From b71f9804f66c2592d4c3a2397b7374a4039005a5 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 18 Apr 2025 22:46:52 -0700 Subject: timekeeping: Prevent coarse clocks going backwards Lei Chen raised an issue with CLOCK_MONOTONIC_COARSE seeing time inconsistencies. Lei tracked down that this was being caused by the adjustment: tk->tkr_mono.xtime_nsec -= offset; which is made to compensate for the unaccumulated cycles in offset when the multiplicator is adjusted forward, so that the non-_COARSE clockids don't see inconsistencies. However, the _COARSE clockid getter functions use the adjusted xtime_nsec value directly and do not compensate the negative offset via the clocksource delta multiplied with the new multiplicator. In that case the caller can observe time going backwards in consecutive calls. By design, this negative adjustment should be fine, because the logic run from timekeeping_adjust() is done after it accumulated approximately multiplicator * interval_cycles into xtime_nsec. The accumulated value is always larger then the mult_adj * offset value, which is subtracted from xtime_nsec. Both operations are done together under the tk_core.lock, so the net change to xtime_nsec is always always be positive. However, do_adjtimex() calls into timekeeping_advance() as well, to apply the NTP frequency adjustment immediately. In this case, timekeeping_advance() does not return early when the offset is smaller then interval_cycles. In that case there is no time accumulated into xtime_nsec. But the subsequent call into timekeeping_adjust(), which modifies the multiplicator, subtracts from xtime_nsec to correct for the new multiplicator. Here because there was no accumulation, xtime_nsec becomes smaller than before, which opens a window up to the next accumulation, where the _COARSE clockid getters, which don't compensate for the offset, can observe the inconsistency. This has been tried to be fixed by forwarding the timekeeper in the case that adjtimex() adjusts the multiplier, which resets the offset to zero: 757b000f7b93 ("timekeeping: Fix possible inconsistencies in _COARSE clockids") That works correctly, but unfortunately causes a regression on the adjtimex() side. There are two issues: 1) The forwarding of the base time moves the update out of the original period and establishes a new one. 2) The clearing of the accumulated NTP error is changing the behaviour as well. User-space expects that multiplier/frequency updates are in effect, when the syscall returns, so delaying the update to the next tick is not solving the problem either. Commit 757b000f7b93 was reverted so that the established expectations of user space implementations (ntpd, chronyd) are restored, but that obviously brought the inconsistencies back. One of the initial approaches to fix this was to establish a separate storage for the coarse time getter nanoseconds part by calculating it from the offset. That was dropped on the floor because not having yet another state to maintain was simpler. But given the result of the above exercise, this solution turns out to be the right one. Bring it back in a slightly modified form. Thus introduce timekeeper::coarse_nsec and store that nanoseconds part in it, switch the time getter functions and the VDSO update to use that value. coarse_nsec is set on operations which forward or initialize the timekeeper and after time was accumulated during a tick. If there is no accumulation the timestamp is unchanged. This leaves the adjtimex() behaviour unmodified and prevents coarse time from going backwards. [ jstultz: Simplified the coarse_nsec calculation and kept behavior so coarse clockids aren't adjusted on each inter-tick adjtimex call, slightly reworked the comments and commit message ] Fixes: da15cfdae033 ("time: Introduce CLOCK_REALTIME_COARSE") Reported-by: Lei Chen Signed-off-by: Thomas Gleixner Signed-off-by: John Stultz Signed-off-by: Thomas Gleixner Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/all/20250419054706.2319105-1-jstultz@google.com Closes: https://lore.kernel.org/lkml/20250310030004.3705801-1-lei.chen@smartx.com/ --- include/linux/timekeeper_internal.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h index e39d4d563b19..785048a3b3e6 100644 --- a/include/linux/timekeeper_internal.h +++ b/include/linux/timekeeper_internal.h @@ -51,7 +51,7 @@ struct tk_read_base { * @offs_real: Offset clock monotonic -> clock realtime * @offs_boot: Offset clock monotonic -> clock boottime * @offs_tai: Offset clock monotonic -> clock tai - * @tai_offset: The current UTC to TAI offset in seconds + * @coarse_nsec: The nanoseconds part for coarse time getters * @tkr_raw: The readout base structure for CLOCK_MONOTONIC_RAW * @raw_sec: CLOCK_MONOTONIC_RAW time in seconds * @clock_was_set_seq: The sequence number of clock was set events @@ -76,6 +76,7 @@ struct tk_read_base { * ntp shifted nano seconds. * @ntp_err_mult: Multiplication factor for scaled math conversion * @skip_second_overflow: Flag used to avoid updating NTP twice with same second + * @tai_offset: The current UTC to TAI offset in seconds * * Note: For timespec(64) based interfaces wall_to_monotonic is what * we need to add to xtime (or xtime corrected for sub jiffy times) @@ -100,7 +101,7 @@ struct tk_read_base { * which results in the following cacheline layout: * * 0: seqcount, tkr_mono - * 1: xtime_sec ... tai_offset + * 1: xtime_sec ... coarse_nsec * 2: tkr_raw, raw_sec * 3,4: Internal variables * @@ -121,7 +122,7 @@ struct timekeeper { ktime_t offs_real; ktime_t offs_boot; ktime_t offs_tai; - s32 tai_offset; + u32 coarse_nsec; /* Cacheline 2: */ struct tk_read_base tkr_raw; @@ -144,6 +145,7 @@ struct timekeeper { u32 ntp_error_shift; u32 ntp_err_mult; u32 skip_second_overflow; + s32 tai_offset; }; #ifdef CONFIG_GENERIC_TIME_VSYSCALL -- cgit v1.2.3 From f31fe8165d365379d858c53bef43254c7d6d1cfd Mon Sep 17 00:00:00 2001 From: Naman Jain Date: Fri, 2 May 2025 13:18:10 +0530 Subject: uio_hv_generic: Fix sysfs creation path for ring buffer On regular bootup, devices get registered to VMBus first, so when uio_hv_generic driver for a particular device type is probed, the device is already initialized and added, so sysfs creation in hv_uio_probe() works fine. However, when the device is removed and brought back, the channel gets rescinded and the device again gets registered to VMBus. However this time, the uio_hv_generic driver is already registered to probe for that device and in this case sysfs creation is tried before the device's kobject gets initialized completely. Fix this by moving the core logic of sysfs creation of ring buffer, from uio_hv_generic to HyperV's VMBus driver, where the rest of the sysfs attributes for the channels are defined. While doing that, make use of attribute groups and macros, instead of creating sysfs directly, to ensure better error handling and code flow. Problematic path: vmbus_process_offer (A new offer comes for the VMBus device) vmbus_add_channel_work vmbus_device_register |-> device_register | |... | |-> hv_uio_probe | |... | |-> sysfs_create_bin_file (leads to a warning as | the primary channel's kobject, which is used to | create the sysfs file, is not yet initialized) |-> kset_create_and_add |-> vmbus_add_channel_kobj (initialization of the primary channel's kobject happens later) Above code flow is sequential and the warning is always reproducible in this path. Fixes: 9ab877a6ccf8 ("uio_hv_generic: make ring buffer attribute for primary channel") Cc: stable@kernel.org Suggested-by: Saurabh Sengar Suggested-by: Michael Kelley Reviewed-by: Michael Kelley Tested-by: Michael Kelley Reviewed-by: Dexuan Cui Signed-off-by: Naman Jain Link: https://lore.kernel.org/r/20250502074811.2022-2-namjain@linux.microsoft.com Signed-off-by: Greg Kroah-Hartman --- drivers/hv/hyperv_vmbus.h | 6 +++ drivers/hv/vmbus_drv.c | 100 ++++++++++++++++++++++++++++++++++++++++++- drivers/uio/uio_hv_generic.c | 39 ++++++++--------- include/linux/hyperv.h | 6 +++ 4 files changed, 128 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h index 29780f3a7478..0b450e53161e 100644 --- a/drivers/hv/hyperv_vmbus.h +++ b/drivers/hv/hyperv_vmbus.h @@ -477,4 +477,10 @@ static inline int hv_debug_add_dev_dir(struct hv_device *dev) #endif /* CONFIG_HYPERV_TESTING */ +/* Create and remove sysfs entry for memory mapped ring buffers for a channel */ +int hv_create_ring_sysfs(struct vmbus_channel *channel, + int (*hv_mmap_ring_buffer)(struct vmbus_channel *channel, + struct vm_area_struct *vma)); +int hv_remove_ring_sysfs(struct vmbus_channel *channel); + #endif /* _HYPERV_VMBUS_H */ diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 8d3cff42bdbb..0f16a83cc2d6 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -1802,6 +1802,27 @@ static ssize_t subchannel_id_show(struct vmbus_channel *channel, } static VMBUS_CHAN_ATTR_RO(subchannel_id); +static int hv_mmap_ring_buffer_wrapper(struct file *filp, struct kobject *kobj, + const struct bin_attribute *attr, + struct vm_area_struct *vma) +{ + struct vmbus_channel *channel = container_of(kobj, struct vmbus_channel, kobj); + + /* + * hv_(create|remove)_ring_sysfs implementation ensures that mmap_ring_buffer + * is not NULL. + */ + return channel->mmap_ring_buffer(channel, vma); +} + +static struct bin_attribute