a/drivers/iommu/intel/perfmon.c b/drivers/iommu/intel/perfmon.c index e17d9743a0d8..cf43e798eca4 100644 --- a/drivers/iommu/intel/perfmon.c +++ b/drivers/iommu/intel/perfmon.c @@ -773,19 +773,34 @@ static void iommu_pmu_unset_interrupt(struct intel_iommu *iommu) iommu->perf_irq = 0; } -static int iommu_pmu_cpu_online(unsigned int cpu) +static int iommu_pmu_cpu_online(unsigned int cpu, struct hlist_node *node) { + struct iommu_pmu *iommu_pmu = hlist_entry_safe(node, typeof(*iommu_pmu), cpuhp_node); + if (cpumask_empty(&iommu_pmu_cpu_mask)) cpumask_set_cpu(cpu, &iommu_pmu_cpu_mask); + if (cpumask_test_cpu(cpu, &iommu_pmu_cpu_mask)) + iommu_pmu->cpu = cpu; + return 0; } -static int iommu_pmu_cpu_offline(unsigned int cpu) +static int iommu_pmu_cpu_offline(unsigned int cpu, struct hlist_node *node) { - struct dmar_drhd_unit *drhd; - struct intel_iommu *iommu; - int target; + struct iommu_pmu *iommu_pmu = hlist_entry_safe(node, typeof(*iommu_pmu), cpuhp_node); + int target = cpumask_first(&iommu_pmu_cpu_mask); + + /* + * The iommu_pmu_cpu_mask has been updated when offline the CPU + * for the first iommu_pmu. Migrate the other iommu_pmu to the + * new target. + */ + if (target < nr_cpu_ids && target != iommu_pmu->cpu) { + perf_pmu_migrate_context(&iommu_pmu->pmu, cpu, target); + iommu_pmu->cpu = target; + return 0; + } if (!cpumask_test_and_clear_cpu(cpu, &iommu_pmu_cpu_mask)) return 0; @@ -795,45 +810,50 @@ static int iommu_pmu_cpu_offline(unsigned int cpu) if (target < nr_cpu_ids) cpumask_set_cpu(target, &iommu_pmu_cpu_mask); else - target = -1; + return 0; - rcu_read_lock(); - - for_each_iommu(iommu, drhd) { - if (!iommu->pmu) - continue; - perf_pmu_migrate_context(&iommu->pmu->pmu, cpu, target); - } - rcu_read_unlock(); + perf_pmu_migrate_context(&iommu_pmu->pmu, cpu, target); + iommu_pmu->cpu = target; return 0; } static int nr_iommu_pmu; +static enum cpuhp_state iommu_cpuhp_slot; static int iommu_pmu_cpuhp_setup(struct iommu_pmu *iommu_pmu) { int ret; - if (nr_iommu_pmu++) - return 0; + if (!nr_iommu_pmu) { + ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, + "driver/iommu/intel/perfmon:online", + iommu_pmu_cpu_online, + iommu_pmu_cpu_offline); + if (ret < 0) + return ret; + iommu_cpuhp_slot = ret; + } - ret = cpuhp_setup_state(CPUHP_AP_PERF_X86_IOMMU_PERF_ONLINE, - "driver/iommu/intel/perfmon:online", - iommu_pmu_cpu_online, - iommu_pmu_cpu_offline); - if (ret) - nr_iommu_pmu = 0; + ret = cpuhp_state_add_instance(iommu_cpuhp_slot, &iommu_pmu->cpuhp_node); + if (ret) { + if (!nr_iommu_pmu) + cpuhp_remove_multi_state(iommu_cpuhp_slot); + return ret; + } + nr_iommu_pmu++; - return ret; + return 0; } static void iommu_pmu_cpuhp_free(struct iommu_pmu *iommu_pmu) { + cpuhp_state_remove_instance(iommu_cpuhp_slot, &iommu_pmu->cpuhp_node); + if (--nr_iommu_pmu) return; - cpuhp_remove_state(CPUHP_AP_PERF_X86_IOMMU_PERF_ONLINE); + cpuhp_remove_multi_state(iommu_cpuhp_slot); } void iommu_pmu_register(struct intel_iommu *iommu) diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index c6fab004104a..5b2f8147d1ae 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -218,7 +218,6 @@ enum cpuhp_state { CPUHP_AP_PERF_X86_CQM_ONLINE, CPUHP_AP_PERF_X86_CSTATE_ONLINE, CPUHP_AP_PERF_X86_IDXD_ONLINE, - CPUHP_AP_PERF_X86_IOMMU_PERF_ONLINE, CPUHP_AP_PERF_S390_CF_ONLINE, CPUHP_AP_PERF_S390_SF_ONLINE, CPUHP_AP_PERF_ARM_CCI_ONLINE, -- cgit v1.2.3 From 653a180957a85c3fc30320cc7e84f5dc913a64f8 Mon Sep 17 00:00:00 2001 From: Michael Sit Wei Hong Date: Thu, 30 Mar 2023 17:14:02 +0800 Subject: net: phylink: add phylink_expects_phy() method Provide phylink_expects_phy() to allow MAC drivers to check if it is expecting a PHY to attach to. Since fixed-linked setups do not need to attach to a PHY. Provides a boolean value as to if the MAC should expect a PHY. Returns true if a PHY is expected. Reviewed-by: Russell King (Oracle) Signed-off-by: Michael Sit Wei Hong Signed-off-by: David S. Miller --- drivers/net/phy/phylink.c | 19 +++++++++++++++++++ include/linux/phylink.h | 1 + 2 files changed, 20 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 1a2f074685fa..30c166b33468 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -1586,6 +1586,25 @@ void phylink_destroy(struct phylink *pl) } EXPORT_SYMBOL_GPL(phylink_destroy); +/** + * phylink_expects_phy() - Determine if phylink expects a phy to be attached + * @pl: a pointer to a &struct phylink returned from phylink_create() + * + * When using fixed-link mode, or in-band mode with 1000base-X or 2500base-X, + * no PHY is needed. + * + * Returns true if phylink will be expecting a PHY. + */ +bool phylink_expects_phy(struct phylink *pl) +{ + if (pl->cfg_link_an_mode == MLO_AN_FIXED || + (pl->cfg_link_an_mode == MLO_AN_INBAND && + phy_interface_mode_is_8023z(pl->link_config.interface))) + return false; + return true; +} +EXPORT_SYMBOL_GPL(phylink_expects_phy); + static void phylink_phy_change(struct phy_device *phydev, bool up) { struct phylink *pl = phydev->phylink; diff --git a/include/linux/phylink.h b/include/linux/phylink.h index c492c26202b5..637698ed5cb6 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -574,6 +574,7 @@ struct phylink *phylink_create(struct phylink_config *, struct fwnode_handle *, phy_interface_t iface, const struct phylink_mac_ops *mac_ops); void phylink_destroy(struct phylink *); +bool phylink_expects_phy(struct phylink *pl); int phylink_connect_phy(struct phylink *, struct phy_device *); int phylink_of_phy_connect(struct phylink *, struct device_node *, u32 flags); -- cgit v1.2.3 From ea65b41807a26495ff2a73dd8b1bab2751940887 Mon Sep 17 00:00:00 2001 From: John Keeping Date: Mon, 27 Mar 2023 18:36:46 +0100 Subject: ftrace: Mark get_lock_parent_ip() __always_inline If the compiler decides not to inline this function then preemption tracing will always show an IP inside the preemption disabling path and never the function actually calling preempt_{enable,disable}. Link: https://lore.kernel.org/linux-trace-kernel/20230327173647.1690849-1-john@metanate.com Cc: Masami Hiramatsu Cc: Mark Rutland Cc: stable@vger.kernel.org Fixes: f904f58263e1d ("sched/debug: Fix preempt_disable_ip recording for preempt_disable()") Signed-off-by: John Keeping Signed-off-by: Steven Rostedt (Google) --- include/linux/ftrace.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 366c730beaa3..402fc061de75 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -980,7 +980,7 @@ static inline void __ftrace_enabled_restore(int enabled) #define CALLER_ADDR5 ((unsigned long)ftrace_return_address(5)) #define CALLER_ADDR6 ((unsigned long)ftrace_return_address(6)) -static inline unsigned long get_lock_parent_ip(void) +static __always_inline unsigned long get_lock_parent_ip(void) { unsigned long addr = CALLER_ADDR0; -- cgit v1.2.3 From 3dd4432549415f3c65dd52d5c687629efbf4ece1 Mon Sep 17 00:00:00 2001 From: Liam R. Howlett Date: Mon, 27 Feb 2023 09:36:07 -0800 Subject: mm: enable maple tree RCU mode by default Use the maple tree in RCU mode for VMA tracking. The maple tree tracks the stack and is able to update the pivot (lower/upper boundary) in-place to allow the page fault handler to write to the tree while holding just the mmap read lock. This is safe as the writes to the stack have a guard VMA which ensures there will always be a NULL in the direction of the growth and thus will only update a pivot. It is possible, but not recommended, to have VMAs that grow up/down without guard VMAs. syzbot has constructed a testcase which sets up a VMA to grow and consume the empty space. Overwriting the entire NULL entry causes the tree to be altered in a way that is not safe for concurrent readers; the readers may see a node being rewritten or one that does not match the maple state they are using. Enabling RCU mode allows the concurrent readers to see a stable node and will return the expected result. [Liam.Howlett@Oracle.com: we don't need to free the nodes with RCU[ Link: https://lore.kernel.org/linux-mm/000000000000b0a65805f663ace6@google.com/ Link: https://lkml.kernel.org/r/20230227173632.3292573-9-surenb@google.com Fixes: d4af56c5c7c6 ("mm: start tracking VMAs with maple tree") Signed-off-by: Liam R. Howlett Signed-off-by: Suren Baghdasaryan Reported-by: syzbot+8d95422d3537159ca390@syzkaller.appspotmail.com Cc: Signed-off-by: Andrew Morton --- include/linux/mm_types.h | 3 ++- kernel/fork.c | 3 +++ mm/mmap.c | 3 ++- 3 files changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 0722859c3647..a57e6ae78e65 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -774,7 +774,8 @@ struct mm_struct { unsigned long cpu_bitmap[]; }; -#define MM_MT_FLAGS (MT_FLAGS_ALLOC_RANGE | MT_FLAGS_LOCK_EXTERN) +#define MM_MT_FLAGS (MT_FLAGS_ALLOC_RANGE | MT_FLAGS_LOCK_EXTERN | \ + MT_FLAGS_USE_RCU) extern struct mm_struct init_mm; /* Pointer magic because the dynamic array size confuses some compilers. */ diff --git a/kernel/fork.c b/kernel/fork.c index c0257cbee093..0c92f224c68c 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -617,6 +617,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, if (retval) goto out; + mt_clear_in_rcu(vmi.mas.tree); for_each_vma(old_vmi, mpnt) { struct file *file; @@ -700,6 +701,8 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, retval = arch_dup_mmap(oldmm, mm); loop_out: vma_iter_free(&vmi); + if (!retval) + mt_set_in_rcu(vmi.mas.tree); out: mmap_write_unlock(mm); flush_tlb_mm(oldmm); diff --git a/mm/mmap.c b/mm/mmap.c index ad499f7b767f..ff68a67a2a7c 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2277,7 +2277,7 @@ do_vmi_align_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma, int count = 0; int error = -ENOMEM; MA_STATE(mas_detach, &mt_detach, 0, 0); - mt_init_flags(&mt_detach, MT_FLAGS_LOCK_EXTERN); + mt_init_flags(&mt_detach, vmi->mas.tree->ma_flags & MT_FLAGS_LOCK_MASK); mt_set_external_lock(&mt_detach, &mm->mmap_lock); /* @@ -3037,6 +3037,7 @@ void exit_mmap(struct mm_struct *mm) */ set_bit(MMF_OOM_SKIP, &mm->flags); mmap_write_lock(mm); + mt_clear_in_rcu(&mm->mm_mt); free_pgtables(&tlb, &mm->mm_mt, vma, FIRST_USER_ADDRESS, USER_PGTABLES_CEILING); tlb_finish_mmu(&tlb); -- cgit v1.2.3 From 195d8e5da3acb17c5357526494f818a21e97cd10 Mon Sep 17 00:00:00 2001 From: Reinette Chatre Date: Wed, 29 Mar 2023 13:13:11 -0700 Subject: PCI/MSI: Provide missing stub for pci_msix_can_alloc_dyn() pci_msix_can_alloc_dyn() is not declared when CONFIG_PCI_MSI is disabled. There is no existing user of pci_msix_can_alloc_dyn() but work is in progress to change this. This work encounters the following error when CONFIG_PCI_MSI is disabled: drivers/vfio/pci/vfio_pci_intrs.c:427:21: error: implicit declaration of function 'pci_msix_can_alloc_dyn' [-Werror=implicit-function-declaration] Provide definition for pci_msix_can_alloc_dyn() in preparation for users that need to compile when CONFIG_PCI_MSI is disabled. [bhelgaas: Also reported by Arnd Bergmann in drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c; added his Fixes: line] Fixes: fb0a6a268dcd ("net/mlx5: Provide external API for allocating vectors") Fixes: 34026364df8e ("PCI/MSI: Provide post-enable dynamic allocation interfaces for MSI-X") Link: https://lore.kernel.org/oe-kbuild-all/202303291000.PWFqGCxH-lkp@intel.com/ Link: https://lore.kernel.org/r/310ecc4815dae4174031062f525245f0755c70e2.1680119924.git.reinette.chatre@intel.com Reported-by: kernel test robot Signed-off-by: Reinette Chatre Signed-off-by: Bjorn Helgaas Reviewed-by: Kuppuswamy Sathyanarayanan Cc: stable@vger.kernel.org # v6.2+ --- include/linux/pci.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index fafd8020c6d7..5e2dab675943 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1623,6 +1623,8 @@ pci_alloc_irq_vectors(struct pci_dev *dev, unsigned int min_vecs, flags, NULL); } +static inline bool pci_msix_can_alloc_dyn(struct pci_dev *dev) +{ return false; } static inline struct msi_map pci_msix_alloc_irq_at(struct pci_dev *dev, unsigned int index, const struct irq_affinity_desc *affdesc) { -- cgit v1.2.3