chan_attr_ring_buffer = { + .attr = { + .name = "ring", + .mode = 0600, + }, + .size = 2 * SZ_2M, + .mmap = hv_mmap_ring_buffer_wrapper, +}; static struct attribute *vmbus_chan_attrs[] = { &chan_attr_out_mask.attr, &chan_attr_in_mask.attr, @@ -1821,6 +1842,11 @@ static struct attribute *vmbus_chan_attrs[] = { NULL }; +static struct bin_attribute *vmbus_chan_bin_attrs[] = { + &chan_attr_ring_buffer, + NULL +}; + /* * Channel-level attribute_group callback function. Returns the permission for * each attribute, and returns 0 if an attribute is not visible. @@ -1841,9 +1867,24 @@ static umode_t vmbus_chan_attr_is_visible(struct kobject *kobj, return attr->mode; } +static umode_t vmbus_chan_bin_attr_is_visible(struct kobject *kobj, + const struct bin_attribute *attr, int idx) +{ + const struct vmbus_channel *channel = + container_of(kobj, struct vmbus_channel, kobj); + + /* Hide ring attribute if channel's ring_sysfs_visible is set to false */ + if (attr == &chan_attr_ring_buffer && !channel->ring_sysfs_visible) + return 0; + + return attr->attr.mode; +} + static const struct attribute_group vmbus_chan_group = { .attrs = vmbus_chan_attrs, - .is_visible = vmbus_chan_attr_is_visible + .bin_attrs = vmbus_chan_bin_attrs, + .is_visible = vmbus_chan_attr_is_visible, + .is_bin_visible = vmbus_chan_bin_attr_is_visible, }; static const struct kobj_type vmbus_chan_ktype = { @@ -1851,6 +1892,63 @@ static const struct kobj_type vmbus_chan_ktype = { .release = vmbus_chan_release, }; +/** + * hv_create_ring_sysfs() - create "ring" sysfs entry corresponding to ring buffers for a channel. + * @channel: Pointer to vmbus_channel structure + * @hv_mmap_ring_buffer: function pointer for initializing the function to be called on mmap of + * channel's "ring" sysfs node, which is for the ring buffer of that channel. + * Function pointer is of below type: + * int (*hv_mmap_ring_buffer)(struct vmbus_channel *channel, + * struct vm_area_struct *vma)) + * This has a pointer to the channel and a pointer to vm_area_struct, + * used for mmap, as arguments. + * + * Sysfs node for ring buffer of a channel is created along with other fields, however its + * visibility is disabled by default. Sysfs creation needs to be controlled when the use-case + * is running. + * For example, HV_NIC device is used either by uio_hv_generic or hv_netvsc at any given point of + * time, and "ring" sysfs is needed only when uio_hv_generic is bound to that device. To avoid + * exposing the ring buffer by default, this function is reponsible to enable visibility of + * ring for userspace to use. + * Note: Race conditions can happen with userspace and it is not encouraged to create new + * use-cases for this. This was added to maintain backward compatibility, while solving + * one of the race conditions in uio_hv_generic while creating sysfs. + * + * Returns 0 on success or error code on failure. + */ +int hv_create_ring_sysfs(struct vmbus_channel *channel, + int (*hv_mmap_ring_buffer)(struct vmbus_channel *channel, + struct vm_area_struct *vma)) +{ + struct kobject *kobj = &channel->kobj; + + channel->mmap_ring_buffer = hv_mmap_ring_buffer; + channel->ring_sysfs_visible = true; + + return sysfs_update_group(kobj, &vmbus_chan_group); +} +EXPORT_SYMBOL_GPL(hv_create_ring_sysfs); + +/** + * hv_remove_ring_sysfs() - remove ring sysfs entry corresponding to ring buffers for a channel. + * @channel: Pointer to vmbus_channel structure + * + * Hide "ring" sysfs for a channel by changing its is_visible attribute and updating sysfs group. + * + * Returns 0 on success or error code on failure. + */ +int hv_remove_ring_sysfs(struct vmbus_channel *channel) +{ + struct kobject *kobj = &channel->kobj; + int ret; + + channel->ring_sysfs_visible = false; + ret = sysfs_update_group(kobj, &vmbus_chan_group); + channel->mmap_ring_buffer = NULL; + return ret; +} +EXPORT_SYMBOL_GPL(hv_remove_ring_sysfs); + /* * vmbus_add_channel_kobj - setup a sub-directory under device/channels */ diff --git a/drivers/uio/uio_hv_generic.c b/drivers/uio/uio_hv_generic.c index 1b19b5647495..69c1df0f4ca5 100644 --- a/drivers/uio/uio_hv_generic.c +++ b/drivers/uio/uio_hv_generic.c @@ -131,15 +131,12 @@ static void hv_uio_rescind(struct vmbus_channel *channel) vmbus_device_unregister(channel->device_obj); } -/* Sysfs API to allow mmap of the ring buffers +/* Function used for mmap of ring buffer sysfs interface. * The ring buffer is allocated as contiguous memory by vmbus_open */ -static int hv_uio_ring_mmap(struct file *filp, struct kobject *kobj, - const struct bin_attribute *attr, - struct vm_area_struct *vma) +static int +hv_uio_ring_mmap(struct vmbus_channel *channel, struct vm_area_struct *vma) { - struct vmbus_channel *channel - = container_of(kobj, struct vmbus_channel, kobj); void *ring_buffer = page_address(channel->ringbuffer_page); if (channel->state != CHANNEL_OPENED_STATE) @@ -149,15 +146,6 @@ static int hv_uio_ring_mmap(struct file *filp, struct kobject *kobj, channel->ringbuffer_pagecount << PAGE_SHIFT); } -static const struct bin_attribute ring_buffer_bin_attr = { - .attr = { - .name = "ring", - .mode = 0600, - }, - .size = 2 * SZ_2M, - .mmap = hv_uio_ring_mmap, -}; - /* Callback from VMBUS subsystem when new channel created. */ static void hv_uio_new_channel(struct vmbus_channel *new_sc) @@ -178,8 +166,7 @@ hv_uio_new_channel(struct vmbus_channel *new_sc) /* Disable interrupts on sub channel */ new_sc->inbound.ring_buffer->interrupt_mask = 1; set_channel_read_mode(new_sc, HV_CALL_ISR); - - ret = sysfs_create_bin_file(&new_sc->kobj, &ring_buffer_bin_attr); + ret = hv_create_ring_sysfs(new_sc, hv_uio_ring_mmap); if (ret) { dev_err(device, "sysfs create ring bin file failed; %d\n", ret); vmbus_close(new_sc); @@ -350,10 +337,18 @@ hv_uio_probe(struct hv_device *dev, goto fail_close; } - ret = sysfs_create_bin_file(&channel->kobj, &ring_buffer_bin_attr); - if (ret) - dev_notice(&dev->device, - "sysfs create ring bin file failed; %d\n", ret); + /* + * This internally calls sysfs_update_group, which returns a non-zero value if it executes + * before sysfs_create_group. This is expected as the 'ring' will be created later in + * vmbus_device_register() -> vmbus_add_channel_kobj(). Thus, no need to check the return + * value and print warning. + * + * Creating/exposing sysfs in driver probe is not encouraged as it can lead to race + * conditions with userspace. For backward compatibility, "ring" sysfs could not be removed + * or decoupled from uio_hv_generic probe. Userspace programs can make use of inotify + * APIs to make sure that ring is created. + */ + hv_create_ring_sysfs(channel, hv_uio_ring_mmap); hv_set_drvdata(dev, pdata); @@ -375,7 +370,7 @@ hv_uio_remove(struct hv_device *dev) if (!pdata) return; - sysfs_remove_bin_file(&dev->channel->kobj, &ring_buffer_bin_attr); + hv_remove_ring_sysfs(dev->channel); uio_unregister_device(&pdata->info); hv_uio_cleanup(dev, pdata); diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 675959fb97ba..d6ffe01962c2 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1002,6 +1002,12 @@ struct vmbus_channel { /* The max size of a packet on this channel */ u32 max_pkt_size; + + /* function to mmap ring buffer memory to the channel's sysfs ring attribute */ + int (*mmap_ring_buffer)(struct vmbus_channel *channel, struct vm_area_struct *vma); + + /* boolean to control visibility of sysfs for ring buffer */ + bool ring_sysfs_visible; }; #define lock_requestor(channel, flags) \ -- cgit v1.2.3 From e12a42f64fc3d74872b349eedd47f90c6676b78a Mon Sep 17 00:00:00 2001 From: Michael-CY Lee Date: Mon, 5 May 2025 16:19:46 +0800 Subject: wifi: mac80211: fix the type of status_code for negotiated TID to Link Mapping The status code should be type of __le16. Fixes: 83e897a961b8 ("wifi: ieee80211: add definitions for negotiated TID to Link map") Fixes: 8f500fbc6c65 ("wifi: mac80211: process and save negotiated TID to Link mapping request") Signed-off-by: Michael-CY Lee Link: https://patch.msgid.link/20250505081946.3927214-1-michael-cy.lee@mediatek.com Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 2 +- net/mac80211/mlme.c | 12 ++++++------ 2 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 508d466de1cc..457b4fba88bd 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1526,7 +1526,7 @@ struct ieee80211_mgmt { struct { u8 action_code; u8 dialog_token; - u8 status_code; + __le16 status_code; u8 variable[]; } __packed ttlm_res; struct { diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 5d1f2d6d09ad..35eaf0812c5b 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -7675,6 +7675,7 @@ ieee80211_send_neg_ttlm_res(struct ieee80211_sub_if_data *sdata, int hdr_len = offsetofend(struct ieee80211_mgmt, u.action.u.ttlm_res); int ttlm_max_len = 2 + 1 + sizeof(struct ieee80211_ttlm_elem) + 1 + 2 * 2 * IEEE80211_TTLM_NUM_TIDS; + u16 status_code; skb = dev_alloc_skb(local->tx_headroom + hdr_len + ttlm_max_len); if (!skb) @@ -7697,19 +7698,18 @@ ieee80211_send_neg_ttlm_res(struct ieee80211_sub_if_data *sdata, WARN_ON(1); fallthrough; case NEG_TTLM_RES_REJECT: - mgmt->u.action.u.ttlm_res.status_code = - WLAN_STATUS_DENIED_TID_TO_LINK_MAPPING; + status_code = WLAN_STATUS_DENIED_TID_TO_LINK_MAPPING; break; case NEG_TTLM_RES_ACCEPT: - mgmt->u.action.u.ttlm_res.status_code = WLAN_STATUS_SUCCESS; + status_code = WLAN_STATUS_SUCCESS; break; case NEG_TTLM_RES_SUGGEST_PREFERRED: - mgmt->u.action.u.ttlm_res.status_code = - WLAN_STATUS_PREF_TID_TO_LINK_MAPPING_SUGGESTED; + status_code = WLAN_STATUS_PREF_TID_TO_LINK_MAPPING_SUGGESTED; ieee80211_neg_ttlm_add_suggested_map(skb, neg_ttlm); break; } + mgmt->u.action.u.ttlm_res.status_code = cpu_to_le16(status_code); ieee80211_tx_skb(sdata, skb); } @@ -7875,7 +7875,7 @@ void ieee80211_process_neg_ttlm_res(struct ieee80211_sub_if_data *sdata, * This can be better implemented in the future, to handle request * rejections. */ - if (mgmt->u.action.u.ttlm_res.status_code != WLAN_STATUS_SUCCESS) + if (le16_to_cpu(mgmt->u.action.u.ttlm_res.status_code) != WLAN_STATUS_SUCCESS) __ieee80211_disconnect(sdata); } -- cgit v1.2.3 From 78cd408356fe3edbac66598772fd347bf3e32c1f Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Mon, 5 May 2025 18:19:19 -0700 Subject: net: add missing instance lock to dev_set_promiscuity Accidentally spotted while trying to understand what else needs to be renamed to netif_ prefix. Most of the calls to dev_set_promiscuity are adjacent to dev_set_allmulti or dev_disable_lro so it should be safe to add the lock. Note that new netif_set_promiscuity is currently unused, the locked paths call __dev_set_promiscuity directly. Fixes: ad7c7b2172c3 ("net: hold netdev instance lock during sysfs operations") Signed-off-by: Stanislav Fomichev Link: https://patch.msgid.link/20250506011919.2882313-1-sdf@fomichev.me Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 1 + net/core/dev.c | 14 +------------- net/core/dev_api.c | 23 +++++++++++++++++++++++ 3 files changed, 25 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 2d11d013cabe..7ea022750e4e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4972,6 +4972,7 @@ static inline void __dev_mc_unsync(struct net_device *dev, /* Functions used for secondary unicast and multicast support */ void dev_set_rx_mode(struct net_device *dev); +int netif_set_promiscuity(struct net_device *dev, int inc); int dev_set_promiscuity(struct net_device *dev, int inc); int netif_set_allmulti(struct net_device *dev, int inc, bool notify); int dev_set_allmulti(struct net_device *dev, int inc); diff --git a/net/core/dev.c b/net/core/dev.c index 92e004c354ea..11da1e272ec2 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -9193,18 +9193,7 @@ static int __dev_set_promiscuity(struct net_device *dev, int inc, bool notify) return 0; } -/** - * dev_set_promiscuity - update promiscuity count on a device - * @dev: device - * @inc: modifier - * - * Add or remove promiscuity from a device. While the count in the device - * remains above zero the interface remains promiscuous. Once it hits zero - * the device reverts back to normal filtering operation. A negative inc - * value is used to drop promiscuity on the device. - * Return 0 if successful or a negative errno code on error. - */ -int dev_set_promiscuity(struct net_device *dev, int inc) +int netif_set_promiscuity(struct net_device *dev, int inc) { unsigned int old_flags = dev->flags; int err; @@ -9216,7 +9205,6 @@ int dev_set_promiscuity(struct net_device *dev, int inc) dev_set_rx_mode(dev); return err; } -EXPORT_SYMBOL(dev_set_promiscuity); int netif_set_allmulti(struct net_device *dev, int inc, bool notify) { diff --git a/net/core/dev_api.c b/net/core/dev_api.c index 90898cd540ce..f9a160ab596f 100644 --- a/net/core/dev_api.c +++ b/net/core/dev_api.c @@ -267,6 +267,29 @@ void dev_disable_lro(struct net_device *dev) } EXPORT_SYMBOL(dev_disable_lro); +/** + * dev_set_promiscuity() - update promiscuity count on a device + * @dev: device + * @inc: modifier + * + * Add or remove promiscuity from a device. While the count in the device + * remains above zero the interface remains promiscuous. Once it hits zero + * the device reverts back to normal filtering operation. A negative inc + * value is used to drop promiscuity on the device. + * Return 0 if successful or a negative errno code on error. + */ +int dev_set_promiscuity(struct net_device *dev, int inc) +{ + int ret; + + netdev_lock_ops(dev); + ret = netif_set_promiscuity(dev, inc); + netdev_unlock_ops(dev); + + return ret; +} +EXPORT_SYMBOL(dev_set_promiscuity); + /** * dev_set_allmulti() - update allmulti count on a device * @dev: device -- cgit v1.2.3 From a0309faf1cb0622cac7c820150b7abf2024acff5 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 25 Apr 2025 17:11:07 -0700 Subject: mm: vmalloc: support more granular vrealloc() sizing Introduce struct vm_struct::requested_size so that the requested (re)allocation size is retained separately from the allocated area size. This means that KASAN will correctly poison the correct spans of requested bytes. This also means we can support growing the usable portion of an allocation that can already be supported by the existing area's existing allocation. Link: https://lkml.kernel.org/r/20250426001105.it.679-kees@kernel.org Fixes: 3ddc2fefe6f3 ("mm: vmalloc: implement vrealloc()") Signed-off-by: Kees Cook Reported-by: Erhard Furtner Closes: https://lore.kernel.org/all/20250408192503.6149a816@outsider.home/ Reviewed-by: Danilo Krummrich Cc: Michal Hocko Cc: "Uladzislau Rezki (Sony)" Cc: Vlastimil Babka Cc: Signed-off-by: Andrew Morton --- include/linux/vmalloc.h | 1 + mm/vmalloc.c | 31 ++++++++++++++++++++++++------- 2 files changed, 25 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 31e9ffd936e3..5ca8d4dd149d 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -61,6 +61,7 @@ struct vm_struct { unsigned int nr_pages; phys_addr_t phys_addr; const void *caller; + unsigned long requested_size; }; struct vmap_area { diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 3ed720a787ec..2d7511654831 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1940,7 +1940,7 @@ static inline void setup_vmalloc_vm(struct vm_struct *vm, { vm->flags = flags; vm->addr = (void *)va->va_start; - vm->size = va_size(va); + vm->size = vm->requested_size = va_size(va); vm->caller = caller; va->vm = vm; } @@ -3133,6 +3133,7 @@ struct vm_struct *__get_vm_area_node(unsigned long size, area->flags = flags; area->caller = caller; + area->requested_size = requested_size; va = alloc_vmap_area(size, align, start, end, node, gfp_mask, 0, area); if (IS_ERR(va)) { @@ -4063,6 +4064,8 @@ EXPORT_SYMBOL(vzalloc_node_noprof); */ void *vrealloc_noprof(const void *p, size_t size, gfp_t flags) { + struct vm_struct *vm = NULL; + size_t alloced_size = 0; size_t old_size = 0; void *n; @@ -4072,15 +4075,17 @@ void *vrealloc_noprof(const void *p, size_t size, gfp_t flags) } if (p) { - struct vm_struct *vm; - vm = find_vm_area(p); if (unlikely(!vm)) { WARN(1, "Trying to vrealloc() nonexistent vm area (%p)\n", p); return NULL; } - old_size = get_vm_area_size(vm); + alloced_size = get_vm_area_size(vm); + old_size = vm->requested_size; + if (WARN(alloced_size < old_size, + "vrealloc() has mismatched area vs requested sizes (%p)\n", p)) + return NULL; } /* @@ -4088,14 +4093,26 @@ void *vrealloc_noprof(const void *p, size_t size, gfp_t flags) * would be a good heuristic for when to shrink the vm_area? */ if (size <= old_size) { - /* Zero out spare memory. */ - if (want_init_on_alloc(flags)) + /* Zero out "freed" memory. */ + if (want_init_on_free()) memset((void *)p + size, 0, old_size - size); + vm->requested_size = size; kasan_poison_vmalloc(p + size, old_size - size); - kasan_unpoison_vmalloc(p, size, KASAN_VMALLOC_PROT_NORMAL); return (void *)p; } + /* + * We already have the bytes available in the allocation; use them. + */ + if (size <= alloced_size) { + kasan_unpoison_vmalloc(p + old_size, size - old_size, + KASAN_VMALLOC_PROT_NORMAL); + /* Zero out "alloced" memory. */ + if (want_init_on_alloc(flags)) + memset((void *)p + old_size, 0, size - old_size); + vm->requested_size = size; + } + /* TODO: Grow the vm_area, i.e. allocate and map additional pages. */ n = __vmalloc_noprof(size, flags); if (!n) -- cgit v1.2.3 From f4818881c47fd91fcb6d62373c57c7844e3de1c0 Mon Sep 17 00:00:00 2001 From: Pawan Gupta Date: Fri, 21 Jun 2024 20:23:23 -0700 Subject: x86/its: Enable Indirect Target Selection mitigation Indirect Target Selection (ITS) is a bug in some pre-ADL Intel CPUs with eIBRS. It affects prediction of indirect branch and RETs in the lower half of cacheline. Due to ITS such branches may get wrongly predicted to a target of (direct or indirect) branch that is located in the upper half of the cacheline. Scope of impact =============== Guest/host isolation -------------------- When eIBRS is used for guest/host isolation, the indirect branches in the VMM may still be predicted with targets corresponding to branches in the guest. Intra-mode ---------- cBPF or other native gadgets can be used for intra-mode training and disclosure using ITS. User/kernel isolation --------------------- When eIBRS is enabled user/kernel isolation is not impacted. Indirect Branch Prediction Barrier (IBPB) ----------------------------------------- After an IBPB, indirect branches may be predicted with targets corresponding to direct branches which were executed prior to IBPB. This is mitigated by a microcode update. Add cmdline parameter indirect_target_selection=off|on|force to control the mitigation to relocate the affected branches to an ITS-safe thunk i.e. located in the upper half of cacheline. Also add the sysfs reporting. When retpoline mitigation is deployed, ITS safe-thunks are not needed, because retpoline sequence is already ITS-safe. Similarly, when call depth tracking (CDT) mitigation is deployed (retbleed=stuff), ITS safe return thunk is not used, as CDT prevents RSB-underflow. To not overcomplicate things, ITS mitigation is not supported with spectre-v2 lfence;jmp mitigation. Moreover, it is less practical to deploy lfence;jmp mitigation on ITS affected parts anyways. Signed-off-by: Pawan Gupta Signed-off-by: Dave Hansen Reviewed-by: Josh Poimboeuf Reviewed-by: Alexandre Chartre --- Documentation/ABI/testing/sysfs-devices-system-cpu | 1 + Documentation/admin-guide/kernel-parameters.txt | 13 ++ arch/x86/kernel/cpu/bugs.c | 140 ++++++++++++++++++++- drivers/base/cpu.c | 3 + include/linux/cpu.h | 2 + 5 files changed, 155 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu index 206079d3bd5b..6a1acabb29d8 100644 --- a/Documentation/ABI/testing/sysfs-devices-system-cpu +++ b/Documentation/ABI/testing/sysfs-devices-system-cpu @@ -511,6 +511,7 @@ Description: information about CPUs heterogeneity. What: /sys/devices/system/cpu/vulnerabilities /sys/devices/system/cpu/vulnerabilities/gather_data_sampling + /sys/devices/system/cpu/vulnerabilities/indirect_target_selection /sys/devices/system/cpu/vulnerabilities/itlb_multihit /sys/devices/system/cpu/vulnerabilities/l1tf /sys/devices/system/cpu/vulnerabilities/mds diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index d9fd26b95b34..d3e78e795e0d 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -2202,6 +2202,18 @@ different crypto accelerators. This option can be used to achieve best performance for particular HW. + indirect_target_selection= [X86,Intel] Mitigation control for Indirect + Target Selection(ITS) bug in Intel CPUs. Updated + microcode is also required for a fix in IBPB. + + on: Enable mitigation (default). + off: Disable mitigation. + force: Force the ITS bug and deploy default + mitigation. + + For details see: + Documentation/admin-guide/hw-vuln/indirect-target-selection.rst + init= [KNL] Format: Run specified binary instead of /sbin/init as init @@ -3693,6 +3705,7 @@ expose users to several CPU vulnerabilities. Equivalent to: if nokaslr then kpti=0 [ARM64] gather_data_sampling=off [X86] + indirect_target_selection=off [X86] kvm.nx_huge_pages=off [X86] l1tf=off [X86] mds=off [X86] diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 362602b705cc..417596ce5352 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -49,6 +49,7 @@ static void __init srbds_select_mitigation(void); static void __init l1d_flush_select_mitigation(void); static void __init srso_select_mitigation(void); static void __init gds_select_mitigation(void); +static void __init its_select_mitigation(void); /* The base value of the SPEC_CTRL MSR without task-specific bits set */ u64 x86_spec_ctrl_base; @@ -66,6 +67,14 @@ static DEFINE_MUTEX(spec_ctrl_mutex); void (*x86_return_thunk)(void) __ro_after_init = __x86_return_thunk; +static void __init set_return_thunk(void *thunk) +{ + if (x86_return_thunk != __x86_return_thunk) + pr_warn("x86/bugs: return thunk changed\n"); + + x86_return_thunk = thunk; +} + /* Update SPEC_CTRL MSR and its cached copy unconditionally */ static void update_spec_ctrl(u64 val) { @@ -178,6 +187,7 @@ void __init cpu_select_mitigations(void) */ srso_select_mitigation(); gds_select_mitigation(); + its_select_mitigation(); } /* @@ -1118,7 +1128,7 @@ do_cmd_auto: setup_force_cpu_cap(X86_FEATURE_RETHUNK); setup_force_cpu_cap(X86_FEATURE_UNRET); - x86_return_thunk = retbleed_return_thunk; + set_return_thunk(retbleed_return_thunk); if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD && boot_cpu_data.x86_vendor != X86_VENDOR_HYGON) @@ -1153,7 +1163,7 @@ do_cmd_auto: setup_force_cpu_cap(X86_FEATURE_RETHUNK); setup_force_cpu_cap(X86_FEATURE_CALL_DEPTH); - x86_return_thunk = call_depth_return_thunk; + set_return_thunk(call_depth_return_thunk); break; default: @@ -1187,6 +1197,115 @@ do_cmd_auto: pr_info("%s\n", retbleed_strings[retbleed_mitigation]); } +#undef pr_fmt +#define pr_fmt(fmt) "ITS: " fmt + +enum its_mitigation_cmd { + ITS_CMD_OFF, + ITS_CMD_ON, +}; + +enum its_mitigation { + ITS_MITIGATION_OFF, + ITS_MITIGATION_ALIGNED_THUNKS, + ITS_MITIGATION_RETPOLINE_STUFF, +}; + +static const char * const its_strings[] = { + [ITS_MITIGATION_OFF] = "Vulnerable", + [ITS_MITIGATION_ALIGNED_THUNKS] = "Mitigation: Aligned branch/return thunks", + [ITS_MITIGATION_RETPOLINE_STUFF] = "Mitigation: Retpolines, Stuffing RSB", +}; + +static enum its_mitigation its_mitigation __ro_after_init = ITS_MITIGATION_ALIGNED_THUNKS; + +static enum its_mitigation_cmd its_cmd __ro_after_init = + IS_ENABLED(CONFIG_MITIGATION_ITS) ? ITS_CMD_ON : ITS_CMD_OFF; + +static int __init its_parse_cmdline(char *str) +{ + if (!str) + return -EINVAL; + + if (!IS_ENABLED(CONFIG_MITIGATION_ITS)) { + pr_err("Mitigation disabled at compile time, ignoring option (%s)", str); + return 0; + } + + if (!strcmp(str, "off")) { + its_cmd = ITS_CMD_OFF; + } else if (!strcmp(str, "on")) { + its_cmd = ITS_CMD_ON; + } else if (!strcmp(str, "force")) { + its_cmd = ITS_CMD_ON; + setup_force_cpu_bug(X86_BUG_ITS); + } else { + pr_err("Ignoring unknown indirect_target_selection option (%s).", str); + } + + return 0; +} +early_param("indirect_target_selection", its_parse_cmdline); + +static void __init its_select_mitigation(void) +{ + enum its_mitigation_cmd cmd = its_cmd; + + if (!boot_cpu_has_bug(X86_BUG_ITS) || cpu_mitigations_off()) { + its_mitigation = ITS_MITIGATION_OFF; + return; + } + + /* Retpoline+CDT mitigates ITS, bail out */ + if (boot_cpu_has(X86_FEATURE_RETPOLINE) && + boot_cpu_has(X86_FEATURE_CALL_DEPTH)) { + its_mitigation = ITS_MITIGATION_RETPOLINE_STUFF; + goto out; + } + + /* Exit early to avoid irrelevant warnings */ + if (cmd == ITS_CMD_OFF) { + its_mitigation = ITS_MITIGATION_OFF; + goto out; + } + if (spectre_v2_enabled == SPECTRE_V2_NONE) { + pr_err("WARNING: Spectre-v2 mitigation is off, disabling ITS\n"); + its_mitigation = ITS_MITIGATION_OFF; + goto out; + } + if (!IS_ENABLED(CONFIG_MITIGATION_RETPOLINE) || + !IS_ENABLED(CONFIG_MITIGATION_RETHUNK)) { + pr_err("WARNING: ITS mitigation depends on retpoline and rethunk support\n"); + its_mitigation = ITS_MITIGATION_OFF; + goto out; + } + if (IS_ENABLED(CONFIG_DEBUG_FORCE_FUNCTION_ALIGN_64B)) { + pr_err("WARNING: ITS mitigation is not compatible with CONFIG_DEBUG_FORCE_FUNCTION_ALIGN_64B\n"); + its_mitigation = ITS_MITIGATION_OFF; + goto out; + } + if (boot_cpu_has(X86_FEATURE_RETPOLINE_LFENCE)) { + pr_err("WARNING: ITS mitigation is not compatible with lfence mitigation\n"); + its_mitigation = ITS_MITIGATION_OFF; + goto out; + } + + switch (cmd) { + case ITS_CMD_OFF: + its_mitigation = ITS_MITIGATION_OFF; + break; + case ITS_CMD_ON: + its_mitigation = ITS_MITIGATION_ALIGNED_THUNKS; + if (!boot_cpu_has(X86_FEATURE_RETPOLINE)) + setup_force_cpu_cap(X86_FEATURE_INDIRECT_THUNK_ITS); + setup_force_cpu_cap(X86_FEATURE_RETHUNK); + set_return_thunk(its_return_thunk); + break; + } +out: + pr_info("%s\n", its_strings[its_mitigation]); +} + #undef pr_fmt #define pr_fmt(fmt) "Spectre V2 : " fmt @@ -2607,10 +2726,10 @@ static void __init srso_select_mitigation(void) if (boot_cpu_data.x86 == 0x19) { setup_force_cpu_cap(X86_FEATURE_SRSO_ALIAS); - x86_return_thunk = srso_alias_return_thunk; + set_return_thunk(srso_alias_return_thunk); } else { setup_force_cpu_cap(X86_FEATURE_SRSO); - x86_return_thunk = srso_return_thunk; + set_return_thunk(srso_return_thunk); } if (has_microcode) srso_mitigation = SRSO_MITIGATION_SAFE_RET; @@ -2800,6 +2919,11 @@ static ssize_t rfds_show_state(char *buf) return sysfs_emit(buf, "%s\n", rfds_strings[rfds_mitigation]); } +static ssize_t its_show_state(char *buf) +{ + return sysfs_emit(buf, "%s\n", its_strings[its_mitigation]); +} + static char *stibp_state(void) { if (spectre_v2_in_eibrs_mode(spectre_v2_enabled) && @@ -2982,6 +3106,9 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr case X86_BUG_RFDS: return rfds_show_state(buf); + case X86_BUG_ITS: + return its_show_state(buf); + default: break; } @@ -3061,6 +3188,11 @@ ssize_t cpu_show_reg_file_data_sampling(struct device *dev, struct device_attrib { return cpu_show_common(dev, attr, buf, X86_BUG_RFDS); } + +ssize_t cpu_show_indirect_target_selection(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_ITS); +} #endif void __warn_thunk(void) diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index a7e511849875..50651435577c 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -600,6 +600,7 @@ CPU_SHOW_VULN_FALLBACK(spec_rstack_overflow); CPU_SHOW_VULN_FALLBACK(gds); CPU_SHOW_VULN_FALLBACK(reg_file_data_sampling); CPU_SHOW_VULN_FALLBACK(ghostwrite); +CPU_SHOW_VULN_FALLBACK(indirect_target_selection); static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL); static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL); @@ -616,6 +617,7 @@ static DEVICE_ATTR(spec_rstack_overflow, 0444, cpu_show_spec_rstack_overflow, NU static DEVICE_ATTR(gather_data_sampling, 0444, cpu_show_gds, NULL); static DEVICE_ATTR(reg_file_data_sampling, 0444, cpu_show_reg_file_data_sampling, NULL); static DEVICE_ATTR(ghostwrite, 0444, cpu_show_ghostwrite, NULL); +static DEVICE_ATTR(indirect_target_selection, 0444, cpu_show_indirect_target_selection, NULL); static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_meltdown.attr, @@ -633,6 +635,7 @@ static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_gather_data_sampling.attr, &dev_attr_reg_file_data_sampling.attr, &dev_attr_ghostwrite.attr, + &dev_attr_indirect_target_selection.attr, NULL }; diff --git a/include/linux/cpu.h b/include/linux/cpu.h index e3049543008b..3aa955102b34 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -78,6 +78,8 @@ extern ssize_t cpu_show_gds(struct device *dev, extern ssize_t cpu_show_reg_file_data_sampling(struct device *dev, struct device_attribute *attr, char *buf); extern ssize_t cpu_show_ghostwrite(struct device *dev, struct device_attribute *attr, char *buf); +extern ssize_t cpu_show_indirect_target_selection(struct device *dev, + struct device_attribute *attr, char *buf); extern __printf(4, 5) struct device *cpu_device_create(struct device *parent, void *drvdata, -- cgit v1.2.3 From d6d1e3e6580ca35071ad474381f053cbf1fb6414 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 23 Apr 2025 16:30:11 +0200 Subject: mm/execmem: Unify early execmem_cache behaviour Early kernel memory is RWX, only at the end of early boot (before SMP) do we mark things ROX. Have execmem_cache mirror this behaviour for early users. This avoids having to remember what code is execmem and what is not -- we can poke everything with impunity ;-) Also performance for not having to do endless text_poke_mm switches. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Pawan Gupta Signed-off-by: Dave Hansen Reviewed-by: Alexandre Chartre --- arch/x86/mm/init_32.c | 3 +++ arch/x86/mm/init_64.c | 3 +++ include/linux/execmem.h | 8 +++++++- mm/execmem.c | 40 +++++++++++++++++++++++++++++++++++++--- 4 files changed, 50 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index ad662cc4605c..7fa3965dcef1 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -30,6 +30,7 @@ #include #include #include +#include #include #include @@ -755,6 +756,8 @@ void mark_rodata_ro(void) pr_info("Write protecting kernel text and read-only data: %luk\n", size >> 10); + execmem_cache_make_ro(); + kernel_set_to_readonly = 1; #ifdef CONFIG_CPA_DEBUG diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 7c4f6f591f2b..949a447f75ec 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -34,6 +34,7 @@ #include #include #include +#include #include #include @@ -1391,6 +1392,8 @@ void mark_rodata_ro(void) (end - start) >> 10); set_memory_ro(start, (end - start) >> PAGE_SHIFT); + execmem_cache_make_ro(); + kernel_set_to_readonly = 1; /* diff --git a/include/linux/execmem.h b/include/linux/execmem.h index 65655a5d1be2..089c71cc8ddf 100644 --- a/include/linux/execmem.h +++ b/include/linux/execmem.h @@ -53,7 +53,7 @@ enum execmem_range_flags { EXECMEM_ROX_CACHE = (1 << 1), }; -#ifdef CONFIG_ARCH_HAS_EXECMEM_ROX +#if defined(CONFIG_ARCH_HAS_EXECMEM_ROX) && defined(CONFIG_EXECMEM) /** * execmem_fill_trapping_insns - set memory to contain instructions that * will trap @@ -93,9 +93,15 @@ int execmem_make_temp_rw(void *ptr, size_t size); * Return: 0 on success or negative error code on failure. */ int execmem_restore_rox(void *ptr, size_t size); + +/* + * Called from mark_readonly(), where the system transitions to ROX. + */ +void execmem_cache_make_ro(void); #else static inline int execmem_make_temp_rw(void *ptr, size_t size) { return 0; } static inline int execmem_restore_rox(void *ptr, size_t size) { return 0; } +static inline void execmem_cache_make_ro(void) { } #endif /** diff --git a/mm/execmem.c b/mm/execmem.c index e6c4f5076ca8..6f7a2653b280 100644 --- a/mm/execmem.c +++ b/mm/execmem.c @@ -254,6 +254,34 @@ out_unlock: return ptr; } +static bool execmem_cache_rox = false; + +void execmem_cache_make_ro(void) +{ + struct maple_tree *free_areas = &execmem_cache.free_areas; + struct maple_tree *busy_areas = &execmem_cache.busy_areas; + MA_STATE(mas_free, free_areas, 0, ULONG_MAX); + MA_STATE(mas_busy, busy_areas, 0, ULONG_MAX); + struct mutex *mutex = &execmem_cache.mutex; + void *area; + + execmem_cache_rox = true; + + mutex_lock(mutex); + + mas_for_each(&mas_free, area, ULONG_MAX) { + unsigned long pages = mas_range_len(&mas_free) >> PAGE_SHIFT; + set_memory_ro(mas_free.index, pages); + } + + mas_for_each(&mas_busy, area, ULONG_MAX) { + unsigned long pages = mas_range_len(&mas_busy) >> PAGE_SHIFT; + set_memory_ro(mas_busy.index, pages); + } + + mutex_unlock(mutex); +} + static int execmem_cache_populate(struct execmem_range *range, size_t size) { unsigned long vm_flags = VM_ALLOW_HUGE_VMAP; @@ -274,9 +302,15 @@ static int execmem_cache_populate(struct execmem_range *range, size_t size) /* fill memory with instructions that will trap */ execmem_fill_trapping_insns(p, alloc_size, /* writable = */ true); - err = set_memory_rox((unsigned long)p, vm->nr_pages); - if (err) - goto err_free_mem; + if (execmem_cache_rox) { + err = set_memory_rox((unsigned long)p, vm->nr_pages); + if (err) + goto err_free_mem; + } else { + err = set_memory_x((unsigned long)p, vm->nr_pages); + if (err) + goto err_free_mem; + } err = execmem_cache_add(p, alloc_size); if (err) -- cgit v1.2.3 From 872df34d7c51a79523820ea6a14860398c639b87 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 14 Oct 2024 10:05:48 -0700 Subject: x86/its: Use dynamic thunks for indirect branches ITS mitigation moves the unsafe indirect branches to a safe thunk. This could degrade the prediction accuracy as the source address of indirect branches becomes same for different execution paths. To improve the predictions, and hence the performance, assign a separate thunk for each indirect callsite. This is also a defense-in-depth measure to avoid indirect branches aliasing with each other. As an example, 5000 dynamic thunks would utilize around 16 bits of the address space, thereby gaining entropy. For a BTB that uses 32 bits for indexing, dynamic thunks could provide better prediction accuracy over fixed thunks. Have ITS thunks be variable sized and use EXECMEM_MODULE_TEXT such that they are both more flexible (got to extend them later) and live in 2M TLBs, just like kernel code, avoiding undue TLB pressure. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Pawan Gupta Signed-off-by: Dave Hansen Reviewed-by: Alexandre Chartre --- arch/x86/Kconfig | 1 + arch/x86/include/asm/alternative.h | 10 +++ arch/x86/kernel/alternative.c | 127 ++++++++++++++++++++++++++++++++++++- arch/x86/kernel/module.c | 6 ++ include/linux/execmem.h | 3 + include/linux/module.h | 5 ++ 6 files changed, 149 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index a6bd0590c437..a1156a554f6d 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -2714,6 +2714,7 @@ config MITIGATION_ITS bool "Enable Indirect Target Selection mitigation" depends on CPU_SUP_INTEL && X86_64 depends on MITIGATION_RETPOLINE && MITIGATION_RETHUNK + select EXECMEM default y help Enable Indirect Target Selection (ITS) mitigation. ITS is a bug in diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index 4037c611537c..47948ebbb409 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -124,6 +124,16 @@ static __always_inline int x86_call_depth_emit_accounting(u8 **pprog, } #endif +#ifdef CONFIG_MITIGATION_ITS +extern void its_init_mod(struct module *mod); +extern void its_fini_mod(struct module *mod); +extern void its_free_mod(struct module *mod); +#else /* CONFIG_MITIGATION_ITS */ +static inline void its_init_mod(struct module *mod) { } +static inline void its_fini_mod(struct module *mod) { } +static inline void its_free_mod(struct module *mod) { } +#endif + #if defined(CONFIG_MITIGATION_RETHUNK) && defined(CONFIG_OBJTOOL) extern bool cpu_wants_rethunk(void); extern bool cpu_wants_rethunk_at(void *addr); diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 6e0b09b2c972..7a10e3ed5d0b 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include @@ -32,6 +33,7 @@ #include #include #include +#include int __read_mostly alternatives_patched; @@ -125,6 +127,121 @@ const unsigned char * const x86_nops[ASM_NOP_MAX+1] = #endif }; +#ifdef CONFIG_MITIGATION_ITS + +static struct module *its_mod; +static void *its_page; +static unsigned int its_offset; + +/* Initialize a thunk with the "jmp *reg; int3" instructions. */ +static void *its_init_thunk(void *thunk, int reg) +{ + u8 *bytes = thunk; + int i = 0; + + if (reg >= 8) { + bytes[i++] = 0x41; /* REX.B prefix */ + reg -= 8; + } + bytes[i++] = 0xff; + bytes[i++] = 0xe0 + reg; /* jmp *reg */ + bytes[i++] = 0xcc; + + return thunk; +} + +void its_init_mod(struct module *mod) +{ + if (!cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS)) + return; + + mutex_lock(&text_mutex); + its_mod = mod; + its_page = NULL; +} + +void its_fini_mod(struct module *mod) +{ + if (!cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS)) + return; + + WARN_ON_ONCE(its_mod != mod); + + its_mod = NULL; + its_page = NULL; + mutex_unlock(&text_mutex); + + for (int i = 0; i < mod->its_num_pages; i++) { + void *page = mod->its_page_array[i]; + execmem_restore_rox(page, PAGE_SIZE); + } +} + +void its_free_mod(struct module *mod) +{ + if (!cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS)) + return; + + for (int i = 0; i < mod->its_num_pages; i++) { + void *page = mod->its_page_array[i]; + execmem_free(page); + } + kfree(mod->its_page_array); +} + +static void *its_alloc(void) +{ + void *page __free(execmem) = execmem_alloc(EXECMEM_MODULE_TEXT, PAGE_SIZE); + + if (!page) + return NULL; + + if (its_mod) { + void *tmp = krealloc(its_mod->its_page_array, + (its_mod->its_num_pages+1) * sizeof(void *), + GFP_KERNEL); + if (!tmp) + return NULL; + + its_mod->its_page_array = tmp; + its_mod->its_page_array[its_mod->its_num_pages++] = page; + + execmem_make_temp_rw(page, PAGE_SIZE); + } + + return no_free_ptr(page); +} + +static void *its_allocate_thunk(int reg) +{ + int size = 3 + (reg / 8); + void *thunk; + + if (!its_page || (its_offset + size - 1) >= PAGE_SIZE) { + its_page = its_alloc(); + if (!its_page) { + pr_err("ITS page allocation failed\n"); + return NULL; + } + memset(its_page, INT3_INSN_OPCODE, PAGE_SIZE); + its_offset = 32; + } + + /* + * If the indirect branch instruction will be in the lower half + * of a cacheline, then update the offset to reach the upper half. + */ + if ((its_offset + size - 1) % 64 < 32) + its_offset = ((its_offset - 1) | 0x3F) + 33; + + thunk = its_page + its_offset; + its_offset += size; + + return its_init_thunk(thunk, reg); +} + +#endif + /* * Nomenclature for variable names to simplify and clarify this code and ease * any potential staring at it: @@ -637,9 +754,13 @@ static int emit_call_track_retpoline(void *addr, struct insn *insn, int reg, u8 #ifdef CONFIG_MITIGATION_ITS static int emit_its_trampoline(void *addr, struct insn *insn, int reg, u8 *bytes) { - return __emit_trampoline(addr, insn, bytes, - __x86_indirect_its_thunk_array[reg], - __x86_indirect_its_thunk_array[reg]); + u8 *thunk = __x86_indirect_its_thunk_array[reg]; + u8 *tmp = its_allocate_thunk(reg); + + if (tmp) + thunk = tmp; + + return __emit_trampoline(addr, insn, bytes, thunk, thunk); } /* Check if an indirect branch is at ITS-unsafe address */ diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index a7998f351701..ff07558b7ebc 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -266,6 +266,8 @@ int module_finalize(const Elf_Ehdr *hdr, ibt_endbr = s; } + its_init_mod(me); + if (retpolines || cfi) { void *rseg = NULL, *cseg = NULL; unsigned int rsize = 0, csize = 0; @@ -286,6 +288,9 @@ int module_finalize(const Elf_Ehdr *hdr, void *rseg = (void *)retpolines->sh_addr; apply_retpolines(rseg, rseg + retpolines->sh_size); } + + its_fini_mod(me); + if (returns) { void *rseg = (void *)returns->sh_addr; apply_returns(rseg, rseg + returns->sh_size); @@ -326,4 +331,5 @@ int module_finalize(const Elf_Ehdr *hdr, void module_arch_cleanup(struct module *mod) { alternatives_smp_module_del(mod); + its_free_mod(mod); } diff --git a/include/linux/execmem.h b/include/linux/execmem.h index 089c71cc8ddf..ca42d5e46ccc 100644 --- a/include/linux/execmem.h +++ b/include/linux/execmem.h @@ -4,6 +4,7 @@ #include #include +#include #if (defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)) && \ !defined(CONFIG_KASAN_VMALLOC) @@ -176,6 +177,8 @@ void *execmem_alloc(enum execmem_type type, size_t size); */ void execmem_free(void *ptr); +DEFINE_FREE(execmem, void *, if (_T) execmem_free(_T)); + #ifdef CONFIG_MMU /** * execmem_vmap - create virtual mapping for EXECMEM_MODULE_DATA memory diff --git a/include/linux/module.h b/include/linux/module.h index b3329110d668..8050f77c3b64 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -586,6 +586,11 @@ struct module { atomic_t refcnt; #endif +#ifdef CONFIG_MITIGATION_ITS + int its_num_pages; + void **its_page_array; +#endif + #ifdef CONFIG_CONSTRUCTORS /* Constructor functions. */ ctor_fn_t *ctors; -- cgit v1.2.3 From 1f93d877f09d987f08baedd50597aaaa72a37be4 Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Thu, 8 May 2025 21:12:07 +0300 Subject: ALSA/hda: intel-sdw-acpi: Correct sdw_intel_acpi_scan() function parameter The acpi_handle should be just a handle and not a pointer in sdw_intel_acpi_scan() parameter list. It is called with 'acpi_handle handle' as parameter and it is passing it to acpi_walk_namespace, which also expects acpi_handle and not acpi_handle* Signed-off-by: Peter Ujfalusi Reviewed-by: Bard Liao Reviewed-by: Liam Girdwood Reviewed-by: Ranjani Sridharan Link: https://patch.msgid.link/20250508181207.22113-1-peter.ujfalusi@linux.intel.com Signed-off-by: Takashi Iwai --- include/linux/soundwire/sdw_intel.h | 2 +- sound/hda/intel-sdw-acpi.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw_intel.h b/include/linux/soundwire/sdw_intel.h index 493d9de4e472..dc6ebaee3d18 100644 --- a/include/linux/soundwire/sdw_intel.h +++ b/include/linux/soundwire/sdw_intel.h @@ -365,7 +365,7 @@ struct sdw_intel_res { * on e.g. which machine driver to select (I2S mode, HDaudio or * SoundWire). */ -int sdw_intel_acpi_scan(acpi_handle *parent_handle, +int sdw_intel_acpi_scan(acpi_handle parent_handle, struct sdw_intel_acpi_info *info); void sdw_intel_process_wakeen_event(struct sdw_intel_ctx *ctx); diff --git a/sound/hda/intel-sdw-acpi.c b/sound/hda/intel-sdw-acpi.c index 8686adaf4531..d3511135f7d3 100644 --- a/sound/hda/intel-sdw-acpi.c +++ b/sound/hda/intel-sdw-acpi.c @@ -177,7 +177,7 @@ static acpi_status sdw_intel_acpi_cb(acpi_handle handle, u32 level, * sdw_intel_startup() is required for creation of devices and bus * startup */ -int sdw_intel_acpi_scan(acpi_handle *parent_handle, +int sdw_intel_acpi_scan(acpi_handle parent_handle, struct sdw_intel_acpi_info *info) { acpi_status status; -- cgit v1.2.3 From 0ae0227fa31dda5bfc6b5a0145952d46fe57408b Mon Sep 17 00:00:00 2001 From: David Wang Date: Tue, 6 May 2025 03:30:34 +0800 Subject: mm/codetag: move tag retrieval back upfront in __free_pages() Commit 51ff4d7486f0 ("mm: avoid extra mem_alloc_profiling_enabled() checks") introduces a possible use-after-free scenario, when page is non-compound, page[0] could be released by other thread right after put_page_testzero failed in current thread, pgalloc_tag_sub_pages afterwards would manipulate an invalid page for accounting remaining pages: [timeline] [thread1] [thread2] | alloc_page non-compound V | get_page, rf counter inc V | in ___free_pages | put_page_testzero fails V | put_page, page released V | in ___free_pages, | pgalloc_tag_sub_pages | manipulate an invalid page V Restore __free_pages() to its state before, retrieve alloc tag beforehand. Link: https://lkml.kernel.org/r/20250505193034.91682-1-00107082@163.com Fixes: 51ff4d7486f0 ("mm: avoid extra mem_alloc_profiling_enabled() checks") Signed-off-by: David Wang <00107082@163.com> Acked-by: Suren Baghdasaryan Reviewed-by: Vlastimil Babka Cc: Brendan Jackman Cc: Johannes Weiner Cc: Michal Hocko Cc: Shakeel Butt Cc: Vlastimil Babka Cc: Zi Yan Signed-off-by: Andrew Morton --- include/linux/pgalloc_tag.h | 8 ++++++++ mm/page_alloc.c | 15 ++++++--------- 2 files changed, 14 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pgalloc_tag.h b/include/linux/pgalloc_tag.h index c74077977830..8a7f4f802c57 100644 --- a/include/linux/pgalloc_tag.h +++ b/include/linux/pgalloc_tag.h @@ -188,6 +188,13 @@ static inline struct alloc_tag *__pgalloc_tag_get(struct page *page) return tag; } +static inline struct alloc_tag *pgalloc_tag_get(struct page *page) +{ + if (mem_alloc_profiling_enabled()) + return __pgalloc_tag_get(page); + return NULL; +} + void pgalloc_tag_split(struct folio *folio, int old_order, int new_order); void pgalloc_tag_swap(struct folio *new, struct folio *old); @@ -199,6 +206,7 @@ static inline void clear_page_tag_ref(struct page *page) {} static inline void alloc_tag_sec_init(void) {} static inline void pgalloc_tag_split(struct folio *folio, int old_order, int new_order) {} static inline void pgalloc_tag_swap(struct folio *new, struct folio *old) {} +static inline struct alloc_tag *pgalloc_tag_get(struct page *page) { return NULL; } #endif /* CONFIG_MEM_ALLOC_PROFILING */ diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 5669baf2a6fe..1b00e14a9780 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1151,14 +1151,9 @@ static inline void pgalloc_tag_sub(struct page *page, unsigned int nr) __pgalloc_tag_sub(page, nr); } -static inline void pgalloc_tag_sub_pages(struct page *page, unsigned int nr) +/* When tag is not NULL, assuming mem_alloc_profiling_enabled */ +static inline void pgalloc_tag_sub_pages(struct alloc_tag *tag, unsigned int nr) { - struct alloc_tag *tag; - - if (!mem_alloc_profiling_enabled()) - return; - - tag = __pgalloc_tag_get(page); if (tag) this_cpu_sub(tag->counters->bytes, PAGE_SIZE * nr); } @@ -1168,7 +1163,7 @@ static inline void pgalloc_tag_sub_pages(struct page *page, unsigned int nr) static inline void pgalloc_tag_add(struct page *page, struct task_struct *task, unsigned int nr) {} static inline void pgalloc_tag_sub(struct page *page, unsigned int nr) {} -static inline void pgalloc_tag_sub_pages(struct page *page, unsigned int nr) {} +static inline void pgalloc_tag_sub_pages(struct alloc_tag *tag, unsigned int nr) {} #endif /* CONFIG_MEM_ALLOC_PROFILING */ @@ -5065,11 +5060,13 @@ static void ___free_pages(struct page *page, unsigned int order, { /* get PageHead before we drop reference */ int head = PageHead(page); + /* get alloc tag in case the page is released by others */ + struct alloc_tag *tag = pgalloc_tag_get(page); if (put_page_testzero(page)) __free_frozen_pages(page, order, fpi_flags); else if (!head) { - pgalloc_tag_sub_pages(page, (1 << order) - 1); + pgalloc_tag_sub_pages(tag, (1 << order) - 1); while (order-- > 0) __free_frozen_pages(page + (1 << order), order, fpi_flags); -- cgit v1.2.3 From e8007fad5457ea547ca63bb011fdb03213571c7e Mon Sep 17 00:00:00 2001 From: Steve Siwinski Date: Thu, 8 May 2025 16:01:22 -0400 Subject: scsi: sd_zbc: block: Respect bio vector limits for REPORT ZONES buffer The REPORT ZONES buffer size is currently limited by the HBA's maximum segment count to ensure the buffer can be mapped. However, the block layer further limits the number of iovec entries to 1024 when allocating a bio. To avoid allocation of buffers too large to be mapped, further restrict the maximum buffer size to BIO_MAX_INLINE_VECS. Replace the UIO_MAXIOV symbolic name with the more contextually appropriate BIO_MAX_INLINE_VECS. Fixes: b091ac616846 ("sd_zbc: Fix report zones buffer allocation") Cc: stable@vger.kernel.org Signed-off-by: Steve Siwinski Link: https://lore.kernel.org/r/20250508200122.243129-1-ssiwinski@atto.com Reviewed-by: Damien Le Moal Signed-off-by: Martin K. Petersen --- block/bio.c | 2 +- drivers/scsi/sd_zbc.c | 6 +++++- include/linux/bio.h | 1 + 3 files changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/block/bio.c b/block/bio.c index 4e6c85a33d74..4be592d37fb6 100644 --- a/block/bio.c +++ b/block/bio.c @@ -611,7 +611,7 @@ struct bio *bio_kmalloc(unsigned short nr_vecs, gfp_t gfp_mask) { struct bio *bio; - if (nr_vecs > UIO_MAXIOV) + if (nr_vecs > BIO_MAX_INLINE_VECS) return NULL; return kmalloc(struct_size(bio, bi_inline_vecs, nr_vecs), gfp_mask); } diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c index 7a447ff600d2..a8db66428f80 100644 --- a/drivers/scsi/sd_zbc.c +++ b/drivers/scsi/sd_zbc.c @@ -169,6 +169,7 @@ static void *sd_zbc_alloc_report_buffer(struct scsi_disk *sdkp, unsigned int nr_zones, size_t *buflen) { struct request_queue *q = sdkp->disk->queue; + unsigned int max_segments; size_t bufsize; void *buf; @@ -180,12 +181,15 @@ static void *sd_zbc_alloc_report_buffer(struct scsi_disk *sdkp, * Furthermore, since the report zone command cannot be split, make * sure that the allocated buffer can always be mapped by limiting the * number of pages allocated to the HBA max segments limit. + * Since max segments can be larger than the max inline bio vectors, + * further limit the allocated buffer to BIO_MAX_INLINE_VECS. */ nr_zones = min(nr_zones, sdkp->zone_info.nr_zones); bufsize = roundup((nr_zones + 1) * 64, SECTOR_SIZE); bufsize = min_t(size_t, bufsize, queue_max_hw_sectors(q) << SECTOR_SHIFT); - bufsize = min_t(size_t, bufsize, queue_max_segments(q) << PAGE_SHIFT); + max_segments = min(BIO_MAX_INLINE_VECS, queue_max_segments(q)); + bufsize = min_t(size_t, bufsize, max_segments << PAGE_SHIFT); while (bufsize >= SECTOR_SIZE) { buf = kvzalloc(bufsize, GFP_KERNEL | __GFP_NORETRY); diff --git a/include/linux/bio.h b/include/linux/bio.h index cafc7c215de8..b786ec5bcc81 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -11,6 +11,7 @@ #include #define BIO_MAX_VECS 256U +#define BIO_MAX_INLINE_VECS UIO_MAXIOV struct queue_limits; -- cgit v1.2.3 From 8c619eb21b8e87ae95877e9cca9fcb0e3115776e Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Sun, 4 May 2025 10:14:34 +0200 Subject: net: phy: micrel: remove KSZ9477 EEE quirks now handled by phylink The KSZ9477 PHY driver contained workarounds for broken EEE capability advertisements by manually masking supported EEE modes and forcibly disabling EEE if MICREL_NO_EEE was set. With proper MAC-side EEE handling implemented via phylink, these quirks are no longer necessary. Remove MICREL_NO_EEE handling and the use of ksz9477_get_features(). This simplifies the PHY driver and avoids duplicated EEE management logic. Signed-off-by: Oleksij Rempel Cc: stable@vger.kernel.org # v6.14+ Link: https://patch.msgid.link/20250504081434.424489-3-o.rempel@pengutronix.de Signed-off-by: Paolo Abeni --- drivers/net/phy/micrel.c | 7 ------- include/linux/micrel_phy.h | 1 - 2 files changed, 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 24882d30f685..e2c6569d8c45 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -2027,12 +2027,6 @@ static int ksz9477_config_init(struct phy_device *phydev) return err; } - /* According to KSZ9477 Errata DS80000754C (Module 4) all EEE modes - * in this switch shall be regarded as broken. - */ - if (phydev->dev_flags & MICREL_NO_EEE) - phy_disable_eee(phydev); - return kszphy_config_init(phydev); } @@ -5705,7 +5699,6 @@ static struct phy_driver ksphy_driver[] = { .handle_interrupt = kszphy_handle_interrupt, .suspend = genphy_suspend, .resume = ksz9477_resume, - .get_features = ksz9477_get_features, } }; module_phy_driver(ksphy_driver); diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h index 591bf5b5e8dc..9af01bdd86d2 100644 --- a/include/linux/micrel_phy.h +++ b/include/linux/micrel_phy.h @@ -44,7 +44,6 @@ #define MICREL_PHY_50MHZ_CLK BIT(0) #define MICREL_PHY_FXEN BIT(1) #define MICREL_KSZ8_P1_ERRATA BIT(2) -#define MICREL_NO_EEE BIT(3) #define MICREL_KSZ9021_EXTREG_CTRL 0xB #define MICREL_KSZ9021_EXTREG_DATA_WRITE 0xC -- cgit v1.2.3 From 539fbab37881e32ba6a708a100de6db19e1e7e7d Mon Sep 17 00:00:00 2001 From: Jarkko Sakkinen Date: Mon, 7 Apr 2025 15:28:05 +0300 Subject: tpm: Mask TPM RC in tpm2_start_auth_session() tpm2_start_auth_session() does not mask TPM RC correctly from the callers: [ 28.766528] tpm tpm0: A TPM error (2307) occurred start auth session Process TPM RCs inside tpm2_start_auth_session(), and map them to POSIX error codes. Cc: stable@vger.kernel.org # v6.10+ Fixes: 699e3efd6c64 ("tpm: Add HMAC session start and end functions") Reported-by: Herbert Xu Closes: https://lore.kernel.org/linux-integrity/Z_NgdRHuTKP6JK--@gondor.apana.org.au/ Reviewed-by: Stefano Garzarella Signed-off-by: Jarkko Sakkinen --- drivers/char/tpm/tpm2-sessions.c | 20 ++++++-------------- include/linux/tpm.h | 19 +++++++++++++++++++ 2 files changed, 25 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/drivers/char/tpm/tpm2-sessions.c b/drivers/char/tpm/tpm2-sessions.c index 3f89635ba5e8..7b5049b3d476 100644 --- a/drivers/char/tpm/tpm2-sessions.c +++ b/drivers/char/tpm/tpm2-sessions.c @@ -40,11 +40,6 @@ * * These are the usage functions: * - * tpm2_start_auth_session() which allocates the opaque auth structure - * and gets a session from the TPM. This must be called before - * any of the following functions. The session is protected by a - * session_key which is derived from a random salt value - * encrypted to the NULL seed. * tpm2_end_auth_session() kills the session and frees the resources. * Under normal operation this function is done by * tpm_buf_check_hmac_response(), so this is only to be used on @@ -963,16 +958,13 @@ err: } /** - * tpm2_start_auth_session() - create a HMAC authentication session with the TPM - * @chip: the TPM chip structure to create the session with + * tpm2_start_auth_session() - Create an a HMAC authentication session + * @chip: A TPM chip * - * This function loads the NULL seed from its saved context and starts - * an authentication session on the null seed, fills in the - * @chip->auth structure to contain all the session details necessary - * for performing the HMAC, encrypt and decrypt operations and - * returns. The NULL seed is flushed before this function returns. + * Loads the ephemeral key (null seed), and starts an HMAC authenticated + * session. The null seed is flushed before the return. * - * Return: zero on success or actual error encountered. + * Returns zero on success, or a POSIX error code. */ int tpm2_start_auth_session(struct tpm_chip *chip) { @@ -1024,7 +1016,7 @@ int tpm2_start_auth_session(struct tpm_chip *chip) /* hash algorithm for session */ tpm_buf_append_u16(&buf, TPM_ALG_SHA256); - rc = tpm_transmit_cmd(chip, &buf, 0, "start auth session"); + rc = tpm_ret_to_err(tpm_transmit_cmd(chip, &buf, 0, "StartAuthSession")); tpm2_flush_context(chip, null_key); if (rc == TPM2_RC_SUCCESS) diff --git a/include/linux/tpm.h b/include/linux/tpm.h index 6c3125300c00..9ac9768cc8f7 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -257,6 +257,7 @@ enum tpm2_return_codes { TPM2_RC_TESTING = 0x090A, /* RC_WARN */ TPM2_RC_REFERENCE_H0 = 0x0910, TPM2_RC_RETRY = 0x0922, + TPM2_RC_SESSION_MEMORY = 0x0903, }; enum tpm2_command_codes { @@ -437,6 +438,24 @@ static inline u32 tpm2_rc_value(u32 rc) return (rc & BIT(7)) ? rc & 0xbf : rc; } +/* + * Convert a return value from tpm_transmit_cmd() to POSIX error code. + */ +static inline ssize_t tpm_ret_to_err(ssize_t ret) +{ + if (ret < 0) + return ret; + + switch (tpm2_rc_value(ret)) { + case TPM2_RC_SUCCESS: + return 0; + case TPM2_RC_SESSION_MEMORY: + return -ENOMEM; + default: + return -EFAULT; + } +} + #if defined(CONFIG_TCG_TPM) || defined(CONFIG_TCG_TPM_MODULE) extern int tpm_is_tpm2(struct tpm_chip *chip); -- cgit v1.2.3 From 2f661f71fda1fc0c42b7746ca5b7da529eb6b5be Mon Sep 17 00:00:00 2001 From: Michal Suchanek Date: Fri, 4 Apr 2025 10:23:14 +0200 Subject: tpm: tis: Double the timeout B to 4s With some Infineon chips the timeouts in tpm_tis_send_data (both B and C) can reach up to about 2250 ms. Timeout C is retried since commit de9e33df7762 ("tpm, tpm_tis: Workaround failed command reception on Infineon devices") Timeout B still needs to be extended. The problem is most commonly encountered with context related operation such as load context/save context. These are issued directly by the kernel, and there is no retry logic for them. When a filesystem is set up to use the TPM for unlocking the boot fails, and restarting the userspace service is ineffective. This is likely because ignoring a load context/save context result puts the real TPM state and the TPM state expected by the kernel out of sync. Chips known to be affected: tpm_tis IFX1522:00: 2.0 TPM (device-id 0x1D, rev-id 54) Description: SLB9672 Firmware Revision: 15.22 tpm_tis MSFT0101:00: 2.0 TPM (device-id 0x1B, rev-id 22) Firmware Revision: 7.83 tpm_tis MSFT0101:00: 2.0 TPM (device-id 0x1A, rev-id 16) Firmware Revision: 5.63 Link: https://lore.kernel.org/linux-integrity/Z5pI07m0Muapyu9w@kitsune.suse.cz/ Signed-off-by: Michal Suchanek Reviewed-by: Jarkko Sakkinen Signed-off-by: Jarkko Sakkinen --- drivers/char/tpm/tpm_tis_core.h | 2 +- include/linux/tpm.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/char/tpm/tpm_tis_core.h b/drivers/char/tpm/tpm_tis_core.h index 970d02c337c7..6c3aa480396b 100644 --- a/drivers/char/tpm/tpm_tis_core.h +++ b/drivers/char/tpm/tpm_tis_core.h @@ -54,7 +54,7 @@ enum tis_int_flags { enum tis_defaults { TIS_MEM_LEN = 0x5000, TIS_SHORT_TIMEOUT = 750, /* ms */ - TIS_LONG_TIMEOUT = 2000, /* 2 sec */ + TIS_LONG_TIMEOUT = 4000, /* 4 secs */ TIS_TIMEOUT_MIN_ATML = 14700, /* usecs */ TIS_TIMEOUT_MAX_ATML = 15000, /* usecs */ }; diff --git a/include/linux/tpm.h b/include/linux/tpm.h index 9ac9768cc8f7..a3d8305e88a5 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -224,7 +224,7 @@ enum tpm2_const { enum tpm2_timeouts { TPM2_TIMEOUT_A = 750, - TPM2_TIMEOUT_B = 2000, + TPM2_TIMEOUT_B = 4000, TPM2_TIMEOUT_C = 200, TPM2_TIMEOUT_D = 30, TPM2_DURATION_SHORT = 20, -- cgit v1.2.3 From 45a442fe369e6c4e0b4aa9f63b31c3f2f9e2090e Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Mon, 12 May 2025 17:06:04 -0700 Subject: Drivers: hv: vmbus: Remove vmbus_sendpacket_pagebuffer() With the netvsc driver changed to use vmbus_sendpacket_mpb_desc() instead of vmbus_sendpacket_pagebuffer(), the latter has no remaining callers. Remove it. Cc: # 6.1.x Signed-off-by: Michael Kelley Link: https://patch.msgid.link/20250513000604.1396-6-mhklinux@outlook.com Signed-off-by: Jakub Kicinski --- drivers/hv/channel.c | 59 -------------------------------------------------- include/linux/hyperv.h | 7 ------ 2 files changed, 66 deletions(-) (limited to 'include/linux') diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c index 4ffd5eaa7817..35f26fa1ffe7 100644 --- a/drivers/hv/channel.c +++ b/drivers/hv/channel.c @@ -1076,65 +1076,6 @@ int vmbus_sendpacket(struct vmbus_channel *channel, void *buffer, } EXPORT_SYMBOL(vmbus_sendpacket); -/* - * vmbus_sendpacket_pagebuffer - Send a range of single-page buffer - * packets using a GPADL Direct packet type. This interface allows you - * to control notifying the host. This will be useful for sending - * batched data. Also the sender can control the send flags - * explicitly. - */ -int vmbus_sendpacket_pagebuffer(struct vmbus_channel *channel, - struct hv_page_buffer pagebuffers[], - u32 pagecount, void *buffer, u32 bufferlen, - u64 requestid) -{ - int i; - struct vmbus_channel_packet_page_buffer desc; - u32 descsize; - u32 packetlen; - u32 packetlen_aligned; - struct kvec bufferlist[3]; - u64 aligned_data = 0; - - if (pagecount > MAX_PAGE_BUFFER_COUNT) - return -EINVAL; - - /* - * Adjust the size down since vmbus_channel_packet_page_buffer is the - * largest size we support - */ - descsize = sizeof(struct vmbus_channel_packet_page_buffer) - - ((MAX_PAGE_BUFFER_COUNT - pagecount) * - sizeof(struct hv_page_buffer)); - packetlen = descsize + bufferlen; - packetlen_aligned = ALIGN(packetlen, sizeof(u64)); - - /* Setup the descriptor */ - desc.type = VM_PKT_DATA_USING_GPA_DIRECT; - desc.flags = VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED; - desc.dataoffset8 = descsize >> 3; /* in 8-bytes granularity */ - desc.length8 = (u16)(packetlen_aligned >> 3); - desc.transactionid = VMBUS_RQST_ERROR; /* will be updated in hv_ringbuffer_write() */ - desc.reserved = 0; - desc.rangecount = pagecount; - - for (i = 0; i < pagecount; i++) { - desc.range[i].len = pagebuffers[i].len; - desc.range[i].offset = pagebuffers[i].offset; - desc.range[i].pfn = pagebuffers[i].pfn; - } - - bufferlist[0].iov_base = &desc; - bufferlist[0].iov_len = descsize; - bufferlist[1].iov_base = buffer; - bufferlist[1].iov_len = bufferlen; - bufferlist[2].iov_base = &aligned_data; - bufferlist[2].iov_len = (packetlen_aligned - packetlen); - - return hv_ringbuffer_write(channel, bufferlist, 3, requestid, NULL); -} -EXPORT_SYMBOL_GPL(vmbus_sendpacket_pagebuffer); - /* * vmbus_sendpacket_mpb_desc - Send one or more multi-page buffer packets * using a GPADL Direct packet type. diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 675959fb97ba..ea806cef4a0d 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1161,13 +1161,6 @@ extern int vmbus_sendpacket(struct vmbus_channel *channel, enum vmbus_packet_type type, u32 flags); -extern int vmbus_sendpacket_pagebuffer(struct vmbus_channel *channel, - struct hv_page_buffer pagebuffers[], - u32 pagecount, - void *buffer, - u32 bufferlen, - u64 requestid); - extern int vmbus_sendpacket_mpb_desc(struct vmbus_channel *channel, struct vmbus_packet_mpb_array *mpb, u32 desc_size, -- cgit v1.2.3 From dcd21b609d4abc7303f8683bce4f35d78d7d6830 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 27 Apr 2025 18:21:06 -0400 Subject: NFS: Avoid flushing data while holding directory locks in nfs_rename() The Linux client assumes that all filehandles are non-volatile for renames within the same directory (otherwise sillyrename cannot work). However, the existence of the Linux 'subtree_check' export option has meant that nfs_rename() has always assumed it needs to flush writes before attempting to rename. Since NFSv4 does allow the client to query whether or not the server exhibits this behaviour, and since knfsd does actually set the appropriate flag when 'subtree_check' is enabled on an export, it should be OK to optimise away the write flushing behaviour in the cases where it is clearly not needed. Signed-off-by: Trond Myklebust Reviewed-by: Jeff Layton --- fs/nfs/client.c | 2 ++ fs/nfs/dir.c | 15 ++++++++++++++- include/linux/nfs_fs_sb.h | 12 +++++++++--- 3 files changed, 25 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 2115c1189c2d..6d63b958c4bb 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -1105,6 +1105,8 @@ struct nfs_server *nfs_create_server(struct fs_context *fc) if (server->namelen == 0 || server->namelen > NFS2_MAXNAMLEN) server->namelen = NFS2_MAXNAMLEN; } + /* Linux 'subtree_check' borkenness mandates this setting */ + server->fh_expire_type = NFS_FH_VOL_RENAME; if (!(fattr->valid & NFS_ATTR_FATTR)) { error = ctx->nfs_mod->rpc_ops->getattr(server, ctx->mntfh, diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index bd23fc736b39..d0e0b435a843 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -2676,6 +2676,18 @@ nfs_unblock_rename(struct rpc_task *task, struct nfs_renamedata *data) unblock_revalidate(new_dentry); } +static bool nfs_rename_is_unsafe_cross_dir(struct dentry *old_dentry, + struct dentry *new_dentry) +{ + struct nfs_server *server = NFS_SB(old_dentry->d_sb); + + if (old_dentry->d_parent != new_dentry->d_parent) + return false; + if (server->fh_expire_type & NFS_FH_RENAME_UNSAFE) + return !(server->fh_expire_type & NFS_FH_NOEXPIRE_WITH_OPEN); + return true; +} + /* * RENAME * FIXME: Some nfsds, like the Linux user space nfsd, may generate a @@ -2763,7 +2775,8 @@ int nfs_rename(struct mnt_idmap *idmap, struct inode *old_dir, } - if (S_ISREG(old_inode->i_mode)) + if (S_ISREG(old_inode->i_mode) && + nfs_rename_is_unsafe_cross_dir(old_dentry, new_dentry)) nfs_sync_inode(old_inode); task = nfs_async_rename(old_dir, new_dir, old_dentry, new_dentry, must_unblock ? nfs_unblock_rename : NULL); diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 71319637a84e..ee03f3cef30c 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -213,6 +213,15 @@ struct nfs_server { char *fscache_uniq; /* Uniquifier (or NULL) */ #endif + /* The following #defines numerically match the NFSv4 equivalents */ +#define NFS_FH_NOEXPIRE_WITH_OPEN (0x1) +#define NFS_FH_VOLATILE_ANY (0x2) +#define NFS_FH_VOL_MIGRATION (0x4) +#define NFS_FH_VOL_RENAME (0x8) +#define NFS_FH_RENAME_UNSAFE (NFS_FH_VOLATILE_ANY | NFS_FH_VOL_RENAME) + u32 fh_expire_type; /* V4 bitmask representing file + handle volatility type for + this filesystem */ u32 pnfs_blksize; /* layout_blksize attr */ #if IS_ENABLED(CONFIG_NFS_V4) u32 attr_bitmask[3];/* V4 bitmask representing the set @@ -236,9 +245,6 @@ struct nfs_server { u32 acl_bitmask; /* V4 bitmask representing the ACEs that are supported on this filesystem */ - u32 fh_expire_type; /* V4 bitmask representing file - handle volatility type for - this filesystem */ struct pnfs_layoutdriver_type *pnfs_curr_ld; /* Active layout driver */ struct rpc_wait_queue roc_rpcwaitq; void *pnfs_ld_data; /* per mount point data */ -- cgit v1.2.3